WO2014015267A2 - Method of and system for inferring user intent in search input in a conversational interfaction system - Google Patents
Method of and system for inferring user intent in search input in a conversational interfaction system Download PDFInfo
- Publication number
- WO2014015267A2 WO2014015267A2 PCT/US2013/051288 US2013051288W WO2014015267A2 WO 2014015267 A2 WO2014015267 A2 WO 2014015267A2 US 2013051288 W US2013051288 W US 2013051288W WO 2014015267 A2 WO2014015267 A2 WO 2014015267A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- content items
- input
- metadata
- items
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 132
- 230000003993 interaction Effects 0.000 claims abstract description 21
- 230000004044 response Effects 0.000 claims description 67
- 238000013507 mapping Methods 0.000 claims description 16
- 230000009118 appropriate response Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims 1
- 238000013459 approach Methods 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000000717 retained effect Effects 0.000 description 4
- 241000282412 Homo Species 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 239000000470 constituent Substances 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012552 review Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 235000007639 Anthemis cotula Nutrition 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 244000042664 Matricaria chamomilla Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000013549 information retrieval technique Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000010399 physical interaction Effects 0.000 description 1
- 235000013550 pizza Nutrition 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24573—Query processing with adaptation to user needs using data annotations, e.g. user-defined metadata
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
- G06F16/84—Mapping; Conversion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9558—Details of hyperlinks; Management of linked annotations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
Definitions
- the invention generally relates to conversational interaction techniques, and, more specifically, to inferring user input intent based on resolving input ambiguities and/or inferring a change in conversational session has occurred.
- Conversational systems are poised to become a preferred mode of navigating large information repositories across a range of devices: Smartphones, Tablets, TVs/STBs, multi-modal devices such as wearable computing devices such as "Goggles” (Google's sunglasses), hybrid gesture recognition/speech recognition systems like Xbox/Kinect, automobile information systems, and generic home entertainment systems.
- wearable computing devices such as "Goggles” (Google's sunglasses)
- hybrid gesture recognition/speech recognition systems like Xbox/Kinect
- automobile information systems and generic home entertainment systems.
- the era of touch based interfaces being center stage, as the primaiy mode of interaction, is perhaps slowly coming to an end, where in many daily life use cases, user would rather speak his intent, and the system understands and executes on the intent. This has also been triggered by the significant hardware, software and algorithmic advances making text to speech significantly effective compared to a few years ago.
- J0OO9J Systems that engage in a dialog or conversation, which go beyond the simple multi-step travel/dinner reservation making (e.g., where the steps in the dialog are well defined request / response subsequences with not much ambiguity resolution in each step), also encounter the complexity of having to maintain the state of the conversation in order to be effective. For example, such systems would need to infer implicit references to intents and entities (e.g., reference to people, objects or any noun) and attributes that qualify the intent in user's sentences (e.g., "show me the latest movies of Tom Hanks and not the old ones; "show me more action and less violence). Further still, applicants have discovered that it is beneficial to track not only references made by the user to entities, attributes, etc.
- intents and entities e.g., reference to people, objects or any noun
- attributes that qualify the intent in user's sentences (e.g., "show me the latest movies of Tom Hanks and not the old ones; "show me more action and less violence).
- Another challenge facing systems that engage a user in conversation is the determination of the user's intent change, even if it is within the same domain. For example, user may start off with the intent of finding an answer to a question, e.g., in the entertainment domain. While engaging in the conversation of exploring more about that question, decide to pursue a completely different intent path. Current systems expect user to offer a clear cue that a new conversation is being initiated. If the user fails to provide that important clue, the system responses would be still be constrained to the narrow scope of the exploration path user has gone down, and will constrain users input to that narrow context, ty pically resulting undesira ble, if not evident, responses.
- a human naturally recognizes such a drastic domain switch by the very nature of the statement, and responds accordingly (e.g., "Shall we order pizza?"). Even in the remote scenario where the transition to new domain is not so evident, a human participant may falter, but quickly recover, upon feedback from the first speaker ('Oh no. 1 mean 1 am hungry - 1 would like to eat!).
- embodiments of the techniques disclosed herein attempt to closely match user ' s intent and engage the user in a conversation not unlike human interactions. Certain embodiments exhibit any one or more of the following, non- exhaustive list of characteristics: a) resolve ambiguities in intent and/or description of the intent and, whenever applicable, leverage off of user's preferences (some implementations use computing elements and logic that are based on domain specific vertical information); b) maintain state of active intents and/or entities/attributes describing the intent across exchanges with the user, so as to implicitly infer references made by user indirectly to intents/entities/attributes mentioned earlier in a conversation; c) tailor responses to user, whenever applicable, to match user's preferences; d) implicitly determine conversation boundaries that start a new topic within and across domains and tailor a response accordingly; e) given a failure to understand user's intent (e.g., either because the intent cannot be found or the confidence score of its best guess is below a threshold), engage in a minimal dialog to understand user intent
- a method of inferring user intent in a search input based on resolving ambiguous portions of the search input includes providing access to a set of content items. Each of the content items is associated with metadata that describes the corresponding content item. The method also includes providing a user preference signature. The user preference signature describes preferences of the user for at least one of (i) particular content items and (ii) metadata associated with the content items. The method also includes receiving search input from the user. The search input is intended by the user to identify at least one desired content item. The method also includes determining that a portion of the search input contains an ambiguous identifier. The ambiguous identifier being intended by the user to identify, at least in part, the at least one desired content item.
- the method also includes inferring a meaning for the ambiguous identifier based on matching portions of the search input to the preferences of the user described by the user preference signature and selecting content items from the set of content items based on comparing the search input and the inferred meaning of the ambiguous identifier with metadata associated with the content items.
- the ambiguous identifier can be a pronoun, a syntactic expletive, an entertainment genre, and/ or at least a portion of a name.
- the metadata associated with the content items includes a mapping of relationships between entities associated with the content items.
- the user preference signature is based on explicit preferences provided by the user and/or is based on analyzing content item selections by user conducted over a period of time.
- the user preference signature describes preferences of the user for metadata associated with the content items, the metadata including entities preferred by the user.
- a method of inferring user intent in a search input based on resolving ambiguous portions of the search input includes providing access to a set of content items. Each of the content i tems is associated with metadata that describes the corresponding content item. The method also includes receiving search input from the user. The search input is intended by the user to identify at least one desired content item. The method also includes determining whether or not a portion of the search input contains an ambiguous identifier. The ambiguous identifier being intended by the user to identify, at least in part, the at least one desired content item.
- the method includes: inferring a meaning for the ambiguous identifier based on matching portions of the search input to preferences of the user described by a user preference signature, selecting content items from the set of content items based on comparing the search input and the inferred meaning of the ambiguous identifier with metadata associated with the content item, and, upon a condition in which the search input does not contain an ambiguous identifier, selecting content items from the set of content items based on comparing the search input with metadata associated with the content items.
- Figure 1 illustrates a user interface approach incorporated here for elucidative purposes.
- FIG. 0025J Figure 2 illustrates a user interface approach incorporated here for elucidative purposes.
- Figure 3 illustrates a user interface approach incorporated here for elucidative purposes.
- Figure 4 illustrates a user interface approach incorporated here for elucidative purposes.
- Figure 5 illustrates a user interface approach incorporated here for elucidative purposes.
- Figure 6 illustrates an example of a graph that represents entities and relationships between entities.
- Figure 7 illustrates an example of a graph that represents entities and relationships between entities.
- Figure 8 illustrates an example of a graph that represents entities and relationships between entities.
- Figure 9 illustrates an example of a graph that represents entities and relationships between entities.
- Figure 10 illustrates an architecture that is an embodiment of the present invention.
- Figure 1 1 illustrates a simplified flowchart of the operation of embodiments of the invention.
- Figure 12 illustrates a control flow of the operation of embodiments of the invention.
- Preferred embodiments of the invention include methods of and systems for inferring user's intent and satisfying that intent in a conversational exchange. Certain implementations are able to resolve ambiguities in user input, maintain state of intent, entities, and'Or attributes associated with the conversational exchange, tailor responses to match user's preferences, infer conversational boundaries that start a new topic (i.e. infer a change of a conversational session), and/or engage in a minimal dialog to understand user intent.
- the concepts that follow are used to describe embodiments of the invention.
- Information repositories are associated with domains, which are groupings of similar types of information and'Or certain types of content items. Certain types of information repositories include entities arid relationships between the entities. Each entity / relationship has a type, respectively, from a set of types. Furthermore, associated with each entity / reiationship are a set of attributes, which can be captitred, in some embodiments, as a defined finite set of name-value fields. The entity / relationship mapping also serves as a set of metadata associated with the content items because the entity / relationship mapping provides information that describes the various content items.
- each entity in the mapping can have attributes assigned to it or to the relationships that connect the entity to other entities in the mapping.
- a media entertainment domain includes entities, such as, movies, TV- shows, episodes, crew, roles/characters, actors/personalities, athletes, games, teams, leagues and tournaments, sports people, music artists and performers, composers, albums, songs, news personalities, and/or content distributors. These entities have relationships that are captured in the information repository. For example, a movie entity is related via an "acted in” relationship to one or more actor/personality entities. Similarly, a movie entity may be related to an music album entity via an "original sound track” relationship, which in turn may be related to a song entity via a "track in album” relationship. Meanwhile, names, descriptions, schedule information, reviews, ratings, costs, URLs to videos or audios, application or content store handles, scores, etc. may be deemed attribute fields.
- a personal electronic mail (email) domain includes entities, such as, emails, email-threads, contacts, senders, recipients, company names,
- relationships include an email entity related to its sender entity (as well as the to, cc, bcc, receivers, and email thread entities.) Meanwhile, relationships between a contact and his or her company, department, office location can exist.
- instances of attribute fields associated with entities include contacts' names, designations, email handles, other contact information, email sent/received timestamp, subject, body, attachments, priority levels, an office's location information, and/or a department's name and description,
- a travel-related / hotels and sightseeing domain includes entities, such as, cities, hotels, hotel brands, individual points of interest, categories of points of interest, consumer facing retail chains, car rental sites, and/or car rental companies. Relationships between such entities include location, membership in chains, and/or categories. Furthermore, names, descriptions, keywords, costs, types of service, ratings, reviews, etc. all amount of attribute fields.
- An electronic commerce domain includes eniities, such as, product items, product categories and subcategories, brands, stores, etc. Relationships between such entities can include compatibility information between product items, a product "sold by" a store, etc. Attribute fields in include descriptions, keywords, reviews, ratings, costs, and/or availability information.
- An address book domain includes entities and information such as contact names, electronic mail addresses, telephone numbers, physical addresses, and employer.
- Embodiments of the present invention may also use repositories that are not structured information repositories as described above.
- the information repository corresponding to network-based documents e.g., the Internet / World Wide Web
- entities e.g., the Internet / World Wide Web
- no directly applicable type structure can meaningfully describe, in a nontrivial way, all the kinds of entities and relationships and attributes associated with elements of the Internet in the sense of the structured information repositories described above.
- elements such as domain names, internet media types, filenames, filename extension, etc. can be used as entities or attributes with such information.
- J0O45J For example, consider a corpus consisting of a set of unstructured text documents. In this case, no directly applicable type structure can enumerate a set of entities and relationships that meaningfully describe the document contents. However, application of semantic information extraction processing techniques as a pre- processing step may yield entities and relationships that can partially uncover structure from such a corpus. of the present invention
- a user is interested in one or more entities of some type - generally called intent type herein - which the user wishes to unco ver by specifying only attribute field constraints that the entities must satisfy.
- query-constraints are generally called attribute-only constraints herein.
- a user is interested in one or more entities of the intent type by specifying not only attribute field constraints on the intent type entities but also by specifying attribute field constraints on or naming other entities to which the intent type entities are connected via relationships in some well-defined way.
- Such query-constraints are generally called connection oriented constraints herein.
- connection oriented constraint is when the user wants a movie (an intent type) based on specifying tw o or more actors of the movie or a movie based on an actor and an award the movie won.
- email email
- email email
- a further example is if the user wants to book a hotel room (intent type ) to a train station as well as a Starbucks outlet.
- a television set intent type
- Samsung Samsung that is also compatible with a Nintendo Wii. All of these are instances of connection oriented constraints queries,
- connection-oriented constraint examples the user explicitly describes or specifies the other entities connected to the intent entities.
- constraints are generally called explicit connection oriented constraints and such entities as explicit entities herein.
- connection oriented constraints that include unspecified or implicit entities as part of the constraint specification.
- the user is attempting to identify a piece of information, entity, attribuie, etc. that is not know through relationships between the unknown item and items the user does now.
- constraints are generally called implicit connection oriented constraints herein and the unspecified entities are generally called implicit entities of the constraint herein,
- the user may wish to identify a movie she is seeking via naming two characters in the movie. However, the user does not recall the name of one of the characters, but she does recall that a particular actor played the character. Thus, in her query, she states one character by name and identifies the unknown character by stating that the character was played by the particular actor.
- an example includes a user wanting to get the last email (intent) from an unspecified woman from a specified company 'Intel' to whom he was introduced via email (an attribute specifier) last week.
- the implicit entity is a contact who can be discovered by examining contacts from 'Intel', via an employee / company relationship, who was a first time common- email-reeipient with the user last week,
- Figure 1 shows a search interface 00 for a search engine for movie and television content that is known in the art (i.e., the IMDb search interface).
- Figure 1 includes a pull-down control 105 that allows the user to expressly select an entity type or attribute.
- Title means intent entity type is Movie or TV Show
- TV Episode means the intent type is Episode
- Names means intent type is Personality
- Companies means the intent type is Company (e.g., Production house or Studio etc.)
- Characters means the intent type is Role.
- Keywords, Quotes, and Plots specify attribute fields associated with intent entities of type Movie or TV Show or Episode that are sought to be searched.
- the pull-down control 1 10 allows the user to only specify attributes for entities of type Movie, Episode, or TV Show.
- Figure 2. shows the Advanced Title Search graphical user interface of the TMDB search interface (known in the art) 200.
- the Title Type choice 205 amounts to selection of intent entity type.
- Release Date 2.10, User R ating 215, and Number of Vo tes 220 are all attributes of entities of type movies, TV Shows, episodes, etc. If the number of Genres 225 and Title Groups 230 shown here is deemed small enough, then those genres and title groups can be deemed descriptive attributes of entities. So the genre and title groups section here is also a way of specifying attribute constraints.
- the Title Data 235 section is specifying the constraint corresponding to the data source attribute.
- Figure 3 illustrates graphical user interface 300 for an electronic- commerce website's search utility that is known in the art.
- the user interface allowed users to specify sets of attribute constraints before initiating any search in the information repository.
- Figure 3 shows the user interface after the user has first launched a text-only search query 'car stereo'.
- the post-search user interface is constructed by dynamically picking a subset of attributes for this set of search results, which allows the user to specify further attribute constraints for them.
- the user is forced to follow the specific flow of first doing a text search or category filtering and then specifying the constraints on further attributes.
- connection oriented constraints are examples of explicit connection oriented constraints employed in information retrieval systems.
- Graph model terminology of nodes and edges can also be used to describe connection oriented constraints as can the terminology of entities and relationships.
- birth and death place specifications in the graphical user interface 400 are specifications for nodes connected to the intended personality node.
- the filmography filter 410 in the graphical user interface 400 allows a user to specify the name of a movie or TV show node, etc., which is again another node connected to the intended personality node.
- the other filters 500, shown in Figure 5, of the graphical user interface are specifiers of the attributes of the intended node.
- a user may specify two movie or TV show nodes when his intent is to get the personalities who collaborated on both these nodes.
- a user may specify two personality nodes when his intent is to get movie or TV show nodes
- Figure 6 illustrates a graph 600 of the nodes (entities) and edges
- a further example is a user asking for the name of the movie starring Tom Cruise based on a John Grisham book.
- the query becomes: Get the node of type Movie (intent) connected by an 'Acted In' edge to the explicit node of type
- the user wants the role (intent) played by a specified actor/personality (e.g., Michelle Pfeiffer) in an unspecified movie that is about a specified role (e.g., the character Tony Montana.)
- a specified actor/personality e.g., Michelle Pfeiffer
- the user's constraint includes an unspecified or implicit entity.
- the implicit entity is the movie 'Scarface'.
- Figure 7 illustrates a graph 700 of the entities and relationships analyzed by the techniques disclosed herein to arrive at the desired result.
- the graph 700 is an illustrative visual representation of a structured information repository.
- the implicit movie entity 'Scarface' 705 is arrived at via a 'Acted In' relationship 710 between the movie entity 'Scarface' 705 and the actor entity 'Michelle Pfeiffer' 715 and a 'Character In' relationship 720 between the character entity 'Tony Montana' 725 and the movie entity 'Scarface' 705,
- the role entity 'Elvira Hancock' 730 played by 'Michelle Pfeiffer' is then discovered by the 'Acted by' relationship 735 to 'Michelle Pfeiffer' and the 'Character In' relationship 740 to the movie entity 'Scarface' 705.
- the implicit actor entity Ewan McGregor 805 is arrived at via an Acted In relationship 810 with at least one movie entity Star Wars 815 and via a Character relationship 820 to a character entity Obi- Wan Kenobi 825, which in turn is related via a Character relationship 830 to the movie entity Star Wars 815.
- the result entity The Island 835 is arrived at via an Acted In relationship 840 between the actor/personality entity Scarlett Johansson 845 and the movie entity The Island 835 and an Acted In relationship 850 between the implicit actor entity Ewan McGregor 805 and the movie entity The Island.
- Figure 9 illustrates a graph 900 of the entities and relationships analyzed by the techniques disclosed herein to arrive at a desired result.
- This example uses the terminology of nodes and edges. The user knows that there is a band that covered a Led Zeppelin song for a new movie starring Daniel Craig. The user recalls neither the name of the covered song nor the name of the movie, but he wants to explore the other music (i.e., songs) of the band that did that Led Zeppelin cover. Thus, by specifying the known entities of Led Zeppelin (as the song composer) and Daniel Craig (as an actor in the movie), the interposing implied nodes are discovered to find the user ' s desired result.
- embodiments of the inventive techniques herein compose the query constraint as follows: Return the nodes of type Song (intent) connected by a 'Composer' edge 905 to an implicit node of type Band 910 (Trent Reznor) such that this Band node has a 'Cover Performer' edge 915 with an implicit node of type Song 920 (Immigrant Song) which in turn has a 'Composer' edge 925 with an explicit node of type Band named 'Led Zeppelin' 930 and also a 'Track in Album ' ' edge 935 with an implicit node of type Album 940 (Girl with the Dragon Tattoo Original Sound Track) which has an 'Original Sound Track (OST)' edge 945 with an implicit node of type Movie 950 (Girl with the Dragon Tattoo Original Sound Track) that has an 'Acted In' edge 955 with the explicit node of type Personality named 'Daniel Craig'. 960.
- an inventive conversational interaction interface Described herein are embodiments of an inventive conversational interaction interface. These embodiments enable a user to interact with an information retrieval system by posing a query and/or instruction by speaking to it and, optionally, selecting options by physical interaction (e.g., touching interface, keypad, keyboard, and/or mouse). Response to a user query may be performed by machine generated spoken text to speech and may be supplemented by information displayed on a user screen.
- Embodiments of the conversation interaction interface in general, allow a user to pose his next information retrieval query or instruction in reaction to the information retrieval system's response to a previous query, so that an information retrieval session is a sequence of operations, each of which has the user first posing a query or instruction and the system the presenting a response to the user.
- Embodiments of the present invention are a more powerfu l and expressive paradigm than graphical user interfaces for the query-constraints discussed herein.
- the graphical user interface approach does not work well or does not work at all.
- embodiments of the conversational interaction interface of the present invention are a much more natural fit.
- embodiments of the present invention are more scalable in terms of the number of distinct attributes a user may specify as well as the number of explicit connected node constraints and the number of implicit node constraints relative to graphical user interfaces.
- FIG. 10 represents the overall system architecture 1000 of an embodiment of the present invention.
- User 1001 speaks his or her question that is fed to a speech to text engine 1002. While the input could be speech, the embodiment does not preclude the input to be direct text input.
- the text form of the user input is fed to session dialog content module 1003. This module maintains state across a conversation session, a key use of which is to help in understanding user intent during a conversation, as described below.
- the session dialog content module 1003 in conjunction with a Language Analyzer 1006, a Domain Specific Named Entity Recognizer 1007, a Domain Specific Context and Intent Analyzer 1008, a Personalization Based Intent Analyzer 1009, a Domain Specific Graph Engine 1010, and an Application Specific Attribute Search Engine 101 1 (all described in more detail below) process the user input so as to return criteria to a Query Execution Engine 1004.
- the Query Execution Engine 1004 uses the criteria to perform a search of any available source of information and content to return a result set.
- a Response Transcoding Engine 1005 dispatches the result set to the user for consumption, e.g., in the device through which user is interacting. If the device is a tablet device with no display constraints, embodiments of the present invention may leverage off the display to show a graphical rendition of connection similar in spirit to Figures 7, 6, 9, and 8, with which the user can interact with to express intent. In a display-constrained device such as a smartphone, the Response Transcoding Engine 105 may respond with text and/or speech (using a standard text to speech engine).
- Figure 10 is a conversation architecture showing the modules for a specific domain
- the present embodiment is a conversation interface that can take user input and engage in a dialog where user's intent can span domains. In an embodiment of the invention, this is accomplished by having multiple instances of the domain specific architecture shown in Figure 10, and scoring the intent weights across domains to determine user intent. This scoring mechanism is also used to implicitly determine conversation topic switching (for example, during a entertainment information retrieval session, a user could just say "I am hungry").
- Figure 1 1 illustrates a simplified flowchart of the operation of embodiments of the invention.
- the user's speech input is converted to text by a speech recognition engine 1 101.
- the input is then broken down into intent, entities, and attributes 1 102. This process is assisted by information from the prior conversation state 1 103.
- the breakdown into intents, entities, and attributes enables the system to generate a response to the user 1 104.
- the conversation state 1 103 is updated to reflect the modifications of the current user input and any relevant returned response information.
- Figure 12 illustrates the control flow in more detail.
- the query execution coordination 1202 oversees the breakdown of the user input to understand user's input.
- the query execution coordination 1202 makes use of language analysis 1203 that parses the user input and generates a parse tree.
- the query execution coordination 1202 also makes use of the maintenance and updating of the dialog state 1208.
- the parse tree and any relevant dialog state values are passed to modules that perform intent analysis 1204, entity analysis 1205, and attribute analysis 1206. These analysis processes work concurrently, because sequential processing of these three analysis steps may not be possible. For instance, in some cases of user input, the recognition of entities may require the recognition of intents and vice versa.
- dialog state is also updated 1208 to reflect the modifications of the current input and return of relevant results.
- certain linguistic elements e.g., spoken / recognized words and'or phrases
- the Session Dialog Content Module 1003 in conjunction with a Language Analyzer 1006, and the other recognizer module, analyzer modules, and/or engines described in more detail below, perform the analysis steps mentioned in connection with Figure 12 and break down the sentence into its constituent parts.
- the Language Analyzer 1006 creates a parse tree from the text generated from the user input, and the other recognizer module, analyzer modules, and/or engines operate on the parse tree to determine the constituent parts.
- Those parts can be broadly categorized as (1) intents - the actual intent of the user (such as “find a movie”, “play a song”, “tune to a channel”, “respond to an email”, etc.), (2) entities - noun or pronoun phrases describing or associated with the intent, and (3) attributes - qualifiers to entities such as the "latest” movie, "less” violence, etc.
- intents the actual intent of the user (such as “find a movie”, “play a song”, “tune to a channel”, “respond to an email”, etc.)
- entities - noun or pronoun phrases describing or associated with the intent such as “latest” movie, "less” violence, etc.
- attributes - qualifiers to entities such as the "latest” movie, "less” violence, etc.
- Other constituent part categories are within the scope of the invention.
- conversational interface the expectation is clearly higher - the system must ideally understand the (movie, rating) intent corresponding to the expected response of the rating of the movie and the age group it is appropriate for.
- a conversational interface response degenerating to that of a search engine is tantamount to a failure of the system from a user perspective. Intent determination and, even more importantly, responding to user's question that appears closer to a human's response when the intent is not known or clearly discernible is an important aspect for a conversational interface that strives to be closer to human interaction than to a search engine.
- Intent Analyzer 1008 is a domain specific module that analyzes and classifies intent for a domain and works in conjunction with other modules - domain specific entity recognizer 1007, personalization based intent analyzer 1009 that classifies intent based on user's personal preferences, and the domain specific graph engine 1010.
- the attribute specific search engine 101 1 assists in recognizing attributes and their weights influence the entities they qualify.
- the intent analyzer 1008 in an embodiment of the invention, is a rules driven intent recognizer and/or a naive Bayes classifier with supervised training.
- the rules and/or training set capture how various words and word sets relate to user intent. It takes as input a parse tree, entity recognizer output, and attribute specific search engine output (discussed above and below). In some implementations, user input may- go through multiple entity recognition, the attribute recognition, and intent recognition steps, until the input is fully resolved.
- the intent recognizer deciphers the intent of a sentence, and also deciphers the differences in nuances of intent. For instance, given "I would like to see the movie Top Gun” versus "I would like to see a movie like Top Gun", the parse trees would be different.
- the rules based recognition recognizes sentences based on predefined rules. Predefined rules are specific to a domain space, for example, entertainment.
- the naive Bayes classifier component just requires a training data set to recognize intent.
- the entity recognizer 1 07 uses the inputs mentioned above, recognizes entities in user input. Examples of entities are “Tom cruise” in “can I watch a Tom Cruise movie", or "Where Eagles Dare” in “when was Where Eagles Dare released”.
- the entity recognizer 1007 can be rules driven and/or a Bayes classifer. For example, linguistic elements such as nouns and gerunds can be designated as entities in a set of rules, or that association can arise during a supervised training process for the Bayes classifer. Entity recognition can, optionally, involve error correction or compensation for errors in user input (such as errors in speech to text recognition).
- a component used for resolution is the entity relationship graph.
- an output of the entity recognizer 1007 is a probability score for subsets of input to be entities.
- the application specific attribute search engine 1011 recognizes attributes such as “latest”, “recent”, “like” etc. Here again, there could be conflicts with entities. For example “Tomorrow None Dies” is an entity (a movie), and, when used in a sentence, there could be an ambiguity in interpreting "tomorrow” as an attribute. The scoring of tomorrow as an attribute may be lower than the scoring of "tomorrow” as part of "Tomorrow None Dies” as determined by entity relationship graph (which may depend on other elements of the input, e.g., the words “movie”, “show”, “actor”, etc.).
- the output of the attribute search engine 101 1 is a probability score for input words similar to that of the output of entity recognizer 1007.
- the language analyzer 1006 is a pluggable module in the architecture to enable to system to support multiple languages. While understanding the semantics of user input is not constrained to the language analyzer 1006 alone, the core modules of the architecture such as dialog context module 1003 or graph engine 1010 are language independent. As mentioned earlier, the language module alone cannot do much more than analysis of a sentence and performing tasks such a relating a pronoun to its subject/object etc. ("The Led Zeppelin song in the OST of the recent Daniel Craig movie... Who perfonned it?"), it is ineffective in isolation to associate pronouns across exchanges. It is the interaction with the session dialog context module 1003, that enables resolution of pronouns across exchanges as in the following: Ql : Who acts as obi- wan Kenobi in the new star wars?
- dialog session context is a simple state maintenance of the last active enti ty or entities
- the following examples show the lurking complexity in dialog session context:
- pronouns "his”, “hers”, and “they” are words that link the present user input to a previous user input and/or system response.
- Other pronouns, as well as syntactic expletives, can act as linguistic linking elements.
- Whether a particular word or phrase used by the user in a later question is a suitable or appropriate link to an entity mentioned in an earlier input (or some other part of the earlier input) is determined by examining the attributes of the earlier entity and the attributes of the potential linking element. For example, ''his" is a suitable link to Dustm Hoffman in the example above because Dustin Hoffman is male, and “his” is a male gender pronoun. Moreover, “his” is a possessive pronoun, which is appropriate because the user is referring to movies in which Dustin Hoffman appears.
- the system may elect to save all intents during a session (and/or entities, attributes, etc.), but may only use the one intent that is scored highest for a particular input.
- an intent that accrued relatively earlier in the dialog exchange applies much later in the conversation. Maintaining the state in this way facilitates a succinct and directed response as in A2, almost matching a human interaction.
- the directed responses illustrated above are possible with the intent analyzer 1008 and entity recognizer 1009 working in close concert with the personalization based intent analyzer 1009.
- These modules are all assisted by an application specific attribute search engine 1011 that assists in determining relevant attributes (e.g., latest, less of violence, more of action) and assigns weights to them. So a user input exchange would come from the speech to text engine 1002, would be processed by the modules, analyzers, and engines working in concert (with the query execittion engine 1004 playing a coordinating role), and would yield one or more candidate interpretations of the user input.
- the syste may have two alternative candidate representations wherein one has "Bombay” as an entity (there is a movie called Bombay) with “bomb blast” being another and the other has “Bombay bomb blast” as a single entity in another.
- the system attempts to resolve between these candidate representations by engaging in a dialog with the user, on the basis of the presence of the o ther recognized entity Kay Kay Menon who is an actor.
- the question(s) to formulate depend on the ambiguity that arises.
- the actor entity is known, it is the associated movie entities that are ambiguous.
- the system would ask questions concerning the movie entities.
- the system has a set of forms that are used as a model to form questions to resolve the ambiguities.
- resolution of ambiguity can be done, without engaging in a dialog, by knowing user's preferences. For instance, the user may ask "Is there a sox game tonight?" While this question has an ambiguous portion - the ambiguity of the team being the Boston Red Sox or the Chicago White Sox - if the system is aware that user's preference is Red Sox, then the response can be directed to displaying a Red Sox game schedule if there is one thai night. In instances where there are multiple matches across domains, the domain match resulting in the higher overall confidence score will win.
- Personalization of results can also be done, when applicable, based on the nature of the query. For instance, if the user states “show me movies of Tom Cruise tonight”, this query should not apply personalization but just return latest movies of Tom Cruise. However if user states "show me sports tonight", system should apply personalization and display sports and games that are known to be of interest to the user based on his explicit preferences or implicit actions captured from various sources of user activity information.
- a user preference signature can be provided by the system using known techniques for discovering and storing such user preference information.
- the relationship or connection engine 1010 is one of the modules that plays role in comprehending user input to offer a directed response.
- the relationship engine could be implemented in many ways, a graph data structure being one instance so that we may call the relationship engine by the name graph engine.
- the graph engine evaluates the user input in the backdrop of known weighted connections between entities.
- the graph engine in this instance is trivially able to disambiguate since a quick analysis of the path between the two Tony Montana entities respectively and the entity of Michelle Pfeifier quickly reveals that the actor Tony Montana never collaborated with Michelle Pfeiffer, whereas the movie Scarface (about the character Tony Montana) starred Michelle Pfeiffer. Thus, the system will conclude that it can safely ignore the actor Tony Montana and that the user wants to know the name of the character played by Michelle Pfeiffer in the movie Scarface.
- the graph engine 1010 assists when the system is unable to determine the user intent despite the fact that the entity recognizer 1007 has computed the entities specified by the user. This is illustrated by the follo ing examples in which the user intent cannot be inferred or when the confidence score of the user intent is below a threshold. In such a scenario, two illustrative strategies could be taken by a conversation system to get the user's specific intent.
- the system determined the most important keywords from the user utterance and treats each result candidate as a document, calculates a relevance score of each document based on the each keyword's relevance, and presents the top few documents to the user for him to peruse. This approach is similar to the web search engines.
- the system admits to the user that it cannot process the user request or that the information it gathered is insufficient, thereby prompting the user to provide more information or a subsequent query.
- a third strategy is employed so long as entity recognition has succeeded (even when the specific user intent calculation has failed). Note that entity recognition computation is successful in a large number of cases, especially when the user names or gives very good clues as to the entities in his utterance, which is usually the case.
- Entities are nodes and relationships are edges in this graph. This mapping involving entities / nodes and relationships / edges can involve one-to-one, one-to-many, and many-to-many mapping based on information and metadata associated with the entities being mapped.
- Entities / nodes have types from a finite and well-defined set of types.
- a . Number of presently recognized entities is 0: In this case, the system gives one from a fixed set of responses based on response templates using the information from the user that is recognized. The template selections is based on rules and/or Bayes classifier determinations.
- b. Number of recognized entities is 1 : Suppose that the entity identifier is A and the ty pe of the entity is B and we know the finite set S of all the distinct
- edge/relationship types A can be involved in.
- a system employing the techniques set forth herein speaks and/or displays a human- consumption multi-modal response template T(A,B,S) that follows from an applicable template response based on A, B and S.
- the template response is selected from a set of manually constructed template responses based on a priori knowledge of all possible node types and edge types, which form finite well-defined sets.
- the response and I system is designed to allo the user to select, using a touch interface or even vocally, more information and entities related to A.
- the IR system appropriately employs and delivers (via speech and/or display) the corresponding two independent human-consumption multi-modal response templates T(A, B, S) and T(A', B " . S').
- the IR system selects a shortest edge length path between A and A'. If there are clues available in user utterance, the IR system may prefer some shortest paths to others. Let there be k ' nodes in the selected shortest path denoted A ::: A /, A , A3, ...Ak' :::: A ' where k' ⁇ k ⁇ l and for each 2, where i goes from / to k ', the ith entity node of the path is represented by the 3-tuple A h B it E : , where A; is the entity identifier, B, is the entity type and E,- is a list of one or two elements corresponding to the one or two edges connected to A t that are present in the selected shortest path, in this case the IR system then delivers to the user an appropriate response based on an intelligent composition of the sequence of human -consumption multi-modal response templates T(A t , B t , E
- the 1R system simply calculates K maximal components Ci,C2,..Ck where each component C; is such each entity node A in Q is at a distance of no more than k edges away from at least one other node A' of Q. For each Q . the IR System selects an appropriate representative sequence of human-consumption multi-modal response template sequences, similar to c. above and composes a response based on the response template sequences for each component.
- the techniques set forth above are also used, in certain implementations, to reset all or part of the conversation state values. For example, assume a system has retained certain entities and/or attributes from user input and system responses. When the user provides subsequent input, the techniques disclosed herein enable the new- input to be evaluated against the retained values.
- the techniques disclosed herein enable the new- input to be evaluated against the retained values.
- Speaking in terms of a graph model if linguistic elements of the subsequent input are found in an entity / relationship graph to be too far removed from the retained information (also in the graph), it can be inferred that the user's subsequent intent has changed from the previous one. In such a case, the earlier retained information can be reset and/or disregarded when performing the subsequent search.
- embodiments of the invention can recognize that a user has provided subsequent input that lacks entities, attributes, or relationship information, but the input is an appropriate response to an earlier system response.
- a system implementing the techniques set forth herein may present a set of movies as a response to a first user input. The user may then respond that she is not interested in any of the movies presented. In such a case, the system would retain the various conversation state values and make a further attempt to satisfy the user's previous request (by, e.g., requesting additional information about the ty e of movie desired or requesting additional information to better focus the search, such as actor names, genre, etc.).
- the techniques and systems disclosed herein may be implemented as a computer program product for use with a computer system or computerized electronic device.
- Such implementations may include a series of computer instructions, or logic, fixed either on a tangible medium, such as a computer readable medium (e.g., a diskette, CD-ROM, ROM, flash memory or other memory or fixed disk) or transmittable to a computer system or a device, via a modem or other interface device, such as a communications adapter connected to a network over a medium.
- a computer readable medium e.g., a diskette, CD-ROM, ROM, flash memory or other memory or fixed disk
- modem or other interface device such as a communications adapter connected to a network over a medium.
- the medium may be either a tangible medium (e.g., optical or analog communications lines) or a medium implemented with wireless techniques (e.g., Wi- Fi, cellular, microwave, infrared or other transmission techniques).
- the series of computer instructions embodies at least part of the functionality described herein with respect to the system. Those skilled in the art should appreciate that such computer instructions can be written in a number of programming languages for use with many computer architectures or operating systems.
- Such instructions may be stored in any tangible memory device, such as semiconductor, magnetic, optical or other memory devices, and may be transmitted using any communications technology, such as optical, infrared, microwave, or other transmission technologies.
- Such a computer program product may be distributed as a removable medium with accompanying printed or electronic documentation (e.g., shrink wrapped software), preloaded with a computer system (e.g., on system ROM or fixed disk), or distributed from a server or electronic bulletin board o ver the network (e.g., the Internet or World Wide Web).
- a computer system e.g., on system ROM or fixed disk
- a server or electronic bulletin board e.g., the Internet or World Wide Web
- some embodiments of the invention may be implemented as a combination of both software (e.g., a computer program product) and hardware. Still other embodiments of the invention are implemented as entirely hardware, or entirely software (e.g., a computer program product).
Abstract
Description
Claims
Priority Applications (13)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015523287A JP6313298B2 (en) | 2012-07-20 | 2013-07-19 | Method for estimating user intention in search input of interactive interaction system and system therefor |
MX2017005665A MX362496B (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interfaction system. |
KR1020197028910A KR102229850B1 (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversαtional interaction system |
AU2013292377A AU2013292377B2 (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interaction system |
CA2879778A CA2879778C (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interaction system |
KR1020157004024A KR102030078B1 (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversαtional interaction system |
EP22020584.3A EP4195094A1 (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interaction system |
CN201380046675.3A CN104871150B (en) | 2012-07-20 | 2013-07-19 | The method and system of the user view in search input is inferred in dialogue interactive system |
EP13819772.8A EP2875445A4 (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interfaction system |
MX2019000838A MX2019000838A (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interfaction system. |
EP17210590.0A EP3346393A1 (en) | 2012-07-20 | 2013-07-19 | Inferring user intent in search input in a conversational interaction system using domains |
MX2015000909A MX347542B (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interfaction system. |
AU2019203718A AU2019203718A1 (en) | 2012-07-20 | 2019-05-28 | Method of and system for inferring user intent in search input in a conversational interaction system |
Applications Claiming Priority (10)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201261673867P | 2012-07-20 | 2012-07-20 | |
US61/673,867 | 2012-07-20 | ||
US201261712721P | 2012-10-11 | 2012-10-11 | |
US61/712,721 | 2012-10-11 | ||
US13/667,400 US9424233B2 (en) | 2012-07-20 | 2012-11-02 | Method of and system for inferring user intent in search input in a conversational interaction system |
US13/667,400 | 2012-11-02 | ||
US13/667,388 US8577671B1 (en) | 2012-07-20 | 2012-11-02 | Method of and system for using conversation state information in a conversational interaction system |
US13/667,388 | 2012-11-02 | ||
US13/874,523 | 2013-05-01 | ||
US13/874,523 US9183183B2 (en) | 2012-07-20 | 2013-05-01 | Method of and system for inferring user intent in search input in a conversational interaction system |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2014015267A2 true WO2014015267A2 (en) | 2014-01-23 |
WO2014015267A3 WO2014015267A3 (en) | 2014-05-15 |
Family
ID=49487944
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2013/051288 WO2014015267A2 (en) | 2012-07-20 | 2013-07-19 | Method of and system for inferring user intent in search input in a conversational interfaction system |
Country Status (10)
Country | Link |
---|---|
US (8) | US8577671B1 (en) |
EP (5) | EP2875445A4 (en) |
JP (4) | JP6313298B2 (en) |
KR (2) | KR102229850B1 (en) |
CN (2) | CN107633042A (en) |
AU (2) | AU2013292377B2 (en) |
CA (3) | CA3125021A1 (en) |
HK (1) | HK1257944A1 (en) |
MX (4) | MX2019000838A (en) |
WO (1) | WO2014015267A2 (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893771A (en) * | 2016-04-15 | 2016-08-24 | 北京搜狗科技发展有限公司 | Information service method and device and device used for information services |
US10713288B2 (en) | 2017-02-08 | 2020-07-14 | Semantic Machines, Inc. | Natural language content generator |
US10762892B2 (en) | 2017-02-23 | 2020-09-01 | Semantic Machines, Inc. | Rapid deployment of dialogue system |
US10817170B2 (en) | 2018-03-23 | 2020-10-27 | Hyundai Motor Company | Apparatus and method for operating touch control based steering wheel |
US10824798B2 (en) | 2016-11-04 | 2020-11-03 | Semantic Machines, Inc. | Data collection for a new conversational dialogue system |
US11069340B2 (en) | 2017-02-23 | 2021-07-20 | Microsoft Technology Licensing, Llc | Flexible and expandable dialogue system |
US11132499B2 (en) | 2017-08-28 | 2021-09-28 | Microsoft Technology Licensing, Llc | Robust expandable dialogue system |
US11195516B2 (en) | 2017-02-23 | 2021-12-07 | Microsoft Technology Licensing, Llc | Expandable dialogue system |
US11436411B2 (en) | 2019-02-27 | 2022-09-06 | Google Llc | Detecting continuing conversations with computing devices |
US11676582B2 (en) | 2019-02-27 | 2023-06-13 | Google Llc | Detecting conversations with computing devices |
US11934787B2 (en) | 2021-04-29 | 2024-03-19 | International Business Machines Corporation | Intent determination in a messaging dialog manager system |
Families Citing this family (199)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8073681B2 (en) | 2006-10-16 | 2011-12-06 | Voicebox Technologies, Inc. | System and method for a cooperative conversational voice user interface |
US7818176B2 (en) | 2007-02-06 | 2010-10-19 | Voicebox Technologies, Inc. | System and method for selecting and presenting advertisements based on natural language processing of voice-based input |
US8140335B2 (en) | 2007-12-11 | 2012-03-20 | Voicebox Technologies, Inc. | System and method for providing a natural language voice user interface in an integrated voice navigation services environment |
US9305548B2 (en) | 2008-05-27 | 2016-04-05 | Voicebox Technologies Corporation | System and method for an integrated, multi-modal, multi-device natural language voice services environment |
US8326637B2 (en) | 2009-02-20 | 2012-12-04 | Voicebox Technologies, Inc. | System and method for processing multi-modal device interactions in a natural language voice services environment |
US8577671B1 (en) | 2012-07-20 | 2013-11-05 | Veveo, Inc. | Method of and system for using conversation state information in a conversational interaction system |
US9465833B2 (en) | 2012-07-31 | 2016-10-11 | Veveo, Inc. | Disambiguating user intent in conversational interaction system for large corpus information retrieval |
US9799328B2 (en) | 2012-08-03 | 2017-10-24 | Veveo, Inc. | Method for using pauses detected in speech input to assist in interpreting the input during conversational interaction for information retrieval |
US10031968B2 (en) | 2012-10-11 | 2018-07-24 | Veveo, Inc. | Method for adaptive conversation state management with filtering operators applied dynamically as part of a conversational interface |
US9111011B2 (en) | 2012-12-10 | 2015-08-18 | Google Inc. | Local query suggestions |
CN103020047A (en) * | 2012-12-31 | 2013-04-03 | 威盛电子股份有限公司 | Method for revising voice response and natural language dialogue system |
EP2994908B1 (en) | 2013-05-07 | 2019-08-28 | Veveo, Inc. | Incremental speech input interface with real time feedback |
US9946757B2 (en) | 2013-05-10 | 2018-04-17 | Veveo, Inc. | Method and system for capturing and exploiting user intent in a conversational interaction based information retrieval system |
US20190129941A2 (en) * | 2013-05-21 | 2019-05-02 | Happify, Inc. | Systems and methods for dynamic user interaction for improving happiness |
EP3937107A1 (en) | 2013-05-21 | 2022-01-12 | Tomer Ben-Kiki | Systems and methods for providing on-line services |
US10813584B2 (en) | 2013-05-21 | 2020-10-27 | Happify, Inc. | Assessing adherence fidelity to behavioral interventions using interactivity and natural language processing |
US9594542B2 (en) | 2013-06-20 | 2017-03-14 | Viv Labs, Inc. | Dynamically evolving cognitive architecture system based on training by third-party developers |
US10083009B2 (en) | 2013-06-20 | 2018-09-25 | Viv Labs, Inc. | Dynamically evolving cognitive architecture system planning |
US9633317B2 (en) * | 2013-06-20 | 2017-04-25 | Viv Labs, Inc. | Dynamically evolving cognitive architecture system based on a natural language intent interpreter |
US10474961B2 (en) | 2013-06-20 | 2019-11-12 | Viv Labs, Inc. | Dynamically evolving cognitive architecture system based on prompting for additional user input |
US20150088923A1 (en) * | 2013-09-23 | 2015-03-26 | Google Inc. | Using sensor inputs from a computing device to determine search query |
CN104598445B (en) * | 2013-11-01 | 2019-05-10 | 腾讯科技(深圳)有限公司 | Automatically request-answering system and method |
US10811013B1 (en) * | 2013-12-20 | 2020-10-20 | Amazon Technologies, Inc. | Intent-specific automatic speech recognition result generation |
US10140373B2 (en) | 2014-04-15 | 2018-11-27 | Facebook, Inc. | Eliciting user sharing of content |
US10474671B2 (en) | 2014-05-12 | 2019-11-12 | Google Llc | Interpreting user queries based on nearby locations |
US9645703B2 (en) * | 2014-05-14 | 2017-05-09 | International Business Machines Corporation | Detection of communication topic change |
US9477713B2 (en) | 2014-06-06 | 2016-10-25 | Netflix, Inc. | Selecting and ordering groups of titles |
US10275485B2 (en) | 2014-06-10 | 2019-04-30 | Google Llc | Retrieving context from previous sessions |
US9811352B1 (en) | 2014-07-11 | 2017-11-07 | Google Inc. | Replaying user input actions using screen capture images |
US10116600B2 (en) * | 2014-08-14 | 2018-10-30 | Excalibur Ip, Llc | Expressing statements in messages with personalized expression style |
JP5957048B2 (en) * | 2014-08-19 | 2016-07-27 | インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Machines Corporation | Teacher data generation method, generation system, and generation program for eliminating ambiguity |
WO2016028695A1 (en) | 2014-08-20 | 2016-02-25 | Google Inc. | Interpreting user queries based on device orientation |
US10430445B2 (en) * | 2014-09-12 | 2019-10-01 | Nuance Communications, Inc. | Text indexing and passage retrieval |
US10460239B2 (en) | 2014-09-16 | 2019-10-29 | International Business Machines Corporation | Generation of inferred questions for a question answering system |
US9626703B2 (en) | 2014-09-16 | 2017-04-18 | Voicebox Technologies Corporation | Voice commerce |
US9898459B2 (en) | 2014-09-16 | 2018-02-20 | Voicebox Technologies Corporation | Integration of domain information into state transitions of a finite state transducer for natural language processing |
EP3207467A4 (en) | 2014-10-15 | 2018-05-23 | VoiceBox Technologies Corporation | System and method for providing follow-up responses to prior natural language inputs of a user |
US10216846B2 (en) * | 2014-10-22 | 2019-02-26 | Thomson Reuters (Grc) Llc | Combinatorial business intelligence |
US10431214B2 (en) * | 2014-11-26 | 2019-10-01 | Voicebox Technologies Corporation | System and method of determining a domain and/or an action related to a natural language input |
US10614799B2 (en) | 2014-11-26 | 2020-04-07 | Voicebox Technologies Corporation | System and method of providing intent predictions for an utterance prior to a system detection of an end of the utterance |
US9672203B1 (en) * | 2014-12-01 | 2017-06-06 | Amazon Technologies, Inc. | Calculating a maturity level of a text string |
US9466297B2 (en) | 2014-12-09 | 2016-10-11 | Microsoft Technology Licensing, Llc | Communication system |
US10885129B2 (en) * | 2014-12-10 | 2021-01-05 | Google Llc | Using frames for action dialogs |
US10417345B1 (en) * | 2014-12-22 | 2019-09-17 | Amazon Technologies, Inc. | Providing customer service agents with customer-personalized result of spoken language intent |
US11574621B1 (en) | 2014-12-23 | 2023-02-07 | Amazon Technologies, Inc. | Stateless third party interactions |
US9852136B2 (en) | 2014-12-23 | 2017-12-26 | Rovi Guides, Inc. | Systems and methods for determining whether a negation statement applies to a current or past query |
US9854049B2 (en) | 2015-01-30 | 2017-12-26 | Rovi Guides, Inc. | Systems and methods for resolving ambiguous terms in social chatter based on a user profile |
US10418032B1 (en) | 2015-04-10 | 2019-09-17 | Soundhound, Inc. | System and methods for a virtual assistant to manage and use context in a natural language dialog |
US9747279B2 (en) * | 2015-04-17 | 2017-08-29 | Microsoft Technology Licensing, Llc | Context carryover in language understanding systems or methods |
US20160335544A1 (en) * | 2015-05-12 | 2016-11-17 | Claudia Bretschneider | Method and Apparatus for Generating a Knowledge Data Model |
US20160360264A1 (en) | 2015-06-02 | 2016-12-08 | Rovi Guides, Inc. | Systems and methods for determining conceptual boundaries in content |
US10631057B2 (en) | 2015-07-24 | 2020-04-21 | Nuance Communications, Inc. | System and method for natural language driven search and discovery in large data sources |
US10847175B2 (en) * | 2015-07-24 | 2020-11-24 | Nuance Communications, Inc. | System and method for natural language driven search and discovery in large data sources |
US10255921B2 (en) * | 2015-07-31 | 2019-04-09 | Google Llc | Managing dialog data providers |
US10134389B2 (en) | 2015-09-04 | 2018-11-20 | Microsoft Technology Licensing, Llc | Clustering user utterance intents with semantic parsing |
US10236017B1 (en) * | 2015-09-29 | 2019-03-19 | Amazon Technologies, Inc. | Goal segmentation in speech dialogs |
US10831811B2 (en) * | 2015-12-01 | 2020-11-10 | Oracle International Corporation | Resolution of ambiguous and implicit references using contextual information |
US10311862B2 (en) * | 2015-12-23 | 2019-06-04 | Rovi Guides, Inc. | Systems and methods for conversations with devices about media using interruptions and changes of subjects |
US9996531B1 (en) * | 2016-03-29 | 2018-06-12 | Facebook, Inc. | Conversational understanding |
WO2017197018A2 (en) * | 2016-05-10 | 2017-11-16 | Trustees Of Tufts College | Systems and methods enabling online one-shot learning and generalization by intelligent systems of task-relevant features and transfer to a cohort of intelligent systems |
CN107402912B (en) * | 2016-05-19 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Method and device for analyzing semantics |
US11036743B2 (en) * | 2016-05-23 | 2021-06-15 | Google Llc | Methods, systems, and media for presenting content organized by category |
CN107589828A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
US10083451B2 (en) | 2016-07-08 | 2018-09-25 | Asapp, Inc. | Using semantic processing for customer support |
WO2018009231A1 (en) | 2016-07-08 | 2018-01-11 | Asapp, Inc. | Automatically responding to a request of a user |
US10331784B2 (en) | 2016-07-29 | 2019-06-25 | Voicebox Technologies Corporation | System and method of disambiguating natural language processing requests |
US20180052842A1 (en) * | 2016-08-16 | 2018-02-22 | Ebay Inc. | Intelligent online personal assistant with natural language understanding |
US20180052885A1 (en) * | 2016-08-16 | 2018-02-22 | Ebay Inc. | Generating next user prompts in an intelligent online personal assistant multi-turn dialog |
CN106469212B (en) | 2016-09-05 | 2019-10-15 | 北京百度网讯科技有限公司 | Man-machine interaction method and device based on artificial intelligence |
CN115858730A (en) | 2016-09-29 | 2023-03-28 | 微软技术许可有限责任公司 | Conversational data analysis |
JP6951712B2 (en) * | 2016-09-30 | 2021-10-20 | 株式会社Nextremer | Dialogue devices, dialogue systems, dialogue methods, and programs |
GB201616990D0 (en) * | 2016-10-06 | 2016-11-23 | Microsoft Technology Licensing Llc | User interface |
US11232101B2 (en) | 2016-10-10 | 2022-01-25 | Microsoft Technology Licensing, Llc | Combo of language understanding and information retrieval |
US11200273B2 (en) * | 2016-10-16 | 2021-12-14 | Ebay Inc. | Parallel prediction of multiple image aspects |
US11004131B2 (en) | 2016-10-16 | 2021-05-11 | Ebay Inc. | Intelligent online personal assistant with multi-turn dialog based on visual search |
US10860898B2 (en) | 2016-10-16 | 2020-12-08 | Ebay Inc. | Image analysis and prediction based visual search |
US11748978B2 (en) | 2016-10-16 | 2023-09-05 | Ebay Inc. | Intelligent online personal assistant with offline visual search database |
US10431202B2 (en) * | 2016-10-21 | 2019-10-01 | Microsoft Technology Licensing, Llc | Simultaneous dialogue state management using frame tracking |
US10535005B1 (en) | 2016-10-26 | 2020-01-14 | Google Llc | Providing contextual actions for mobile onscreen content |
EP3533022B1 (en) | 2016-10-31 | 2024-03-27 | Rovi Guides, Inc. | Systems and methods for flexibly using trending topics as parameters for recommending media assets that are related to a viewed media asset |
GB201620714D0 (en) | 2016-12-06 | 2017-01-18 | Microsoft Technology Licensing Llc | Information retrieval system |
US10888271B2 (en) * | 2016-12-08 | 2021-01-12 | Louise M. Falevsky | Systems, apparatus and methods for using biofeedback to facilitate a discussion |
US10109275B2 (en) | 2016-12-19 | 2018-10-23 | Asapp, Inc. | Word hash language model |
US10650311B2 (en) | 2016-12-19 | 2020-05-12 | Asaap, Inc. | Suggesting resources using context hashing |
KR20180075009A (en) * | 2016-12-26 | 2018-07-04 | 현대자동차주식회사 | Speech processing apparatus, vehicle having the same and speech processing method |
US10389707B2 (en) * | 2017-01-30 | 2019-08-20 | International Business Machines Corporation | System, method and computer program product for generating a cognitive one-time password |
EP3552114A4 (en) * | 2017-02-08 | 2020-05-20 | Semantic Machines, Inc. | Natural language content generator |
US11100384B2 (en) | 2017-02-14 | 2021-08-24 | Microsoft Technology Licensing, Llc | Intelligent device user interactions |
US11010601B2 (en) | 2017-02-14 | 2021-05-18 | Microsoft Technology Licensing, Llc | Intelligent assistant device communicating non-verbal cues |
US10467510B2 (en) | 2017-02-14 | 2019-11-05 | Microsoft Technology Licensing, Llc | Intelligent assistant |
US10325592B2 (en) * | 2017-02-15 | 2019-06-18 | GM Global Technology Operations LLC | Enhanced voice recognition task completion |
WO2018156930A1 (en) * | 2017-02-24 | 2018-08-30 | Endotronix, Inc. | Wireless sensor reader assembly |
US10489400B2 (en) | 2017-03-03 | 2019-11-26 | International Business Machines Corporation | Question pre-processing in a question and answer system |
WO2018175291A1 (en) * | 2017-03-20 | 2018-09-27 | Ebay Inc. | Detection of mission change in conversation |
US10636418B2 (en) | 2017-03-22 | 2020-04-28 | Google Llc | Proactive incorporation of unsolicited content into human-to-computer dialogs |
US11488033B2 (en) | 2017-03-23 | 2022-11-01 | ROVl GUIDES, INC. | Systems and methods for calculating a predicted time when a user will be exposed to a spoiler of a media asset |
US11695711B2 (en) | 2017-04-06 | 2023-07-04 | International Business Machines Corporation | Adaptive communications display window |
CN108733686A (en) * | 2017-04-17 | 2018-11-02 | 伊姆西Ip控股有限责任公司 | Information processing method and equipment |
CN107273406B (en) * | 2017-04-27 | 2020-06-05 | 上海奔影网络科技有限公司 | Dialogue processing method and device in task dialogue system |
US9865260B1 (en) * | 2017-05-03 | 2018-01-09 | Google Llc | Proactive incorporation of unsolicited content into human-to-computer dialogs |
US10606894B2 (en) | 2017-05-12 | 2020-03-31 | International Business Machines Corporation | Cognitive search query validation |
US10552426B2 (en) | 2017-05-23 | 2020-02-04 | International Business Machines Corporation | Adaptive conversational disambiguation system |
CA3002383A1 (en) | 2017-05-24 | 2018-11-24 | Arun Sreedhara | Methods and systems for correcting, based on speech, input generated using automatic speech recognition |
US10909441B2 (en) | 2017-06-02 | 2021-02-02 | Microsoft Technology Licensing, Llc | Modeling an action completion conversation using a knowledge graph |
US10789425B2 (en) * | 2017-06-05 | 2020-09-29 | Lenovo (Singapore) Pte. Ltd. | Generating a response to a natural language command based on a concatenated graph |
US10510336B2 (en) * | 2017-06-12 | 2019-12-17 | International Business Machines Corporation | Method, apparatus, and system for conflict detection and resolution for competing intent classifiers in modular conversation system |
EP3619620A4 (en) | 2017-06-26 | 2020-11-18 | Microsoft Technology Licensing, LLC | Generating responses in automated chatting |
US10762423B2 (en) | 2017-06-27 | 2020-09-01 | Asapp, Inc. | Using a neural network to optimize processing of user requests |
US10387463B2 (en) | 2017-07-06 | 2019-08-20 | International Business Machines Corporation | Dialog agent for conducting task-oriented computer-based communications |
US10861455B2 (en) * | 2017-07-13 | 2020-12-08 | Microsoft Technology Licensing, Llc | Inference on date time constraint expressions |
US10318927B2 (en) | 2017-07-17 | 2019-06-11 | ExpertHiring, LLC | Method and system for managing, matching, and sourcing employment candidates in a recruitment campaign |
US10884598B2 (en) * | 2017-09-29 | 2021-01-05 | Oracle International Corporation | Analytics for a bot system |
JP7095254B2 (en) * | 2017-10-10 | 2022-07-05 | トヨタ自動車株式会社 | Dialogue system and domain determination method |
WO2019074069A1 (en) | 2017-10-11 | 2019-04-18 | 株式会社ブリヂストン | Vibration-damping device |
US10769186B2 (en) | 2017-10-16 | 2020-09-08 | Nuance Communications, Inc. | System and method for contextual reasoning |
US11372862B2 (en) | 2017-10-16 | 2022-06-28 | Nuance Communications, Inc. | System and method for intelligent knowledge access |
CN107992562A (en) * | 2017-11-29 | 2018-05-04 | 宁波高新区锦众信息科技有限公司 | A kind of intelligent interactive method and system |
US10497004B2 (en) | 2017-12-08 | 2019-12-03 | Asapp, Inc. | Automating communications using an intent classifier |
US10489792B2 (en) | 2018-01-05 | 2019-11-26 | Asapp, Inc. | Maintaining quality of customer support messages |
US10430447B2 (en) * | 2018-01-31 | 2019-10-01 | International Business Machines Corporation | Predicting intent of a user from anomalous profile data |
US11145291B2 (en) * | 2018-01-31 | 2021-10-12 | Microsoft Technology Licensing, Llc | Training natural language system with generated dialogues |
US10861440B2 (en) * | 2018-02-05 | 2020-12-08 | Microsoft Technology Licensing, Llc | Utterance annotation user interface |
KR101914583B1 (en) * | 2018-02-12 | 2018-11-05 | 주식회사 머니브레인 | Interactive ai agent system and method for actively providing a security related service based on monitoring of a dialogue session among users via the dialogue session or a separate session, computer readable recording medium |
US10210244B1 (en) | 2018-02-12 | 2019-02-19 | Asapp, Inc. | Updating natural language interfaces by processing usage data |
US11182565B2 (en) * | 2018-02-23 | 2021-11-23 | Samsung Electronics Co., Ltd. | Method to learn personalized intents |
KR102445365B1 (en) | 2018-03-19 | 2022-09-20 | 현대자동차주식회사 | Dialogue processing apparatus, vehicle having the same and dialogue processing method |
US11133001B2 (en) * | 2018-03-20 | 2021-09-28 | Microsoft Technology Licensing, Llc | Generating dialogue events for natural language system |
CN108763264B (en) * | 2018-03-30 | 2022-06-17 | 斑马网络技术有限公司 | Intelligent search system based on vehicle and search method thereof |
CN108595423A (en) * | 2018-04-16 | 2018-09-28 | 苏州英特雷真智能科技有限公司 | A kind of semantic analysis of the dynamic ontology structure based on the variation of attribute section |
CN108549700B (en) * | 2018-04-17 | 2021-06-29 | 携程旅游网络技术(上海)有限公司 | Page pre-search method and system, storage medium and electronic equipment |
US10782986B2 (en) * | 2018-04-20 | 2020-09-22 | Facebook, Inc. | Assisting users with personalized and contextual communication content |
US10169315B1 (en) | 2018-04-27 | 2019-01-01 | Asapp, Inc. | Removing personal information from text using a neural network |
US11520989B1 (en) * | 2018-05-17 | 2022-12-06 | Workday, Inc. | Natural language processing with keywords |
US11314940B2 (en) | 2018-05-22 | 2022-04-26 | Samsung Electronics Co., Ltd. | Cross domain personalized vocabulary learning in intelligent assistants |
CN108920497B (en) * | 2018-05-23 | 2021-10-15 | 北京奇艺世纪科技有限公司 | Man-machine interaction method and device |
US10776582B2 (en) * | 2018-06-06 | 2020-09-15 | International Business Machines Corporation | Supporting combinations of intents in a conversation |
US10915588B2 (en) | 2018-08-02 | 2021-02-09 | International Business Machines Corporation | Implicit dialog approach operating a conversational access interface to web content |
US10824658B2 (en) | 2018-08-02 | 2020-11-03 | International Business Machines Corporation | Implicit dialog approach for creating conversational access to web content |
US11216510B2 (en) | 2018-08-03 | 2022-01-04 | Asapp, Inc. | Processing an incomplete message with a neural network to generate suggested messages |
CN109492077B (en) * | 2018-09-29 | 2020-09-29 | 北京智通云联科技有限公司 | Knowledge graph-based petrochemical field question-answering method and system |
US11551004B2 (en) | 2018-11-13 | 2023-01-10 | Asapp, Inc. | Intent discovery with a prototype classifier |
US10747957B2 (en) | 2018-11-13 | 2020-08-18 | Asapp, Inc. | Processing communications using a prototype classifier |
US10769378B2 (en) | 2018-11-14 | 2020-09-08 | International Business Machines Corporation | Extending system entities for conversational system |
CN111223477B (en) * | 2018-11-23 | 2023-01-24 | 珠海格力电器股份有限公司 | Method and device for topic upward movement during man-machine interaction |
CN109544195A (en) * | 2018-12-24 | 2019-03-29 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
US11151578B2 (en) * | 2018-12-31 | 2021-10-19 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for processing customer inquiries |
US10754909B2 (en) * | 2018-12-31 | 2020-08-25 | Ebay Inc. | Dynamic link preview generation |
WO2020142084A1 (en) * | 2018-12-31 | 2020-07-09 | Didi Research America, Llc | Methods and systems for processing customer inquiries |
US10924417B2 (en) | 2019-01-11 | 2021-02-16 | International Business Machines Corporation | Cognitive communication channel-adaptation based on context |
US10586532B1 (en) * | 2019-01-28 | 2020-03-10 | Babylon Partners Limited | Flexible-response dialogue system through analysis of semantic textual similarity |
WO2020166183A1 (en) * | 2019-02-13 | 2020-08-20 | ソニー株式会社 | Information processing device and information processing method |
CN110442694A (en) * | 2019-02-26 | 2019-11-12 | 北京蓦然认知科技有限公司 | A kind of intelligent interaction platform training method, apparatus, equipment |
CN111737408A (en) * | 2019-03-25 | 2020-10-02 | 阿里巴巴集团控股有限公司 | Dialogue method and equipment based on script and electronic equipment |
US11948582B2 (en) | 2019-03-25 | 2024-04-02 | Omilia Natural Language Solutions Ltd. | Systems and methods for speaker verification |
CN110083685B (en) * | 2019-04-26 | 2021-05-04 | 北京零秒科技有限公司 | Data configuration method and device for intention recognition |
US11256868B2 (en) * | 2019-06-03 | 2022-02-22 | Microsoft Technology Licensing, Llc | Architecture for resolving ambiguous user utterance |
CN110232077B (en) * | 2019-06-19 | 2021-05-14 | 北京百度网讯科技有限公司 | Event context generation method and device |
US20210026901A1 (en) * | 2019-07-26 | 2021-01-28 | Rovi Guides, Inc. | Systems and methods for generating search suggestions for a search query of multiple entities |
US11126793B2 (en) * | 2019-10-04 | 2021-09-21 | Omilia Natural Language Solutions Ltd. | Unsupervised induction of user intents from conversational customer service corpora |
US11425064B2 (en) | 2019-10-25 | 2022-08-23 | Asapp, Inc. | Customized message suggestion with user embedding vectors |
US11329932B2 (en) | 2019-11-01 | 2022-05-10 | Microsoft Technology Licensing, Llc | Visual design of a conversational bot |
US11232791B2 (en) * | 2019-11-08 | 2022-01-25 | Rovi Guides, Inc. | Systems and methods for automating voice commands |
CA3143953A1 (en) | 2019-11-08 | 2021-05-14 | Rovi Guides, Inc. | Systems and methods for automating voice commands |
US10862841B1 (en) | 2019-11-08 | 2020-12-08 | Rovi Guides, Inc. | Systems and methods for automating voice commands |
CN111046256B (en) * | 2019-12-03 | 2024-02-06 | 上海二六三通信有限公司 | Method and device for voice interaction based on interaction engine cluster |
CN111124347B (en) * | 2019-12-03 | 2023-05-26 | 杭州蓦然认知科技有限公司 | Method and device for forming interaction engine cluster through aggregation |
US11625535B1 (en) * | 2019-12-05 | 2023-04-11 | American Express Travel Related Services Company, Inc. | Computer-based systems having data structures configured to execute SIC4/SIC8 machine learning embedded classification of entities and methods of use thereof |
US11481442B2 (en) | 2019-12-12 | 2022-10-25 | International Business Machines Corporation | Leveraging intent resolvers to determine multiple intents |
US11586677B2 (en) | 2019-12-12 | 2023-02-21 | International Business Machines Corporation | Resolving user expression having dependent intents |
CN111177358B (en) * | 2019-12-31 | 2023-05-12 | 华为技术有限公司 | Intention recognition method, server and storage medium |
US20230025049A1 (en) * | 2020-01-07 | 2023-01-26 | Lg Electronics Inc. | Multi-modal input-based service provision device and service provision method |
CN111341308B (en) * | 2020-02-12 | 2023-07-21 | 百度在线网络技术(北京)有限公司 | Method and device for outputting information |
US11321534B2 (en) * | 2020-03-11 | 2022-05-03 | International Business Machines Corporation | Conversation space artifact generation using natural language processing, machine learning, and ontology-based techniques |
CN111460083B (en) * | 2020-03-31 | 2023-07-25 | 北京百度网讯科技有限公司 | Method and device for constructing document title tree, electronic equipment and storage medium |
US11531821B2 (en) * | 2020-08-13 | 2022-12-20 | Salesforce, Inc. | Intent resolution for chatbot conversations with negation and coreferences |
US11556716B2 (en) * | 2020-08-24 | 2023-01-17 | Intuit Inc. | Intent prediction by machine learning with word and sentence features for routing user requests |
US11263407B1 (en) | 2020-09-01 | 2022-03-01 | Rammer Technologies, Inc. | Determining topics and action items from conversations |
US11756553B2 (en) | 2020-09-17 | 2023-09-12 | International Business Machines Corporation | Training data enhancement |
US11527237B1 (en) * | 2020-09-18 | 2022-12-13 | Amazon Technologies, Inc. | User-system dialog expansion |
CN112269607A (en) * | 2020-11-17 | 2021-01-26 | 北京百度网讯科技有限公司 | Applet control method, system, server and terminal device |
US11093718B1 (en) * | 2020-12-01 | 2021-08-17 | Rammer Technologies, Inc. | Determining conversational structure from speech |
CN112579758A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Model training method, device, equipment, storage medium and program product |
US11610249B2 (en) * | 2021-01-13 | 2023-03-21 | Walmart Apollo, Llc | System, method, and computer readable medium for automatic item rankings |
US11269969B1 (en) * | 2021-02-08 | 2022-03-08 | Capital One Services, Llc | Systems and methods for automatic and adaptive browser bookmarks |
US11417428B1 (en) | 2021-04-05 | 2022-08-16 | Lark Technologies, Inc. | Conversational services for artificial intelligence health support |
US11450422B1 (en) * | 2021-04-05 | 2022-09-20 | Lark Technologies, Inc. | Artificial intelligence health support architecture |
KR102624790B1 (en) * | 2021-05-12 | 2024-01-12 | 주식회사 카카오엔터프라이즈 | Natural language processing apparatus for intent analysis and processing of multi-intent speech, program and its control method |
TWI776589B (en) * | 2021-07-13 | 2022-09-01 | 國立臺灣師範大學 | Emotional Reply System |
WO2023003605A1 (en) * | 2021-07-21 | 2023-01-26 | Get Together AI, Inc. | Channel agnostic scheduling system |
US11908083B2 (en) | 2021-08-31 | 2024-02-20 | Snap Inc. | Deforming custom mesh based on body mesh |
US11663792B2 (en) | 2021-09-08 | 2023-05-30 | Snap Inc. | Body fitted accessory with physics simulation |
US11798238B2 (en) | 2021-09-14 | 2023-10-24 | Snap Inc. | Blending body mesh into external mesh |
US11836866B2 (en) | 2021-09-20 | 2023-12-05 | Snap Inc. | Deforming real-world object using an external mesh |
US11790614B2 (en) | 2021-10-11 | 2023-10-17 | Snap Inc. | Inferring intent from pose and speech input |
US11836862B2 (en) | 2021-10-11 | 2023-12-05 | Snap Inc. | External mesh with vertex attributes |
US11763481B2 (en) | 2021-10-20 | 2023-09-19 | Snap Inc. | Mirror-based augmented reality experience |
WO2023074918A1 (en) * | 2021-10-25 | 2023-05-04 | 엘지전자 주식회사 | Display device |
US11302314B1 (en) | 2021-11-10 | 2022-04-12 | Rammer Technologies, Inc. | Tracking specialized concepts, topics, and activities in conversations |
US11599713B1 (en) | 2022-07-26 | 2023-03-07 | Rammer Technologies, Inc. | Summarizing conversational speech |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060149555A1 (en) * | 2005-01-05 | 2006-07-06 | At&T Corp. | System and method of providing an automated data-collection in spoken dialog systems |
US20090144248A1 (en) * | 2001-12-20 | 2009-06-04 | Sybase 365, Inc. | Context-Based Suggestions Mechanism and Adaptive Push Mechanism for Natural Language Systems |
US20090177745A1 (en) * | 2008-01-04 | 2009-07-09 | Yahoo! Inc. | System and method for delivery of augmented messages |
US20110246496A1 (en) * | 2008-12-11 | 2011-10-06 | Chung Hee Sung | Information search method and information provision method based on user's intention |
US20120016678A1 (en) * | 2010-01-18 | 2012-01-19 | Apple Inc. | Intelligent Automated Assistant |
Family Cites Families (257)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB1530444A (en) | 1974-11-11 | 1978-11-01 | Xerox Corp | Automatic writing system and methods of word processing therefor |
CH644246B (en) | 1981-05-15 | 1900-01-01 | Asulab Sa | SPEECH-COMMANDED WORDS INTRODUCTION DEVICE. |
US5255386A (en) | 1990-02-08 | 1993-10-19 | International Business Machines Corporation | Method and apparatus for intelligent help that matches the semantic similarity of the inferred intent of query or command to a best-fit predefined command intent |
JPH06266779A (en) | 1993-03-15 | 1994-09-22 | Hitachi Ltd | Controller |
US6856986B1 (en) * | 1993-05-21 | 2005-02-15 | Michael T. Rossides | Answer collection and retrieval system governed by a pay-off meter |
US6239794B1 (en) | 1994-08-31 | 2001-05-29 | E Guide, Inc. | Method and system for simultaneously displaying a television program and information about the program |
US5748841A (en) * | 1994-02-25 | 1998-05-05 | Morin; Philippe | Supervised contextual language acquisition system |
EP0692765B1 (en) * | 1994-06-21 | 2003-05-21 | Canon Kabushiki Kaisha | Text preparing system using knowledge base and method therefor |
US5715468A (en) * | 1994-09-30 | 1998-02-03 | Budzinski; Robert Lucius | Memory system for storing and retrieving experience and knowledge with natural language |
US5887120A (en) | 1995-05-31 | 1999-03-23 | Oracle Corporation | Method and apparatus for determining theme for discourse |
US6006221A (en) | 1995-08-16 | 1999-12-21 | Syracuse University | Multilingual document retrieval system and method using semantic vector matching |
US6388714B1 (en) | 1995-10-02 | 2002-05-14 | Starsight Telecast Inc | Interactive computer system for providing television schedule information |
JPH09146972A (en) | 1995-11-24 | 1997-06-06 | Oki Electric Ind Co Ltd | Natural language interactive type information processor |
US5859972A (en) | 1996-05-10 | 1999-01-12 | The Board Of Trustees Of The University Of Illinois | Multiple server repository and multiple server remote application virtual client computer |
JP3212618B2 (en) * | 1996-09-26 | 2001-09-25 | 三菱電機株式会社 | Dialogue processing device |
US6177931B1 (en) | 1996-12-19 | 2001-01-23 | Index Systems, Inc. | Systems and methods for displaying and recording control interface with television programs, video, advertising information and program scheduling information |
US6044347A (en) | 1997-08-05 | 2000-03-28 | Lucent Technologies Inc. | Methods and apparatus object-oriented rule-based dialogue management |
US6564378B1 (en) | 1997-12-08 | 2003-05-13 | United Video Properties, Inc. | Program guide system with browsing display |
US6064960A (en) | 1997-12-18 | 2000-05-16 | Apple Computer, Inc. | Method and apparatus for improved duration modeling of phonemes |
EP2076033A3 (en) | 1998-03-04 | 2009-09-30 | United Video Properties, Inc. | Program guide system with targeted advertising |
US6236968B1 (en) * | 1998-05-14 | 2001-05-22 | International Business Machines Corporation | Sleep prevention dialog based car system |
US7711672B2 (en) | 1998-05-28 | 2010-05-04 | Lawrence Au | Semantic network methods to disambiguate natural language meaning |
CN1867068A (en) | 1998-07-14 | 2006-11-22 | 联合视频制品公司 | Client-server based interactive television program guide system with remote server recording |
US6144958A (en) | 1998-07-15 | 2000-11-07 | Amazon.Com, Inc. | System and method for correcting spelling errors in search queries |
AR020608A1 (en) | 1998-07-17 | 2002-05-22 | United Video Properties Inc | A METHOD AND A PROVISION TO SUPPLY A USER REMOTE ACCESS TO AN INTERACTIVE PROGRAMMING GUIDE BY A REMOTE ACCESS LINK |
EP1099339B1 (en) | 1998-07-17 | 2002-10-09 | United Video Properties, Inc. | Interactive television program guide having multiple devices at one location |
US6195635B1 (en) | 1998-08-13 | 2001-02-27 | Dragon Systems, Inc. | User-cued speech recognition |
US8914507B2 (en) | 1998-09-01 | 2014-12-16 | International Business Machines Corporation | Advice provided for offering highly targeted advice without compromising individual privacy |
US6256664B1 (en) | 1998-09-01 | 2001-07-03 | Bigfix, Inc. | Method and apparatus for computed relevance messaging |
US7197534B2 (en) | 1998-09-01 | 2007-03-27 | Big Fix, Inc. | Method and apparatus for inspecting the properties of a computer |
EP1133734A4 (en) * | 1998-10-02 | 2005-12-14 | Ibm | Conversational browser and conversational systems |
US7165098B1 (en) | 1998-11-10 | 2007-01-16 | United Video Properties, Inc. | On-line schedule system with personalization features |
US6601059B1 (en) | 1998-12-23 | 2003-07-29 | Microsoft Corporation | Computerized searching tool with spell checking |
US6317708B1 (en) | 1999-01-07 | 2001-11-13 | Justsystem Corporation | Method for producing summaries of text document |
JP2001034292A (en) | 1999-07-26 | 2001-02-09 | Denso Corp | Word string recognizing device |
US6317718B1 (en) | 1999-02-26 | 2001-11-13 | Accenture Properties (2) B.V. | System, method and article of manufacture for location-based filtering for shopping agent in the physical world |
US7039639B2 (en) | 1999-03-31 | 2006-05-02 | International Business Machines Corporation | Optimization of system performance based on communication relationship |
US6408293B1 (en) | 1999-06-09 | 2002-06-18 | International Business Machines Corporation | Interactive framework for understanding user's perception of multimedia data |
US6901366B1 (en) | 1999-08-26 | 2005-05-31 | Matsushita Electric Industrial Co., Ltd. | System and method for assessing TV-related information over the internet |
JP2001100787A (en) | 1999-09-29 | 2001-04-13 | Mitsubishi Electric Corp | Speech interactive system |
US20030191625A1 (en) | 1999-11-05 | 2003-10-09 | Gorin Allen Louis | Method and system for creating a named entity language model |
JP3446886B2 (en) | 1999-12-21 | 2003-09-16 | 日本電気株式会社 | Personal network data management system and personal network search method |
JP2001188784A (en) * | 1999-12-28 | 2001-07-10 | Sony Corp | Device and method for processing conversation and recording medium |
EP1275042A2 (en) * | 2000-03-06 | 2003-01-15 | Kanisa Inc. | A system and method for providing an intelligent multi-step dialog with a user |
US20020065813A1 (en) | 2000-04-18 | 2002-05-30 | Scanlon Henry R. | Image relationships derived from thresholding of historically tracked user data for facilitating image based searching |
US6999963B1 (en) * | 2000-05-03 | 2006-02-14 | Microsoft Corporation | Methods, apparatus, and data structures for annotating a database design schema and/or indexing annotations |
US7092928B1 (en) * | 2000-07-31 | 2006-08-15 | Quantum Leap Research, Inc. | Intelligent portal engine |
US6766320B1 (en) | 2000-08-24 | 2004-07-20 | Microsoft Corporation | Search engine with natural language-based robust parsing for user query and relevance feedback learning |
JP2002083148A (en) | 2000-09-06 | 2002-03-22 | Seiko Epson Corp | Browsing information forming system and digital contents delivery system |
JP2002108915A (en) | 2000-09-28 | 2002-04-12 | Toshiba Corp | Natural language interaction system and natural language processing method |
US6782384B2 (en) | 2000-10-04 | 2004-08-24 | Idiom Merger Sub, Inc. | Method of and system for splitting and/or merging content to facilitate content processing |
US6731307B1 (en) | 2000-10-30 | 2004-05-04 | Koninklije Philips Electronics N.V. | User interface/entertainment device that simulates personal interaction and responds to user's mental state and/or personality |
US6937983B2 (en) * | 2000-12-20 | 2005-08-30 | International Business Machines Corporation | Method and system for semantic speech recognition |
WO2002073331A2 (en) * | 2001-02-20 | 2002-09-19 | Semantic Edge Gmbh | Natural language context-sensitive and knowledge-based interaction environment for dynamic and flexible product, service and information search and presentation applications |
KR101548473B1 (en) | 2001-02-21 | 2015-08-28 | 로비 가이드스, 인크. | Systems and methods for interactive program guides with personal video recording features |
GB2377046A (en) * | 2001-06-29 | 2002-12-31 | Ibm | Metadata generation |
US20050234727A1 (en) | 2001-07-03 | 2005-10-20 | Leo Chiu | Method and apparatus for adapting a voice extensible markup language-enabled voice system for natural speech recognition and system response |
US7299270B2 (en) * | 2001-07-10 | 2007-11-20 | Lycos, Inc. | Inferring relations between internet objects that are not connected directly |
US20040215443A1 (en) * | 2001-07-27 | 2004-10-28 | Hatton Charles Malcolm | Computers that communicate in the english language and complete work assignments by reading english language sentences |
AUPR701701A0 (en) | 2001-08-14 | 2001-09-06 | Mcdonald, Nathan | Document analysis system and method |
JP3691773B2 (en) | 2001-08-20 | 2005-09-07 | 株式会社ジャストシステム | Sentence analysis method and sentence analysis apparatus capable of using the method |
US7711570B2 (en) | 2001-10-21 | 2010-05-04 | Microsoft Corporation | Application abstraction with dialog purpose |
US8229753B2 (en) * | 2001-10-21 | 2012-07-24 | Microsoft Corporation | Web server controls for web enabled recognition and/or audible prompting |
US7085709B2 (en) | 2001-10-30 | 2006-08-01 | Comverse, Inc. | Method and system for pronoun disambiguation |
US7209876B2 (en) | 2001-11-13 | 2007-04-24 | Groove Unlimited, Llc | System and method for automated answering of natural language questions and queries |
US20030188307A1 (en) * | 2002-03-29 | 2003-10-02 | Yusuke Mizuno | Digital broadcasting receiver |
US8126713B2 (en) | 2002-04-11 | 2012-02-28 | Shengyang Huang | Conversation control system and conversation control method |
JP3762327B2 (en) | 2002-04-24 | 2006-04-05 | 株式会社東芝 | Speech recognition method, speech recognition apparatus, and speech recognition program |
US7403890B2 (en) * | 2002-05-13 | 2008-07-22 | Roushar Joseph C | Multi-dimensional method and apparatus for automated language interpretation |
US6946715B2 (en) * | 2003-02-19 | 2005-09-20 | Micron Technology, Inc. | CMOS image sensor and method of fabrication |
US7676452B2 (en) | 2002-07-23 | 2010-03-09 | International Business Machines Corporation | Method and apparatus for search optimization based on generation of context focused queries |
US20040148170A1 (en) | 2003-01-23 | 2004-07-29 | Alejandro Acero | Statistical classifiers for spoken language understanding and command/control scenarios |
US7885963B2 (en) | 2003-03-24 | 2011-02-08 | Microsoft Corporation | Free text and attribute searching of electronic program guide (EPG) data |
US7340460B1 (en) | 2003-04-04 | 2008-03-04 | Yahoo! Inc. | Vector analysis of histograms for units of a concept network in search query processing |
JP2004362280A (en) | 2003-06-05 | 2004-12-24 | Hitachi Ltd | Broadcast program accumulation device |
US7143078B2 (en) | 2003-06-27 | 2006-11-28 | Microsoft Corporation | System and method for managed database query pre-optimization |
US8140980B2 (en) | 2003-08-05 | 2012-03-20 | Verizon Business Global Llc | Method and system for providing conferencing services |
CA2536271A1 (en) * | 2003-08-21 | 2005-03-03 | Idilia Inc. | System and method for associating documents with contextual advertisements |
US7475010B2 (en) | 2003-09-03 | 2009-01-06 | Lingospot, Inc. | Adaptive and scalable method for resolving natural language ambiguities |
US20050060140A1 (en) * | 2003-09-15 | 2005-03-17 | Maddox Paul Christopher | Using semantic feature structures for document comparisons |
GB0321916D0 (en) | 2003-09-19 | 2003-10-22 | Heatsafe Cable Systems Ltd | Self-regulating electrical heating cable |
US7593687B2 (en) | 2003-10-07 | 2009-09-22 | Immersion Entertainment, Llc | System and method for providing event spectators with audio/video signals pertaining to remote events |
WO2005033909A2 (en) * | 2003-10-08 | 2005-04-14 | Any Language Communications Inc. | Relationship analysis system and method for semantic disambiguation of natural language |
US7240049B2 (en) | 2003-11-12 | 2007-07-03 | Yahoo! Inc. | Systems and methods for search query processing using trend analysis |
US7356772B2 (en) | 2003-11-25 | 2008-04-08 | International Business Machines Corporation | Multi-column user interface for managing on-line threaded conversations |
US8160883B2 (en) | 2004-01-10 | 2012-04-17 | Microsoft Corporation | Focus tracking in dialogs |
US7542903B2 (en) * | 2004-02-18 | 2009-06-02 | Fuji Xerox Co., Ltd. | Systems and methods for determining predictive models of discourse functions |
US20070018953A1 (en) | 2004-03-03 | 2007-01-25 | The Boeing Company | System, method, and computer program product for anticipatory hypothesis-driven text retrieval and argumentation tools for strategic decision support |
US7761858B2 (en) * | 2004-04-23 | 2010-07-20 | Microsoft Corporation | Semantic programming language |
US20050246740A1 (en) * | 2004-05-03 | 2005-11-03 | Teraci Richard D | Apparatus and method for evaluating media |
US7720674B2 (en) | 2004-06-29 | 2010-05-18 | Sap Ag | Systems and methods for processing natural language queries |
US7856441B1 (en) | 2005-01-10 | 2010-12-21 | Yahoo! Inc. | Search systems and methods using enhanced contextual queries |
WO2006011819A1 (en) | 2004-07-30 | 2006-02-02 | Eurekster, Inc. | Adaptive search engine |
US7310602B2 (en) | 2004-09-27 | 2007-12-18 | Kabushiki Kaisha Equos Research | Navigation apparatus |
US20060074980A1 (en) * | 2004-09-29 | 2006-04-06 | Sarkar Pte. Ltd. | System for semantically disambiguating text information |
US7565627B2 (en) | 2004-09-30 | 2009-07-21 | Microsoft Corporation | Query graphs indicating related queries |
WO2006068731A2 (en) | 2004-11-12 | 2006-06-29 | Haley Systems, Inc. | A system for enterprise knowledge management and automation |
JP2006172280A (en) * | 2004-12-17 | 2006-06-29 | Keywalker Inc | Creation method and device for automatic response output such as automatic interaction |
PL1839297T3 (en) | 2005-01-11 | 2019-05-31 | Koninklijke Philips Nv | Scalable encoding/decoding of audio signals |
US7895039B2 (en) | 2005-02-04 | 2011-02-22 | Vocollect, Inc. | Methods and systems for optimizing model adaptation for a speech recognition system |
US7386545B2 (en) * | 2005-03-31 | 2008-06-10 | International Business Machines Corporation | System and method for disambiguating entities in a web page search |
US20090058860A1 (en) * | 2005-04-04 | 2009-03-05 | Mor (F) Dynamics Pty Ltd. | Method for Transforming Language Into a Visual Form |
JP2008537225A (en) * | 2005-04-11 | 2008-09-11 | テキストディガー,インコーポレイテッド | Search system and method for queries |
US7912701B1 (en) | 2005-05-04 | 2011-03-22 | IgniteIP Capital IA Special Management LLC | Method and apparatus for semiotic correlation |
US7653627B2 (en) * | 2005-05-13 | 2010-01-26 | Microsoft Corporation | System and method for utilizing the content of an online conversation to select advertising content and/or other relevant information for display |
US20060282776A1 (en) | 2005-06-10 | 2006-12-14 | Farmer Larry C | Multimedia and performance analysis tool |
US20070043736A1 (en) * | 2005-08-22 | 2007-02-22 | Microsoft Corporation | Smart find |
US7747639B2 (en) | 2005-08-24 | 2010-06-29 | Yahoo! Inc. | Alternative search query prediction |
US7912458B2 (en) | 2005-09-14 | 2011-03-22 | Jumptap, Inc. | Interaction analysis and prioritization of mobile content |
US9009046B1 (en) * | 2005-09-27 | 2015-04-14 | At&T Intellectual Property Ii, L.P. | System and method for disambiguating multiple intents in a natural language dialog system |
JP4542974B2 (en) | 2005-09-27 | 2010-09-15 | 株式会社東芝 | Speech recognition apparatus, speech recognition method, and speech recognition program |
US7590541B2 (en) * | 2005-09-30 | 2009-09-15 | Rockwell Automation Technologies, Inc. | HMI presentation layer configuration system |
US9201923B2 (en) | 2005-10-04 | 2015-12-01 | Robert Bosch Corporation | Method and apparatus for organizing and optimizing content in dialog systems |
KR100755677B1 (en) * | 2005-11-02 | 2007-09-05 | 삼성전자주식회사 | Apparatus and method for dialogue speech recognition using topic detection |
US7756855B2 (en) | 2006-10-11 | 2010-07-13 | Collarity, Inc. | Search phrase refinement by search term replacement |
US20070156521A1 (en) | 2005-12-29 | 2007-07-05 | United Video Properties, Inc. | Systems and methods for commerce in media program related merchandise |
US20100153885A1 (en) | 2005-12-29 | 2010-06-17 | Rovi Technologies Corporation | Systems and methods for interacting with advanced displays provided by an interactive media guidance application |
US8832569B2 (en) * | 2006-01-25 | 2014-09-09 | International Business Machines Corporation | Scrolling chat for participation in multiple instant messaging conversations |
JP2007219190A (en) | 2006-02-17 | 2007-08-30 | Murata Mach Ltd | Speech recognition device and recognision method, and program therefor |
US8204751B1 (en) | 2006-03-03 | 2012-06-19 | At&T Intellectual Property Ii, L.P. | Relevance recognition for a human machine dialog system contextual question answering based on a normalization of the length of the user input |
US7657526B2 (en) * | 2006-03-06 | 2010-02-02 | Veveo, Inc. | Methods and systems for selecting and presenting content based on activity level spikes associated with the content |
US20070226295A1 (en) | 2006-03-23 | 2007-09-27 | Nokia Corporation | Method and apparatuses for retrieving messages |
JP4734155B2 (en) | 2006-03-24 | 2011-07-27 | 株式会社東芝 | Speech recognition apparatus, speech recognition method, and speech recognition program |
US20070231781A1 (en) * | 2006-03-31 | 2007-10-04 | Birgit Zimmermann | Estimation of adaptation effort based on metadata similarity |
EP2911071A1 (en) | 2006-04-20 | 2015-08-26 | Veveo, Inc. | User interface methods and systems for selecting and presenting content based on user navigation and selection actions associated with the content |
US8069182B2 (en) * | 2006-04-24 | 2011-11-29 | Working Research, Inc. | Relevancy-based domain classification |
US7483894B2 (en) | 2006-06-07 | 2009-01-27 | Platformation Technologies, Inc | Methods and apparatus for entity search |
US20080240379A1 (en) | 2006-08-03 | 2008-10-02 | Pudding Ltd. | Automatic retrieval and presentation of information relevant to the context of a user's conversation |
WO2008045981A2 (en) * | 2006-10-10 | 2008-04-17 | Secondspace, Inc. | Virtual network of real-world entities |
US8600922B2 (en) | 2006-10-13 | 2013-12-03 | Elsevier Inc. | Methods and systems for knowledge discovery |
US20080091634A1 (en) * | 2006-10-15 | 2008-04-17 | Lisa Seeman | Content enhancement system and method and applications thereof |
US8073681B2 (en) * | 2006-10-16 | 2011-12-06 | Voicebox Technologies, Inc. | System and method for a cooperative conversational voice user interface |
US20080109741A1 (en) * | 2006-11-02 | 2008-05-08 | Ripl Corp. | User-generated content with instant-messaging functionality |
US20080120093A1 (en) | 2006-11-16 | 2008-05-22 | Seiko Epson Corporation | System for creating dictionary for speech synthesis, semiconductor integrated circuit device, and method for manufacturing semiconductor integrated circuit device |
US7814086B2 (en) | 2006-11-16 | 2010-10-12 | Yahoo! Inc. | System and method for determining semantically related terms based on sequences of search queries |
CN100449547C (en) * | 2006-12-06 | 2009-01-07 | 华为技术有限公司 | Medium contents management system and method |
US8024280B2 (en) | 2006-12-21 | 2011-09-20 | Yahoo! Inc. | Academic filter |
US20080155701A1 (en) | 2006-12-22 | 2008-06-26 | Yahoo! Inc. | Method and system for unauthorized content detection and reporting |
US8156135B2 (en) | 2006-12-22 | 2012-04-10 | Yahoo! Inc. | Method and system for progressive disclosure of search results |
US8171087B2 (en) * | 2007-01-16 | 2012-05-01 | Oracle International Corporation | Thread-based conversation management |
KR101322821B1 (en) * | 2007-02-23 | 2013-10-25 | 에스케이커뮤니케이션즈 주식회사 | System and method for keyword searching in messenger and computer readable medium processing the method |
US20080221866A1 (en) | 2007-03-06 | 2008-09-11 | Lalitesh Katragadda | Machine Learning For Transliteration |
US20110054900A1 (en) | 2007-03-07 | 2011-03-03 | Phillips Michael S | Hybrid command and control between resident and remote speech recognition facilities in a mobile voice-to-speech application |
US8219406B2 (en) | 2007-03-15 | 2012-07-10 | Microsoft Corporation | Speech-centric multimodal user interface design in mobile technology |
CN101271461B (en) | 2007-03-19 | 2011-07-13 | 株式会社东芝 | Cross-language retrieval request conversion and cross-language information retrieval method and system |
JP4247284B2 (en) | 2007-03-28 | 2009-04-02 | 株式会社東芝 | Information search apparatus, information search method, and information search program |
US8285539B2 (en) | 2007-06-18 | 2012-10-09 | International Business Machines Corporation | Extracting tokens in a natural language understanding application |
US20080319733A1 (en) | 2007-06-20 | 2008-12-25 | At&T Corp. | System and method to dynamically manipulate and disambiguate confusable speech input using a table |
US8156138B2 (en) | 2007-06-26 | 2012-04-10 | Richrelevance, Inc. | System and method for providing targeted content |
US8260809B2 (en) | 2007-06-28 | 2012-09-04 | Microsoft Corporation | Voice-based search processing |
CN101339551B (en) | 2007-07-05 | 2013-01-30 | 日电(中国)有限公司 | Natural language query demand extension equipment and its method |
US8645390B1 (en) | 2007-08-31 | 2014-02-04 | Google Inc. | Reordering search query results in accordance with search context specific predicted performance functions |
US8594996B2 (en) * | 2007-10-17 | 2013-11-26 | Evri Inc. | NLP-based entity recognition and disambiguation |
US7693940B2 (en) | 2007-10-23 | 2010-04-06 | International Business Machines Corporation | Method and system for conversation detection in email systems |
US9092733B2 (en) * | 2007-12-28 | 2015-07-28 | Genesys Telecommunications Laboratories, Inc. | Recursive adaptive interaction management system |
US20090198488A1 (en) | 2008-02-05 | 2009-08-06 | Eric Arno Vigen | System and method for analyzing communications using multi-placement hierarchical structures |
US8165884B2 (en) | 2008-02-15 | 2012-04-24 | Microsoft Corporation | Layered prompting: self-calibrating instructional prompting for verbal interfaces |
US8172637B2 (en) | 2008-03-12 | 2012-05-08 | Health Hero Network, Inc. | Programmable interactive talking device |
US8190604B2 (en) * | 2008-04-03 | 2012-05-29 | Microsoft Corporation | User intention modeling for interactive image retrieval |
US8171007B2 (en) * | 2008-04-18 | 2012-05-01 | Microsoft Corporation | Creating business value by embedding domain tuned search on web-sites |
US8521512B2 (en) | 2008-04-30 | 2013-08-27 | Deep Sky Concepts, Inc | Systems and methods for natural language communication with a computer |
US8364528B2 (en) | 2008-05-06 | 2013-01-29 | Richrelevance, Inc. | System and process for improving product recommendations for use in providing personalized advertisements to retail customers |
US8869015B2 (en) | 2008-05-08 | 2014-10-21 | Dialogic (Us) Inc. | System and method to permit language independence for web interfaces |
US7958442B2 (en) | 2008-05-08 | 2011-06-07 | Dialogic Corporation | System and method to permit language independence for web interfaces |
US8219397B2 (en) | 2008-06-10 | 2012-07-10 | Nuance Communications, Inc. | Data processing system for autonomously building speech identification and tagging data |
US8375308B2 (en) * | 2008-06-24 | 2013-02-12 | International Business Machines Corporation | Multi-user conversation topic change |
US20100002685A1 (en) * | 2008-06-30 | 2010-01-07 | Shaham Eliezer | Method and system for providing communication |
US20100088262A1 (en) | 2008-09-29 | 2010-04-08 | Neuric Technologies, Llc | Emulated brain |
US9978365B2 (en) | 2008-10-31 | 2018-05-22 | Nokia Technologies Oy | Method and system for providing a voice interface |
US20100131365A1 (en) | 2008-11-25 | 2010-05-27 | Microsoft Corporation | Context-Sensitive Advertising for Mobile Content |
KR101173556B1 (en) | 2008-12-11 | 2012-08-13 | 한국전자통신연구원 | Topic map based indexing apparatus, topic map based searching apparatus, topic map based searching system and its method |
US8060524B2 (en) * | 2008-12-11 | 2011-11-15 | Microsoft Corporation | History answer for re-finding search results |
US8156129B2 (en) | 2009-01-15 | 2012-04-10 | Microsoft Corporation | Substantially similar queries |
US20110093500A1 (en) * | 2009-01-21 | 2011-04-21 | Google Inc. | Query Optimization |
US9805089B2 (en) | 2009-02-10 | 2017-10-31 | Amazon Technologies, Inc. | Local business and product search system and method |
KR101048546B1 (en) | 2009-03-05 | 2011-07-11 | 엔에이치엔(주) | Content retrieval system and method using ontology |
US8335754B2 (en) | 2009-03-06 | 2012-12-18 | Tagged, Inc. | Representing a document using a semantic structure |
US20100235313A1 (en) | 2009-03-16 | 2010-09-16 | Tim Rea | Media information analysis and recommendation platform |
US8515754B2 (en) | 2009-04-06 | 2013-08-20 | Siemens Aktiengesellschaft | Method for performing speech recognition and processing system |
US8214366B2 (en) | 2009-11-17 | 2012-07-03 | Glace Holding Llc | Systems and methods for generating a language database that can be used for natural language communication with a computer |
US20100306249A1 (en) | 2009-05-27 | 2010-12-02 | James Hill | Social network systems and methods |
US8417649B2 (en) * | 2009-07-13 | 2013-04-09 | International Business Machines Corporation | Providing a seamless conversation service between interacting environments |
US8533175B2 (en) | 2009-08-13 | 2013-09-10 | Gilbert Marquard ROSWELL | Temporal and geographic presentation and navigation of linked cultural, artistic, and historic content |
US9166714B2 (en) | 2009-09-11 | 2015-10-20 | Veveo, Inc. | Method of and system for presenting enriched video viewing analytics |
US20110066645A1 (en) | 2009-09-16 | 2011-03-17 | John Cooper | System and method for assembling, verifying, and distibuting financial information |
US20110066644A1 (en) | 2009-09-16 | 2011-03-17 | John Cooper | System and method for assembling, verifying, and distibuting financial information |
US20110066643A1 (en) | 2009-09-16 | 2011-03-17 | John Cooper | System and method for assembling, verifying, and distibuting financial information |
US8943094B2 (en) * | 2009-09-22 | 2015-01-27 | Next It Corporation | Apparatus, system, and method for natural language processing |
US8326859B2 (en) | 2009-11-02 | 2012-12-04 | Microsoft Corporation | Task prediction |
US9502025B2 (en) | 2009-11-10 | 2016-11-22 | Voicebox Technologies Corporation | System and method for providing a natural language content dedication service |
US8358749B2 (en) | 2009-11-21 | 2013-01-22 | At&T Intellectual Property I, L.P. | System and method to search a media content database based on voice input data |
US8903793B2 (en) | 2009-12-15 | 2014-12-02 | At&T Intellectual Property I, L.P. | System and method for speech-based incremental search |
KR20110072847A (en) | 2009-12-23 | 2011-06-29 | 삼성전자주식회사 | Dialog management system or method for processing information seeking dialog |
CA2787103A1 (en) | 2010-01-15 | 2011-07-21 | Compass Labs, Inc. | User communication analysis systems and methods |
US8315602B2 (en) | 2010-02-05 | 2012-11-20 | Research In Motion Limited | Communications system including aggregation server for determining updated metadata of e-mail messages and related methods |
US20110212428A1 (en) | 2010-02-18 | 2011-09-01 | David Victor Baker | System for Training |
US8315849B1 (en) * | 2010-04-09 | 2012-11-20 | Wal-Mart Stores, Inc. | Selecting terms in a document |
US8762375B2 (en) * | 2010-04-15 | 2014-06-24 | Palo Alto Research Center Incorporated | Method for calculating entity similarities |
US20110295688A1 (en) * | 2010-05-28 | 2011-12-01 | Microsoft Corporation | Defining user intent |
US9436764B2 (en) | 2010-06-29 | 2016-09-06 | Microsoft Technology Licensing, Llc | Navigation to popular search results |
US8219628B2 (en) | 2010-07-23 | 2012-07-10 | International Business Machines Corporation | Method to change instant messaging status based on text entered during conversation |
DE212011100017U1 (en) | 2010-08-19 | 2012-04-03 | David Black | Predictive query completion and predictive search results |
US20120059713A1 (en) * | 2010-08-27 | 2012-03-08 | Adchemy, Inc. | Matching Advertisers and Users Based on Their Respective Intents |
US20120084291A1 (en) * | 2010-09-30 | 2012-04-05 | Microsoft Corporation | Applying search queries to content sets |
US8515984B2 (en) | 2010-11-16 | 2013-08-20 | Microsoft Corporation | Extensible search term suggestion engine |
GB2486002A (en) | 2010-11-30 | 2012-06-06 | Youview Tv Ltd | Media Content Provision |
US8631002B2 (en) | 2010-12-09 | 2014-01-14 | Microsoft Corporation | Web-relevance based query classification |
US9928296B2 (en) * | 2010-12-16 | 2018-03-27 | Microsoft Technology Licensing, Llc | Search lexicon expansion |
US8849931B2 (en) | 2011-03-15 | 2014-09-30 | Idt Messaging, Llc | Linking context-based information to text messages |
WO2012145782A1 (en) | 2011-04-27 | 2012-11-01 | Digital Sonata Pty Ltd | Generic system for linguistic analysis and transformation |
US20120310622A1 (en) | 2011-06-02 | 2012-12-06 | Ortsbo, Inc. | Inter-language Communication Devices and Methods |
US8880423B2 (en) | 2011-07-01 | 2014-11-04 | Yahoo! Inc. | Inventory estimation for search retargeting |
US9442928B2 (en) | 2011-09-07 | 2016-09-13 | Venio Inc. | System, method and computer program product for automatic topic identification using a hypertext corpus |
GB201117052D0 (en) | 2011-10-04 | 2011-11-16 | Daybees Ltd | Automated diary population |
US9619554B2 (en) | 2011-11-03 | 2017-04-11 | Microsoft Technology Licensing, Llc | Domain specific query-completion suggestions |
US20130145385A1 (en) * | 2011-12-02 | 2013-06-06 | Microsoft Corporation | Context-based ratings and recommendations for media |
US9201859B2 (en) * | 2011-12-15 | 2015-12-01 | Microsoft Technology Licensing, Llc | Suggesting intent frame(s) for user request(s) |
US9721039B2 (en) | 2011-12-16 | 2017-08-01 | Palo Alto Research Center Incorporated | Generating a relationship visualization for nonhomogeneous entities |
US9547832B2 (en) | 2012-01-10 | 2017-01-17 | Oracle International Corporation | Identifying individual intentions and determining responses to individual intentions |
WO2013109793A1 (en) | 2012-01-18 | 2013-07-25 | Kinectus LLC | Systems and methods for establishing communications between mobile device users |
US20170140405A1 (en) | 2012-03-01 | 2017-05-18 | o9 Solutions, Inc. | Global market modeling for advanced market intelligence |
US20180359477A1 (en) * | 2012-03-05 | 2018-12-13 | Google Inc. | Distribution of video in multiple rating formats |
US8935277B2 (en) * | 2012-03-30 | 2015-01-13 | Sap Se | Context-aware question answering system |
US8504562B1 (en) | 2012-04-03 | 2013-08-06 | Google Inc. | Evaluation of substitute terms |
US9542482B1 (en) | 2012-04-06 | 2017-01-10 | Amazon Technologies Inc. | Providing items of interest |
US8346563B1 (en) * | 2012-04-10 | 2013-01-01 | Artificial Solutions Ltd. | System and methods for delivering advanced natural language interaction applications |
US20130275429A1 (en) | 2012-04-12 | 2013-10-17 | Graham York | System and method for enabling contextual recommendations and collaboration within content |
KR101694286B1 (en) | 2012-05-02 | 2017-01-09 | 한국전자통신연구원 | Apparatus and method for providing two-way automatic interpretation and tranlating service |
US9183310B2 (en) | 2012-06-12 | 2015-11-10 | Microsoft Technology Licensing, Llc | Disambiguating intents within search engine result pages |
US20140006012A1 (en) | 2012-07-02 | 2014-01-02 | Microsoft Corporation | Learning-Based Processing of Natural Language Questions |
US8577671B1 (en) | 2012-07-20 | 2013-11-05 | Veveo, Inc. | Method of and system for using conversation state information in a conversational interaction system |
CA2879668C (en) | 2012-07-24 | 2020-07-07 | Ab Initio Technology Llc | Mapping entities in data models |
US9465833B2 (en) | 2012-07-31 | 2016-10-11 | Veveo, Inc. | Disambiguating user intent in conversational interaction system for large corpus information retrieval |
US20150169701A1 (en) | 2013-01-25 | 2015-06-18 | Google Inc. | Providing customized content in knowledge panels |
US20140214401A1 (en) | 2013-01-29 | 2014-07-31 | Tencent Technology (Shenzhen) Company Limited | Method and device for error correction model training and text error correction |
US20140223481A1 (en) | 2013-02-07 | 2014-08-07 | United Video Properties, Inc. | Systems and methods for updating a search request |
US10747837B2 (en) | 2013-03-11 | 2020-08-18 | Creopoint, Inc. | Containing disinformation spread using customizable intelligence channels |
EP2994908B1 (en) | 2013-05-07 | 2019-08-28 | Veveo, Inc. | Incremental speech input interface with real time feedback |
US9946757B2 (en) | 2013-05-10 | 2018-04-17 | Veveo, Inc. | Method and system for capturing and exploiting user intent in a conversational interaction based information retrieval system |
CN104462084B (en) | 2013-09-13 | 2019-08-16 | Sap欧洲公司 | Search refinement is provided based on multiple queries to suggest |
US9852136B2 (en) | 2014-12-23 | 2017-12-26 | Rovi Guides, Inc. | Systems and methods for determining whether a negation statement applies to a current or past query |
US20160227283A1 (en) | 2015-01-30 | 2016-08-04 | Rovi Guides, Inc. | Systems and methods for providing a recommendation to a user based on a user profile and social chatter |
US9854049B2 (en) | 2015-01-30 | 2017-12-26 | Rovi Guides, Inc. | Systems and methods for resolving ambiguous terms in social chatter based on a user profile |
US9640177B2 (en) | 2015-06-01 | 2017-05-02 | Quest Software Inc. | Method and apparatus to extrapolate sarcasm and irony using multi-dimensional machine learning based linguistic analysis |
US9959328B2 (en) | 2015-06-30 | 2018-05-01 | Microsoft Technology Licensing, Llc | Analysis of user text |
CN106484681B (en) | 2015-08-25 | 2019-07-09 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and electronic equipment generating candidate translation |
US20180226073A1 (en) | 2017-02-06 | 2018-08-09 | International Business Machines Corporation | Context-based cognitive speech to text engine |
US20180225013A1 (en) | 2017-02-06 | 2018-08-09 | Likemoji Inc. | Network-based graphical communication system |
US10304154B2 (en) | 2017-04-24 | 2019-05-28 | Intel Corporation | Coordination and increased utilization of graphics processors during inference |
US11417235B2 (en) | 2017-05-25 | 2022-08-16 | Baidu Usa Llc | Listen, interact, and talk: learning to speak via interaction |
US10909441B2 (en) | 2017-06-02 | 2021-02-02 | Microsoft Technology Licensing, Llc | Modeling an action completion conversation using a knowledge graph |
US20190108447A1 (en) | 2017-11-30 | 2019-04-11 | Intel Corporation | Multifunction perceptrons in machine learning environments |
US11074829B2 (en) | 2018-04-12 | 2021-07-27 | Baidu Usa Llc | Systems and methods for interactive language acquisition with one-shot visual concept learning through a conversational game |
US10482674B1 (en) | 2018-06-27 | 2019-11-19 | Beijing Jingdong Shangke Information Technology Co., Ltd. | System and method for mobile augmented reality |
US11710034B2 (en) | 2019-02-27 | 2023-07-25 | Intel Corporation | Misuse index for explainable artificial intelligence in computing environments |
US10990763B2 (en) | 2019-03-01 | 2021-04-27 | Oracle International Corporation | Bias parameters for topic modeling |
US11232267B2 (en) | 2019-05-24 | 2022-01-25 | Tencent America LLC | Proximity information retrieval boost method for medical knowledge question answering systems |
-
2012
- 2012-11-02 US US13/667,388 patent/US8577671B1/en active Active
- 2012-11-02 US US13/667,400 patent/US9424233B2/en active Active
-
2013
- 2013-05-01 US US13/874,523 patent/US9183183B2/en active Active
- 2013-07-19 EP EP13819772.8A patent/EP2875445A4/en not_active Ceased
- 2013-07-19 CN CN201710825932.3A patent/CN107633042A/en active Pending
- 2013-07-19 CA CA3125021A patent/CA3125021A1/en active Pending
- 2013-07-19 CA CA2879778A patent/CA2879778C/en active Active
- 2013-07-19 EP EP16207431.4A patent/EP3196774A1/en not_active Ceased
- 2013-07-19 MX MX2019000838A patent/MX2019000838A/en unknown
- 2013-07-19 MX MX2015000909A patent/MX347542B/en active IP Right Grant
- 2013-07-19 WO PCT/US2013/051288 patent/WO2014015267A2/en active Application Filing
- 2013-07-19 EP EP22020584.3A patent/EP4195094A1/en active Pending
- 2013-07-19 KR KR1020197028910A patent/KR102229850B1/en active IP Right Grant
- 2013-07-19 AU AU2013292377A patent/AU2013292377B2/en active Active
- 2013-07-19 EP EP17210590.0A patent/EP3346393A1/en not_active Ceased
- 2013-07-19 EP EP16207432.2A patent/EP3206134A1/en not_active Ceased
- 2013-07-19 KR KR1020157004024A patent/KR102030078B1/en active IP Right Grant
- 2013-07-19 MX MX2017005665A patent/MX362496B/en unknown
- 2013-07-19 CN CN201380046675.3A patent/CN104871150B/en active Active
- 2013-07-19 CA CA3125015A patent/CA3125015C/en active Active
- 2013-07-19 JP JP2015523287A patent/JP6313298B2/en active Active
- 2013-11-04 US US14/071,168 patent/US9477643B2/en active Active
- 2013-11-04 US US14/070,778 patent/US8954318B2/en active Active
-
2015
- 2015-01-20 MX MX2022000147A patent/MX2022000147A/en unknown
-
2016
- 2016-08-04 US US15/228,847 patent/US10592575B2/en active Active
-
2018
- 2018-03-22 JP JP2018054618A patent/JP6629375B2/en active Active
- 2018-03-22 JP JP2018054619A patent/JP6505903B2/en active Active
-
2019
- 2019-01-09 HK HK19100306.8A patent/HK1257944A1/en unknown
- 2019-03-27 JP JP2019060532A patent/JP6813615B2/en active Active
- 2019-05-28 AU AU2019203718A patent/AU2019203718A1/en not_active Abandoned
-
2020
- 2020-02-04 US US16/781,830 patent/US11436296B2/en active Active
-
2022
- 2022-07-26 US US17/873,912 patent/US20230019782A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090144248A1 (en) * | 2001-12-20 | 2009-06-04 | Sybase 365, Inc. | Context-Based Suggestions Mechanism and Adaptive Push Mechanism for Natural Language Systems |
US20060149555A1 (en) * | 2005-01-05 | 2006-07-06 | At&T Corp. | System and method of providing an automated data-collection in spoken dialog systems |
US20090177745A1 (en) * | 2008-01-04 | 2009-07-09 | Yahoo! Inc. | System and method for delivery of augmented messages |
US20110246496A1 (en) * | 2008-12-11 | 2011-10-06 | Chung Hee Sung | Information search method and information provision method based on user's intention |
US20120016678A1 (en) * | 2010-01-18 | 2012-01-19 | Apple Inc. | Intelligent Automated Assistant |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893771A (en) * | 2016-04-15 | 2016-08-24 | 北京搜狗科技发展有限公司 | Information service method and device and device used for information services |
US10824798B2 (en) | 2016-11-04 | 2020-11-03 | Semantic Machines, Inc. | Data collection for a new conversational dialogue system |
US10713288B2 (en) | 2017-02-08 | 2020-07-14 | Semantic Machines, Inc. | Natural language content generator |
US10762892B2 (en) | 2017-02-23 | 2020-09-01 | Semantic Machines, Inc. | Rapid deployment of dialogue system |
US11069340B2 (en) | 2017-02-23 | 2021-07-20 | Microsoft Technology Licensing, Llc | Flexible and expandable dialogue system |
US11195516B2 (en) | 2017-02-23 | 2021-12-07 | Microsoft Technology Licensing, Llc | Expandable dialogue system |
US11132499B2 (en) | 2017-08-28 | 2021-09-28 | Microsoft Technology Licensing, Llc | Robust expandable dialogue system |
US10817170B2 (en) | 2018-03-23 | 2020-10-27 | Hyundai Motor Company | Apparatus and method for operating touch control based steering wheel |
US11436411B2 (en) | 2019-02-27 | 2022-09-06 | Google Llc | Detecting continuing conversations with computing devices |
US11676582B2 (en) | 2019-02-27 | 2023-06-13 | Google Llc | Detecting conversations with computing devices |
US11893350B2 (en) | 2019-02-27 | 2024-02-06 | Google Llc | Detecting continuing conversations with computing devices |
US11934787B2 (en) | 2021-04-29 | 2024-03-19 | International Business Machines Corporation | Intent determination in a messaging dialog manager system |
Also Published As
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11436296B2 (en) | Method of and system for inferring user intent in search input in a conversational interaction system | |
US11544310B2 (en) | Method for adaptive conversation state management with filtering operators applied dynamically as part of a conversational interface |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13819772 Country of ref document: EP Kind code of ref document: A2 |
|
ENP | Entry into the national phase |
Ref document number: 2879778 Country of ref document: CA Ref document number: 2015523287 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: MX/A/2015/000909 Country of ref document: MX |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2013819772 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 20157004024 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2013292377 Country of ref document: AU Date of ref document: 20130719 Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13819772 Country of ref document: EP Kind code of ref document: A2 |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112015001363 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112015001363 Country of ref document: BR Kind code of ref document: A2 Effective date: 20150121 |