CN100511223C - Methods and systems for conceptually organizing and presenting information - Google Patents

Methods and systems for conceptually organizing and presenting information Download PDF

Info

Publication number
CN100511223C
CN100511223C CNB2004800358406A CN200480035840A CN100511223C CN 100511223 C CN100511223 C CN 100511223C CN B2004800358406 A CNB2004800358406 A CN B2004800358406A CN 200480035840 A CN200480035840 A CN 200480035840A CN 100511223 C CN100511223 C CN 100511223C
Authority
CN
China
Prior art keywords
inquiry
selection
user
conceptual dependency
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CNB2004800358406A
Other languages
Chinese (zh)
Other versions
CN1890664A (en
Inventor
A·柯蒂斯
A·莱文
A·杰拉索利斯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
IAC Search and Media Inc
Original Assignee
IAC Search and Media Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US10/853,552 external-priority patent/US7181447B2/en
Priority claimed from US10/853,860 external-priority patent/US7451131B2/en
Application filed by IAC Search and Media Inc filed Critical IAC Search and Media Inc
Publication of CN1890664A publication Critical patent/CN1890664A/en
Application granted granted Critical
Publication of CN100511223C publication Critical patent/CN100511223C/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9536Search customisation based on social or collaborative filtering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9538Presentation of query results

Abstract

Methods and systems for providing a response to a query. Multiple users' search engine activity in regard to a query is correlated. A response is provided based upon this correlated search engine activity information. For one embodiment of the invention, in the context of search engine result optimization, the user activity and/or user information of multiple users, during a search session, is correlated with queries to effect an evolving association between queries and the organization and presentation of documents. Systems in accordance with such embodiments employ the ability to store users' activity over the entire search session, thus making possible the correlation of a number of different types of user activity and user information. The use of correlated user input allows such systems to provide relevant search results without the limitations imposed by the key-word-based systems of the prior art.

Description

The method and system of conceptive tissue and statement information
Priority request
The application relates to and the right of priority of the provisional application that requires to submit on Dec 8th, 2003 number 60/528,139, and its content is incorporated into this as quoting.
Technical field
The field that relates to notional organizational information that embodiments of the invention are general, and the operational analysis that relates in particular to conceptual dependency information is with effective organizational information.
Background technology
Along with increasing rapidly of information, the ability of organizational information is also increasing.On the relevant network (for example WWW) in internet or other the Internet sources, can find the bulk information source.The internet is the extended network of computer network, and information is exchange on the internet by well known to a person skilled in the art method (for example use of TCP and IP agreement or the like).The internet allows the user to transmit and receive data being connected between the computing machine of this network.These data can comprise website, homepage, database, text collection, audio frequency, video or the information by any other available on the internet type of the computer server that is connected to the internet.These information can be called as file or document, and can comprise other data that comprise in data, webpage annex or the memory device (for example database) on webpage, the webpage.
Understand the meaning of large volume document like this set and in this environment search information, be very difficult when not having special supplementary means.A kind of method of auxiliary positioning information is to use keyword.That is to say that document can comprise that expression is included in the keyword of the selected part of the information in the document.These keywords are available to other computing machines on the internet and allow other computing machine location the document.
In order to locate the document on the internet, the user of remote computer uses the search utility that is called as search engine and searching key word.Search engine is to allow the long-distance user to key in the program of one or more search words.Search engine is compared search inquiry and is had part with the keyword of search inquiry coupling at least in the search file with the keyword in the document then.Search engine is to user display part document, for example title then.The user can be in the local document that retrieves rolling view and select required document.
Early stage keyword search engine demonstrates major defect.For example, in order to increase the occurrence rate of particular document, the document supplier can use the as much as possible search word relevant with document.In fact, each speech in some document or the search engine use document is as keyword.Therefore, search engine can retrieve a large amount of need haveing nothing to do by the theme that the search word combination is sought with the user or the relevant document in edge only.And, thereby a lot of users of these search engines and be unfamiliar with the skill that forms keyword search query and produce too wide in range search and often retrieve thousands of documents.The user must check about the summary info of each document with the location information needed so.
This defective is solved by the differentiation of search engine, promptly comprises the information organization based on one or more users' search activities.These methods are based on user preference degree prevailing view rather than towards the parameter (for example text) of document and to sort result.Wherein a kind of such method is according to based on the evolution score of employed keyword and to document ordering.That is to say that document receives the relevance score relevant with the keyword of search inquiry.When selecting document along with user's inputted search inquiry and in the lists of documents that inquiry produces, the relevance score of document is adjusted.These marks are used to the results list of organizes documents to carry out subsequent searches." clicks " number of times (being the selecteed number of times of document) that these methods typical (at least on part) receive based on document and definite degree of correlation.These methods are commonly referred to " popularity sort method " or " clicking people's gas method ", provide the document that will attract and satisfy the previous user of most most to be arranged in top search result list.And, click people's gas method and produce the contextual result of reflection search.For example, previous searching method can return the document that comprises all query words, but can not get rid of the speech that is not query portion automatically.Therefore, result about " New Mexico " is most possibly returned in search for the text matches of " Mexico ".Click people's gas method and can reduce this error result, because the user of search " Mexico " can not click about the page of " New Mexico " usually and can tend to click them and think and " Mexico " maximally related page, thereby increased the degree of correlation of required document.
Because the information relevant with query word be along with the time may change, determine the degree of correlation result that may lead to errors based on number of clicks.For example, ad hoc inquiry for " democracy pioneer ", the document that relates to early stage pioneer HowardDean may be selected many times in Dec, 2003, but the user who imports this inquiry in March, 2004 may be desirably in the result of this moment as leader's John Kerry.And, come top result and can be subjected to out-of-proportion more use usually, caused the Search Results more and more distorted like this, it is replaced never wherein to come top result.
Comprise based on the time with based on the search engine that a large amount of factors of the factor of using are organized the information that provides in response to inquiry by use and to have solved a part in these defectives.For example, this method may use previous user to adjust the degree of correlation of inquiry response document in response to the activity of ad hoc inquiry.Such User Activity can comprise number of clicks and the previous user time to the selection or the use of customizing messages.Where these methods can also be arranged in particular document in previous the results list when formerly the user selects it, how actual the and contrast of expectation frequency of utilization of document and selected document are used etc. is taken into account.
Yet, in current method, still have a large amount of defectives.For example, current method does not solve the problem of very rare inquiry, does not wherein compile enough user activity data.In the case, the possibility of result seldom or not exists.And, click quality and integrality that the result depends on data source.Current method can not solve the greatest differences of data source quality.And current method is subjected to the deception influence, may influence the integrality of Search Results.Attempt to solve some problem according to a kind of exemplary method of prior art by on the basis of User Activity, upgrading search-engine results.This method is called in name in the U.S. Patent No. 6,421,675 of " SearchEngine " and is described, and its content is as quoting and be incorporated into this, thereby provides comprehensive description of prior art and clearly distinguish the feature of each embodiment of the present invention.
Summary of the invention
One embodiment of the present of invention provide a kind of method, wherein provide the conceptual dependency ensemble of communication for a plurality of users.One or more responses for the conceptual dependency information that is provided are provided from two or more users each.Then from the response associated (correlate) of two or more users, describedly be associated as the related or selections-selection association of selection-inquiry, wherein selection-inquiry is related interrelates the inquiry of writing down during the user conversation, the selection of sending is associated during these inquiries and this user conversation, selection-selection is related to interrelate other selections of sending during the selection of sending during the user conversation and this session, and revises the statement of described conceptual dependency information based on the response after the association.
Description of drawings
Can better understand the present invention by the following description of reference, and utilize accompanying drawing to represent embodiments of the invention.In the accompanying drawings:
Fig. 1 is for showing according to an embodiment of the invention the process flow diagram based on the program of the tissue of revising the conceptual dependency ensemble of communication from the association of a plurality of users' response and statement;
Fig. 2 is for showing the process flow diagram that influences the program of getting in touch of user inquiring and memory contents according to an embodiment of the invention during other users' similar information search sessions by the association based on User Activity that obtains and/or user profile;
Fig. 3 is used to organize and explain conceptual dependency information according to an embodiment of the invention and is used to get in touch the particular memory content and the structural drawing of the system of each user inquiring for showing;
Fig. 4 has shown the search daily record of three isolated users according to an embodiment of the invention;
Fig. 5 is for showing the process flow diagram of the program that more heterogeneous pass Search Results is provided according to an embodiment of the invention;
Fig. 6 is for showing the process flow diagram of the program that the relevant inquiring suggestion is provided according to an embodiment of the invention;
Fig. 6 A is for showing the process flow diagram of the program that the query spelling correction suggestion is provided according to an embodiment of the invention;
Fig. 7 is the process flow diagram that shows the program of the inquiry of offering suggestions according to an embodiment of the invention;
Fig. 8 is for showing the process flow diagram of the program that similar results is provided according to an embodiment of the invention;
Fig. 9 is correlated with the process flow diagram of program that more relevant Search Results is provided to information for showing according to an embodiment of the invention;
Figure 10 is for showing according to an embodiment of the invention according to providing the process flow diagram of the program of more relevant Search Results based on customer location with the position of selecting to be associated;
Figure 11 is for showing according to an embodiment of the invention the process flow diagram that the user is provided the program of more relevant Search Results based on customer location; And
Figure 12 shows the structural drawing of digital processing system according to an embodiment of the invention.
Embodiment
General introduction
Embodiments of the invention provide the method and system that is used for conceptive tissue and statement information, wherein use related optimum tissue and the statement to determine information of user to the response of information organization and statement.In one embodiment of the invention, in the context that search-engine results is optimized, during the search sessions a plurality of users' User Activity and/or user profile and inquiry carry out related, with the tissue of influence inquiry and document and the evolution between explaining get in touch.Store User Activity in the whole search sessions process according to the system of these embodiment, thereby can make a large amount of dissimilar User Activities can be related with user profile.Using related user to import these systems of permission provides relevant Search Results and can not produce in the prior art restriction that the system based on keyword brings.
To provide a large amount of specific detail in the following description.Yet, should be appreciated that embodiments of the invention may be embodied as and do not have these specific detail.In other embodiments, known circuit, structure and technology are not described in detail to avoid fuzzy understanding of this description.
" embodiment " who mentions in the whole instructions or " embodiment " expression comprise at least one embodiment of the present invention in conjunction with special characteristic, structure or the characteristics that this embodiment describes.Therefore, phrase " in one embodiment " or " in an embodiment " that many places occur in whole instructions might not all be meant same embodiment.And, can in any appropriate manner special characteristic, structure or characteristics be combined in one or more embodiments.
And the aspect of being invented is included in all features that are less than single disclosed embodiment.Therefore, instructions accompanying Claim book clearly is included in this embodiment, and every claims self are as an independent embodiment of the present invention.
Program
Fig. 1 has shown according to an embodiment of the invention based on from the association of a plurality of users' response and revise the tissue of conceptual dependency ensemble of communication and the program of statement.
Program 100 shown in Fig. 1 starts from operating 105, and wherein the conceptual dependency ensemble of communication is organized by the informant and is given a plurality of users by statement.In one embodiment, the conceptual dependency ensemble of communication is the set page that includes about the information of the interested universal of particular group of users.This set page can comprise the correlator notion of a large amount of any kind ofs, comprise and the linking of file, catalogue, database, spreadsheet, news item, audio frequency, video, image, application program, advertisement, product description and reference information, with linking of any catalogue of tabulation, form, tree or above-mentioned project, and with other set the linking of the pages, all these contents can be collected from the source of any amount.In one embodiment, the separately tissue and the statement of a plurality of set page creation ensemble of communication for a change that forms comprises quantity, type, arrangement and the significance of correlator notion.Like this, the informant attempts the optimum way of intended tissue and statement information.
In operation 110, the informant is from the response of user's reception about information organization and statement.User's response can be for selecting the form of (perhaps not selecting) certain partial information.For example, the certain user can select the information of the specific sub-notion of the given set page, and does not select other.
In operation 115, associated from the response that a plurality of users receive.That is to say, determine on the identical statistics that the individual consumer carries out the effectively degree of contact.In alternative embodiment of the present invention, the association of response can be taked any form.The example association of various user's responses is hereinafter with more detailed description.
In operation 120, revise the tissue and the statement of conceptual dependency ensemble of communication based on the response after the association.For example, can form the set page again to satisfy individual consumer, user's group or certain class user or all users' needs more fully.Except the statement of the information of revising original statement, described formation again can comprise and adding or deletion information.For example, can add one or more sub-notions to the set page or from wherein deletion.
Although top general tissue and the statement of use user response with optimization information set (for example gathering the page) of having described, embodiments of the invention can be used to influence the contact of user search engine queries and memory contents (for example one or more document).That is to say that embodiments of the invention can be used for determining relevant more Search Results (being general relevant or more relevant to the specific user more) in response to ad hoc inquiry.
Fig. 2 has shown the program of getting in touch that influences user inquiring and memory contents according to an embodiment of the invention during other users' similar information search sessions by the association based on user search engine (USE) activity of obtaining and/or user profile.
Program 200 shown in Figure 2 starts from operating 205, wherein to USE action message and/or user profile during the session of some isolated user record searchings.Search sessions comprises the sequence of any search engine action (can by the activity of search engine record) of given user.The USE activity can comprise the link of sending inquiry, clicking guiding inside on the searched page or external data, click the link of guiding inside on the follow-up internal pages or external data and return searched page or any internal pages after clicking inside or external linkage.The USE activity can be for continuous or continue to take place in the cycle in reality.That is to say the time cycle that to specify the expression search sessions to stop.For example, if the interruption in the User Activity that is write down has surpassed the fixed time, can suppose that in practice search sessions finishes.The subsequent user activity can be thought new search sessions.
In operation 210, the USE action message and/or the user profile of the some isolated users that write down are associated.Described message reflection each user's whole search sessions, can carry out association in every way according to alternative embodiment of the present invention.The example association of various USE activities and/or user profile will be described in detail hereinafter more.
In operation 215, the USE action message by operating the 210 some isolated users that write down that obtain and/or the association results of user profile are used to influence the contact between particular memory content and the respective user inquiry.This contact can provide general or for the Search Results of the relevant more given inquiry of one or more specific users.
System
Embodiments of the invention can be implemented in network environment.Fig. 3 has shown and has been used to organize and explain conceptual dependency information according to an embodiment of the invention and is used to get in touch the particular memory content and the system of each user inquiring.System 300 has as shown in Figure 3 shown the network of digital processing system (DPS) 300, comprises the one or more server DPS that are shown as server DPS320, and a plurality of client DPS that are shown as client DPS305-308.The DPS of system 300 is connected to each other and is configured to exchange a plurality of various types of memory contentss that comprise document, and for example the content of storing on Webpage, the Webpage comprises text, picture and Voice ﹠ Video content.For example, the content of being stored can be audio/video file, for example has the program of mobile image and audio frequency.Information can communicate between DPS by the communication network of any kind, a plurality of distinct devices can communicate by described communication network, for example (but being not limited to) internet, the wide area network (WAN) that does not show, Local Area Network, Intranet or the like.For example, as shown in Figure 3, DPS is connected to each other by internet 310, and internet 310 is comprise a plurality of networks with aforesaid data communications method wherein a kind of, and is known for those skilled in the art.The communication linkage of Connection Service device DPS and client DPS might not be direct link, but can be indirect link, includes but not limited to broadcast wireless signal, network service or the like.Although shown the DPS of example among Fig. 3, be appreciated that to be connected to each other a large amount of such DPS.
The embodiment that can be used for the digital processing system of server DPS 320 or client DPS 305-308 according to an embodiment of the invention will be described with reference to Figure 12 hereinafter.
According to one embodiment of the invention, the page is for example gathered in the set of conceptual dependency information, gives some users by client DPS 305-308 statements.Described conceptual dependency information can also be the Search Results in response to the user inquiring that sends from one or more client DPS 305-308.Described information can adopt various ways, for example can be the webpage URL address list that provides by the Webpage developer.In case be expressed on the client DPS, the user makes a provisioning response to described statement.For example, the user can carry out aforesaid USE activity.Relevant user responds and other user profile are recorded and are sent to user's response/information/affiliate application 321 with user's information is explained.321 couples of some users' of this application program user response and information are carried out related, and based on the tissue and the statement of the results modification conceptual dependency information of association.
Data analysis
Embodiments of the invention obtain USE action message and/or user profile and these information are carried out association, to select and the auxiliary definition degree of correlation by the majority that uses a plurality of users.Described association analysis comprises the program of estimating common actions or a plurality of user profile, goes up effectively contact with the identification statistics.Term " contact (association) " and " effectively contact (statisticallysignificant association) on the statistics " that these embodiment are used are defined as follows." contact " is that the user is clearly or indirectly, consciously or any pairing of unconscious definite inquiry, term, notion, document or other network datas and combination thereof during the search sessions.Contact can be by sending inquiry and/or selecting the link (for example hyperlink) of guiding inquiry, term, notion, document or other network datas to represent.Effectively get in touch to not belonging to the contact of random occurrence on the probability on the statistics.When by two or write down described association when more independent user is added up effectively contact on the multilist face.
Embodiments of the invention provide the search-engine results more relevant than art methods by the more a large amount of information of record far away with information specific (comprising USE action message and/or user profile) more, and have realized the more deep analysis of information.
One embodiment of the present of invention provide a kind of system that safeguards the data file of all USE action messages and user profile as shown in table 1 of creating and operate.(form that is used to describe each embodiment of the present invention only is exemplary and not necessarily represents the actual data structure of the embodiment of the invention.)
Figure C200480035840D00171
Table 1 ( *=not the inquiry of contact selection)
Table 1 has shown the data file that comprises the mass data element, and these data elements have write down the inquiry of each time point a large number of users and select the URL (selection) of (click) after each inquiry of each user.This data file can comprise a large amount of other data elements of expression USE action message and/or user profile.These data elements for example can be represented the result's that the user clicks during the demonstration ordering, session of selection result order, IP address, geographic position of IP address or the like.
This is different with various art methods, and in the prior art, in cyclical process and after loading new data, the inquiry of simplification-result selects (Q2RP) related by the input database form, for example shows 1A.According to one embodiment of the invention, these not typings of information, but keep with daily record form (log form), data element is represented all USE action message and user profile.
Figure C200480035840D00181
Table 1A
Table 1A is the simplification example of prior art data structure, and the score known to can comprising in the prior art is adjusted the territory.For example, score can also can be the result of complicated more adjustment algorithm simply for selecting the summation of number of times.Score and adjustment also can be stored.
Prior art data structure among the table 1A is enough to produce the Search Results of ordering, but it has represented the loss of a large amount of raw informations.As show shown in the 1A a large amount of available USE action message and user profile during art methods does not have record or analyzes search sessions.This is owing to a variety of causes causes, and comprises the storage restriction, lacks the actual use of these information and does not recognize the adaptable prospect of these information.
According to one embodiment of the invention, can omit these scores of record by the extension of record and canned data and adjust the territory.That is to say,, do not store the score adjustment information, because required any score can be based on institute's canned data and parametrization is calculated these embodiment.And parameter that counts the score and algorithm can change as required and not influence the data of being stored.
Each embodiment according to the present invention depends on the ability of the associated data (comprising USE action message and user profile) between identification and the record isolated user to the in-depth analysis of information.That is to say, by record with analyze more a large amount of information, almost comprise all information during the user conversation, the Search Results that can obtain to have the higher degree of correlation far away.
For example, consider that the user sends a series of inquiries and interleaves the user conversation of selection wherein.Common, be incoherent sending the URL that selects before the inquiry A with inquiry A, because the user often changes theme.Similarly, the great majority selection that takes place after follow-up inquiry B is incoherent with inquiry A.
And, consider that all have write down a large amount of isolated users that comprise the search sessions of inquiring about A.Can expect these users before inquiry A and selected various irrelevant themes afterwards, therefore, irrelevant selection meeting wide dispersion is on a large amount of URL, and each URL can obtain very low score, has reflected that they lack with inquiry A to get in touch.Typically, only have very small amount of, remained on user-selected related urls on those themes relevant really by those and can accumulate of the rearrangement of sufficiently high click popularity mark with the related Search Results of influence and inquiry A with inquiring about A.
For example, suppose 1000 user search queries A.Then, 900 people among them select the inquiry B1 to B900 that has nothing to do.100 remaining people continue to search for the various variations of original theme and select relevant inquiry A1-A9.Each of inquiring about among the result who produces by B can receive once or twice and the associated selection of inquiry A, but the result who produces by relevant inquiring A1-A9 on average can accumulate ten times selection.
For one embodiment of the invention, can force such requirement, promptly the URL after the inquiry necessary selected at least twice is with relevant with original query.A large amount of B inquiry selections that the A mistake is got in touch can be eliminated and inquire about to such requirement.
According to one embodiment of the invention, provide the association analysis that depends on a large amount of statistical samples, to discern a plurality of relevant contacts.For these embodiment, reduced in the prior art restriction and the random data of the contact analyzed have been divided to increase the degree of correlation.That is to say that record and the more a large amount of user session information of analysis also allow to analyze the contact of more heterogeneous pass type.
The USE activity association of example
According to one embodiment of the invention, provide a kind of use one or the small set of how basic association and the system of combination thereof.Common, each embodiment according to the present invention can determine the related of any amount and be used to realize that the Search Results degree of correlation increases or other targets.Describe the association of some example below in detail.
Inquiry-selection (QUERY-TO-PICK)
Inquiry-selection (Q2P) association will be inquired about with selection and interrelate.When a plurality of isolated users carried out identical contact, this identical contact was related candidate.When search engine response when inquiry return results and user selects this as a result, this is the particular case (Q2RP) of this association.In practice, search engine algorithms substitutes second isolated user.According to one embodiment of the invention, the Q2P association will inquire about with user conversation in all selection interrelate.This is different with the scheme of prior art, in the prior art, promptly stops getting in touch between given inquiry and the selection in case send subsequent query.
By Q2P, the given inquiry of sending during all selections of writing down during the user conversation and this user conversation interrelates.In one embodiment, be that based on various factors each contact distributes score, these factors comprise inquiry and select between time, the inquiry that interleaves and/or selection quantity and with respect to the inquiry order of selecting.
And, can adjust the score of each contact based on known factor, the time limit of the time limit of the ordering of selecting in the results list when these factors comprise contact, the perdurability of selection (interval before the next known users action), contact or first known example of order (with respect to contact older or that upgrade) and contact.
Each user conversation can have the unlimited duration.In actual applications, can force the restriction of rational time restriction or insert action, exceed outside this restriction then select and inquiry between specified relationship not.Interchangeable or additional, the interruption of enough duration can be represented the interruption of session.Searching for Log Summary according to an embodiment of the invention is presented in the following table 2.In various alternative embodiments, can search at this and catch any other project in daily record, but for clarity in this omission.
Figure C200480035840D00211
Table 2 ( *=not the inquiry of contact selection)
Fig. 4 has shown the search daily record of three isolated users according to an embodiment of the invention.Search Log Summary 400 shown in Figure 4 comprises the search daily record 410,420 and 430 of the search information of describing three isolated user U1, U2 and U3 respectively, and is described as above reference table 2.Frame of broken lines in each search daily record is represented the Q2RP part in the Q2P search information.For example, search daily record 410 comprises Q2RP part 411, wherein inquires about Q1 and has produced selection P5.Search daily record 410 also comprises Q2RP part 412, wherein inquires about Q2 and has produced selection P1, P2 and P3.
Search daily record 420 comprises that the duration is 48 hours interruption 421.In one embodiment of the invention, interruption can be represented two independent sessions so for a long time, can not specify the relation between any selection and the inquiry between the two.Opposite, search daily record 430 comprises that the duration is 2 hours interruption 431.In one embodiment of the invention, two independent user conversations can not be represented in this interruption.That is to say that all search activities of search daily record 430 can be thought the information of single user session and respective associated.
Table 2A has shown the form of the click information that comprises in the table 2 according to an embodiment of the invention.For relatively, table 2B has shown the form of the click information that comprises in the table 2 according to the typical art methods that adopts the Q2RP association.
Figure C200480035840D00221
Table 2A (Q2P result)
Table 2B (the Q2RP result of prior art)
Our supposition once selects the expression score to increase 0 in damaed cordition below, because a large amount of factor may change score or make the score loss, we suppose selection=score+1 1 time.Suppose a time threshold value, the click in the row 103 is all lost in two forms, because the user only spends the very short time on this URL.Assumption database is carried out the batch processing renewal every day, can be lost as clicking 201 repetition usually in the prior art form of the click in the row 203 in table 2B.According to one embodiment of the invention, the click in the row 203 and 402 is lost in form as clicking 201 repetition.
According to one embodiment of the invention, for inquiry Q1, the URLP1 that never clicks immediately Q1 after has obtained high score in form because a plurality of user send inquire about Q1 before or afterwards (although be not immediately after) selected it.According to one embodiment of the invention, whole the sub matrix of form is more substantial, because write down more contact.Some mark is lower, the mark of Q2P4 for example, and this is because the session data of preserving is represented all clicks from unique user, thereby allows that identification is more to be repeated.
In the practical application of Q2P, we can keep specific contact is the also difference of right and wrong Q2RP of Q2RP.Single, not related non-Q2RP clicks (for example Q3P1 in the form) and can not produce and enough provide the result degree of confidence to the user, yet click for single, not related Q2RP, provide the result's of original search the fact to strengthen contact by search engine.
Selection-inquiry (PICK-TO-QUERY)
Selection-inquiry (P2Q) association is that all inquiries of will write down during the user conversation interrelate, and the given selection of sending is associated during these inquiries and this user conversation.Search Log Summary in the table 2 has shown the relevant output of P2Q.That is to say, can regroup index to P2Q the identical data that Q2P produces.
Inquiry-inquiry (QUERY-TO-QUERY)
Inquiry-inquiry (Q2Q) association be will send during the user conversation all inquiries and this session during the every other inquiry of sending interrelate.In one embodiment, can be that each contact specifies score based on various factors, these factors comprise whether time limit of quantity, contact of the time between the inquiry, the inquiry that interleaves and/or selection or order (with respect to contact older or that upgrade), Query Result have produced and select and the paired order of the inquiry of contact.
Determine whether Query Result has produced and select and the paired order of the inquiry of contact can provide many especially information, because they can represent whether one query is " association " of another time inquiry.For any practical application, know which correct which mistake in the inquiry of two contacts is of great use.
Searching for Log Summary according to an embodiment of the invention is presented in the following table 3.Only need to search for the query portion of daily record to create the Q2Q form.
Figure C200480035840D00241
Table 3
Table 3A has shown the form (order of sending inquiry is ignored in supposition) of the click information that comprises in the table 3 according to an embodiment of the invention.
Figure C200480035840D00242
Table 3A (Q2Q result)
The following Delta Region of table 3A can be used to preserve paired inquiry order information, avoids two registration (double-booking) situations as going together 301-303.
As mentioned above, can adopt the point system of utilizing various factors to change score or making the score loss.For example, can punish repeating (such as the contact in the contact in row 101 and 102 and row 401 and 402).Perhaps, not related Q2Q contact, Q2Q3 for example, can not produce enough provides the result degree of confidence to the user.
Selection-selection (PICK-TO-PICK)
Selection-selection (P2P) association be will send during the user conversation all select with this session during the every other selection of sending interrelate, like this, the related and above-mentioned Q2Q association class of P2P is seemingly.Same, according to each embodiment, can specify score, these factors to comprise the paired order of the selection of time limit of quantity, contact of the time between the selection, the inquiry that interleaves and/or selection or order (with respect to contact older or that upgrade) and contact to each contact based on various factors.
Searching for Log Summary according to an embodiment of the invention is presented in the following table 4.Only need to search for the selection part of daily record to create the P2P form.
Figure C200480035840D00251
Figure C200480035840D00261
Table 4
Table 4A has shown the form (order of sending selection is ignored in supposition) of the click information that comprises in the table 4 according to an embodiment of the invention.
Figure C200480035840D00262
Table 4A (P2P result)
Same, repeat (such as the contact that relates to row 201 and relate to the contact of row 203) and may incur loss, the cost user of very short time on URL also can incur loss.
The following Delta Region of table 4A can be used to preserve paired order of preference information, avoids the two registration situations as going together 201-203.
The combination of the USE activity association of example
The various alternative embodiments according to the present invention can link together two or more associations (for example described above related substantially) so that relevant more Search Results to be provided.For example, thereby can connect two or more basic related strengthen its result, particularly need under the situation of additional result of broad match in rare data or generation to imitate basic association.
Selection or inquiry rather than user are used in association after the connection, to form the link between other selections and the inquiry.Common, the association of connection is many more, and the result departs from initial selected or inquiry is far away more.Therefore, under many circumstances, connecting minimum association is optimum approach to produce required result.
Table 5 has shown may making up of the movable basic related two kinds of associations of above-mentioned USE.
Figure C200480035840D00271
Table 5
Connect the related relation that may introduce mistake, therefore, in one embodiment of the invention, association is carried out in association.For example, if the Q2Q association needs two isolated users, the QQQ associated character string should need to link two inquiries of original and final inquiry.In QQQ, the inquiry that interknits (Q3) interrelates an inquiry (Q1) and another inquiry (Q2).If identical contact is carried out in two or more inquiries that independently, interknits, then this is a kind of association.
As above with reference to basic related described, the contact between original selection or inquiry and output selection or the inquiry forms (perhaps adding body one by one by a search engine) by two each and every one bodies at least.By the association that connects, can there be individual consumer's (perhaps search engine) that original selection or inquiry are selected or inquire about with any output to interrelate.Two isolated users of the also minimum needs of indirect association.
On effect, the association of connection tend to predict lot of data more is collected into future during certain time point basic association what may be.In essence, their discern the possible association that is not observed as yet.
Related combination needs the association between a plurality of middle selections or the inquiry.Link original and relevant selection or the different selection of inquiry and/or the quantity of inquiry, than centre selection and/or inquiry and original and relevant selection and/or query link Duo approaching more important.For an association, at least two different link paths must be arranged, and no matter there are how many users to set up these links.That is to say,, also can't form association between Q1 and the Q2 even a plurality of user has set up this contact by intermediate node Q3 contact Q1 and Q2.
A large amount of factor affecting related intensity, comprise the quantity of link path, the intensity of each direct correlation component link and the uniqueness of each intermediate node.For example, link may produce than passing through unique more two associations that selection is more weak of intermediate queries (such as " 1965 Ford wild horse roadster ") link far away by public and general inquiry two related selections of (for example " automobile ").
Connecting association " inquiry-selection-inquiry " (QPQ) the example of related advantage after by following connection can better understand.
Table 6A and table 6B have shown the multiplied result of the intersection QP score of table 2A and 2B respectively, and for inquiry with these results added to determine the contact score after the combination.(this might not be an optimal algorithm, but is used for the example purpose).
Figure C200480035840D00281
Table 6A
Figure C200480035840D00282
Table 6B
Table 6C and table 6D have shown the equivalent Q2Q association table of table 6A and table 6B respectively.
Table 6C
Figure C200480035840D00291
Table 6D
As mentioned above, according to one embodiment of the invention, the QPQ association results has produced more related far away than the narrower QRPQ association of more specific alternative embodiment of the present invention, and beguine according to the Q2Q of another embodiment of the present invention related produce more far away related.And, use the related inquiry that allows to produce Search Results to incorrect formation of QPQ to offer suggestions.This is impossible in art methods.
User-user
Can pass through user's association as inquiring about and/or selecting, the user can be by inquiring about and/or selecting and association.Be called as user to user (U2U) as general program with indirect association like the QPQ association class.The U2U association of selecting based on the result (promptly two users have imported identical inquiry and selection) is presented in the following table 7.This association should be user-result selection-user (URPU), although there are other U2U associations of the alternative embodiment according to the present invention.Same, according to various embodiment, can specify score to each contact based on various factors.For example, suppose time threshold, the click in the row 103 is lost, because the user only spends the seldom time on URL.
Figure C200480035840D00292
Figure C200480035840D00301
Table 7
Table 7A has shown the form of the click information that comprises in the table 7 according to an embodiment of the invention.
Figure C200480035840D00302
Table 7A
According to one embodiment of the invention, a given user (for example U1) is to the unison quantity that can be defined as inquiry/selection that this user and another user share of another user's (for example U2) class, (is that class is unison divided by inquiry/selection sum of given user U1-U2=(the QP that shares U1-U2)/(QP U1Sum)).In alternative embodiment of the present invention, can use the complicated more unison algorithm of class.For example, according to one embodiment of the invention, the unison algorithm of class can be taken the difference of search rate into account and inquiry, selection are imposed different weights with inquiry-selection.
Table 7B has shown the unison information of class that the click information of his-and-hers watches 7A is calculated.
Figure C200480035840D00311
Table 7B
Use the unison information of this class, when the inquiry that given user is sent in the future bears results, adjust the selection score of respective user according to the unison information of described class.For example, the following Query Result of user U1 will be adjusted the selection score that user U3 produces with the 0.67 selection score and 0.33 of adjusting user U2 generation.The selection that does not have the unison user's generation of class is with designated certain default value.
Example application
The method and system of the tissue of above-mentioned each alternative embodiment of reference the present invention and statement data can be used for various practical applications, and this it will be apparent to those skilled in the art that.These application more comprehensively are discussed below.The use of specific USE action message and/or user profile can be more suitable for application-specific than other information.For example, for application-specific, it is will be more practical, more effectively or more accurate that association is carried out in specific USE activity.Below example application will describe at the USE action message of the actual enforcement that is particularly suitable for application-specific and/or user profile.
The Q2P of example uses
Of the present inventionly Q2P and/or Q2P equivalent combinations USE action message are carried out related embodiment allow the user to obtain relevant more Search Results in every way.For example, the user can precision search and revised result's some part and original search interrelated.That is to say that the document of selection might not be related with original search on literal, and only be notional relation.Conceptual relation can provide original search better response.Avoided the restriction of text based retrieval in the art methods based on the Search Results of the association of Q2P USE action message.User's search procedure again can be preserved and utilize to embodiments of the invention.This ability can be used to realize to have a large amount of obviously systems of advantage than art methods.
Association according to the Q2P USE action message of a large amount of isolated users of various embodiments of the invention has not only utilized previous user's the degree of correlation to judge, and has utilized its research effort.Subsequent user does not need the previous user's of repetition mistake, but can be benefited from the lesson of trial-mistake of previous user.
Fig. 5 has shown the program that more heterogeneous pass Search Results is provided according to an embodiment of the invention.Program 500 shown in Figure 5 starts from operating 505, wherein receives inquiry from the user.Described inquiry can have one or more particular characteristics, and these characteristics are in a single day identified, then can be used as the basis that according to the present invention each alternative embodiment provides relevant more Search Results.
In operation 510, the Q2P USE action message of a large number of users carries out association for received inquiry.Each inquiry can have various particular characteristics, and these characteristics can be determined by the association of Q2P USE action message.These particular characteristics for example can comprise: inquiry can have different meanings to different user, inquiry can be spelt by mistake, inquiry can have wording of equal value, inquiry can have comparatively relevant part and not too relevant part, inquiry can interrelate with particular result output or output combination as a result, and inquiry can have wideer or narrower Search Results.Each characteristic in these characteristics no matter be independent or combine, may be useful for relevant more Search Results is provided under different condition.
In operation 515, be provided for the user in response to inquiry based on the Search Results of the Q2P USE action message after the association.The Search Results that is provided can be based on one or more characteristic of inquiry.For example, when definite described inquiry has different meaning, can provide the result who has based on more popular meaning in response to inquiry.
Some example results of obtaining by program 500 compare with the result who obtains by typical prior art, show below with respect to the special characteristic of above-mentioned inquiry.
Table 8 has shown the exemplary search results that has more than a kind of some inquiries of meaning.It is as shown in the table, compares with art methods, and embodiments of the invention allow Search Results to be related to the more popular meaning of ad hoc inquiry.
Figure C200480035840D00331
Table 8
Table 9 has shown the exemplary search results (for example " encycopidea ") of mistake spelling.It is as shown in the table, and embodiments of the invention allow Search Results to be related to the inquiry that may correctly spell.In this way, embodiments of the invention can be determined the correct spelling of mistake spelling inquiry.Art methods can not produce Search Results, perhaps very poor Search Results usually to this mistake spelling.
Figure C200480035840D00332
Table 9
In one embodiment of the invention, this spelling correction is that a kind of " soft " proofreaies and correct.That is to say that according to one embodiment of the invention, the result who provides in response to inquiry is the accurate result of the most of user institute preference of inquiry of input.If most users think that this inquiry is mistake spelling, then large result will comprise the inquiry after the correction.If most users think that this inquiry is intentional, then large result will comprise the inquiry of not changing.If two kinds of explanations all are legal, then the result is the two combination.For this embodiment,, therefore unlikely provide wrong spelling correction owing to all corrections all are that conceptual dependency is not only a literal similarity.
Opposite, the spelling correction of prior art is generally " firmly " and proofreaies and correct.That is to say that these method identification mistake spelling inquiries are attempted proofreading and correct then based on proofreading and correct Search Results.When legal inquiry is mistake spelling by wrong diagnosis, perhaps inquiry really the mistake spelling when but the correction by algorithm still was not required inquiry, these methods can provide incoherent result." initiatively " correction can require user clicks on links so that the inquiry of suggestion is searched for once more, so also may be error recovery once more.
Table 10 has shown the exemplary search results of the inquiry with two kinds or more explanations or wording of equal value (for example " Burma and Myanmar ").It is as shown in the table, and embodiments of the invention provide Search Results to having each highly concomitant wording of equal value.For the example that is provided, there are five to be identical among nine top Search Results URL for each wording of equal value.This compares with art methods has higher similarity far away.
Figure C200480035840D00341
Table 10
The user usually comprises the keyword that relevant information can not be provided in inquiry, but search engine has been brought unnecessary text matches requirement, has caused the Search Results of the lower degree of correlation in art methods.Embodiments of the invention have overcome this defective.
Table 11 has shown the exemplary search results of the inquiry that comprises redundance.It is as shown in the table, and embodiments of the invention allow to ignore unnecessary, the inessential and uncorrelated part in the inquiry, and relevant more more succinct inquiry is provided like this.
Table 11
According to one embodiment of the invention, fair play is selected the Search Results of various result products (for example picture, audio/video, text, image, news item or the like).That is to say that the user does not need to specify them seeking the result of which kind of type.The result who provides can reflect the preference of preference that this user had before shown or previous isolated user.For example, if thereby inquiry produces the selection that the picture search specific image is a top score very continually, and then this image may be provided as Search Results according to its score.In one embodiment, each top score result of Different Results product need not be staggered according to the score order, but can be expressed as according to the product grouping.For this embodiment, the result product of user search need not understood and discern inquiry with language tool when attempt to confirm customer objective.
Table 12 has shown the sample query Search Results that is produced by Search Results product combination (for example comprising the picture result).It is as shown in the table, and embodiments of the invention allow Search Results to comprise the product combination.
Figure C200480035840D00352
Table 12
Embodiments of the invention can select the weight of score to change the scope of Search Results to Q2RP by regulating Q2P.Table 13 has shown the Search Results to the narrower and broad of inquiry " Stanford ".
Figure C200480035840D00361
Table 13
First row of table 13 comprise the narrower result who relates to the selection of inquiry.The secondary series of table 13 has shown broad result (for example only having shown the selection of making less than the result in response to original query).The result of secondary series represents to inquire about the relative broad range of theme, and the result of first row helps the user to probe into the degree of depth of inquiry theme.In fact, the narrower and combination broad result can provide maximally related Search Results.In one embodiment of the invention, created a large amount of combinations with different range, allow the user to select " widening the result " or " focusing result " link, perhaps change control to adjust combination.
The Q2Q of example uses
One embodiment of the present of invention are carried out association to Q2Q and/or Q2Q equivalent combinations USE action message, allow the user to obtain the inquiry of the suggestion relevant with its search.Fig. 6 has shown the program that the relevant inquiring suggestion is provided according to an embodiment of the invention.Program 600 shown in Figure 6 starts from operating 605, wherein receives inquiry from the user.
In operation 610, Q2Q (and/or Q2Q equivalent combinations) USE action message is associated.Related Q2Q USE action message directly tends to produce the result of the remarkable precision of inquiry.Related Q2Q equivalent combinations USE action message tends to produce more various result, although have the repetition of height usually.In one embodiment of the invention, to the related Q2Q equivalent combinations of fuzzy relatively original query USE action message, because this association produces more query suggestion usually far away.
The query suggestion that provides in response to original query " electroniceavesdropping devices " according to an embodiment of the invention has been provided table 14.First row of table 14 comprise directly the query suggestion based on the association of Q2QUSE action message, and the secondary series of table 14 comprises the query suggestion based on the association of Q2Q equivalent combinations (being QPQ) USE action message.
Figure C200480035840D00371
Table 14
In operation 615, provide based on one or more query suggestion of the Q2Q after the association (and/or Q2Q equivalent combinations) USE action message and give the user.In one embodiment of the invention, query suggestion can be expressed on the results page.Replaceable or additional, can on the page of query suggestion, provide link.When original query produced the query suggestion of a large amount of height correlations (for example high score), this embodiment was very practical.In one embodiment of the invention, query suggestion can be classified as accurate (comprising all original search words) and relevant search before statement.
According to one embodiment of the invention, the association of Q2Q (and/or Q2Q equivalent combinations) USE action message is used to produce query spelling bearing calibration initiatively.In query spelling bearing calibration initiatively, the query correction that the user selects to advise is to obtain the Search Results based on query correction.
Fig. 6 A has shown the program that the query spelling correction suggestion is provided according to an embodiment of the invention.Program 600A shown in Fig. 6 A starts from operating 605A, wherein receives inquiry from the user.This inquiry may be the misspellings of the required inquiry of user.
At operation 610A, the operation 610 of referral procedure 600 and associated as mentioned above of Q2Q (and/or Q2Q equivalent combinations) USE action message.
At operation 611A, determine one or more query suggestion based on the Q2Q after the association (and/or Q2Q equivalent combinations) USE action message.
At operation 612A, one or more query suggestion is confirmed as the spelling correction (i.e. the inquiry that receives at operation 605A) of original query.According to alternative embodiment of the present invention, the determining of query suggestion is affected with various different modes according to received inquiry.For example, for the inquiry that had before observed, when having Q2Q information, the similar inquiry of conceptual dependency and text can be used Q2Q related information and editing distance computational algorithm and be identified.In the case, can use various standards to realize determining as the query suggestion of the spelling correction of original (being received) inquiry.For example, when determined query suggestion is associated with received inquiry, similar and can be confirmed as the spelling correction of received inquiry than the general more determined query suggestion of received inquiry with received query text.In alternative embodiment, can consider that more standards are with the confidence level determined of raising as the query suggestion of the spelling correction of received inquiry.For example, when before received inquiry, query suggestion is tended to more frequent when sending after received inquiry, when perhaps query suggestion was tended to produce more user and select than received inquiry, these standards can improve to be determined as the confidence level aspect the query suggestion of the spelling correction of received inquiry.
Then there is not Q2Q information in the inquiry of inquiry for before not observing when receiving at operation 605A.In the case,, there is mistake, then assessed in one of two ways according to before whether observing the speech of described suspection if suspect a speech in the inquiry according to one embodiment of the invention.
When before observing the speech of described suspection, then identify other inquiries that this speech occurs.Based on the keyword identical these inquiries are weighted with the inquiry that receives.At last, the correction of the suspicious speech of previous consideration is checked and be used for based on the keyword weight of the frequency of the correction of previous suggestion and inquiry that should suspicious speech appearance and the correction of offering suggestions.
When before not observing the speech of described suspection, other inquiries that the every other keyword in the received inquiry occurs can be identified.In one embodiment of the invention, when this standard is not satisfied in inquiry, can discern the inquiry that has the public speech of the most unusual (the most distinctive) (low frequency) with received inquiry.For each embodiment, the inquiry of being discerned can be based on being weighted with the text similarity of the inquiry that is received and identification and received inquiry have the most general inquiry of very high text similarity.
In one embodiment of the invention, when condition does not allow to use the method for above-mentioned spell correction suggestions program, the use that combines of the Q2Q USE action message after the association and traditional n-gram-type model.In this embodiment, go out speech contact frequency so that speech determined to follow jointly in known keyword or phrase from the enquiry frequency data extract.These data and editing distance combine and are used to the unknown word in the inquiry of many speech is determined inquiry as possible spell correction suggestions.
At operation 615A, one or more query suggestion that is defined as the spelling correction of received inquiry is provided for the possible spelling correction of user as received inquiry.In one embodiment of the invention, when not having query suggestion to be confirmed as the possible spelling correction of received inquiry, then with reference to the operation 615 aforesaid query suggestion that provide of the program 600 of figure 6.
The P2Q of example uses
According to one embodiment of the invention, can use P2Q or P2Q equivalent combinations and provide about the suggestion of particular result page inquiry.
Fig. 7 has shown the program of the inquiry of offering suggestions according to an embodiment of the invention.Program 700 shown in Figure 7 starts from operating 705, wherein receives inquiry and the corresponding Search Results that large result URL is provided.
In operation 710, to each URL association as a result P2Q (perhaps P2Q equivalent combinations) USE action message.
In operation 715, based on the P2Q USE action message after the association to each URL inquiry of offering suggestions as a result.That is to say, provide with Search Results in the suggestion Query List that is closely related of any page.These suggestions under the situation of fuzzy query may for the user provide by URL in one rather than other the focusing meaning that realizes.
Table 15 has shown the exemplary search results page of inquiry " rangers " according to an embodiment of the invention and the correspondence suggestion inquiry of example.
Figure C200480035840D00401
Table 15
The P2P of example uses
According to one embodiment of the invention, similar to particular result one or the more results who provides in response to received inquiry uses P2P or P2P equivalent combinations and provides.For example, receive inquiry and assessment result corresponding to this inquiry.Based on described assessment, provide similar results equally.That is to say for example, can have the new results page of additional similar results along with the result specifies some related pages and/or link to lead.Common, the similar results of image can produce other images mostly, and the similar results of webpage can produce other webpages mostly, and the like.
Fig. 8 shows the program that similar results is provided according to an embodiment of the invention.Program 800 shown in Figure 8 starts from operating 805, wherein receives inquiry and determines corresponding Search Results.
In operation 810, to related P2P (perhaps P2P equivalent combinations) the USE action message of the Search Results of correspondence.
In operation 815, provide one or more similar results (promptly being similar to received result) based on the P2P USE action message after the association.That is to say, the results list that is closely related with received result is provided.Similar results can be formed search selection, image, news item or the like.
The example similar results that provides in response to inquiry " phoenix " according to an embodiment of the invention has been provided table 16.
Figure C200480035840D00411
Table 16
The user profile of example is used
Personalized search
The notion of personalized search is based on following prerequisite, promptly can provide relevant more Search Results when some information of knowing about the user.The recommendation of sharing the user of certain user's at least interest and suggestion in the past is considered to have bigger value than the user's who does not share its interest and taste recommendation.
Individuation search method of the prior art is discerned user's demography usually, yet customizes the result according to the preference of other members in this demography group.This method has serious defective, and promptly preference changes widely different in a population statistical body.Each user belongs to a lot of and the very difficult usually demographic group that is in harmonious proportion usually, and the user does not provide reliable demographic information usually.
According to one embodiment of the invention, each user is a group of thinking that a people forms, has unison with respect to other users' class.
Fig. 9 shown according to an embodiment of the invention information is carried out related so that the program of more relevant Search Results to be provided.Program 900 shown in Figure 9 starts from operating 905, wherein each is showed the unison matrix of user's compute classes of minimum at least search activities.In one embodiment of the invention, calculate the unison matrix of described class and can followingly carry out.At first, extract inquiry and the selection of all given user U1.Then, be identified with the inquiry of U1 and/or N at least user U2 that repeats in the selection, and identification remaining inquiry of U2 and selection.Then to each inquiry and selection specified weight and the unison mark of compute classes.Described weight can be inversely proportional to this inquiry and/or the common degree that is chosen among all users, and compares and the unison mark of compute classes by will be after the weighting total selection/inquiry and total weighting selection/inquiry.
In operation 910, the Search Results that the new inquiry of U1 produces is analyzed, and if any previous selection belong to user then the mark that increases each result with the unison mark of non-zero class.
In operation 915, based on operation 910 mark adjustment and to result's rearrangement and the expression of results after will reordering give the user.
Alternative embodiment according to the present invention can be used to increase the degree of correlation that search is advised with program 900 similar programs.
The localization search
A kind of important kind of user profile is the position.The position has advantage than other demographic informations, because it does not need user to provide itself and no matter who all is to keep real using a computer.
In one embodiment of the invention, user profile comprises user's geographical location information, and comprises its inquiry and selection by expansion.Described geographical location information can comprise longitude and latitude and city, state name and name of the country.According to an embodiment, these user profile are used to provide Search Results based on user's geographic position.For example, the U.S. user of input inquiry " osu " may represent " Ohio State University (Ohio State University) ", " Oklahoma State University (Oklahoma StateUniversity) " or " Oregon State University (Oregon State University) ".In one embodiment, the Search Results that is provided is also related with the user with similar user profile (for example similar position).
Figure 10 has shown according to an embodiment of the invention according to the program that more relevant Search Results is provided based on customer location with the position of selecting to interrelate.Program 1000 shown in Figure 10 starts from operating 1005, has wherein obtained " " center " and " coverage " that are assigned with latitude-longitude more than the URL of the selection of specified quantity.The center is the position apart from certain function minimization of summation that arrives that the effective user of statistics of each record selects.For example, in one embodiment, the center can represent that URL (URL with local tendency) concrete (brick-and-mortar) position in real world is to realize the height precision.When not having local tendency, the center has seldom or is nonsensical at all.For example, the URL that does not have a real world particular location can not have nationwide local tendency.
Coverage is to expect URL to the highly attractive geographical radius of user, and expectation is not attractive outside this.Radius is more little, and attractive force descends steep more or attractive force " localization " more.The radius of coverage is inversely proportional to certain tolerance of local tendency.For example, highly Ben Dihua URL for example www.canariesbaseball.com form the center at Sioux Falls, the very compact coverage of SD (being the local of Sioux FallsCanaries).
In operation 1010, coverage adjusts according to statistics.For example, some position generates and more clicks than other position.Adjust original click data to reflect this species diversity.
In operation 1015, compared with the response ad hoc inquiry with precalculated position data set in user's geographic position, and adjust the Search Results score based on user's geographic position.Near those and have highly that the mark of the URL of localization is increased, and the mark of URL is reduced (mark that does not have the URL of very big localization tendency remains unchanged) at a distance.
In operation 1020, the user is provided the Search Results that has at least in part based on user's geographic position.The permission user receives the subjective correlated results in the initial SOME RESULTS like this.For example, compared with prior art, the easier state tax form that is provided the Wyoming State of user of the Wyoming State of input " state tax form (state taxforms) ".
Subscriber's localization
As mentioned above, localization can be based on selection, perhaps can be according to alternative embodiment and based on the user.In one embodiment of the invention, buffer memory gets up by the compass of competency to allow the result of popular inquiry based on user's localization, and position-based offers the user and without any need for real-time calculating then.
Figure 11 has shown according to an embodiment of the invention the program that the user is provided more relevant Search Results based on customer location.Program 1100 shown in Figure 11 starts from operating 1105, wherein determines the compass of competency for the specified portions of the click of given inquiry, starts from the compass of competency of highest level.For example, inquiry " car insurance " produces the mixing of U.S. and Britain's website, and the user who is positioned at Britain more clicks Britain's website, and the user who is positioned at the U.S. more clicks U.S.'s website.
In operation 1110, be increased for the click mark of the compass of competency of the assign thresholds part of clicking, and create the independent the results list that is labeled as this compass of competency.
In operation 1115, the click mark of the user outside described compass of competency is reduced, and has produced the generality tabulation for the user outside the compass of competency of the assign thresholds part of clicking.In alternative embodiment, create the real-time tabulation that mixes with the adjacency in zone in a given jurisdiction based on the user.
In operation 1116, if, then in operation 1120, provide the result based on the user compass of competency not at the compass of competency of the certain threshold level part of clicking.
In operation 1116, if exist at the certain threshold level of clicking compass of competency partly, then program circulation again in operation 1125 by proceeding to other compass of competency of even lower level, and arrive operation 1105 thus.
In alternative embodiment, with the position related with URL and do not consider the inquiry.Has the advantage on the effective statistical significance like this, because can assemble more multidata.For example, consider that all select the user's of specific state tax website source place to any inquiry, give extra weight at the user in the topmost state to particular station then and no matter the inquiry that relates to.Potential defective is, if the user of Wyoming State input " Florida state tax form ", if Wyoming State tax website among the result, then it gets branch and obtains effective and without basis increase.
General issue
Embodiments of the invention provide the method and system of conceptive combination and statement information, wherein use user's response and information combination to determine the optimum tissue and the statement of information with the related of statement.Although abovely describe at some example embodiment, alternative embodiment of the present invention has a lot of additional application.
The present invention includes various operations.A lot of methods are described with its citation form, but can any method interpolation or deletion action not deviated from base region of the present invention.Operation of the present invention can or can realize by the hardware execution in the executable instruction of aforesaid machine.Interchangeable, these steps can be carried out by the combination of hardware and software.The present invention can be provided as computer program, can comprise the machine readable media of having stored instruction, and these instructions can be used for computing machine (perhaps other electronic equipments) is programmed to carry out according to aforesaid program of the present invention.
Figure 12 is for showing the embodiment that can be used for according to an embodiment of the invention with reference to the digital processing system of figure 3 described server DPS320 or client DPS305-308.In alternative embodiment of the present invention, disposal system 1201 can be computing machine or set-top box, comprises the processor 1203 that is connected with bus 1207.In one embodiment, internal memory 1205, storage unit 1211, display controller 1209, communication interface 1213 and i/o controller 1215 also are connected to bus 1207.
Disposal system 1201 is connected to external system by communication interface 1213.Communication interface 1213 can comprise analog modem, integrated services digital network network (ISDN) modulator-demodular unit, cable modem, digital subscriber line (DSL) modulator-demodular unit, T-1 line interface, T-3 line interface, light carrier interface (for example OC-3), token-ring network interface, satellite transmission interface, wave point or be used to connect devices to other interfaces of other equipment.Communication interface 1213 can also comprise transceiver or radiophone signal or the like.
In one embodiment of the invention, reception/transmission signal of communication 1225 between communication interface 1213 and cloud shape symbol 1230.In one embodiment of the invention, signal of communication 1225 can be used for disposal system 1201 is connected to another computer system, hub, router or the like.In one embodiment of the invention, signal of communication 1225 is machine-readable medium, can pass through circuit, cable, optical fiber or atmosphere or the like transmission.
In one embodiment of the invention, processor 1203 can be traditional microprocessor, such as but not limited to Intel Pentium series processors, Motorola systematic microprocessor or the like.Internal memory 1205 can be machine readable media, for example dynamic RAM (DRAM) and can comprise static random-access memory (SRAM).Display controller 1209 is according to traditional approach control display 1219, and in one embodiment of the invention, display 1219 can be cathode ray tube (CRT) display, LCD (LCD), Active Matrix Display, TV monitor or the like.Input-output apparatus 1217 is connected to i/o controller 1215, can comprise mouse, roller ball, touch pad or the like for keyboard, disc driver, printer, scanner and other input and output devices.
Storage unit 1211 can comprise machine readable media, such as but not limited to hard disk, floppy disk, CD, smart card or other forms of data storage cell.In one embodiment of the invention, storage unit 1211 can comprise can wipe medium, read-only medium, read/writable medium or the like.Some data can be passed through the direct memory access program and write memory 1205 in the software execute process of computer system 1201.Should be appreciated that software can reside in storage unit 1211, the internal memory 1205, perhaps can send or receive by modulator-demodular unit or communication interface 1213.For illustration, term " machine readable media " thus will be understood that it is to comprise can storing data, information or instruction sequence being encoded to carry out any medium that causes processor 1203 to carry out method of the present invention by processor 1203.Term " machine readable media " should include but not limited to solid-state memory, CD and disk, carrier signal or the like.
Although described the present invention with reference to some embodiment, it will be understood by those skilled in the art that the present invention is not limited to described embodiment, rather than can implement by the modifications and variations within appended claims essence and scope.Therefore this instructions should be considered to illustrative rather than restrictive.

Claims (40)

1. the method for conceptive tissue and statement information comprises:
A plurality of users are given in the ensemble of communication of statement conceptual dependency;
From two or more users each receives one or more response for the statement of described conceptual dependency information;
To carry out association from the response of two or more users, describedly be associated as the related or selections-selection association of selection-inquiry, wherein selection-inquiry is related interrelates the inquiry of writing down during the user conversation, the selection of sending is associated during these inquiries and this user conversation, and other selection that selection-selection association is sent during with the selection of sending during the user conversation and this session interrelates; And
Revise the statement of described conceptual dependency information based on the response after the described association.
2. method according to claim 1, wherein said conceptual dependency ensemble of communication comprise one or more different set pages with different statements that form.
3. method according to claim 2, wherein said one or more response comprise the selection or the non-selected part of described conceptual dependency ensemble of communication.
4. method according to claim 3, the statement of wherein revising described conceptual dependency information based on the response after the association comprise and form one or more described set page again.
5. method according to claim 1, wherein each response that receives from two or more users is each user's search engine action message.
6. method according to claim 5, the statement of wherein revising described conceptual dependency information comprise customizing messages and respective user inquiry are interrelated.
7. method according to claim 5, wherein said search engine action message comprises all information in the session of user search engine.
8. method according to claim 7, wherein said search engine session is defined by the restriction of insert action in rational time restriction or the search engine activity.
9. method according to claim 5, wherein said each response that receives from two or more users is to select from the group of search engine action message, and the group of described search engine action message comprises the combination of inquiry-selection information, selection-Query Information, selection-selection information, inquiry-Query Information and above-mentioned information.
10. method according to claim 1, wherein said conceptual dependency ensemble of communication comprises Search Results.
11. method according to claim 10, the statement of wherein revising described conceptual dependency information based on the response after the association comprises:
Based on described association described Search Results is resequenced.
12. method according to claim 9, the statement of wherein revising described conceptual dependency information based on the response after the association comprises:
The second search engine active set of statement conceptual dependency, the wherein said second search engine active set is correlated with the conceptual dependency search engine set based on the response after related.
13. method according to claim 12 wherein comprises described response association select the group that inquiry-selection is related from comprising, selection-inquiry is related, selection-selection is related, inquiry-inquiry is related and make up one or more.
14. method according to claim 1 comprises that further the amended conceptual dependency information statement of statement is given to few user.
15. method according to claim 1, the special characteristic of wherein said conceptual dependency ensemble of communication is the feature of the multivalent conceptual dependency ensemble of communication of tool, and the statement of revising described conceptual dependency is based on a certain in the multiple meaning.
16. method according to claim 1, wherein said conceptual dependency ensemble of communication is relevant with search inquiry, and the special characteristic of described inquiry is the feature of inquiry of the required inquiry error spelling of suggestion, and described modification is based on the required inquiry of being advised.
17. method according to claim 1, wherein said conceptual dependency ensemble of communication is relevant with search inquiry, and the special characteristic of described inquiry is the feature with inquiry of multiple statement, and described modification is based on a certain in the multiple statement.
18. method according to claim 1, wherein said conceptual dependency ensemble of communication is relevant with search inquiry, and the special characteristic of described inquiry is the feature that comprises the inquiry of more relevant portion or less relevant portion, and described modification is based on more relevant portion.
19. method according to claim 1, wherein said conceptual dependency information are about each inquiry that receives from a plurality of users.
20. method according to claim 1, wherein described response is carried out association comprise the user inquiring relevant with described conceptual dependency ensemble of communication and the user during the search sessions selected or subsequently user inquiring interrelate.
21. the system of conceptive tissue and statement information comprises:
The server count word processing system, be used to send the conceptual dependency ensemble of communication to a plurality of number clients word processing systems, from two or more users each receives one or more user's response for the statement of described conceptual dependency information, association is carried out in response from two or more users, describedly be associated as the related or selections-selection association of selection-inquiry, wherein selection-inquiry is related interrelates the inquiry of writing down during the user conversation, the selection of sending is associated during these inquiries and this user conversation, selection-selection is related to interrelate other selection of sending during the selection of sending during the user conversation and this session, and revises the statement of described conceptual dependency information based on the response after the association; And
One or more number clients word processing system is used to explain described conceptual dependency information and responds described server count word processing system for a plurality of users and transmission user.
22. system according to claim 21, wherein said conceptual dependency ensemble of communication comprises one or more different set pages with different statements that form.
23. system according to claim 22, wherein said one or more response comprises the selection or the non-selected part of described conceptual dependency ensemble of communication.
24. system according to claim 23, the statement of wherein revising described conceptual dependency information based on the response after the association comprises and forms one or more described set page again.
25. system according to claim 21, wherein said each response that receives from two or more users is each user's search engine action message.
26. system according to claim 25, the statement of wherein revising described conceptual dependency information comprises customizing messages and respective user inquiry is interrelated.
27. system according to claim 25, wherein said search engine action message comprises all information in the session of user search engine.
28. system according to claim 25, wherein said each response that receives from two or more users is to select from the group of search engine action message, and the group of described search engine action message comprises the combination of inquiry-selection information, selection-Query Information, selection-selection information, inquiry-Query Information and above-mentioned information.
29. system according to claim 21, wherein said search engine session is defined by the restriction of insert action in rational time restriction or the search engine activity.
30. system according to claim 21, wherein said conceptual dependency ensemble of communication comprises Search Results.
31. system according to claim 30, the statement of wherein revising described conceptual dependency information based on the response after the association comprises:
Based on described association described Search Results is resequenced.
32. system according to claim 21, the statement of wherein revising described conceptual dependency information based on the response after the association comprises:
The second search engine active set of statement conceptual dependency, the wherein said second search engine active set is correlated with the conceptual dependency search engine set based on the response after related.
33. system according to claim 32 wherein comprises described response association select the group that inquiry-selection is related from comprising, selection-inquiry is related, selection-selection is related, inquiry-inquiry is related and make up one or more.
34. system according to claim 21 comprises that further the amended conceptual dependency information statement of statement is given to few user.
35. system according to claim 21, the special characteristic of wherein said conceptual dependency ensemble of communication is the feature of the multivalent conceptual dependency ensemble of communication of tool, and the statement of revising described conceptual dependency is based on a certain in the multiple meaning.
36. system according to claim 21, wherein said conceptual dependency ensemble of communication is relevant with search inquiry, and the special characteristic of described inquiry is the feature of inquiry of the required inquiry error spelling of suggestion, and described modification is based on the required inquiry of being advised.
37. system according to claim 21, wherein said conceptual dependency ensemble of communication is relevant with search inquiry, and the special characteristic of described inquiry is the feature with inquiry of multiple statement, and described modification is based on a certain in the multiple statement.
38. system according to claim 21, wherein said conceptual dependency ensemble of communication is relevant with search inquiry, and the special characteristic of described inquiry is the feature that comprises the inquiry of more relevant portion or less relevant portion, and described modification is based on more relevant portion.
39. system according to claim 21, wherein said conceptual dependency information are about each inquiry that receives from a plurality of users.
40. system according to claim 21, wherein described response is carried out association comprise the user inquiring relevant with described conceptual dependency ensemble of communication and the user during the search sessions selected or subsequently user inquiring interrelate.
CNB2004800358406A 2003-12-08 2004-12-07 Methods and systems for conceptually organizing and presenting information Expired - Fee Related CN100511223C (en)

Applications Claiming Priority (11)

Application Number Priority Date Filing Date Title
US52813903P 2003-12-08 2003-12-08
US60/528,139 2003-12-08
US10/853,552 US7181447B2 (en) 2003-12-08 2004-05-24 Methods and systems for conceptually organizing and presenting information
US10/853,552 2004-05-24
US10/853,860 US7451131B2 (en) 2003-12-08 2004-05-25 Methods and systems for providing a response to a query
US10/853,860 2004-05-25
US10/917,721 US7739274B2 (en) 2003-12-08 2004-08-12 Methods and systems for providing a response to a query
US10/917,721 2004-08-12
US10/944,251 US7152061B2 (en) 2003-12-08 2004-09-16 Methods and systems for providing a response to a query
US10/944,251 2004-09-16
PCT/US2004/041254 WO2005057368A2 (en) 2003-12-08 2004-12-07 Methods and systems for conceptually organizing and presenting information

Publications (2)

Publication Number Publication Date
CN1890664A CN1890664A (en) 2007-01-03
CN100511223C true CN100511223C (en) 2009-07-08

Family

ID=34682419

Family Applications (2)

Application Number Title Priority Date Filing Date
CNB2004800358406A Expired - Fee Related CN100511223C (en) 2003-12-08 2004-12-07 Methods and systems for conceptually organizing and presenting information
CNA2004800358389A Pending CN1898638A (en) 2003-12-08 2004-12-07 Methods and systems for providing a response to a query

Family Applications After (1)

Application Number Title Priority Date Filing Date
CNA2004800358389A Pending CN1898638A (en) 2003-12-08 2004-12-07 Methods and systems for providing a response to a query

Country Status (7)

Country Link
EP (2) EP1697865A4 (en)
JP (2) JP2007513439A (en)
CN (2) CN100511223C (en)
CA (2) CA2546494C (en)
DE (2) DE04813564T1 (en)
ES (2) ES2288455T1 (en)
WO (4) WO2005057369A2 (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8832098B2 (en) * 2008-07-29 2014-09-09 Yahoo! Inc. Research tool access based on research session detection
US20100070488A1 (en) * 2008-09-12 2010-03-18 Nortel Networks Limited Ranking search results based on affinity criteria
CN101923545B (en) * 2009-06-15 2012-10-10 北京百分通联传媒技术有限公司 Method for recommending personalized information
WO2012022021A1 (en) * 2010-08-16 2012-02-23 Nokia Corporation Method and apparatus for executing device actions based on context awareness
US20150081653A1 (en) * 2013-09-13 2015-03-19 Yahoo! Inc. Type free search assist
CN104102744B (en) * 2014-07-31 2018-10-26 宇龙计算机通信科技(深圳)有限公司 Data retrieval method and data searcher
CN104537072B (en) * 2014-12-30 2019-03-12 百度在线网络技术(北京)有限公司 Searching method and device
WO2017115095A1 (en) * 2015-12-30 2017-07-06 Google, Inc. Suggestion of queries based on group association of user

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3186960B2 (en) * 1995-11-30 2001-07-11 松下電器産業株式会社 Information retrieval method and apparatus
US6421675B1 (en) * 1998-03-16 2002-07-16 S. L. I. Systems, Inc. Search engine
US8121891B2 (en) * 1998-11-12 2012-02-21 Accenture Global Services Gmbh Personalized product report
US6446035B1 (en) * 1999-05-05 2002-09-03 Xerox Corporation Finding groups of people based on linguistically analyzable content of resources accessed
AU7352400A (en) * 1999-09-03 2001-04-10 Lewis, Robert Improved method, system, and architecture for information display and organization
US6546388B1 (en) * 2000-01-14 2003-04-08 International Business Machines Corporation Metadata search results ranking system
JP2002236699A (en) * 2001-02-09 2002-08-23 Asahi Kasei Corp Information retrieval system, server for management and control program
JP2002318801A (en) * 2001-04-20 2002-10-31 Yuji Nobemoto Marketing system
US6920448B2 (en) * 2001-05-09 2005-07-19 Agilent Technologies, Inc. Domain specific knowledge-based metasearch system and methods of using
US7117434B2 (en) * 2001-06-29 2006-10-03 International Business Machines Corporation Graphical web browsing interface for spatial data navigation and method of navigating data blocks
JP2003167852A (en) * 2001-11-29 2003-06-13 Ricoh Co Ltd Information providing system

Also Published As

Publication number Publication date
WO2005057367A3 (en) 2006-03-09
EP1697865A2 (en) 2006-09-06
EP1706816A2 (en) 2006-10-04
WO2005057369A2 (en) 2005-06-23
WO2005057369A3 (en) 2006-06-01
CA2546492A1 (en) 2005-06-23
CN1890664A (en) 2007-01-03
CA2546494A1 (en) 2005-06-23
DE04813565T1 (en) 2007-04-05
EP1697865A4 (en) 2007-10-10
CA2546492C (en) 2014-02-11
JP2007513439A (en) 2007-05-24
WO2005057368A2 (en) 2005-06-23
CN1898638A (en) 2007-01-17
WO2005057366A3 (en) 2005-12-29
CA2546494C (en) 2014-03-25
EP1706816A4 (en) 2007-10-24
WO2005057366A2 (en) 2005-06-23
ES2288454T1 (en) 2008-01-16
DE04813564T1 (en) 2007-05-03
WO2005057367A2 (en) 2005-06-23
ES2288455T1 (en) 2008-01-16
WO2005057368A3 (en) 2006-03-02
JP2007513440A (en) 2007-05-24

Similar Documents

Publication Publication Date Title
US11587114B2 (en) System and method for segmenting and targeting audience members
US7152061B2 (en) Methods and systems for providing a response to a query
US7451131B2 (en) Methods and systems for providing a response to a query
CN1871603B (en) System and method for processing a query
RU2408066C2 (en) Method and device for delivering network information
CN1645370B (en) Building and using subwebs for focused search
US20060230040A1 (en) Methods and systems for providing a response to a query
US7054876B2 (en) Program, apparatus, and method of conducting questionnaire
CN105631707A (en) Advertisement click rate estimation method based on decision tree, application recommendation method and device
US20060247940A1 (en) Compatibility scoring of users in a social network
US8898129B1 (en) Prompt for query clarification
CN101416186A (en) Enhanced search results
CN102859516A (en) Generating improved document classification data using historical search results
CN107656997B (en) Natural language processing method and device, storage medium and terminal equipment
CN100511223C (en) Methods and systems for conceptually organizing and presenting information
CN102354313B (en) Conceptive method and system for organizing and expressing information
US7433865B2 (en) Information collection retrieval system
KR100726544B1 (en) Method for providing evaluation target theme established in customized manner and evaluation information thereof by several netizens based on communication network, and System for implementing the same
CN117708425A (en) Information recommendation method, device, electronic equipment and computer medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20090708

Termination date: 20201207

CF01 Termination of patent right due to non-payment of annual fee