US20060010229A1 - User intention modeling for web navigation - Google Patents
User intention modeling for web navigation Download PDFInfo
- Publication number
- US20060010229A1 US20060010229A1 US11/219,932 US21993205A US2006010229A1 US 20060010229 A1 US20060010229 A1 US 20060010229A1 US 21993205 A US21993205 A US 21993205A US 2006010229 A1 US2006010229 A1 US 2006010229A1
- Authority
- US
- United States
- Prior art keywords
- user
- sequence
- navigation
- computer
- goal
- 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.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/954—Navigation, e.g. using categorised browsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/564—Enhancement of application control based on intercepted application data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/62—Establishing a time schedule for servicing the requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/40—Network security protocols
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/568—Storing data temporarily at an intermediate stage, e.g. caching
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/30—Definitions, standards or architectural aspects of layered protocol stacks
- H04L69/32—Architecture of open systems interconnection [OSI] 7-layer type protocol stacks, e.g. the interfaces between the data link level and the physical level
- H04L69/322—Intralayer communication protocols among peer entities or protocol data unit [PDU] definitions
- H04L69/329—Intralayer communication protocols among peer entities or protocol data unit [PDU] definitions in the application layer [OSI layer 7]
Definitions
- FIG. 2 illustrates an exemplary system to utilize multi-step n-gram user navigation prediction model to predict a user's optimal information goal, wherein the goal is based on a globally optimized navigation path through a sequence of previously visited network content pieces.
- the multi-step n-gram navigation prediction module 310 predicts a user's optimal information goal or content piece 106 , wherein the goal is based on a globally optimized navigation path through a sequence of previously visited network content pieces. In this manner, it can be said that the module 310 predicts at least a subset of all of the possible locations or URLs that lie on that optimized path—the possible locations being determined from a user's prior WWW navigation history.
- a user's navigation path is represented as a sequence of visited content pieces 206 or Web pages w 1 , w 2 , ⁇ , w i , ⁇ , w L , where w i is the ith visited Web page in the sequence.
- the following Bayesian rule is applied to rewrite the probability estimation as equation 2.
- the computer 202 When used in a LAN networking environment, the computer 202 is connected to LAN 557 via network interface or adapter 566 . When used in a WAN networking environment, the computer typically includes a modem 558 or other means for establishing communications over the WAN 559 .
- the modem 558 which may be internal or external, may be connected to the system bus 516 via the user input interface 550 or other appropriate mechanism.
Abstract
The disclosed subject matter models or predicts a user's intention during network or WWW navigation. Specifically, a statistical multi-step n-gram probability model is used to predict a user's optimal information goal. The optimal information goal is based on a sequence of previously visited network content pieces and a globally optimized navigation path through the sequence.
Description
- This patent application is a continuation of U.S. patent application Ser. No. 10/142,625, filed on May 9, 2002, titled “User Intention Modeling for Web Navigation”, commonly owned hereby, and incorporated by reference.
- The following description relates to navigating and accessing information on the World Wide Web (Web).
- The Internet has been growing at an incredible speed. Although not all Internet servers are part of the World Wide Web (WWW), in 1999 it was reported that there were at least 9 million Web servers and 1.5 billion Web pages on the Internet. Some individuals estimated that the number of Web pages on the Internet would reach 7.7 billion by the end of the year 2001. Users surf the WWW by navigating along hyperlinks in electronic documents (e.g., a Web page) that connect various pieces of content. Unfortunately, user navigation of the rapidly growing database of information on the Internet to achieve a particular information goal can be substantially problematic.
- For instance, searching for specific information in such a huge “database” as the WWW is typically a time consuming hit or miss procedure, even with the help of one or more search engines. Additionally, even though high-speed broadband networks have been deployed in many places, the time delay of information transportation on the Internet is still a serious problem. If we could predict a Web surfer's information goals (e.g., what is being sought), we might be able to improve the user's Web navigation experience by recommending related Web pages and reducing the amount of time that the user perceives as having been required to receive desired content (e.g., this is typically achieved by pre-fetching and caching Web pages that are predicted to be visited by the user).
- A number of traditional user intention prediction techniques attempt to achieve such goals. Unfortunately, these conventional navigation intention prediction techniques do not typically adequately address the Web navigation problem. This is because such techniques typically only predict a single “next step” from the user's current Web location. Yet, Web surfers generally have more substantial information requirements including information goals that simply cannot be met by predicting only a single “next step” of navigation.
- The following disclosed subject matter addresses these and other problems of Web navigation.
- This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
- In view of the above, user intention modeling for Web navigation is described. In one aspect, a statistical multi-step n-gram probability model is used to predict a user's optimal information goal. The optimal information goal is based on a sequence of previously visited network content pieces and a globally optimized navigation path through the sequence.
- The same numbers are used throughout the drawings to reference like features and components.
-
FIG. 1 is a block diagram to compare aspects of a novel exemplary globally optimized navigation prediction to a conventional locally maximized navigation prediction. -
FIG. 2 illustrates an exemplary system to utilize multi-step n-gram user navigation prediction model to predict a user's optimal information goal, wherein the goal is based on a globally optimized navigation path through a sequence of previously visited network content pieces. -
FIG. 3 shows an exemplary computing device that utilizes a multi-step dynamic n-gram prediction model to predict a user's optimal information goal, wherein the goal is based on a globally optimized navigation path through a sequence of previously visited network content pieces. -
FIG. 4 shows anexemplary procedure 400 to utilize a multi-step dynamic n-gram prediction model to predict a user's optimal information goal, wherein the goal is based on a globally optimized navigation path through a sequence of previously visited network content pieces. -
FIG. 5 shows an example of a suitable computing environment on which an exemplary system and procedure to utilize multi-step n-gram user navigation prediction model to predict a user's optimal information goal based on probabilities and a “Web surfing history” may be implemented. - The following description sets forth exemplary subject matter to provide user intention modeling for Web navigation. The subject matter is described with specificity to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. Rather, the inventors have contemplated that the claimed subject matter might also be embodied in other ways, to include different elements or combinations of elements similar to the ones described in this document, in conjunction with other present or future technologies.
- Overview
- Systems to help users navigate the WWW or Web are known. For instance, traditional information retrieval methods (such as TF*IDF) have been used to help a user locate information by evaluating the similarity between two documents, and applying a reinforcement learning method to a Website's structure (e.g., hyperlinks on a page). Other conventional information retrieval methods pre-fetch documents based on the assumption that the previous page sequences that a user had visited represent a Markov chain with an applied time factor. Other systems utilize a Bayesian Network to predict a user's next query using only query and trim information, assuming that a next query only depended on the previous query and the time interval—independent on other factors. Yet, other conventional systems rely on determining the longest repeating page subsequence (a path) that all users have visited, or single step n-gram language models that consider a sequence of n Web pages as an n-gram, counting the times each n-gram appears to make a prediction based on the maximal count.
- The principal problem of these conventional techniques is that they typically stop at a partial or local maximal state (i.e., a single “next step” of Web navigation). Yet, users typically have more substantial information requirements or goals, which generally cannot be adequately represented by only a single next action of Web navigation from the user's current navigation state on the Web. This is because the user's ultimate information goal may involve many more actions or navigation steps to an ultimate information goal (e.g., a particular Web-based location or electronic document). The following disclosed subject matter addresses this significant problem by utilizing a multi-step n-gram prediction model to predict a globally optimized navigation path (e.g., set of Universal Resource Locations (URLs)) to the user's information intent.
- Globally Optimized Navigation Vs. Locally Maximized Navigation
-
FIG. 1 is a block diagram showing a comparison of exemplary globally optimized navigation prediction to conventional locally maximized navigation prediction. To illustrate this comparison, assume that the user is at location A and assume that the user's ultimate information goal is atlocation B. Lines 102 through 110 represent the possible navigation paths that the user could take from location A to the ultimate information goal, B. - The
path 102 from A to C represents a conventional one-step n-gram or “next step” prediction of navigation towards B. If we choose one-step prediction, then C is the best choice. But after one reaches reach point C, one will determine that goal B cannot be reached. So one-step prediction is not the global optimization method, but rather, only a local path. - There are other local paths that could also have been selected (e.g.,
paths 104 to E or 106 to D) based on conventional techniques (e.g., one-step n-gram predictions, or predictions based on Web page content, previous queries, mining longest repeating sequences of Web site visits, classifying a sequence of n Web pages as an n-gram to count the times each n-gram appears to make a user intention prediction based on a maximal count, and so on), but as will be described in greater detail below, merely selecting one of these locally maximized predictions from A to C, D, or even E does not take into consideration any probability that once at a particular location (e.g., C, D, or E), that the user will find it easy, natural, or even possible to continue on that particular predicted path to the ultimate information goal B. - In contrast to conventional systems, which do not take into account such probabilities, the disclosed multi-step n-gram prediction model is based on such probabilities. Specifically, a user's previous navigation history is used to calculate the various probabilities of navigation (e.g., from A) towards the user's information goal (e.g., B). To illustrate this, consider that next to each
path 102 through 110 is a “cost=value” distinction to represent a probability that the user will visit a next location A through E from a different location A through E given the user's previous navigation history. The higher the cost value, the lower the probability that the user will visit the next site from the different location. - For the reasons already discussed, we know that
path 102 from A to C is not a good choice to arrive at B, yet now we have additional information that tells us that the cost of visiting C from A has a cost of two (2), which represents a local optima, but not the global optima. This means that if we use one-step prediction, then C is the best answer. However, if we use multi-step prediction, C is not the best answer to reach the goal B for the reasons discussed above. Accordingly, A to C represents a locally optimal path to B, not a globally optimal path to B. - This is especially true since there is no direct history of user navigation from C to B. Looking at
paths paths - To appreciate the global aspect of the foregoing example, consider that had only the next step of navigation from A to B (e.g., from A to D or from A to E) been considered, conventional user predictions techniques (at best) would have selected either D or E—with one location not necessarily being preferable over the other. However, according to the probability information provided in this disclosure, it is evident that there should be a preference over which leg of the navigation to B to select. The cost of leg A to D (3) is less that the cost of A to E (3.5). Thus, the globally best navigation solution involves taking leg A to E—a path that had a global multi-step n-gram solution not been considered, would not have been apparent.
- Accordingly, and in contrast to conventional user navigation prediction techniques, the following disclosed subject matter provides a multi-step dynamic n-gram prediction model to predict an ultimate user information goal based on a globally optimized path through previous sites visited by the user.
- An Exemplary System
-
FIG. 2 illustrates anexemplary system 200 to utilize multi-step n-gram user navigation model to predict a users an optimal information goal based on probabilities and a Web surfing history. Insystem 200 one or more (x)clients 202 are coupled to aninformation content store 204. Theinformation content store 204 is any combination of local storage (e.g., local volatile or non-volatile memory), networked storage (e.g., a parallel connection, an organizational intranet, the Internet, and so on), or other communication configurations. - These communication configurations provide for electronic exchange of information using an appropriate protocol (e.g., TCP/IP, UDP, SOAP, etc.) between the
host device 202 and one or more information content sources or servers (not shown) that include multiple (v) pieces ofinformation content 206. This electronic exchange provides forclient 202 communication withinformation content store 204 to access (e.g., view, search, download, etc.) pieces ofinformation content 206. - The storage of
information content pieces 206 withininformation content store 204 can be arranged in any of a wide variety of manners and according to any of a wide variety of data formats. For example,information content pieces 206 may be stored on multiple servers hosting Web pages accessible via a network using an appropriate protocol such as Hypertext Transfer Protocol (HTTP). Web pages are documents that a user can view or otherwise render and which typically include links to one or more other pages that the user can access. Web pages are typically stored as one or more files at a remote location(s), being accessed by the user via a computer that is operatively coupled to anetwork 204. Web pages often include multiple pieces ofinformation content 206 such still images, frames of motion video, audio, multimedia, and so on. - A user of a
client 202 navigates theinformation content store 204 for pieces ofinformation content 206. As a user operates within the computing environment of aclient 202, theclient 202 monitors the user's navigation session activities and detects the user's current session and historical navigation paths to any number of pieces ofinformation content 206. Theclient 202 analyzes this globally optimized information within a statistical multi-step n-gram probability model to predict a user's optimal information goal. This multi-step n-gram prediction based on probabilities and navigation histories is dynamic, because it is performed in real-time while the user is surfing on the Web. Aspects of the statistical multi-step n-gram probability model are described in greater detail below in reference toprogram module 310 ofFIG. 3 . - A
Client Computer 202 -
FIG. 3 shows anexemplary computing device 202 that utilizes a multi-step n-gram user navigation model to predict a user's optimal information goal based on probabilities and the user's “Web surfing history. Thecomputer 202 is operational as any one of a number of different computing devices such as a personal computer, an image server computer, a thin client, a thick client, a hand-held or laptop device, a multiprocessor system, a microprocessor-based system, a set top box, programmable consumer electronics, a wireless phone, an application specific integrated circuit (ASIC), a network PC, minicomputer, mainframe computer, and so on. - The host computer includes a
processor 302 that is coupled to asystem memory 304. Thesystem memory 304 includes any combination of volatile and non-volatile computer-readable media for reading and writing. Volatile computer-readable media includes, for example, random access memory (RAM). Non-volatile computer-readable media includes, for example, read only memory (ROM), magnetic media such as a hard disk, an optical disk drive, a floppy diskette, a flash memory card, a CD-ROM, and so on. - The
processor 302 is configured to fetch and execute computer program instructions fromprogram modules 306; and configured to fetchdata 308 while executing theprogram modules 306. Program modules typically include routines, programs, objects, components, data structures, etc., for performing particular tasks or implementing particular abstract data types. For instance,program modules 306 include the multi-step n-gram usernavigation prediction module 310, abrowser module 312 such as a Web browser provided by Microsoft Corporation of Redmond, Wash., andother application modules 314. Program data includes aWeb log database 316 andother data 318. We now describe exemplary aspects of thesemodules 306 anddata 308 with respect to the operation of theclient 202. - The N-Gram Model
- The multi-step n-gram
navigation prediction module 310 predicts a user's optimal information goal orcontent piece 106, wherein the goal is based on a globally optimized navigation path through a sequence of previously visited network content pieces. In this manner, it can be said that themodule 310 predicts at least a subset of all of the possible locations or URLs that lie on that optimized path—the possible locations being determined from a user's prior WWW navigation history. - The substantially optimized navigation path to the user's information intention is global because it does consider other possible paths to the user's informational goal—although the
module 310 may determine that certain paths are not appropriate for inclusion in the globally optimized path. The actual number of steps or paths from one location to another that comprise the globally optimized path is not only based on analysis of user navigation history to generate path probabilities, but also based on an entropy evaluation, which is discussed in greater detail below. - A user's navigation path is represented as a sequence of visited
content pieces 206 or Web pages w1, w2,Λ, wi,Λ, wL, where wi is the ith visited Web page in the sequence. To estimate the probability of the navigation path, the following Bayesian rule is applied to rewrite the probability estimation asequation 2. - A statistical language model (SLM) is applied to estimate the probability Pr(wi|w1,Λ,wi−1) in equation (1).
- The n-gram Markov model assumes that each word in a sequence is only determined by its previous (n−1) words. We assume that each Web page sequence with length n is called an n-gram Web page sequence. The next hyperlink the user will select is assumed dependant only on the previous (n−1) hyperlink the user has just clicked. Hence, the n-gram probability is re-written in equation (2).
where, C(wi−n+1, . . . ,wi−2, wi−1, wi) denotes the count of the n-Gram (wi−n+1, . . . , wi−2,wi−1,wi) appearing in the training data. Cn is the total number of the n-grams. Cn−1 is the total number of the (n−1)-grams. C equals to Cn/Cn−1. Cn, Cn−1, and C are constants. From equation (1) and (2) we know that if C(wi−n+1, . . . , wi−2, wi−1) is known, the probability of Pr(wi|w1, w2, . . . , wi−1) is only influenced by the count C(wi−n+1,Λ, wi−1, wi).
The Global Optimization Model - The objective is to predict a user's real intention or information goal based on the user's previous information navigation behavior. However, unlike conventional techniques, which just predict one step ahead towards a user's predicted objective, the multi-step
navigation prediction module 310 predicts one or more steps ahead such that the ultimate Web page after several steps is the user's real intention. - For instance, suppose the user has already visited k−1 Web pages w1, w2.Λ, wi,Λ, wk−1, and the user's real intention is wL. The aim is to find out the path wk, wk+1,Λ, wL such that the probability of the overall navigation path Pr(w1,w2,Λ, wk−1,wk,Λ wL) is maximized. This is a global optimization method or technique. The conventional one-step n-gram model assumes that the local optimization at the next step (e.g., see the local maximized path A to C discussed above in reference to
FIG. 1 ) is the user's real intention. Thus it only chooses a wk to maximize the probability Pr(w1, w2, . . . , wk−1, wk) instead of the global probability—thus, it is likely to reach a local optimal point, especially when the data is not sufficient. This is similar to the “hill-climbing” algorithm and other searching algorithms often utilized in artificial intelligence (AI) algorithms. - For example, if a user likes to read news on a news Web-site but his/her favorite part of news is in always at a very deep level (e.g., the fourth level), each time the user must follow three hyperlinks to reach it. The user is not interested in all of the hyperlinks that are included in this path excepting the last one. In this case, the hyperlinks at the beginning of this path may have very small probabilities. Thus, if conventional one-step n-gram prediction is utilized, the first predicted hyperlink might take the user to a wrong way and the user may never arrive at the informational goal.
- To avoid reaching the local optimal of conventional one step prediction systems, the probability of the entire path is maximized. Specifically, the global optimization is shown in equation (3).
- Next, it is shown that the global optimization reflects the probability of the entire path, i.e. Pr(wk+1wk+2 . . . |w1 . . . wk−1wk). The proof is shown in equation (4).
- Hence, if L goes to infinite, the desired global optimization result is obtained. Furthermore, if the process of user navigation can be assumed to be a second-order Markov process, Pr(wi|w1 . . . wi−2wi−1)=Pr(wi|wi−2wi−1). Thus, equation (3) can be simplified to equation (5):
- Although equation (5) is a simplified model, its complexity is still very high. A dynamic multi-step prediction method reduces this complexity such that i=k+1 to i=k+t, where t is a parameter representing that how many steps should be predicted forward. The parameter t is determined dynamically by employing the perplexity to measure the efficacy of the t-steps prediction. Such perplexity is used in statistical speech recognition techniques. The perplexity reflects the entropy of the path. The perplexity of t-steps prediction is defined in equation (6)
- Finally the user's optimal information goal is expressed in the following equation:
An Exemplary Procedure -
FIG. 4 shows anexemplary procedure 400 that utilizes a multi-step n-gram user navigation model to predict a user's optimal information goal based on probabilities and the user's “Web surfing history. Atblock 402, theprocedure 400 records aWeb log 316 indicating a user's Web navigation history. Such information can be collected by thebrowser 312 to automatically monitor the user's actions, for example, for the following operations. -
- Visits: When a user types in a URL in a
browser 312 address box or choose a URL from a list (e.g., the favorite list), the browser will log the user name, start time, URL and elapse time into thelog 316. - Clicks: When a user click a hyperlink in a web-page, the
browser 312 will log the user name, start time, from URL, click URL, text or image over the click URL and elapse time into thelog 316. - Querys: When a user submits a query to a search engine or type in a query in a text box, the
browser 312 will log the user name, start time, query site, query words, returned results, clicked results, and elapse time into thelog 316. - Save As: When a user clicks a right mouse button and downloads a hyperlink or electronic image, the
browser 312 will log the user name, start time and save object into thelog 316.
- Visits: When a user types in a URL in a
- At
block 404, after generating a user log 316 (i.e., at block 402), a number of heuristic rules (e.g., based on any combination of URL, a hyperlink, a user name, a start time, text corresponding to a URL, a query, elapsed time, and/or an object name) are utilized to segment the surfing logs 316 into different sessions. Each session is represented by a list of URLs: u1,u2,Λ,un. - At
block 406, theprocedure 400 uses the statistical n-gram model to calculate the probability that the user may visit an URL from another URL given list of URLs (i.e., represented in the user log 316). Specifically:
Additionally, a smoothing and back-off method is applied to the calculation of Pr(ui|ui−2, ui−1) to deal with the data sparse problem. - At
block 408, theprocedure 400 dynamically predicts a globally optimized navigation path based on the determined probabilities (block 406) for the user to reach an ultimate information goal. Specifically, given navigation patterns u1,u2,Λ,uk, the most possible next browsing page uk+1 is determined, wherein uk+1 represents the best path to meet the user's real intention based on the following:
This search can be performed by a number of techniques such as a Viterbi Beam Search. (Note, the conventional solution is to determine a local optimization according to:
An Exemplary Computing Environment -
FIG. 5 shows an example of asuitable computing environment 500 on which an exemplary system and procedure using a multi-step dynamic n-gram prediction model to predict a user's optimal information goal, wherein the goal is based on a globally optimized navigation path through a sequence of previously visited network content pieces may be implemented.Exemplary computing environment 500 is only one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality of an exemplary system and procedure to cluster queries. Thecomputing environment 500 should not be interpreted as having any dependency or requirement relating to any one or combination of components illustrated in theexemplary computing environment 500. - An exemplary system and procedure to use a multi-step dynamic n-gram prediction model to predict a user's optimal information goal based on a globally optimized navigation path through a sequence of previously visited network content pieces may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types.
- An exemplary system and procedure to use a multi-step dynamic n-gram prediction model to predict a user's optimal information goal based on a globally optimized navigation path through a sequence of previously visited network content pieces may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
- As shown in
FIG. 5 , thecomputing environment 500 includes a general-purpose computing device in the form of acomputer 202 ofFIGS. 2 and 3 . The components ofcomputer 202 may include, for example, one or more processors orprocessing units 302, asystem memory 304, and abus 516 that couples various system components including thesystem memory 304 to theprocessor 302. -
Bus 516 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnects (PCI) bus also known as Mezzanine bus. -
Computer 202 typically includes a variety of computer-readable media. Such media may be any available media that is accessible by thecomputer 202, and it includes both volatile and non-volatile media, removable and non-removable media. For example, thesystem memory 304 includes computer readable media in the form of volatile memory, such as random access memory (RAM) 520, and/or non-volatile memory, such as read only memory (ROM) 518. A basic input/output system (BIOS) 522, containing the basic routines that help to transfer information between elements withincomputer 202, such as during start-up, is stored inROM 518.RAM 520 typically containsdata 308 and/orprogram modules 306 that are immediately accessible to and/or presently be operated on byprocessor 302. -
Computer 202 may further include other removable/non-removable, volatile/non-volatile computer storage media. By way of example only,FIG. 5 illustrates a hard disk drive 524 for reading from and writing to a non-removable, non-volatile magnetic media (not shown and typically called a “hard drive”), amagnetic disk drive 526 for reading from and writing to a removable, non-volatile magnetic disk 528 (e.g., a “floppy disk”), and anoptical disk drive 530 for reading from or writing to a removable, non-volatileoptical disk 532 such as a CD-ROM, DVD-ROM or other optical media. The hard disk drive 524,magnetic disk drive 526, andoptical disk drive 530 are each connected tobus 516 by one ormore interfaces 534. - The drives and their associated computer-readable media provide nonvolatile storage of computer readable instructions, data structures, program modules, and other data for
computer 202. Although the exemplary environment described herein employs a hard disk, a removablemagnetic disk 528 and a removableoptical disk 532, it should be appreciated by those skilled in the art that other types of computer readable media which can store data that is accessible by a computer, such as magnetic cassettes, flash memory cards, digital video disks, random access memories (RAMs), read only memories (ROM), and the like, may also be used in the exemplary operating environment. - A number of program modules may be stored on the hard disk,
magnetic disk 528,optical disk 532,ROM 518, orRAM 520, including, by way of example, and not limitation, anOS 538, one ormore application programs 306,other program modules 542, andprogram data 308. Eachsuch OS 538, one ormore application programs 306,other program modules 542, and program data 308 (or some combination thereof) may include an embodiment of an exemplary system and procedure to use a multi-step dynamic n-gram prediction model to predict a user's optimal information goal based on a globally optimized navigation path through a sequence of previously visited network content pieces. - A user may enter commands and information into
computer 202 through input devices such askeyboard 546 and pointing device 548 (such as a “mouse”). Other input devices (not shown) may include a microphone, joystick, game pad, satellite dish, serial port, scanner, or the like. These and other input devices are connected to theprocessing unit 302 through auser input interface 550 that is coupled tobus 516, but may be connected by other interface and bus structures, such as a parallel port, game port, or a universal serial bus (USB). - A monitor 552 (e.g., the monitor 330 of
FIG. 3 ) or other type of display device is also connected tobus 516 via an interface, such as avideo adapter 554. In addition to the monitor, personal computers typically include other peripheral output devices (not shown), such as speakers and printers, which may be connected through outputperipheral interface 555. -
Computer 202 may operate in a networked environment using logical connections to one or more remote computers, such as aremote computer 562. Logical connections shown inFIG. 5 are a local area network (LAN) 557 and a general wide area network (WAN) 559. Such networking environments are commonplace in offices, enterprise-wide computer networks, intranets, and the Internet.Remote computer 562 may include many or all of the elements and features described herein relative tocomputer 202. - When used in a LAN networking environment, the
computer 202 is connected toLAN 557 via network interface oradapter 566. When used in a WAN networking environment, the computer typically includes amodem 558 or other means for establishing communications over theWAN 559. Themodem 558, which may be internal or external, may be connected to thesystem bus 516 via theuser input interface 550 or other appropriate mechanism. - Depicted in
FIG. 5 is a specific implementation of a WAN via the Internet.Computer 202 typically includes amodem 558 or other means for establishing communications over theInternet 560.Modem 558, which may be internal or external, is connected tobus 516 viainterface 550. - In a networked environment, program modules depicted relative to the
personal computer 202, or portions thereof, may be stored in a remote memory storage device. By way of example, and not limitation,FIG. 5 illustratesremote application programs 569 as residing on a memory device ofremote computer 562. The network connections shown and described are exemplary and other means of establishing a communications link between the computers may be used. - Computer Readable Media
- An implementation of exemplary subject matter to system and procedure using a multi-step dynamic n-gram prediction model to predict a user's optimal information goal based on a globally optimized navigation path through a sequence of previously visited network content pieces may be stored on or transmitted across some form of computer-readable media. Computer-readable media can be any available media that can be accessed by a computer. By way of example, and not limitation, computer readable media may comprise “computer storage media” and “communications media.”
- “Computer storage media” include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer.
- “Communication media” typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as carrier wave or other transport mechanism. Communication media also includes any information delivery media.
- The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also included within the scope of computer readable media.
- The disclosed subject matter provides a novel multi-step n-gram user navigation prediction model to predict a user's optimal information goal based on a globally optimized navigation path through a sequence of previously visited network content pieces. Although the described subject matter has been described in language specific to structural features and methodological operations, it is understood that the arrangements and procedures as defined the appended claims are not necessarily limited to the specific features or operations described. Rather, the specific features and operations disclosed are preferred forms of implementing the claimed subject matter.
Claims (20)
1. A computer-implemented method for modeling a user intention during network navigation, the method comprising:
predicting, based on a statistical multi-step n-gram probability model, an optimal information goal of the user; and
wherein the optimal information goal is based on a sequence of previously visited network content pieces and a globally optimized navigation path through the sequence.
2. The method of claim 1 , wherein a content piece of the sequence comprises a Web page.
3. The method of claim 1 , wherein predicting the globally optimized navigation path is dynamically performed responsive to user Web navigation.
4. The method of claim 1 , wherein predicting the optimal information goal further comprises:
recording a history of user action, the history comprising information corresponding to user navigation to a plurality of networked content pieces, the information further indicating at least the sequence of previously visited network content pieces;
for at least a portion of the sequence data, calculating respective probabilities that a user would visit a particular content piece n in the sequence from a content piece n−1 in the sequence; and
wherein predicting the optimal information goal is based on the respective probabilities.
5. The method of claim 4 , wherein the history further comprises a URL, a hyperlink, a user name, a start time, text corresponding to a URL, a query, elapsed time, or an object name.
6. The method of claim 4 , wherein calculating respective probabilities that the user would visit a particular content piece n in the sequence from a content piece n−1 in the sequence is performed based on the following:
wherein, Pr represents the probability;
wherein user navigation to the plurality of networked content pieces is represented as w1, w2,Λ, wi,Λ, wL, where wi is the ith visited content piece in the sequence; and
wherein C(wi−n+1, . . . ,wi−2,wi−1,wi) denotes the count of an n-Gram (wi−n+1, . . . , wi−2,wi−1,wi) appearing in training data, Cn is a total number of the n-grams, Cn−1 is a total number of the (n−1)-grams, C equals to Cn/Cn−1, Cn, Cn−, and C are constants.
7. The method of claim 7 , wherein the globally optimized navigation path is based on the following:
wherein k represents a number of networked content pieces that the user has already visited.
8. The method of claim 7 , wherein the globally optimized navigation path is based on the following:
wherein k represents a number of networked content pieces that the user has already visited; and
wherein t indicates how many steps are predicted.
9. The method of claim 9 further comprising dynamically determining how many steps to the optimal information goal are to be predicted by employing a perplexity that reflects the entropy of the globally optimized navigation path.
10. The method of claim 9 , wherein the optimal information goal is determined according to the following:
11. A computer-readable medium for modeling a user intention during network navigation, the computer-readable medium comprising computer-program instructions executable by a processor for:
predicting, based on a statistical multi-step n-gram probability model, an optimal information goal of the user; and
wherein the optimal information goal is based on a sequence of previously visited network content pieces and a globally optimized navigation path through the sequence.
12. The computer-readable medium of claim 12 , wherein predicting the globally optimized navigation path is dynamically performed responsive to user Web navigation.
13. The computer-readable medium of claim 12 , wherein the instructions for predicting the optimal information goal further comprise instructions for:
recording a history of user action, the history comprising information corresponding to user navigation to a plurality of networked content pieces, the information further indicating at least the sequence of previously visited network content pieces;
for at least a portion of the sequence data, calculating respective probabilities that a user would visit a particular content piece n in the sequence from a content piece n−1 in the sequence; and
wherein predicting the optimal information goal is based on the respective probabilities.
14. The computer-readable medium of claim 15 , wherein calculating respective probabilities that the user would visit a particular content piece n in the sequence from a content piece n−1 in the sequence is performed based on the following:
wherein, Pr represents the probability;
wherein user navigation to the plurality of networked content pieces is represented as w1,w2,Λ,wi,Λ,wL, where wi is the ith visited content piece in the sequence; and
wherein C(wi−n+1, . . . ,wi−2,wi−1,wi) denotes the count of an n-Gram (wi−n+1, . . . , wi−2) wi−1,wi) appearing in training data, Cn is a total number of the n-grams, Cn−1 is a total number of the (n−1)-grams, C equals to Cn/Cn−1, Cn, Cn−, and C are constants.
15. The computer-readable medium of claim 17 , wherein the globally optimized navigation path is based on the following:
wherein k represents a number of networked content pieces that the user has already visited.
16. The computer-readable medium of claim 17 , wherein the globally optimized navigation path is based on the following:
wherein k represents a number of networked content pieces that the user has already visited; and
wherein t indicates how many steps are predicted.
17. The computer-readable medium of claim 20 further comprising instructions for dynamically determining how many steps to the optimal information goal are to be predicted by employing a perplexity that reflects the entropy of the globally optimized navigation path.
18. The computer-readable medium of claim 20 , wherein the optimal information goal is determined according to the following:
19. A computing device for modeling a user intention during network navigation, the computing device comprising:
a processor; and
a memory coupled to the processor, the memory comprising computer-program instructions that are fetched and executed by the processor for:
predicting, based on a statistical multi-step n-gram probability model, an optimal information goal of the user; and
wherein the optimal information goal is based on a sequence of previously visited network content pieces and a globally optimized navigation path through the sequence.
20. The computing device of claim 23, wherein the instructions for predicting the optimal information goal further comprise instructions for:
recording a history of user action, the history comprising information corresponding to user navigation to a plurality of networked content pieces, the information further indicating at least the sequence of previously visited network content pieces;
for at least a portion of the sequence data, calculating respective probabilities that a user would visit a particular content piece n in the sequence from a content piece n−1 in the sequence; and
wherein predicting the optimal information goal is based on the respective probabilities.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/219,932 US20060010229A1 (en) | 2002-05-09 | 2005-09-06 | User intention modeling for web navigation |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/142,625 US6993586B2 (en) | 2002-05-09 | 2002-05-09 | User intention modeling for web navigation |
US11/219,932 US20060010229A1 (en) | 2002-05-09 | 2005-09-06 | User intention modeling for web navigation |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/142,625 Continuation US6993586B2 (en) | 2002-05-09 | 2002-05-09 | User intention modeling for web navigation |
Publications (1)
Publication Number | Publication Date |
---|---|
US20060010229A1 true US20060010229A1 (en) | 2006-01-12 |
Family
ID=29399950
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/142,625 Expired - Lifetime US6993586B2 (en) | 2002-05-09 | 2002-05-09 | User intention modeling for web navigation |
US11/219,932 Abandoned US20060010229A1 (en) | 2002-05-09 | 2005-09-06 | User intention modeling for web navigation |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/142,625 Expired - Lifetime US6993586B2 (en) | 2002-05-09 | 2002-05-09 | User intention modeling for web navigation |
Country Status (1)
Country | Link |
---|---|
US (2) | US6993586B2 (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050003859A1 (en) * | 2003-03-28 | 2005-01-06 | Brother Kogyo Kabushiki Kaisha | Data processing system |
US20080294743A1 (en) * | 2007-05-24 | 2008-11-27 | Fuji Xerox Co., Ltd. | Information processing device, computer readable recording medium, and information processing method |
US20090046102A1 (en) * | 2007-08-16 | 2009-02-19 | Hamilton Ii Rick Allen | Method and apparatus for spawning projected avatars in a virtual universe |
US20090046094A1 (en) * | 2007-08-16 | 2009-02-19 | Hamilton Ii Rick Allen | Method and apparatus for predicting avatar movement in a virtual universe |
US20090046109A1 (en) * | 2007-08-16 | 2009-02-19 | Hamilton Ii Rick Allen | Method and apparatus for moving an avatar in a virtual universe |
US20090288002A1 (en) * | 2008-05-15 | 2009-11-19 | Hamilton Ii Rick A | Virtual universe teleportation suggestion service |
US20100114654A1 (en) * | 2008-10-31 | 2010-05-06 | Hewlett-Packard Development Company, L.P. | Learning user purchase intent from user-centric data |
US20100242044A1 (en) * | 2009-03-18 | 2010-09-23 | Microsoft Corporation | Adaptable software resource managers based on intentions |
US20110131536A1 (en) * | 2009-12-02 | 2011-06-02 | Xerox Corporation | Generating and ranking information units including documents associated with document environments |
US20120240019A1 (en) * | 2011-03-17 | 2012-09-20 | Ebay Inc. | Method and system for tracking web link usage |
WO2013126244A1 (en) | 2012-02-23 | 2013-08-29 | Microsoft Corporation | Content pre-fetching for computing devices |
US20150221037A1 (en) * | 2014-02-05 | 2015-08-06 | Wipro Limited | System and method for allocting investment fund for an application |
US9239737B2 (en) | 2013-11-15 | 2016-01-19 | Sap Se | Concise resource addressing |
US9692633B2 (en) | 2013-11-15 | 2017-06-27 | Sap Se | Role-based resource navigation |
US10122646B2 (en) * | 2015-11-06 | 2018-11-06 | Oath Inc. | Resource placement via a web page |
US10282395B2 (en) | 2013-11-15 | 2019-05-07 | Sap Se | Handling timer-based resizing events based on activity detection |
US10284454B2 (en) | 2007-11-30 | 2019-05-07 | Activision Publishing, Inc. | Automatic increasing of capacity of a virtual space in a virtual world |
CN109753601A (en) * | 2018-11-28 | 2019-05-14 | 北京奇艺世纪科技有限公司 | Recommendation information clicking rate determines method, apparatus and electronic equipment |
US10627983B2 (en) | 2007-12-24 | 2020-04-21 | Activision Publishing, Inc. | Generating data for managing encounters in a virtual world environment |
US11972086B2 (en) | 2019-03-18 | 2024-04-30 | Activision Publishing, Inc. | Automatic increasing of capacity of a virtual space in a virtual world |
Families Citing this family (88)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8352400B2 (en) | 1991-12-23 | 2013-01-08 | Hoffberg Steven M | Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore |
US7904187B2 (en) | 1999-02-01 | 2011-03-08 | Hoffberg Steven M | Internet appliance system and method |
US6993586B2 (en) * | 2002-05-09 | 2006-01-31 | Microsoft Corporation | User intention modeling for web navigation |
US7548982B2 (en) * | 2002-10-31 | 2009-06-16 | Hewlett-Packard Development Company, L.P. | Predictive branching and caching method and apparatus for applications |
US7043475B2 (en) * | 2002-12-19 | 2006-05-09 | Xerox Corporation | Systems and methods for clustering user sessions using multi-modal information including proximal cue information |
US7346839B2 (en) * | 2003-09-30 | 2008-03-18 | Google Inc. | Information retrieval based on historical data |
US7978716B2 (en) | 2003-11-24 | 2011-07-12 | Citrix Systems, Inc. | Systems and methods for providing a VPN solution |
US7558834B2 (en) | 2003-12-29 | 2009-07-07 | Ebay Inc. | Method and system to process issue data pertaining to a system |
US7249126B1 (en) * | 2003-12-30 | 2007-07-24 | Shopping.Com | Systems and methods for dynamically updating relevance of a selected item |
US7624160B2 (en) * | 2004-05-04 | 2009-11-24 | International Business Machines Corporation | Methods, systems, and computer program products for client side prefetching and caching of portlets |
US8495305B2 (en) | 2004-06-30 | 2013-07-23 | Citrix Systems, Inc. | Method and device for performing caching of dynamically generated objects in a data communication network |
US7757074B2 (en) | 2004-06-30 | 2010-07-13 | Citrix Application Networking, Llc | System and method for establishing a virtual private network |
US8739274B2 (en) | 2004-06-30 | 2014-05-27 | Citrix Systems, Inc. | Method and device for performing integrated caching in a data communication network |
ATE535078T1 (en) | 2004-07-23 | 2011-12-15 | Citrix Systems Inc | METHOD AND SYSTEM FOR SECURING REMOTE ACCESS TO PRIVATE NETWORKS |
US7724657B2 (en) | 2004-07-23 | 2010-05-25 | Citrix Systems, Inc. | Systems and methods for communicating a lossy protocol via a lossless protocol |
US20060122976A1 (en) | 2004-12-03 | 2006-06-08 | Shumeet Baluja | Predictive information retrieval |
US8549149B2 (en) | 2004-12-30 | 2013-10-01 | Citrix Systems, Inc. | Systems and methods for providing client-side accelerated access to remote applications via TCP multiplexing |
US8700695B2 (en) | 2004-12-30 | 2014-04-15 | Citrix Systems, Inc. | Systems and methods for providing client-side accelerated access to remote applications via TCP pooling |
US8706877B2 (en) | 2004-12-30 | 2014-04-22 | Citrix Systems, Inc. | Systems and methods for providing client-side dynamic redirection to bypass an intermediary |
US8954595B2 (en) | 2004-12-30 | 2015-02-10 | Citrix Systems, Inc. | Systems and methods for providing client-side accelerated access to remote applications via TCP buffering |
US7810089B2 (en) | 2004-12-30 | 2010-10-05 | Citrix Systems, Inc. | Systems and methods for automatic installation and execution of a client-side acceleration program |
US8255456B2 (en) | 2005-12-30 | 2012-08-28 | Citrix Systems, Inc. | System and method for performing flash caching of dynamically generated objects in a data communication network |
CN102123178B (en) | 2005-01-24 | 2014-04-09 | 茨特里克斯系统公司 | Systems and methods for performing caching of dynamically generated objects in network |
US8001456B2 (en) * | 2005-02-28 | 2011-08-16 | International Business Machines Corporation | Methods for maintaining separation between markup and data at a client |
US8230072B1 (en) * | 2005-03-18 | 2012-07-24 | Oracle America, Inc. | Linking to popular navigation paths in a network |
US7454386B2 (en) * | 2005-04-15 | 2008-11-18 | Siemens Corporate Research, Inc. | Learning management server using Bayesian methods for adaptive hypermedia |
US7630976B2 (en) * | 2005-05-10 | 2009-12-08 | Microsoft Corporation | Method and system for adapting search results to personal information needs |
US7860895B1 (en) * | 2005-08-23 | 2010-12-28 | Amazon Technologies, Inc. | Method and system for determining interest spaces among online content sources |
US8719255B1 (en) * | 2005-08-23 | 2014-05-06 | Amazon Technologies, Inc. | Method and system for determining interest levels of online content based on rates of change of content access |
US7747618B2 (en) * | 2005-09-08 | 2010-06-29 | Microsoft Corporation | Augmenting user, query, and document triplets using singular value decomposition |
WO2007038713A2 (en) * | 2005-09-28 | 2007-04-05 | Epacris Inc. | Search engine determining results based on probabilistic scoring of relevance |
US7921184B2 (en) | 2005-12-30 | 2011-04-05 | Citrix Systems, Inc. | System and method for performing flash crowd caching of dynamically generated objects in a data communication network |
US8301839B2 (en) | 2005-12-30 | 2012-10-30 | Citrix Systems, Inc. | System and method for performing granular invalidation of cached dynamically generated objects in a data communication network |
US7659905B2 (en) | 2006-02-22 | 2010-02-09 | Ebay Inc. | Method and system to pre-fetch data in a network |
US8150943B2 (en) * | 2006-03-10 | 2012-04-03 | Staples The Office Superstore, Llc | Methods and apparatus for dynamically generating web pages |
US7752152B2 (en) * | 2006-03-17 | 2010-07-06 | Microsoft Corporation | Using predictive user models for language modeling on a personal device with user behavior models based on statistical modeling |
US8032375B2 (en) * | 2006-03-17 | 2011-10-04 | Microsoft Corporation | Using generic predictive models for slot values in language modeling |
US7689420B2 (en) * | 2006-04-06 | 2010-03-30 | Microsoft Corporation | Personalizing a context-free grammar using a dictation language model |
US7660815B1 (en) * | 2006-06-30 | 2010-02-09 | Amazon Technologies, Inc. | Method and system for occurrence frequency-based scaling of navigation path weights among online content sources |
US9037581B1 (en) * | 2006-09-29 | 2015-05-19 | Google Inc. | Personalized search result ranking |
EP1968243A1 (en) * | 2007-03-07 | 2008-09-10 | British Telecommunications Public Limited Company | Method of transmitting data to a mobile device |
US7860946B1 (en) * | 2007-05-01 | 2010-12-28 | Disintegrated Communication Systems, Llc | Systems, methods, and computer-readable media for searching and concomitantly interacting with multiple information content providers, other individuals, relevant communities of individuals, and information provided over a network |
US8019742B1 (en) | 2007-05-31 | 2011-09-13 | Google Inc. | Identifying related queries |
US9060245B2 (en) * | 2007-10-30 | 2015-06-16 | Google Technology Holdings LLC | Methods and apparatus for collecting and using information regarding location object-based actions |
EP2293192B1 (en) | 2008-01-27 | 2021-03-31 | Citrix Systems, Inc. | Methods and systems for remoting three dimensional graphics |
US7529808B1 (en) * | 2008-03-05 | 2009-05-05 | International Business Machines Corporation | Systems and methods of automatic navigation on the world wide web |
US10068251B1 (en) * | 2008-06-26 | 2018-09-04 | Amazon Technologies, Inc. | System and method for generating predictions based on wireless commerce transactions |
US9183323B1 (en) * | 2008-06-27 | 2015-11-10 | Google Inc. | Suggesting alternative query phrases in query results |
US20110022945A1 (en) * | 2009-07-24 | 2011-01-27 | Nokia Corporation | Method and apparatus of browsing modeling |
US9361631B2 (en) | 2010-01-06 | 2016-06-07 | Ghostery, Inc. | Managing and monitoring digital advertising |
US8849785B1 (en) | 2010-01-15 | 2014-09-30 | Google Inc. | Search query reformulation using result term occurrence count |
US8650172B2 (en) * | 2010-03-01 | 2014-02-11 | Microsoft Corporation | Searchable web site discovery and recommendation |
US8972397B2 (en) * | 2010-03-11 | 2015-03-03 | Microsoft Corporation | Auto-detection of historical search context |
US8515889B2 (en) * | 2010-03-23 | 2013-08-20 | Ebay Inc. | Systems and methods for trend aware self-correcting entity relationship extraction |
EP2558969A4 (en) * | 2010-04-13 | 2013-10-09 | Univ California | Methods of using generalized order differentiation and integration of input variables to forecast trends |
CN102279856B (en) * | 2010-06-09 | 2013-10-02 | 阿里巴巴集团控股有限公司 | Method and system for realizing website navigation |
US10026058B2 (en) * | 2010-10-29 | 2018-07-17 | Microsoft Technology Licensing, Llc | Enterprise resource planning oriented context-aware environment |
US9443028B2 (en) * | 2010-12-11 | 2016-09-13 | Microsoft Technology Licensing, Llc | Relevance estimation using a search satisfaction metric |
US9589056B2 (en) * | 2011-04-05 | 2017-03-07 | Microsoft Technology Licensing Llc | User information needs based data selection |
US8732569B2 (en) | 2011-05-04 | 2014-05-20 | Google Inc. | Predicting user navigation events |
US9769285B2 (en) | 2011-06-14 | 2017-09-19 | Google Inc. | Access to network content |
US8788711B2 (en) | 2011-06-14 | 2014-07-22 | Google Inc. | Redacting content and inserting hypertext transfer protocol (HTTP) error codes in place thereof |
US8745212B2 (en) | 2011-07-01 | 2014-06-03 | Google Inc. | Access to network content |
US8650139B2 (en) | 2011-07-01 | 2014-02-11 | Google Inc. | Predicting user navigation events |
US8744988B1 (en) | 2011-07-15 | 2014-06-03 | Google Inc. | Predicting user navigation events in an internet browser |
US8645300B1 (en) * | 2011-07-20 | 2014-02-04 | Usability Sciences Corporation | System and method for intent data processing |
US8655819B1 (en) | 2011-09-15 | 2014-02-18 | Google Inc. | Predicting user navigation events based on chronological history data |
US8600921B2 (en) * | 2011-09-15 | 2013-12-03 | Google Inc. | Predicting user navigation events in a browser using directed graphs |
US9104664B1 (en) | 2011-10-07 | 2015-08-11 | Google Inc. | Access to search results |
US9584579B2 (en) | 2011-12-01 | 2017-02-28 | Google Inc. | Method and system for providing page visibility information |
CN103218719B (en) | 2012-01-19 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of e-commerce website air navigation aid and system |
US8793235B2 (en) | 2012-01-19 | 2014-07-29 | Google Inc. | System and method for improving access to search results |
US8954524B1 (en) * | 2012-03-14 | 2015-02-10 | Google Inc. | Access to network content |
US9946792B2 (en) | 2012-05-15 | 2018-04-17 | Google Llc | Access to network content |
US8887239B1 (en) | 2012-08-08 | 2014-11-11 | Google Inc. | Access to network content |
US10291492B2 (en) * | 2012-08-15 | 2019-05-14 | Evidon, Inc. | Systems and methods for discovering sources of online content |
US10261938B1 (en) | 2012-08-31 | 2019-04-16 | Amazon Technologies, Inc. | Content preloading using predictive models |
US9141722B2 (en) | 2012-10-02 | 2015-09-22 | Google Inc. | Access to network content |
US9420052B2 (en) | 2012-10-31 | 2016-08-16 | International Business Machines Corporation | Web navigation using web navigation pattern histories |
IN2013MU04124A (en) | 2013-12-30 | 2015-08-07 | Tata Consultancy Services Ltd | |
RU2637882C2 (en) | 2015-03-31 | 2017-12-07 | Общество С Ограниченной Ответственностью "Яндекс" | Method for managing web-resource displays in browser window, method of placing tabs in stack in browser window, electronic device and server |
AU2016249910A1 (en) | 2015-04-11 | 2017-10-26 | Evidon, Inc. | Methods, apparatus, and systems for providing notice of digital tracking technologies in mobile apps on mobile devices, and for recording user consent in connection with same |
US20170212651A1 (en) * | 2016-01-27 | 2017-07-27 | Amadeus S.A.S. | Short cut links in a graphical user interface |
US11392664B1 (en) | 2017-08-29 | 2022-07-19 | Massachusetts Mutual Life Insurance Company | Dynamic web application based on events |
US10796303B2 (en) * | 2017-09-06 | 2020-10-06 | Visa International Service Association | System, method, and computer program product for predicting payment transactions using a machine learning technique based on merchant categories and transaction time data |
US11687802B2 (en) | 2019-11-13 | 2023-06-27 | Walmart Apollo, Llc | Systems and methods for proactively predicting user intents in personal agents |
US11321104B2 (en) * | 2020-03-30 | 2022-05-03 | Bank Of America Corporation | Cognitive automation platform for customized interface generation |
US20220318197A1 (en) * | 2021-03-31 | 2022-10-06 | Atlassian Pty Ltd. | Predictive document recommendation in document collaboration server systems using temporally correlated document viewing sequence sets |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5615286A (en) * | 1995-05-05 | 1997-03-25 | Bell Communications Research, Inc. | Method for determining a most likely sequence of states |
US5774123A (en) * | 1995-12-15 | 1998-06-30 | Ncr Corporation | Apparatus and method for enhancing navigation of an on-line multiple-resource information service |
US5930753A (en) * | 1997-03-20 | 1999-07-27 | At&T Corp | Combining frequency warping and spectral shaping in HMM based speech recognition |
US6014638A (en) * | 1996-05-29 | 2000-01-11 | America Online, Inc. | System for customizing computer displays in accordance with user preferences |
US20010021233A1 (en) * | 2000-03-01 | 2001-09-13 | Jin Gary Q. | Soft-decision decoding of convolutionally encoded codeword |
US6549896B1 (en) * | 2000-04-07 | 2003-04-15 | Nec Usa, Inc. | System and method employing random walks for mining web page associations and usage to optimize user-oriented web page refresh and pre-fetch scheduling |
US6597314B1 (en) * | 1999-12-07 | 2003-07-22 | Microsoft Corporation | Method and apparatus for providing help and settings control to users of an electronic book |
US6700937B1 (en) * | 2000-01-05 | 2004-03-02 | At&T Corp. | Iterative decoding |
US20040128618A1 (en) * | 2000-04-10 | 2004-07-01 | Anindya Datta | Dynamic page generation acceleration using component-level caching |
US6792605B1 (en) * | 1999-06-10 | 2004-09-14 | Bow Street Software, Inc. | Method and apparatus for providing web based services using an XML Runtime model to store state session data |
US20040236736A1 (en) * | 1999-12-10 | 2004-11-25 | Whitman Ronald M. | Selection of search phrases to suggest to users in view of actions performed by prior users |
US20050071332A1 (en) * | 1998-07-15 | 2005-03-31 | Ortega Ruben Ernesto | Search query processing to identify related search terms and to correct misspellings of search terms |
US6993586B2 (en) * | 2002-05-09 | 2006-01-31 | Microsoft Corporation | User intention modeling for web navigation |
US20060167784A1 (en) * | 2004-09-10 | 2006-07-27 | Hoffberg Steven M | Game theoretic prioritization scheme for mobile ad hoc networks permitting hierarchal deference |
-
2002
- 2002-05-09 US US10/142,625 patent/US6993586B2/en not_active Expired - Lifetime
-
2005
- 2005-09-06 US US11/219,932 patent/US20060010229A1/en not_active Abandoned
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5615286A (en) * | 1995-05-05 | 1997-03-25 | Bell Communications Research, Inc. | Method for determining a most likely sequence of states |
US5774123A (en) * | 1995-12-15 | 1998-06-30 | Ncr Corporation | Apparatus and method for enhancing navigation of an on-line multiple-resource information service |
US6014638A (en) * | 1996-05-29 | 2000-01-11 | America Online, Inc. | System for customizing computer displays in accordance with user preferences |
US5930753A (en) * | 1997-03-20 | 1999-07-27 | At&T Corp | Combining frequency warping and spectral shaping in HMM based speech recognition |
US20050071332A1 (en) * | 1998-07-15 | 2005-03-31 | Ortega Ruben Ernesto | Search query processing to identify related search terms and to correct misspellings of search terms |
US6792605B1 (en) * | 1999-06-10 | 2004-09-14 | Bow Street Software, Inc. | Method and apparatus for providing web based services using an XML Runtime model to store state session data |
US6597314B1 (en) * | 1999-12-07 | 2003-07-22 | Microsoft Corporation | Method and apparatus for providing help and settings control to users of an electronic book |
US20040236736A1 (en) * | 1999-12-10 | 2004-11-25 | Whitman Ronald M. | Selection of search phrases to suggest to users in view of actions performed by prior users |
US6700937B1 (en) * | 2000-01-05 | 2004-03-02 | At&T Corp. | Iterative decoding |
US20010021233A1 (en) * | 2000-03-01 | 2001-09-13 | Jin Gary Q. | Soft-decision decoding of convolutionally encoded codeword |
US6549896B1 (en) * | 2000-04-07 | 2003-04-15 | Nec Usa, Inc. | System and method employing random walks for mining web page associations and usage to optimize user-oriented web page refresh and pre-fetch scheduling |
US20040128618A1 (en) * | 2000-04-10 | 2004-07-01 | Anindya Datta | Dynamic page generation acceleration using component-level caching |
US6993586B2 (en) * | 2002-05-09 | 2006-01-31 | Microsoft Corporation | User intention modeling for web navigation |
US20060167784A1 (en) * | 2004-09-10 | 2006-07-27 | Hoffberg Steven M | Game theoretic prioritization scheme for mobile ad hoc networks permitting hierarchal deference |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050003859A1 (en) * | 2003-03-28 | 2005-01-06 | Brother Kogyo Kabushiki Kaisha | Data processing system |
US7336972B2 (en) * | 2003-03-28 | 2008-02-26 | Brother Kogyo Kabushiki Kaisha | Data processing system for a multi-function device |
US20080294743A1 (en) * | 2007-05-24 | 2008-11-27 | Fuji Xerox Co., Ltd. | Information processing device, computer readable recording medium, and information processing method |
US8334871B2 (en) | 2007-08-16 | 2012-12-18 | International Business Machine Corporation | Spawning projected avatars in a virtual universe |
US20090046094A1 (en) * | 2007-08-16 | 2009-02-19 | Hamilton Ii Rick Allen | Method and apparatus for predicting avatar movement in a virtual universe |
US20090046109A1 (en) * | 2007-08-16 | 2009-02-19 | Hamilton Ii Rick Allen | Method and apparatus for moving an avatar in a virtual universe |
US7990387B2 (en) | 2007-08-16 | 2011-08-02 | International Business Machines Corporation | Method and apparatus for spawning projected avatars in a virtual universe |
US20090046102A1 (en) * | 2007-08-16 | 2009-02-19 | Hamilton Ii Rick Allen | Method and apparatus for spawning projected avatars in a virtual universe |
US8692835B2 (en) | 2007-08-16 | 2014-04-08 | Activision Publishing, Inc. | Spawning projected avatars in a virtual universe |
US8345049B2 (en) * | 2007-08-16 | 2013-01-01 | International Business Machine Corporation | Method and apparatus for predicting avatar movement in a virtual universe |
US9003304B2 (en) | 2007-08-16 | 2015-04-07 | International Business Machines Corporation | Method and apparatus for moving an avatar in a virtual universe |
US10284454B2 (en) | 2007-11-30 | 2019-05-07 | Activision Publishing, Inc. | Automatic increasing of capacity of a virtual space in a virtual world |
US10627983B2 (en) | 2007-12-24 | 2020-04-21 | Activision Publishing, Inc. | Generating data for managing encounters in a virtual world environment |
US20090288002A1 (en) * | 2008-05-15 | 2009-11-19 | Hamilton Ii Rick A | Virtual universe teleportation suggestion service |
US8671349B2 (en) | 2008-05-15 | 2014-03-11 | International Business Machines Corporation | Virtual universe teleportation suggestion service |
US20100114654A1 (en) * | 2008-10-31 | 2010-05-06 | Hewlett-Packard Development Company, L.P. | Learning user purchase intent from user-centric data |
US9864637B2 (en) | 2009-03-18 | 2018-01-09 | Microsoft Technology Licensing, Llc | Adaptable software resource managers based on intentions |
US20100242044A1 (en) * | 2009-03-18 | 2010-09-23 | Microsoft Corporation | Adaptable software resource managers based on intentions |
US20110131536A1 (en) * | 2009-12-02 | 2011-06-02 | Xerox Corporation | Generating and ranking information units including documents associated with document environments |
US20180367625A1 (en) * | 2011-03-17 | 2018-12-20 | Ebay Inc. | Method and System for Tracking Web Link Usage |
US10911554B2 (en) * | 2011-03-17 | 2021-02-02 | Ebay Inc. | Method and system for tracking web link usage |
US20120240019A1 (en) * | 2011-03-17 | 2012-09-20 | Ebay Inc. | Method and system for tracking web link usage |
US10091313B2 (en) | 2011-03-17 | 2018-10-02 | Ebay Inc. | Method and system for tracking web link usage |
WO2013126244A1 (en) | 2012-02-23 | 2013-08-29 | Microsoft Corporation | Content pre-fetching for computing devices |
US9692633B2 (en) | 2013-11-15 | 2017-06-27 | Sap Se | Role-based resource navigation |
US10282395B2 (en) | 2013-11-15 | 2019-05-07 | Sap Se | Handling timer-based resizing events based on activity detection |
US9239737B2 (en) | 2013-11-15 | 2016-01-19 | Sap Se | Concise resource addressing |
US20150221037A1 (en) * | 2014-02-05 | 2015-08-06 | Wipro Limited | System and method for allocting investment fund for an application |
US10122646B2 (en) * | 2015-11-06 | 2018-11-06 | Oath Inc. | Resource placement via a web page |
CN109753601A (en) * | 2018-11-28 | 2019-05-14 | 北京奇艺世纪科技有限公司 | Recommendation information clicking rate determines method, apparatus and electronic equipment |
US11972086B2 (en) | 2019-03-18 | 2024-04-30 | Activision Publishing, Inc. | Automatic increasing of capacity of a virtual space in a virtual world |
Also Published As
Publication number | Publication date |
---|---|
US20030212760A1 (en) | 2003-11-13 |
US6993586B2 (en) | 2006-01-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6993586B2 (en) | User intention modeling for web navigation | |
US7774339B2 (en) | Using search trails to provide enhanced search interaction | |
US7493312B2 (en) | Media agent | |
US7809715B2 (en) | Abbreviation handling in web search | |
US7599918B2 (en) | Dynamic search with implicit user intention mining | |
US8099417B2 (en) | Semi-supervised part-of-speech tagging | |
US8346754B2 (en) | Generating succinct titles for web URLs | |
US8996622B2 (en) | Query log mining for detecting spam hosts | |
US9031885B2 (en) | Technologies for encouraging search engine switching based on behavior patterns | |
US8244737B2 (en) | Ranking documents based on a series of document graphs | |
US20090248661A1 (en) | Identifying relevant information sources from user activity | |
US8554764B2 (en) | Algorithm and implementation for fast computation of content recommendations | |
US11087089B2 (en) | Aspect-driven multi-document summarization | |
US20100318531A1 (en) | Smoothing clickthrough data for web search ranking | |
US20110161311A1 (en) | Search suggestion clustering and presentation | |
JP2009528619A (en) | Mining web search user behavior to improve web search relevance | |
US7818334B2 (en) | Query dependant link-based ranking using authority scores | |
US20100082694A1 (en) | Query log mining for detecting spam-attracting queries | |
US20080086466A1 (en) | Search method | |
US8185528B2 (en) | Assigning human-understandable labels to web pages | |
Sun et al. | Intention modeling for web navigation | |
Chimphlee et al. | Using association rules and markov model for predit next access on web usage mining | |
US20120036122A1 (en) | Contextual indexing of search results | |
Setia et al. | Research Article HPM: A Hybrid Model for User’s Behavior Prediction Based on N-Gram Parsing and Access Logs | |
US7792854B2 (en) | Query dependent link-based ranking |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |
|
AS | Assignment |
Owner name: MICROSOFT TECHNOLOGY LICENSING, LLC, WASHINGTON Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MICROSOFT CORPORATION;REEL/FRAME:034766/0001 Effective date: 20141014 |