Methods and systems for conducting a personalized web browser search by probability estimation that is unseen document is of interest to the user

• US 9,098,813 B1
• Filed: 02/12/2014
• Issued: 08/04/2015
• Est. Priority Date: 12/28/1999
• Status: Expired due to Term

• Current Assignee: Personalized User Model LLP
• Original Assignee: Personalized User Model LLP
• Inventors: Konig, Yochai, Twersky, Roy, Berthold, Michael R
• Primary Examiner(s): Barot, Bharat N
• Application Number:
  US14/178,715
• Time in Patent Office: 538 Days
• Field of Search: 709217-226, 709202-203, 705 144- 1441, 705 1472- 1473
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/53 using third party service providers
• CPC Class Codes: H04L 67/55 Push-based network services
• CPC Class Codes: H04L 67/75 Indicating network or usage conditions on the user display
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing

Abstract

A method for providing automatic, personalized information services to a computer user includes the following steps: transparently monitoring user interactions with data during normal use of the computer; updating user-specific data files including a set of user-related documents; estimating parameters of a learning machine that define a User Model specific to the user, using the user-specific data files; analyzing a document to identify its properties; estimating the probability that the user is interested in the document by applying the document properties to the parameters of the User Model; and providing personalized services based on the estimated probability. Personalized services include personalized searches that return only documents of interest to the user, personalized crawling for maintaining an index of documents of interest to the user; personalized navigation that recommends interesting documents that are hyperlinked to documents currently being viewed; and personalized news, in which a third party server customized its interaction with the user.

Claims

1. A computer-implemented method for providing information to a user, the method comprising:

displaying a web page using a browser program running on a computer;

monitoring user interactions with the web page while the user is engaged in the use of said browser program;

analyzing the monitored interactions to estimate parameters of a user specific learning machine;

selecting a plurality of documents related to said web page by computing an estimated probability that the documents are of interest to the user, wherein the selecting step of said plurality of documents comprises for each subject one of the plurality of documents;

identifying properties of the subject document; and

applying the identified properties of the subject document to the user specific learning machine to estimate a probability P(u|d) that the subject unseen document is of interest to the user; and

presenting, via said browser, information regarding at least some of said plurality of documents to the user.

2. The method of claim 1, further comprising analyzing the monitored interactions to determine documents not of interest to the user, and wherein estimating parameters of the user-specific learning machine comprises estimating parameters of the user-specific learning machine based at least in part on the documents not of interest to the user.

3. The method of claim 1, wherein monitoring user interactions with the web page comprises monitoring at least one type of interaction selected from the group consisting of:

information about the user'"'"'s interaction with the web page, context information, the user'"'"'s degree of interest in the web page, time spent by the user viewing the web page, whether the user followed at least one link contained in the web page, and a number of links in the web page followed by the user.

4. The method of claim 1, wherein said plurality of documents correspond to a respective plurality of products.

5. The method of claim 1, wherein, for each respective one of the plurality of documents, estimating the probability that the subject document is of interest to the user comprises estimating the probability that the subject document is of interest to the user according to a relevance of the subject document to the web page displayed to the user.

6. The method of claim 1, wherein identifying properties of the subject document comprises identifying properties selected from the group consisting of:

a topic associated with the subject document, at least one product feature extracted from the subject document, an author of the subject document, and an age of the subject document.

7. The method of claim 1, wherein the estimated probability that the documents are of interest to the user is determined according to information regarding the user.

8. The method of claim 7, wherein the information regarding the user is maintained remotely from the computer running the browser program.

9. A computer-implemented method for providing personalized information services to a user, the method comprising:

displaying a web page using a browser program running on a computer;

monitoring user interactions with the web page while the user is engaged in use of said browser program;

analyzing the monitored interactions to determine documents of interest to the user;

estimating parameters of a user-specific learning machine based at least in part on the documents of interest to the user;

selecting a plurality of documents related to said web page, said relation based on said web page and, for each respective one of the plurality of documents, an estimated probability P(u|d) that the respective document is of interest to the user, wherein the selecting step of said plurality of documents comprises, for each respective one of the plurality of documents;

identifying properties of the respective document, and applying the identified properties of the respective document to the user specific learning machine to estimate the probability that the respective unseen document is of interest to the user; and

presenting information concerning at least some of the plurality of documents to the user via the browser.

10. The method of claim 9, further comprising analyzing the monitored interactions to determine documents not of interest to the user, and wherein estimating parameters of the user-specific learning machine further comprises estimating parameters of the user-specific learning machine based at least in part on the documents not of interest to the user.

11. The method of claim 9, wherein monitoring user interactions comprises monitoring at least one type of interaction selected from the group consisting of:

whether the user viewed the web page, information about the user'"'"'s interaction with the web page, context information, the user'"'"'s degree of interest in the web page, time spent by the user viewing the web page, whether the user followed at least one link contained in the web page, and a number of links in the web page followed by the user.

12. The method of claim 9, wherein said plurality of documents correspond to a respective plurality of products.

13. The method of claim 9, wherein presenting information concerning at least some of the plurality of documents comprises, for each respective document, using the estimated probability for that the respective document is of interest to the user and the relevance of the respective document to the web page displayed to the user to present at least a portion of the respective document to the user.

14. The method of claim 9, wherein identifying properties of the respective document comprises identifying properties selected from the properties consisting of:

a topic associated with the respective document, at least one product feature extracted from the respective document, an author of the respective document, and an age of the respective document.

15. A computer-implemented method for providing information to a user, the method comprising:

displaying a web page using a browser program running on a computer;

monitoring user interactions with the web page while the user is engaged in the use of said browser program;

analyzing the monitored interactions to estimate parameters of a user specific learning machine;

selecting a plurality of documents related to said web page by computing an estimated probability that the documents are of interest to the user, wherein the selecting step of said plurality of documents comprises for each subject one of the plurality of documents;

identifying properties of the subject document; and

applying the identified properties of the subject document to the user specific learning machine to estimate a probability P(u|d,q) that the subject unseen document is of interest to the user; and

presenting, via said browser, information regarding at least some of said plurality of documents to the user.

16. A computer-implemented method for providing personalized information services to a user, the method comprising:

transparently monitoring user interactions with data while the user is engaged in normal use of a browser program running on the computer;

analyzing the monitored data to determine documents of interest to the user;

estimating parameters of a user-specific learning machine based at least in part on the documents of interest to the user;

receiving a search query from the user;

retrieving a plurality of documents based on the search query;

for each retrieved document of said plurality of retrieved documents;

identifying properties of the retrieved document, and applying the identified properties of the retrieved document to the user-specific learning machine to estimate a probability P(u|d) that the retrieved document is of interest to the user, the identified properties of the retrieved document including determining whether at least one of said documents of interest contains a link to said retrieved document; and

using the estimated probabilities for the respective plurality of retrieved documents to present at least a portion of the retrieved documents to the user.