PERSONA-BASED APPLICATION PERSONALIZATION

• US 20080027924A1
• Filed: 07/25/2006
• Published: 01/31/2008
• Est. Priority Date: 07/25/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zhu, Robert, Kourbatov, Alexei, Hamilton, Keith
• Granted Patent: US 7,613,692 B2
• Time in Patent Office: Days
• US Class Current: 707/5
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

Systems and methods that facilitate persona-based application personalization are disclosed. A persona is a conglomeration of a group of archetypal users that represent the personalization needs of many users and is based on observed behavior and patterns associated with the group of users. Users can be grouped into personas, and the personas can be analyzed to facilitate application personalization at a person level. Individual users can then be mapped to personas based on correlations of their respective individual behaviors and/or usage patters to the usage patterns of the persona as a whole.

Claims

1. A computer-implemented system that facilitates personalizing an application for a user, comprising:

a correlation component that evaluates historical usage data associated with one or more users; and

a business intelligence component that maps the one or more users to one or more personas as a function of the historical usage data.

2. The system of claim 1, further comprising a content engine that stores and analyzes link information as a function of keywords associated with content related to a link for related content recommendation.

3. The system of claim 1, further comprising a user information engine that stores and analyzes information related to historical usage and application navigation by one or more users.

4. The system of claim 1, further comprising an analytics engine that determines patterns of user activity relative to content access by one or more users.

5. The system of claim 1, wherein the application is at least one of an online web-based application and an off-line operating system application.

6. The system of claim 1, further comprising a persona inference engine that infers at least one persona to which the one or more users is mapped as a function of the historical usage data associated with the user.

7. The system of claim 6, further comprising a client-server architecture, wherein one or more servers periodically refines the persona inference rules, and a client computer downloads refined persona inference rules from the one or more servers, infers one or more current user personas on the client side based at least in part on the user'"'"'s most recent activity, and reports the one or more inferred personas back to the one or more servers.

8. The system of claim 6, wherein the persona inference engine employs a URL-based inference rule and makes inferences based on substrings associated with URLs visited by the one or more users.

9. The system of claim 6, wherein the persona inference engine employs a keyword-based inference rule and makes inferences based on keywords associated with content viewed by the one or more users.

10. The system of claim 6, wherein the persona-based inference engine employs a search-based inference rule and makes inferences based on user-entered search terms.

11. A computer-implemented method of performing persona-based application personalization, comprising:

evaluating usage history information associated with at least one user of an application; and

inferring a persona to which to map the at least one user as a function of the usage history associated with the at least one user

12. The method of claim 11, wherein the application is at least one of an online web-based application and an off-line application.

13. The method of claim 11, wherein the usage history comprises at least one of web content viewed by the at least one user, search terms entered by the at least one user, and URLs visited by the at least one user.

14. The method of claim 11, further comprising dynamically defining the persona as a function of usage history associated with a plurality of users mapped to the persona.

15. The method of claim 14, further comprising updating the persona as according to changes in usage history over a predefined evaluation period.

16. The method of claim 11, further comprising employing a URL-based inference rule and inferring a persona to which to map the at least one user based on substrings associated with URLs visited by the at least one user.

17. The method of claim 11, further comprising employing a keyword-based inference rule and inferring a persona to which to map the at least one user based on keywords associated with content viewed by the at least one user.

18. The method of claim 11, further comprising employing a search-based inference rule and inferring a persona to which to map the at least one user based on search terms entered by the at least one user.

19. A computer-executable system, comprising:

computer-implemented means for analyzing usage history associated with a user;

computer-implemented means for inferring a persona to which to map the user based on the usage history;

computer-implemented means for mapping the user to the persona; and

computer-implemented means for updating the persona as a function of the usage history of all users mapped to the persona.

20. The system of claim 19, wherein the means for inferring employs an inference rule that is at least one of a URL-based inference rule, a keyword-based inference rule, and a search-based inference rule.