Activity Based Users' Interests Modeling for Determining Content Relevance

• US 20110016121A1
• Filed: 07/16/2009
• Published: 01/20/2011
• Est. Priority Date: 07/16/2009
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Gupta, Sanjeev, Vasudevan, Sudharsan, Monga, Rohan, Sambrani, Hemanth
• Granted Patent: US 8,612,435 B2
• Time in Patent Office: Days
• US Class Current: 707/734
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A method and apparatus for activity-based users'"'"' interests modeling for determining relevance of the content distributed to the users is provided. Modeling of the user'"'"'s interests starts by collecting information about the actions that the user performed and about the contents that were associated with the actions. That information may be used to determine how much interest the user has had in the individual subjects up to date, and to determine which subjects became more or less important to the user over time. Further processing of the information about the interests of each of the individual users in a group of users may produce characteristics indicating the interests of the group as a whole. Additional processing may generate the information reflecting relative importance of the interests of an individual user in the group to the interests of other users in the same group.

Claims

1. A method comprising:

monitoring actions performed by a user that is associated with a profile target;

detecting that said user performed a particular action associated with a particular content;

wherein said particular content is related to a particular set of one or more subjects, each of which has a corresponding subject weight value;

determining a particular action type of said particular action, wherein said particular action type of said particular action is one of a plurality of action types;

determining one or more interest weights for said particular set of one or more subjects based, at least in part, on the subject weight values of said particular set of one or more subjects and said particular action type;

updating a profile associated with said profile target, based, at least in part, on said one or more interest weights;

wherein the step of updating is performed by one or more special-purpose computing devices.

2. The method of claim 1, wherein further comprising determining an action type weight for said particular action type, and updating the profile associated with said profile target based, at least in part, on said action type weight for said particular action type.

3. The method of claim 1, wherein the determining one or more interest weights for said particular set of one or more subjects is based, at least in part, on whether the user was interested in any of the subjects in the particular set of one or more subjects in the past.

4. The method of claim 1, wherein the determining one or more interest weights for said particular set of one or more subjects is based, at least in part, on whether the particular action is associated with a long term interest.

5. The method of claim 1, wherein the determining one or more interest weights for said particular set of one or more subjects is based, at least in part, on whether any user associated with the profile target was interested in any of the subjects in said particular set of one or more subjects in the past.

6. The method of claim 1, wherein the updating a profile associated with said profile target further comprises applying a decay function to said one or more interest weights for said particular set of one or more subjects.

7. The method of claim 1, wherein the user has associated one or more demographic characteristics specific to the profile target.

8. The method of claim 7, wherein the updating a profile associated with said profile target further comprises applying one or more demographic characteristics associated with said user to said one or more interest weights for said particular set of one or more subjects.

9. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 1.

10. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 2.

11. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 3.

12. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 4.

13. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 5.

14. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 6.

15. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 7.

16. One or more storage media storing instructions which, when executed by one or more computing devices, cause performance of the method recited in claim 8.

17. A method comprising:

monitoring actions performed by a user that is associated with a profile target;

detecting that said user performed a particular action associated with a particular content;

wherein said particular content is related to a particular set of one or more subjects;

determining one or more interest present values for said particular set of one or more subjects;

wherein said one or more interest present values indicate how much interest the user presently has in each of the subjects in the particular set of one or more subjects;

determining one or more interest past values for said particular set of one or more subjects;

wherein said one or more interest past values indicate how much interest any user that is associated with the particular target had in the past in each of the subjects in the particular set of one or more subjects;

updating a profile associated with said profile target, based, at least in part, on said one or more interest present values and said one or more interest past values;

wherein the step of updating is performed by one or more special-purpose computing devices programmed to be special purpose machines pursuant to program instructions.

18. The method of claim 17, wherein the determining one or more interest present values for said particular set of one or more subjects is based, at least in part, on subject weight values associated with said particular set of one or more subjects.

19. The method of claim 18, wherein the determining one or more interest present values for said particular set of one or more subjects is based, at least in part, on an action type weight associated with said particular action.

20. The method of claim 17, wherein the updating a profile associated with said profile target further comprises applying a decay function to one or more interest past values for said particular set of one or more subjects.