Method and apparatus for selective updating of a user profile

• US 7,721,310 B2
• Filed: 12/05/2000
• Issued: 05/18/2010
• Est. Priority Date: 12/05/2000
• Status: Expired due to Fees

• Current Assignee: Sisvel S.p.A. (Fineur International S.A.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Gutta, Srinivas, Kurapati, Kaushal, Lee, Kwok Pun, Schaffer, J. David
• Primary Examiner(s): Saltarelli; Dominic D
• Assistant Examiner(s): Parry; Chris
• Application Number:
  US09/730,205
• Publication Number:
  US 20020104087A1
• Time in Patent Office: 3,451 Days
• Field of Search: 725/46, 725/14, 725/16, 725/20, 725/13, 725/9
• US Class Current: 725/46
• CPC Class Codes: H04N 21/44222 Analytics of user selections, e.g. selection of programs or purchase activity monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/454 Content or additional data filtering, e.g. blocking advertisements
• CPC Class Codes: H04N 21/466 Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/4756 for rating content, e.g. scoring a recommended movie
• CPC Class Codes: H04N 7/163 by receiver means only

Abstract

A television programming recommender is disclosed that selectively obtains feedback information from a user to update one or more profiles associated with the user. Previously obtained implicit and explicit preferences are utilized to selectively focus the collection of feedback information to further update and refine the implicit and explicit preferences. The present invention obtains feedback from a user in a manner that maximizes the value of the obtained information and improves the performance of the television programming recommender. The present invention automatically requests feedback from the user upon the occurrence of predefined criteria. The nature of the requested feedback, and the manner in which the obtained feedback is used to adjust a profile, can vary.

Claims

1. A method for updating a user profile stored in a memory, comprising the steps of:

obtaining, from the memory using a processor, said user profile indicating program content preferences of a user;

comparing, using the processor, said preferences to program content of an item selection made by said user;

generating program recommendation scores, using implicit/explicit recommenders, of content based on the preferences in the user profile;

requesting feedback information from said user using a user interface if said selection is inconsistent with said preferences, wherein said feedback request includes an indication of said generated program recommendation score for the program content of said item selection that includes an identification of one or more program features that significantly contributed to the generated program recommendation score; and

updating said user profile with said feedback information.

2. The method as claimed in claim 1, wherein said step of requesting feedback further comprises the steps of placing at least one feedback request in a log file and presenting said feedback request to said user at a later time adapted for reducing obtrusiveness of the feedback request.

3. The method as claimed in claim 2, wherein said feedback requests are presented in a given session during said step of presenting said feedback request based on timing determined by a user-specified parameter only if said content selection is inconsistent with said preferences.

4. The method as claimed in claim 2, wherein said feedback requests are presented in a given session during said step of presenting said feedback request based on timing determined by predetermined criteria only if the program content of said item selection is inconsistent with said preferences.

5. The method as claimed in claim 2, wherein said feedback requests presented in a given session during said step of presenting said feedback request based on timing determined by dynamically determined criteria only if the program content of said item selection is inconsistent with said preferences.

6. The method as claimed in claim 1, wherein said step of requesting feedback information requests said user to provide a scale-based rating of the program content of said item selection only if said program content appears inconsistent with information in said user profile.

7. The method as claimed in claim 1, wherein said step of requesting feedback information requests said user to provide a scale-based rating of the program content of said item selection only if said program content appears inconsistent with the generated program recommendation score.

8. The method as claimed in claim 1, wherein said step of requesting feedback information requests said user to provide a scale-based rating of a content item that is not selected only if said program content appears inconsistent with information in said user profile.

9. The method as claimed in claim 1, wherein said step of requesting feedback information requests said user to provide a scale-based rating of the program content of said item selection only if the generated program recommendation score of said program content is a neutral recommendation score.

10. The method as claimed in claim 1, wherein the generated program recommendation score includes scores from two different recommenders, and said step of requesting feedback information requests said user to provide a scale-based rating of the program content of said item selection only if said program content has been assigned inconsistent recommendation scores by the two different recommenders.

11. A method for updating a user profile stored in a memory, comprising the steps of:

obtaining, from the memory using a processor, said user profile indicating content preferences of a user;

comparing, using the processor, said content preferences to a content selection of said user;

generating recommendation scores, using implicit/explicit recommenders, of content based on the preferences in the user profile;

requesting feedback information from said user using a user interface if said content selection is inconsistent with said content preferences, wherein said feedback request includes an indication of said generated recommendation score for said content selection that includes an identification of one or more program features that significantly contributed to the generated recommendation score; and

updating said user profile with said feedback information.

12. The method as claimed in claim 11, wherein said inconsistent selection is a content selection having content features that do not match said user profile.

13. The method as claimed in claim 11, wherein said inconsistent selection is a content selection for which a low recommendation score is generated.

14. The method as claimed in claim 11, wherein said inconsistent selection is failing to make a content selection for which high recommendation score has been generated in favor of one or more content items for which lower recommendation scores are generated.

15. A method for updating a user profile stored in a memory, comprising the steps of:

establishing, using a processor, a plurality of profile influence rules that dynamically obtain user feedback upon occurrence of predefined criteria;

comparing, using the processor, said plurality of profile influence rules to behavior;

generating recommendation scores, using implicit/explicit recommenders, of content based on the preferences in the user profile; and

requesting feedback from a user using a user interface regarding said content preferences if said predefined criteria of at least one of said profile influence rules is satisfied, wherein said feedback request includes an indication of said generated recommendation score that includes an identification of one or more program features that significantly contributed to the generated recommendation score.

16. The method as claimed in claim 15, wherein said profile influence rules identify user behavior that is inconsistent with content related information recorded in said user profile and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

17. The method as claimed in claim 16, wherein said inconsistent behavior is selecting a content item having content related features that do not match said user profile and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

18. The method as claimed in claim 15, wherein said profile influence rules identify user behavior that is inconsistent with said generated recommendation scores and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

19. The method as claimed in claim 18, wherein said inconsistent user behavior is selecting a content item for which a low recommendation score is generated and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

20. The method as claimed in claim 18, wherein said inconsistent user behavior is failing to select a content item receiving a high recommendation score in favor of one or more content items receiving lower recommendation scores and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

21. The method as claimed in claim 15, wherein said profile influence rules cause a neutral recommendation score to be generated and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

22. The method as claimed in claim 15, wherein said profile influence rules cause inconsistent recommendation scores to be generated and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

23. The method as claimed in claim 22, wherein said inconsistent recommendation scores are generated by two different recommenders and said requested feedback is presented only if said behavior is inconsistent with said content preferences.

24. The method as claimed in claim 15, wherein said profile influence rules specify how said feedback should be employed to update said user profile and said requested feedback is requested at a time adapted for reducing obtrusiveness of the feedback request.

25. The method as claimed in claim 15, wherein said profile influence rules have an associated feedback request command adapting appropriate information that should be requested in order to influence said used profile at a time adapted for reducing obtrusiveness of the feedback request.

26. A method for updating a user profile stored in a memory, comprising the steps of:

establishing, using a processor, a plurality of profile influence rules that dynamically obtain user feedback upon occurrence of predefined criteria;

generating recommendation scores, using implicit/explicit recommenders, of content based on content related preferences in the user profile;

comparing, using the processor, said plurality of profile influence rules to generated content related recommendation scores; and

requesting feedback from a user using a user interface regarding said content related preferences if said predefined criteria of at least one of said profile influence rules is satisfied, wherein said feedback request includes an indication of said generated recommendation score that includes an identification of one or more program features that significantly contributed to the generated recommendation score.

27. The method as claimed in claim 26, wherein said profile influence rules cause a neutral recommendation score to be generated and said requested feedback is requested only if said behavior is inconsistent with said content preferences.

28. The method as claimed in claim 26, wherein said profile influence rules cause inconsistent recommendation scores to be generated and said requested feedback is requested only if said behavior is inconsistent with said content preferences.

29. The method as claimed in claim 28, wherein said inconsistent recommendation scores are generated by two different recommenders and said requested feedback is requested only if said behavior is inconsistent with said content preferences.

30. The method as claimed in claim 26, wherein said profile influence rules specify how said feedback should be employed to update said user profile and said requested feedback is requested at a time adapted for reducing obtrusiveness of the feedback request.

31. The method as claimed in claim 26, wherein said profile influence rules have an associated feedback request command adapting appropriate information that should be requested in order to influence said used profile and said requested feedback is requested at a time adapted for reducing obtrusiveness of the feedback request.