Content recommendation device with user feedback

• US 20050076093A1
• Filed: 06/04/2004
• Published: 04/07/2005
• Est. Priority Date: 06/04/2003
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: RealNetworks GmbH (RealNetworks, Inc.)
• Inventors: Riegler, Andreas, Spechtler, Andreas, Zich, Otto, Schramm, Balthasar, Petro, Oliver, Michelitsch, Stefan, Nemetz, Thomas, Burgstaller, Rainer
• Granted Patent: US 7,337,458 B2
• Time in Patent Office: Days
• US Class Current: 709/217
• 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
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies

Abstract

Content recommendation device with user feedback The invention relates to a content recommendation device, comprising a selection engine (2) that selects content items from a content item pool (4) and generates a selection list (9) comprising the selected content items, wherein said selection engine selects the content items from a content item pool according to a user profile, and/or means to receive a selection list selected from a content item pool according to a user profile, and a user profiling engine that generates a user profile based on a user feedback to at least a part of at least one previously generated selection. According to the invention said user feedback comprises explicit and implicit feedback so that a very simple explicit feedback, which gets refined by the corresponding implicit feedback, is possible.

Claims

1. Content recommendation device, comprising

a selection engine (2) that selects content items from a content item pool (4) and generates a selection list (9) comprising the selected content items, wherein said selection engine selects the content items from a content item pool according to a user profile, and/or

means to receive a selection list selected from a content item pool according to a user profile, and

a user profiling engine that generates a user profile based on a user feedback to at least a part of at least one previously generated selection,

characterized in that

said user feedback comprises explicit and implicit feedback.

2. Content recommendation device according to claim 1, characterized in that said user feedback (10) is a function of a representation of the explicit feedback weighted with a representation of the implicit feedback.

3. Content recommendation device according to claim 1, characterized in that said explicit feedback comprises an indication whether a user likes or dislikes a particular content item.

4. Content recommendation device according to claim 1, characterized in that said implicit feedback is based on the level of reaction accompanying the explicit feedback.

5. Content recommendation device according to claim 4, characterized in that said implicit feedback is based on the intensity the user is operating an input terminal of the content recommendation device.

6. Content recommendation device according to claim 4, characterized in that said implicit feedback comprises a pressure put on an explicit feedback control.

7. Content recommendation device according to claim 4, characterized in that said implicit feedback comprises a reaction time of a user to operate an explicit feedback control.

8. Content recommendation device according to claim 1, characterized in that said selection engine (2) generates said selection list (9) based on item attributes (5) that define every content item in a standardized way.

9. Content recommendation device according to claim 1, characterized in that said selection engine (2) generates said selection list (9) based on business rules (7) that generate a commercially influenced sequence of content items.

10. Content recommendation device according to claim 1, characterized by

an arrangement engine (3) that generates a content recommendation list (12) by re-arranging at least a part of content items of the selection list (9).

11. Content recommendation device according to claim 10, characterized in that said arrangement engine (3) generates said content recommendation list (12) based on arrangement rules (7) that generate a dramaturgic sequence of content items.

12. Content recommendation device according to claim 10, characterized in that said arrangement engine (3) generates said content recommendation list (12) based on item attributes (5) that define every content item in a standardized way.

13. Content recommendation device according to claim 11, characterized in that said arrangement rules (7) combine individual item attributes (5).

14. Content recommendation device according to claim 10, characterized in that said arrangement engine (3) generates said content recommendation list (12) based on business rules (7) that generate a commercially influenced sequence of content items.

15. Content recommendation device according to claim 10, characterized in that said arrangement engine (3) generates said content recommendation list (12) based on a user profile (11).

16. Content recommendation device according to claim 10, characterized in that

said user profiling engine (1) generates a user profile (1 1) based on a user feedback (10) to at least one previously output recommendation list (12).

17. Content recommendation device according to claim 10, characterized in that said user feedback (10) is used to generate an iteratively refined recommendation list (12) on basis of a reduced content item pool that comprises the content items of the selection list (9), or a new selection list (9).

18. Method for content recommendation, comprising the steps

selecting content items from a content item pool (4) according to a user profile and generating a selection list (9) comprising the selected content items, and/or

receiving a selection list selected from a content item pool according to a user profile, and

generating a user profile based on a user feedback to at least a part of at least one previously generated selection,

characterized in that

said user feedback comprises explicit and implicit feedback.

19. Method according to claim 18, characterized in that said user feedback (10) is a function of a representation of the explicit feedback weighted with a representation of the implicit feedback.

20. Method according to claim 18, characterized in that said explicit feedback comprises an indication whether a user likes or dislikes a particular content item.

21. Method according to claim 18, characterized in that said implicit feedback is based on the level of reaction accompanying the explicit feedback.

22. Method according to claim 21, characterized in that said implicit feedback is based on the intensity the user is operating an input terminal of the content recommendation device.

23. Method according to claim 21, characterized in that said implicit feedback comprises a pressure put on an explicit feedback control.

24. Method according to claim 21, characterized in that said implicit feedback comprises a reaction time of a user to operate an explicit feedback control.

25. Method according to claim 18, characterized by generating said selection list (9) based on item attributes (5) that define every content item in a standardized way.

26. Method according to claim 18, characterized by generating said selection list (9) based on business rules (7) that generate a commercially influenced sequence of content items.

27. Method according to claim 18, characterized by

generating a content recommendation list (12) by re-arranging at least a part of content items of the selection list (9).

28. Method according to claim 27, characterized by generating said content recommendation list (12) based on arrangement rules (7) that generate a dramaturgic sequence of content items.

29. Method according to claim 27, characterized by generating said content recommendation list (12) based on item attributes (5) that define every content item in a standardized way.

30. Method according to claim 28, characterized by combining individual item attributes (5) with said arrangement rules (7).

31. Method according to claim 27, characterized by generating said content recommendation list (12) based on business rules (7) that generate a commercially influenced sequence of content items.

32. Method according to claim 27, characterized by generating said content recommendation list (12) based on a user profile (11).

33. Method according to claim 27, characterized by generating a user profile (11) based on a user feedback (10) to at least one previously output recommendation list (12).

34. Method according to claim 33, characterized in that said user feedback (10) is used to generate an iteratively refined recommendation list (12) on basis of a reduced content item pool that comprises the content items of the selection list (9), or a new selection list (9).

35. Computer program product, comprising computer program means adapted to perform the method steps as defined in claim 18 when being executed on a computer, digital signal processor or the like.

36. Computer readable storage means, storing thereon a computer program product according to claim 35.