MEDIA RECOMMENDATION SYSTEM AND METHOD

• US 20080059422A1
• Filed: 09/01/2006
• Published: 03/06/2008
• Est. Priority Date: 09/01/2006
• Status: Active Grant

• Current Assignee: RPX Corporation
• Original Assignee: Nokia Corporation
• Inventors: Tenni, Jarno, Salo, Osmo, Roberton, David, Gray, Geoff, Frisk, Miakki, Horner, Jack, Ming, Zhangjing
• Granted Patent: US 8,677,243 B2
• Time in Patent Office: Days
• US Class Current: 707/3
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/4387 by the use of playlists
• CPC Class Codes: G06F 16/637 Administration of user profiles, e.g. generation, initialization, adaptation or distribution
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

A system and method for providing content offering recommendations to users based on the users'"'"' preferences. Content offerings may be assigned to a primary metagenre and one or more sub-genres, as well as a secondary metagenre (and additional sub-genres if desired). The offerings may also be identified by their source, and this information can be used with the primary/secondary metagenre/sub-genre data to prepare a listing of recommended files. The listing may be generated by first generating three match listings: 1) a strong genre match listing identifying those offerings that match two user preferred metagenres; 2) a genre/style match listing identifying those offerings whose primary metagenre and corresponding sub-genre are preferred by the user; and 3) a weak genre match listing identifying those offerings whose primary metagenre matches a user preference, but whose secondary metagenre does not. These listings may be combined, redundancies may be removed, and a subset may be presented to the user as a recommendation list.

Claims

1. A method, comprising:

storing a plurality of metadata values for each of one or more content offerings, each offering having metadata identifying a primary metagenre, a sub-genre of said primary metagenre, and a secondary metagenre of the offering;

receiving user preference information identifying one or more metagenres preferred by said user, and one or more preferred sub-genres for each preferred metagenre;

generating a first genre match listing of said content offerings whose primary and secondary metagenre data match the user'"'"'s preferences;

generating a second genre match listing of said content offerings whose primary metagenre data and corresponding sub-genre data match the user'"'"'s preferences;

generating a third genre match listing of content offerings whose primary metagenre data matches the user'"'"'s preferences, but whose secondary metagenre data does not match the user'"'"'s preferences; and

generating a recommendation listing for said user based on said three generated genre match listings.

2. The method of claim 1, wherein said plurality of metadata values further includes information identifying recommenders of said content offerings, and said generating said first, second and third genre match listings further comprises ordering content offerings in said genre match listings to eliminate adjacent offerings having one or more common recommenders.

3. The method of claim 1, wherein said generating said first, second and third genre match listings further comprises ordering said genre match listings to eliminate adjacent offerings having one or more common metagenres.

4. The method of claim 1, further comprising sequentially combining said genre match listings.

5. The method of claim 1, wherein said plurality of metadata values further includes a ranking identifying how conventionally said offering fits in said offering'"'"'s primary metagenre.

6. The method of claim 5, further comprising sorting said genre match listings according to said ranking.

7. The method of claim 6, wherein said plurality of metadata values further includes information identifying recommenders of said content offerings, and said generating said first, second and third genre match listings further comprises ordering content offerings of said genre match listing to eliminate adjacent offerings having one or more common recommenders.

8. The method of claim 7, wherein said generating said first, second and third genre match listings further comprises ordering content offerings of said genre match listings to eliminate adjacent offerings having one or more common recommenders.

9. The method of claim 1, wherein said content offerings are audio data files.

10. The method of claim 1, further comprising collecting said one or more content offerings from one or more recommenders.

11. The method of claim 10, further comprising obtaining DRM (Digital Rights Management) information for said one or more content offerings collected from said recommenders.

12. The method of claim 11, further comprising offering access to one or more media files according to said DRM and said content offering information.

13. One or more computer-readable media storing computer-executable instructions for causing a computing device to act as follows:

storing a plurality of metadata values for each of one or more content offerings, each offering having metadata identifying a primary metagenre, a sub-genre of said primary metagenre, and a secondary metagenre of the offering;

receiving user preference information identifying one or more metagenres preferred by said user, and one or more preferred sub-genres for each preferred metagenre;

generating a first genre match listing of said content offerings whose primary and secondary metagenre data match the user'"'"'s preferences;

generating a second genre match listing of said content offerings whose primary metagenre data and corresponding sub-genre data match the user'"'"'s preferences;

generating a third genre match listing of content offerings whose primary metagenre data matches the user'"'"'s preferences, but whose secondary metagenre data does not match the user'"'"'s preferences; and

generating a recommendation listing for said user based on said three generated genre match listings.

14. The one or more computer-readable media of claim 13, wherein said plurality of metadata values further includes information identifying recommenders of said content offerings, and said generating said first, second and third genre match listings further comprises ordering content offerings of said genre match listings to eliminate adjacent offerings having one or more common recommenders.

15. The one or more computer-readable media of claim 13, wherein said generating said first, second and third genre match listings further comprises ordering content offerings of said genre match listings to eliminate adjacent offerings having one or more common metagenres.

16. The one or more computer-readable media of claim 13, further comprising computer-executable instructions for sequentially combining said genre match listings.

17. The one or more computer-readable media of claim 13, wherein said plurality of metadata values further includes a ranking identifying how conventionally said offering fits in said offering'"'"'s primary metagenre.

18. The one or more computer-readable media of claim 17, further comprising computer-executable instructions for sorting said genre match listings according to said ranking.

19. The one or more computer-readable media of claim 18, wherein said plurality of metadata values further includes information identifying recommenders of said content offerings, and said generating said first, second and third genre match listings further comprises ordering said genre match listings to eliminate adjacent offerings having one or more common recommenders.

20. The one or more computer-readable media of claim 19, wherein said generating said first, second and third genre match listings further comprises ordering content offerings of said genre match listings to eliminate adjacent offerings having one or more common recommenders.

21. The one or more computer-readable media of claim 13, wherein said content offerings are audio data files.

22. The one or more computer-readable media of claim 13, further comprising instructions for collecting said one or more content offerings from one or more recommenders.

23. The one or more computer-readable media of claim 22, further comprising instructions for obtaining DRM (Digital Rights Management) information for said one or more content offerings collected from said recommenders.

24. The one or more computer-readable media of claim 23, further comprising instructions for offering access to one or more media files according to said DRM and said content offering information.

25. A method, comprising:

storing a plurality of metadata values for each of one or more content offerings, each offering having metadata identifying a primary metagenre, a sub-genre of said primary metagenre, a secondary metagenre, a recommender source, and a ranking of fit in said primary metagenre of the offering;

receiving user preference information identifying one or more metagenres preferred by said user, and one or more preferred sub-genres for each preferred metagenre;

generating a first genre match listing of said content offerings whose primary and secondary metagenre data match the user'"'"'s preferences;

generating a second genre match listing of said content offerings whose primary metagenre data and corresponding sub-genre data match the user'"'"'s preferences;

generating a third genre match listing of content offerings whose primary metagenre data matches the user'"'"'s preferences, but whose secondary metagenre data does not match the user'"'"'s preferences;

combining said match listings to form a recommendation list that eliminates listings having one or more common adjacent metagenres or recommenders; and

generating a recommendation listing for said user based on said recommendation list.

26. The method of claim 25, wherein said combining further comprises:

creating a first temporary listing by looping through a match listing to sequentially add entries based on genre; and

creating a second temporary listing by looping through said first temporary listing to sequentially add entries based on recommender.

27. A server, comprising:

one or more storage devices storing a plurality of metadata values for each of one or more content offerings, each offering having metadata identifying a primary metagenre, a sub-genre of said primary metagenre, and a secondary metagenre of the offering;

a processor configured to;

receive user preference information identifying one or more metagenres preferred by said user, and one or more preferred sub-genres for each preferred metagenre;

generate a first genre match listing of said content offerings whose primary and secondary metagenre data match the user'"'"'s preferences;

generate a second genre match listing of said content offerings whose primary metagenre data and corresponding sub-genre data match the user'"'"'s preferences;

generate a third genre match listing of content offerings whose primary metagenre data matches the user'"'"'s preferences, but whose secondary metagenre data does not match the user'"'"'s preferences; and

generate a recommendation listing for said user based on said three generated genre match listings.