Media recommendation system and method
View Patent ↗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.
1. A method, comprising:
causing, at least in part, storing at an apparatus 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, one or more recommenders, and rankings assigned to respective metagenres by the recommenders;
receiving at the apparatus user preference information identifying one or more metagenres preferred by a user, and one or more preferred sub-genres for each preferred metagenre;
generating at the apparatus a first genre match listing of said content offerings, by identifying offerings whose primary and secondary metagenre data match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender;
generating at the apparatus a second genre match listing of said content offerings, by identifying offerings whose primary metagenre data and corresponding sub-genre data match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender;
generating at the apparatus a third genre match listing of content offerings, by identifying offerings whose primary metagenre data matches the user's preferences but whose secondary metagenre data does not match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender; and
generating at the apparatus a recommendation listing by combining the match listings, the recommendation list eliminates listings having one or more common adjacent metagenres or recommenders,
wherein said combining further comprises:
creating a first temporary listing via looping each of the match listings to sequentially add entries based on genre; and
creating a second temporary listing via looping the first temporary listing to sequentially add entries based on recommender.
2. The method of claim 1 , wherein said plurality of metadata values further includes information identifying the recommenders, 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 , further comprising: receiving inputs of mainstream/leftfield relative rankings to the primary and secondary metagenres, said mainstream/leftfield relative rankings identifying how conventionally said offering fits in a respective metagenre.
6. The method of claim 5 , further comprising: sorting the offerings with the highest mainstream/leftfield relative ranking to be at the top of the recommendation list; and
incorporating a number of times that at least one of the offerings has been recommended as a tie breaker when two of the offerings have an identical mainstream/leftfield relative ranking.
7. The method of claim 5 , further comprising removing duplicate entries from at least one of the first genre match listing, the second genre match listing, the third genre match listing, and the recommendation listing; and
displaying the recommendation listing including the mainstream/leftfield relative rankings and the recommenders in a new list.
8. The method of claim 1 , 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, and the recommenders include at least one of users of the list, musical fans, customers of the offerings, music stores, and publishing labels.
10. The method of claim 5 , further comprising: sorting the offerings with the highest number of times that at least one of the offerings has been recommended to be at the top of the recommendation list; and
incorporating the mainstream/leftfield relative rankings as a tie breaker when two of the offerings have an identical number of recommended times.
11. The method of claim 1 , further comprising obtaining DRM (Digital Rights Management) information for said offerings.
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. A non-transitory computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform the following steps:
causing, at least in part, storing 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, one or more recommenders, and rankings assigned to respective metagenres by the recommenders;
receiving user preference information identifying one or more metagenres preferred by a user, and one or more preferred sub-genres for each preferred metagenre;
generating a first genre match listing of said content offerings by identifying offerings whose primary and secondary metagenre data match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender;
generating a second genre match listing of said content offerings by identifying offerings whose primary metagenre data and corresponding subgenre data match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender;
generating a third genre match listing of content offerings, by identifying offerings whose primary metagenre data matches the user's preferences but whose secondary metagenre data does not match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender; and
generating a recommendation listing by combining the match listings, the recommendation list eliminates listings having one or more common adjacent metagenres or recommenders
wherein said combining further comprises:
creating a second temporary listing via looping each of the match listings to sequentially add entries based on genre; and
entries based on genre; and
creating a second temporary listing via loop said temporary listing to sequentially add entries based on recommender.
14. The non-transitory computer-readable storage medium 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 non-transitory computer-readable storage medium 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 non-transitory computer-readable storage medium of claim 13 , wherein the apparatus is caused to further perform: sequentially combining said genre match listings.
17. The non-transitory computer-readable storage medium of claim 13 , wherein the apparatus is caused to further perform: receiving inputs of mainstream/leftfield relative rankings to the primary and secondary metagenres, said mainstream/leftfield relative rankings identifying how conventionally said offering fits in a respective metagenre.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the apparatus is caused to further perform: sorting the offerings with the highest mainstrearn/leftfield relative ranking to be at the top of the recommendation list; and incorporating a number of times that at least one of the offering has been recommended as a tie breaker when two of the offerings have an identical mainstream/leftfield relative ranking.
19. The non-transitory computer-readable storage medium of claim 17 , wherein the apparatus is caused to further perform: removing duplicate entries from at least one of the first genre match listing, the second genre match listing, the third genre match listing, and the recommendation listing; and displaying the recommendation listing including the mainstream/leftfield relative rankings and the recommenders in a new list.
20. The non-transitory computer-readable storage medium 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 recommenders.
21. The non-transitory computer-readable storage medium of claim 13 , wherein said content offerings are audio data files, and the recommenders include at least one of users of the list, musical fans, customers of the offerings, music stores, and publishing labels.
22. The non-transitory computer-readable storage medium of claim 17 , wherein the apparatus is caused to further perform: sorting the offerings with the highest mainstrearn/leftfield relative ranking to be at the top of the recommendation list; and incorporating a number of times that at least one of the offering has been recommended as a tie breaker when two of the offerings have an identical mainstream/leftfield relative ranking.
23. The non-transitory computer-readable storage medium of claim 13 , further comprising instructions for obtaining DRM (Digital Rights Management) information for said offerings.
24. The non-transitory computer-readable storage medium of claim 23 , wherein the apparatus is caused to further perform: offering access to one or more media files according to said DRM and said content offering information.
25. A method comprising:
storing 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, one or more recommenders, and mainstream/leftfield relative rankings assigned to respective metagenres by the recommenders, said mainstream/leftfield relative rankings identifying how conventionally said offering fits in a respective metagenre;
causing, at least in part, receiving user preference information identifying one or more metagenres preferred by a 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, by identifying offerings whose primary and secondary metagenre data match the user's preferences, ordering the offerings with highest mainstream/leftfield relative ranking first, and scattering the offerings per metagenre and per recommender;
generating a second genre match listing of said content offerings whose primary metagenre data and corresponding sub-genre data match the user's preferences, by identifying offerings whose primary metagenre data and corresponding sub-genre data match the user's preferences, ordering the offerings with highest mainstream/leftfield relative ranking first, and scattering the offerings per metagenre and per recommender;
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, by identifying offerings whose primary metagenre data matches the user's preferences but whose secondary metagenre data does not match the user's preferences, ordering the offerings with highest mainstream/leftfield relative ranking first, and scattering the offerings per metagenre and per recommender;
combining the match listings to form a recommendation list that eliminates listings having one or more common adjacent metagenres or recommenders; and
generating a recommendation listing based on said recommendation list, the recommendation listing including information identifying one or more recommenders of said recommendation listing and the mainstream/leftfield relative rankings, wherein said combining further comprises:
creating a first temporary listing by looping each of the match listings to sequentially add entries based on genre; and
creating a second temporary listing by looping said first temporary listing to sequentially add entries based on recommender.
26. An apparatus, comprising:
at least one processor; and
at least one memory including computer program code,
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,
cause, at least in part, storing 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, one or more recommenders, and rankings assigned to respective metagenres by the recommenders;
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, by identifying offerings whose primary and secondary metagenre data match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender;
generate a second genre match listing of said content offerings, by identifying offerings whose primary metagenre data and corresponding sub-genre data match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender;
generate a third genre match listing of content offerings, by identifying offerings whose primary metagenre data matches the user's preferences but whose secondary metagenre data does not match the user's preferences, ordering the offerings with highest ranking first, and scattering the offerings per metagenre and per recommender; and
generate a recommendation listing by combining the match listings, the recommendation list eliminates listings having one or more common adjacent metagenres or recommenders,
wherein said combining further comprises:
creating a first temporary listing via looping each of the match listings to sequentially add entries based on genre; and
creating a second temporary listing via looping-said first temporary listing to sequentially add entries based on recommender.
27. The apparatus of claim 26 , wherein the apparatus is further caused to obtain DRM (Digital Rights Management) information for said offerings.
28. The apparatus of claim 27 , wherein the apparatus is further caused to offer access to one or more media files according to said DRM and said content offering information.