System and method for prediction of musical preferences

• US 20030089218A1
• Filed: 09/27/2002
• Published: 05/15/2003
• Est. Priority Date: 06/29/2000
• Status: Active Grant

• Current Assignee: Pandora Media LLC (Liberty Media Corporation)
• Original Assignee: MusicGenome.Com Incorporated
• Inventors: Lehmann, Daniel, Gang, Dan
• Granted Patent: US 7,075,000 B2
• Time in Patent Office: Days
• US Class Current: 84/615
• CPC Class Codes: G06F 16/637 Administration of user profiles, e.g. generation, initialization, adaptation or distribution
• CPC Class Codes: G06F 16/639 using playlists
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G10H 1/0008 Associated control or indicating means
• CPC Class Codes: G10H 1/0058 Transmission between separate instruments or between individual components of a musical system G10H1/0083 takes precedence
• CPC Class Codes: G10H 2240/061 MP3, i.e. MPEG-1 or MPEG-2 Audio Layer III, lossy audio compression
• CPC Class Codes: G10H 2240/081 Genre classification, i.e. descriptive metadata for classification or selection of musical pieces according to style analysis genre G10H2210/036
• CPC Class Codes: G10H 2240/305 Internet or TCP/IP protocol use for any electrophonic musical instrument data or musical parameter transmission purposes
• CPC Class Codes: G10H 2250/151 Fuzzy logic
• CPC Class Codes: G10H 2250/311 Neural networks for electrophonic musical instruments or musical processing, e.g. for musical recognition or control, automatic composition or improvisation musical analysis G10H2210/031; neural networks G06N3/02
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D

Abstract

A system and a method for predicting the musical taste and/or preferences of the user The present invention receives, on one hand, ratings of a plurality of songs from the user and/or other information about the taste of the user, and on the other hand information about the songs in the catalog from which recommendations are to be given The method then combines both types of information in order to determine the musical preferences of the user. These preferences are then matched to at least one musical selection, which is predicted to be preferred by the user

Claims

1. A method for predicting a preference of a user for a media selection, the method comprising:

analyzing a catalog of media selections according to a plurality of characteristics;

rating at least one media selection by the user;

matching said rating with said plurality of characteristics to predict the preference of the user for at least one of the media selections of the catalog; and

recommending at least one predicted media selection to the user.

2. The method of claim 1, wherein a plurality of matching processes are used to match said rating with said plurality of characteristics.

3. The method of claims 1 or 2, wherein a matching process is a neural network, such that said plurality of characteristics of said media selection forms a binary vector and said neural network learns to match said binary vector to characteristics of each rated media selection by the user.

4. The method of claims 1 or 2, wherein a matching process is a map method for creating a matrix of pseudo-distances between each pair of media selections, for comparing each rated media selection to at least one other media selection in said catalog.

5. The method of claim 4, wherein said map method is a selection map method, for comparing all characteristics of each pair of media selections.

6. The method of claim 4, wherein said map method is a feature map method, for comparing a selected group of features of each pair of media selections.

7. The method of claim 4, wherein said map method is a fingerprint map method, for comparing a signature of each pair of media selections.

8. The method of claims 1 or 2, wherein a matching process is a rating method for rating each media selection of said catalog and directly comparing each rating of the user to said rating for said media selection of said catalog.

9. The method of any of claims 1-8, wherein information about each media selection in said catalog is stored in a feature base.

10. The method of any of claims 1-9, wherein each media selection is also characterized by genre.

11. The method of any of claims 1-10, wherein each media selection is a musical selection.

12. The method of claim 11, wherein said musical selection is analyzed along musical features by a trained musician.

13. The method of claim 11, wherein said musical selection is rated by a plurality of users.

14. The method of claim 11, wherein said musical selection is automatically analyzed according to a fingerprint of the audio signal.

15. The method of any of claims 11-14, wherein said musical selections and rating information are presented to the user through a network.

16. The method of claim 15, wherein said network is the Internet.

17. The method of any of claims 11-14, wherein said musical selections and rating information are presented to the user through a stand alone station.

18. The method of any of claims 15-17, further comprising:

purchasing a musical selection by the user.

19. The method of any of claims 1-10, wherein said media selection features printed material.

20. The method of any of claims 1-10, wherein said media selection features visual material.

21. The method of claim 20, wherein said visual material includes video data.

22. The method of claim 1, said media selection is rated by a plurality of users.

23. A method for predicting a preference of a user for a media selection, the method comprising:

analyzing at least a portion of a catalog of media selections according to a characteristic by a group of raters;

rating at least one media selection by the user;

matching said rating with said characteristic to predict the preference of the user for at least one of the media selections of the catalog; and

recommending at least one predicted media selection to the user.

24. A method for predicting a preference of a user for a media selection, the method comprising:

automatically analyzing at least a portion of a catalog of media selections according to a characteristic;

rating at least one media selection by the user;

matching said rating with said characteristic to predict the preference of the user for at least one of the media selections of the catalog; and

recommending at least one predicted media selection to the user.

25. The method of claim 24, wherein said media selection features audio data, and said characteristic is a fingerprint of said audio data as an audio signal.