SYSTEM AND METHOD FOR PLAYLIST GENERATION BASED ON SIMILARITY DATA

• US 20100076983A1
• Filed: 09/30/2008
• Published: 03/25/2010
• Est. Priority Date: 09/08/2008
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Davis, Stephen A., Miller, Jeffrey S., Flowers, Josh, Wadycki, Andrew, Wagner, Richard Frederick, Werner, Jeremy, Gates, Patrick
• Granted Patent: US 8,914,384 B2
• Time in Patent Office: Days
• US Class Current: 707/749
• CPC Class Codes: G06F 16/433 using audio data
• CPC Class Codes: G06F 16/4387 by the use of playlists
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• 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 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G11B 27/105 of operating discs

Abstract

System, method and computer program that encompasses one or more client devices cooperating with a program host'"'"'s on-line data processing center to generate media playlists. Data is transmitted from a program participant'"'"'s client device to the processing center and is representative of media inventory in a media library on the client device and includes identification data of contained individual media items. Data is further received from a plurality of program participants representative of each respective program participant'"'"'s media inventory, regardless of the source of the members of the inventory. Co-occurrence of pairs of individual media items in different program participants'"'"' media libraries is determined and a similarity rating is assigned between the pairs of individual media items based on the determined incidence of co-occurrence in the different program participants'"'"' media libraries. From this, a media playlist is generated.

Claims

1. A method for generating a media playlist based at least in part on media library inventory information provided by a plurality of program participants, said method comprising:

transmitting, from a program participant'"'"'s client device to a program host'"'"'s on-line data processing center, data representative of media inventory in a media library on the client device and which comprises identification data of individual media items presently contained in the inventory of the media library on the client device;

receiving, at the program host'"'"'s on-line data processing center, data from a plurality of program participants representative of each respective program participant'"'"'s media inventory and which comprises identification data of individual media items presently contained in the respective participant'"'"'s media library regardless of the individual media item'"'"'s source;

determining an incidence of co-occurrence of pairs of individual media items in different program participants'"'"' media libraries;

assigning a similarity rating between the pairs of individual media items based on the determined incidence of co-occurrence in the different program participants'"'"' media libraries;

transmitting, from the program host'"'"'s on-line data processing center to the program participant'"'"'s client device, similarity ratings for a plurality of the individual media items contained in the inventory of the media library on the client device; and

generating a media playlist comprising individual media items contained in the inventory of the media library on the client device and having a similarity rating relative to a seed media item selected from the inventory of media items on the client device.

2. The method as recited in claim 1, wherein the incidence of co-occurrence of pairs of individual media items in different program participants'"'"' media libraries is determined at the program host'"'"'s on-line data processing center.

3. The method as recited in claim 1, wherein the similarity ratings between the pairs of individual media items are assigned at the program host'"'"'s on-line data processing center.

4. The method as recited in claim 3, further comprising:

limiting the compilation of similarity rating data for the individual program participant to similarity rating data between the individual media items contained in that program participant'"'"'s media library.

5. The method as recited in claim 1, further comprising:

receiving from the plurality of program participants data representative of descriptive characteristics of at least a majority of the individual media items contained in the participants'"'"' media libraries.

6. The method as recited in claim 1, further comprising:

assigning to each individual media item contained in the participants'"'"' media libraries a program-sourced identifier based on analysis of respective identification data and thereby permitting direct correlation between substantially identical media items contained in the media libraries of different participants.

7. The method as recited in claim 1, further comprising:

associating data obtained from a third party data source and representative of supplemental descriptive item characteristics with at least a portion of the individual media items.

8. The method as recited in claim 1, further comprising:

receiving, from a program participant, update data representative of that program participant'"'"'s present media inventory, including identification data of additional media items added to the participant'"'"'s media library since an immediately-previous data upload by the participant.

9. The method as recited in claim 8, wherein the program participant'"'"'s update data indicates the absence of media items removed from the participant'"'"'s media library since the immediately-previous data uploaded by the participant.

10. The method as recited in claim 9, further comprising:

recompiling similarity ratings in consideration of said update data.

11. The method as recited in claim 1, wherein said individual media items are movies presently contained in participants'"'"' video media libraries.

12. The method as recited in claim 1, wherein said individual media items are audio tracks presently contained in participants'"'"' audio media libraries.

13. The method as recited in claim 1, wherein said individual media items are music tracks presently contained in participants'"'"' music media libraries.

14. A system for the generation of a media playlist comprising:

at least two client devices each having a storage media device containing a media library of individual media items;

a data processing center having a storage media device configured to store data received from a plurality of program participants'"'"' client devices, and a processor in signal communication with the storage media device configured to execute at least a similarity data generation program that receives representative data from the storage media device, wherein said representative data is from a plurality of program participants'"'"' respective inventories and comprises identification data of individual media items presently contained in the respective participants'"'"' media libraries regardless of the individual media item'"'"'s source;

a communication interface configured to facilitate communication between the client devices and the data processing center, whereby the communication interface transmits identification data representative of the individual media items in the media library regardless of the individual media item'"'"'s source from the client devices and transmits similarity rating data to the client devices.

15. The system as recited in claim 14, wherein the communication interface is further configured to transmit update data.

16. The system as recited in claim 14, wherein at least one of the client devices further includes a processor in signal communication with the communication interface and storage media device and is configured to generate a playlist based at least in part on at least one individual media item and similarity rating data for that item.

17. A computer-readable media having a computer-readable program code for deriving similarity relationships between media items for a program participant based at least in part on media library inventory information provided by a plurality of program participants, the computer program code causing a media playlist generation system to:

transmit, from a plurality of program participants, data representative of the respective program participant'"'"'s media inventory and which comprises identification data of individual media items presently contained in that participant'"'"'s media library regardless of the individual media items'"'"' source;

receive, from a plurality of program participants, data representative of the respective program participant'"'"'s media inventory and which comprises identification data of individual media items presently contained in that participant'"'"'s media library regardless of the individual media items'"'"' source;

determine an incidence of co-occurrence of pairs of individual media items in a population of program participants'"'"' media libraries;

assign a similarity rating between the pairs of individual media items based on the determined incidence of co-occurrence in the different program participants'"'"' media libraries;

compile similarity ratings between co-occurring pairs of at least a majority of the individual media items contained in the media libraries of the plurality of program participants;

compile, for an individual program participant, similarity rating data for at least a majority of the individual media items contained in that program participant'"'"'s media library; and

transmit, to a program participant, similarity rating data compiled for the individual program participant.

18. The computer-readable media recited in claim 17, further comprising computer-readable program code for causing the media playlist generation system to limit the compilation of similarity rating data for the individual program participant to similarity rating data between the individual media items contained in that program participant'"'"'s media library.

19. The computer-readable media recited in claim 17, further comprising computer-readable program code for causing the media playlist generation system to generate a media playlist for the individual program participant comprising individual media items contained in that program participant'"'"'s media library and having a similarity rating relative to a seed media item selected from the participant'"'"'s media library.

20. The computer-readable media recited in claim 19, further comprising computer-readable program code for causing the media playlist generation system to transmit the generated playlist to the program participant.

21. The computer-readable media recited in claim 19, further comprising computer-readable program code for causing the media playlist generation system to play the individual media items in the media playlist.

22. The computer-readable media recited in claim 17, further comprising computer-readable program code for causing the media playlist generation system to generate a media playlist for the individual program participant composed exclusively of individual media items contained in that participant'"'"'s media library and having a similarity rating relative to a seed media item selected from the participant'"'"'s media library.

23. The computer-readable media recited in claim 17, further comprising computer-readable program code for causing the media playlist generation system to transmit, from a program participant, update data representative of that program participant'"'"'s present media inventory, including identification data of additional media items added to the participant'"'"'s media library since an immediately-previous data upload by the participant.

24. The computer-readable media recited in claim 17, wherein the computer-readable program code is parsed onto two or more separate media.

25. The computer-readable media recited in claim 17, wherein the computer-readable program code is contained onto two or more separate media.

26. A method for facilitating media playlist generation for a program participant, said method comprising:

transmitting, from a program participant'"'"'s client device to a program host'"'"'s on-line data processing center, data representative of a media inventory in a media library of the program participant and which comprises identification data of individual media items presently contained in the inventory of the media library; and

transmitting, from the program host'"'"'s on-line data processing center to the program participant'"'"'s client device, media item similarity ratings for respective pairs of individual media items presently contained in the inventory of the media library of the program participant and wherein each media item similarity rating is representative of a frequency at which the respective pair of individual media items has occurred in media libraries of others.

27. The method as recited in claim 26, wherein identification data is transmitted by the program participant'"'"'s client device for at least a majority of the individual media items presently contained in the inventory of the program participant'"'"'s media library and wherein said identification data is transmitted regardless of the source from which the individual media item was obtained by the program participant.

28. The method as recited in claim 27, wherein the media item similarity ratings have been compiled based on cumulative data collected from a plurality of program participants and in which the cumulative data comprised identification data of individual media items contained in media libraries of the program participants regardless of each individual media item'"'"'s source.

29. The method as recited in claim 27, wherein the media item similarity ratings have been compiled based on cumulative data collected from a plurality of program participants and in which the cumulative data comprised identification data of individual media items contained in media libraries of the program participants.

30. The method as recited in claim 29, wherein the compilation of the similarity ratings further comprised processing the cumulative data to determine an incidence of co-occurrence of pairs of individual media items in different program participants'"'"' media libraries and making an assignment of a similarity rating between the pairs of individual media items based on the determined incidence of co-occurrence in the different program participants'"'"' media libraries.