CLIENT PLAYLIST GENERATION

• US 20110087665A1
• Filed: 10/12/2009
• Published: 04/14/2011
• Est. Priority Date: 10/12/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Weare, Christopher B.
• Granted Patent: US 8,572,098 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: G06F 16/4387 by the use of playlists
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• 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

Abstract

Client playlist generation is described. In embodiments, relationships between media assets are determined to identify similar media assets that can be included in an automatic playlist of the similar media assets. Projection vectors of the asset-to-asset relationships can be generated for each of the media assets, where a projection vector for a media asset identifies the similar media assets. The projection vectors are then communicated to a client device that utilizes the projection vectors to generate the automatic playlist for any one of the media assets that is selected as a starting media asset of the automatic playlist.

Claims

1. A computer-implemented method, comprising:

determining asset-to-asset relationships to identify similar media assets that can be included in an automatic playlist of the similar media assets;

generating projection vectors of the asset-to-asset relationships for each of the media assets, a projection vector for a media asset identifying the similar media assets; and

communicating the projection vectors to a client device that is configured to utilize the projection vectors to generate the automatic playlist for any one of the media assets that is selected as a starting media asset of the automatic playlist.

2. A computer-implemented method as recited in claim 1, wherein the media assets are at least one of digital files of music tracks, books stored as digital media, or video programs.

3. A computer-implemented method as recited in claim 1, further comprising utilizing random projection to generate the projection vectors of the asset-to-asset relationships for each of the media assets.

4. A computer-implemented method as recited in claim 1, wherein the media assets are music tracks stored for playback at the client device, and wherein the method further comprises:

determining track-to-track relationships to identify similar music tracks that can be used for generation of the automatic playlist of the similar music tracks;

generating the projection vectors of the track-to-track relationships for each of the music tracks, the projection vector for a music track identifying the similar music tracks; and

communicating the projection vectors to the client device that is configured to utilize the projection vectors to generate the automatic playlist for any one of the music tracks that is selected as a starting music track of the automatic playlist.

5. A computer-implemented method as recited in claim 4, further comprising receiving a request from the client device for the projection vectors that are generated at a music service provider;

and

wherein the client device is further configured to utilize the projection vectors to generate the automatic playlist when off-line from the music service provider.

6. A computer-implemented method as recited in claim 5, further comprising:

receiving the automatic playlist from the client device after the automatic playlist is generated; and

determining additional music tracks that are related to the similar music tracks in the automatic playlist, wherein the additional music tracks are not stored for playback at the client device.

7. A computer-implemented method as recited in claim 4, further comprising utilizing random projection to generate the projection vectors of the track-to-track relationships for each of the music tracks.

8. A computer-implemented method as recited in claim 7, wherein a projection vector for a music track is generated based on a weighted similarity measure between the music track and each of the similar music tracks.

9. A computer-implemented method as recited in claim 7, further comprising generating the projection vector for the music track by initializing the projection vector of a dimension length, and for each of the similar music tracks:

generating a random number from a track identifier that is unique to each of the similar music tracks;

generating a product by multiplying the random number by a weight of the track-to-track relationship between the music track and the similar music track; and

adding the product to the projection vector at a next position index in the projection vector.

10. A computer-implemented method as recited in claim 1, further comprising:

updating the asset-to-asset relationships to include the additional media assets;

generating additional projection vectors of the asset-to-asset relationships for each of the additional media assets; and

communicating the additional projection vectors to update the client device for the additional media assets.

11. A music service provider, comprising:

storage media configured to maintain media asset relationship data that identifies music tracks;

a communication device configured to communicate projection vectors to a client device that is configured to utilize the projection vectors to generate an automatic playlist for any one of the music tracks that is selected as a starting music track of the automatic playlist;

at least a memory and a processor that implement an asset model generation service configured to;

determine track-to-track relationships from the media asset relationship data to identify similar music tracks that can be included in the automatic playlist of the similar music tracks; and

generate the projection vectors of the track-to-track relationships for each of the music tracks, a projection vector for a music track identifying the similar music tracks.

12. A music service provider as recited in claim 11, wherein the asset model generation service is further configured to utilize random projection to generate the projection vectors of the track-to-track relationships for each of the music tracks.

13. A music service provider as recited in claim 12, wherein a projection vector for a music track is generated based on a weighted similarity measure between the music track and each of the similar music tracks.

14. A music service provider as recited in claim 12, wherein the asset model generation service is further configured to generate the projection vector for the music track by initializing the projection vector of a dimension length, and for each of the similar music tracks:

generate a random number from a track identifier that is unique to each of the similar music tracks;

generate a product by multiplying the random number by a weight of the track-to-track relationship between the music track and the similar music track; and

add the product to the projection vector at a next position index in the projection vector.

15. A music service provider as recited in claim 11, wherein the asset model generation service is further configured to:

receive the automatic playlist from the client device after the automatic playlist is generated; and

determine additional music tracks that are related to the similar music tracks in the automatic playlist, wherein the additional music tracks are not stored for playback at the client device.

16. A client device, comprising:

a storage media configured to maintain a library of music tracks and projection vectors of track-to-track relationships for each of the music tracks, a projection vector for a music track identifying similar music tracks;

at least a memory and a processor that implement a playlist generator configured to;

communicate a request to a music service provider for the projection vectors when the client device is on-line and configured for communication with the music service provider; and

utilize the projection vectors to generate an automatic playlist for any one of the music tracks that is selected as a starting music track of the automatic playlist, the automatic playlist configured to be generated when the client device is off-line from the music service provider.

17. A client device as recited in claim 16, wherein the playlist generator is further configured to calculate the distances between the starting music track and the similar music tracks using the projection vectors for each music track to generate the automatic playlist.

18. A client device as recited in claim 16, wherein the projection vectors are received from the music service provider that generates the projection vectors of the track-to-track relationships for each of the music tracks by random projection.

19. A client device as recited in claim 18, wherein a projection vector for a music track is generated based on a weighted similarity measure between the music track and each of the similar music tracks.

20. A client device as recited in claim 16, wherein the playlist generator is further configured to communicate the automatic playlist to the music service provider after the automatic playlist is generated, where the music service provider is configured to determine additional music tracks that are related to the similar music tracks in the automatic playlist, wherein the additional music tracks are not stored for playback at the client device.