Mining of user-generated playlists for data regarding relationships between digital works

• US 8,260,656 B1
• Filed: 04/19/2002
• Issued: 09/04/2012
• Est. Priority Date: 04/19/2001
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon.com, Inc.
• Inventors: Snodgrass, Ryan J., Spiegel, Joel R., Harbick, Andrew V.
• Primary Examiner(s): Champagne, Donald L.
• Application Number:
  US10/127,358
• Time in Patent Office: 3,791 Days
• Field of Search: 705/10, 705/14, 705/7.31, 705/7.32, 705/7.33, 705/26.7, 709/203, 709/229
• US Class Current: 705/7.31
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

A computer-implemented service recommends works to a user based on works currently or previously played or downloaded by the user on a player device or based on playlists stored on the player device. The works may be, for example, music files, video files, electronic books, or other digital content for playing by users. A user may thus obtain personalized recommendations that are based on works obtained from sources (web sites, physical CDs, etc.) that are independent of the recommendations system. In one embodiment, the service identifies pairs of works that are related to each other by virtue of the relatively high frequency with which they co-occur on playlists or within play histories of users. The resulting mappings of works to related works are in-turn used to select works to recommend to users.

Claims

1. A computer-implemented method of detecting relationships between digital works, the method comprising:

receiving user-generated playlists from each of a plurality of player devices of each of a plurality of users, each playlist identifying a set of digital works selected by a user for playing;

storing the user-generated playlists in computer storage;

assessing a degree to which a first digital work and a second digital work are related to each other, at least in part, by determining a frequency of co-occurrence of the first and second digital works in the user-generated playlists, wherein said degree is assessed automatically by a system that comprises computer hardware; and

storing a result of the assessment in computer storage.

2. The method of claim 1, wherein the method comprises generating and storing a data value that represents said degree to which the first and second digital works are related.

3. The method of claim 2, further comprising using the data value, and data values representing degrees to which other pairs of digital works are related, to provide personalized recommendations of digital works to users.

4. The method of claim 3, wherein at least some of said personalized recommendations of digital works are provided to the users on pages of a web site that provides functionality for users to purchase digital works.

5. The method of claim 4, wherein the personalized recommendations are additionally based on purchases made by the users via the web site.

6. The method of claim 4, further comprising providing, via said web site, an option for users to expose their respective playlists to other users.

7. The method of claim 1, wherein the player devices include general purpose computing devices that run a player application.

8. The method of claim 1, wherein each user-generated playlist specifies a collection of digital works selected by a user to be played as a single program.

9. The computer-implemented method of claim 1, wherein said method, including receiving and storing the user-generated playlists, assessing said degree, and storing a result of the assessment, is performed by execution of instructions by one or more computing devices.

10. The computer-implemented method of claim 1, wherein assessing said degree to which the first digital work and the second digital work are related comprises determining how many of said user-generated playlists include both the first digital work and the second digital work.

11. A computer system programmed to perform a method comprising:

receiving user-generated playlists from each of a plurality of player devices of each of a plurality of users, each playlist identifying a set of digital works selected by a user for playing;

storing the user-generated playlists in computer storage;

assessing a degree to which a first digital work and a second digital work are related to each other, at least in part, by determining a frequency of co-occurrence of the first and second digital works in the user-generated playlists; and

storing a result of the assessment in computer storage.

12. The computer system of claim 11, further comprising a recommendation system that uses said result, in combination with results of relatedness assessments between other digital works, to select particular digital works to recommend to users, said recommendation system comprising computer hardware.

13. The computer system of claim 12, wherein the computer system is programmed to determine how many of said user-generated playlists include both the first digital work and the second digital work.

14. Physical computer storage that comprises a computer-readable medium, said physical computer storage storing executable instructions that embody a method comprising:

accessing user-generated playlists received from each of a plurality of player devices of each of a plurality of users, each playlist identifying a set of digital works selected by a user for playing;

storing the user-generated playlists in computer storage;

assessing a degree to which a first digital work and a second digital work are related to each other, at least in part, by determining a frequency of co-occurrence of the first and second digital works in the user-generated playlists; and

storing a result of the assessment in computer storage.

15. The physical computer storage of claim 14, wherein the method comprises calculating and storing a data value that represents said degree to which the first and second digital works are related, said data value reflecting how many of said user-generated playlists include both the first digital work and the second digital work.

16. The physical computer storage of claim 14, wherein the method comprises determining how many of the user-generated playlists include both first digital work and the second digital work.

17. The physical computer storage of claim 14, wherein the method further comprises using said result, in combination with results of relatedness assessments between other digital works, to select, via execution of program instructions by computer hardware, particular digital works to recommend to users.

18. The physical computer storage of claim 14, in combination with computer hardware that executes said instructions to perform said method.