Method and device for generating a user profile on the basis of playlists

• US 8,490,123 B2
• Filed: 05/26/2004
• Issued: 07/16/2013
• Est. Priority Date: 06/03/2003
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Bodlaender, Maarten Peter, Verhaegh, Wilhelmus Franciscus Johannes, De Mooij, Arnout Michiel
• Primary Examiner(s): Pendleton, Brian
• Assistant Examiner(s): LUONG, ALAN H
• Application Number:
  US10/558,733
• Publication Number:
  US 20060242661A1
• Time in Patent Office: 3,338 Days
• Field of Search: 725/9, 725/14, 725/46, 725/28, 725/47, 725/50, 725/93, 725/116, 725/146, 455/3.06, 455/3.02, 455/154.1, 705/26, 846/12, 386/46, 709/203
• US Class Current: 725/9
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06F 16/4387 by the use of playlists
• 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: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: H04H 60/46 for recognising users' preferences
• CPC Class Codes: H04H 60/47 for recognising genres
• CPC Class Codes: H04H 60/65 for using the result on users' side
• CPC Class Codes: H04N 21/466 Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61
• CPC Class Codes: H04N 21/4661 Deriving a combined profile for a plurality of end-users of the same client, e.g. for family members within a home user profiles in network data switching protocols H04L67/306
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections

Abstract

In a method and device for generating a user profile on the basis of playlists, the user profile is generated on the basis of the user'"'"'s own playlists and properties derived from them. In this way, more playlists are considered in the generation of a user profile, thereby generating a more reliable user profile. Aspects taken into account includes frequency of occurrence, creation date of the playlist, and relation between content items (songs, video, etc.) in one or more playlists.

Claims

1. A method of generating a user profile for a given user from at least one first playlist including a first sequence of content and being associated with the given user and stored on a media device, said method comprising:

automatically searching for the at least one first playlist among a plurality of playlists, wherein the plurality of playlists includes at least one of a second playlist and a third playlist, wherein the second playlist has a second sequence of content and is associated with a different user and the third playlist has a third sequence of content and is associated with the given user, and each playlist of the plurality of playlists including at least one identifying characteristic of content stored on the media device;

analyzing the at least one first playlist and automatically deriving from the at least one analyzed first playlist at least one playlist feature expressing at least one property of the at least one first playlist, the at least one playlist feature comprising an occurrence frequency or at least a content relationship of the plurality of playlists; and

automatically generating a user profile for the given user based on the analyzed at least one first playlist and the derived at least one playlist feature;

wherein at least one of the said searching, analyzing, and generating comprises use of computerized hardware including a processing element.

2. The method as claimed in claim 1, wherein the at least one playlist feature comprises one or more of:

a feature representing tempo variance,

a feature representing a number of different artists,

a feature representing relative tempo difference,

one or more features representing one or more preferred genres,

a feature representing a number of genre changes,

a feature representing the presence or absence of a particular genre change, and

a feature representing the number of true and false genre changes between songs.

3. The method as claimed in claim 1, said method further comprising generating at least one recommended playlist on the basis of said user profile.

4. The method as claimed in claim 3, wherein said generating of at least one recommended playlist comprises use of a Bayesian analysis and recommendation method.

5. The method as claimed in claim 1, wherein the at least one first playlist comprises an ordered list of content items, including songs or videos, and the content items include metadata.

6. The method as claimed in claim 5, wherein the metadata comprises title, artist, genre, tempo and release year.

7. The method as claimed in claim 1, wherein the generated user profile comprises collections of examples of content items, including at least one of:

songs or videos, liked and/or disliked by the user, collections of transitions liked and/or disliked by the user and collections of playlists liked and/or disliked by the user.

8. The method as claimed in claim 1, wherein the user profile further comprises at least one of:

counts and/or percentages of categorical content-metadata in playlists, and variances of numerical content-metadata in playlists.

9. The method as claimed in claim 1, wherein the media device is a jukebox, a set-top box, a TV, a PC, a DVD player, a hard disk recorder, a solid-state device, a radio or a VCR.

10. The method as claimed in claim 1, wherein the at least one first playlist comprises one or more selected from the group of:

a DVD MPEG Program Stream containing picture and sound signal;

a Blu-Ray MPEG Transport Stream containing picture and sound signal;

a CD sound signal;

a given digital audio format;

a given digital movie format;

a given picture format; and

/or

any format capable of causing said media device to emit a picture signal and/or a sound signal.

12. A non-transitory computer readable medium embodying a computer program product comprising program code for performing the method of claim 1 when the computer program is run on a computer.

13. The method of claim 1, further comprising distinguishing between manually created playlists and commercially available playlists.

14. The method of claim 13, wherein the distinguishing is performed by checking for existence of a playlist on the Internet, or by tagging a playlist during manual creation of the playlists.

18. The method of claim 1, wherein the at least one first playlist comprises a plurality of digital media files.

19. The method of claim 13, wherein the distinguishing is performed by checking for existence of a playlist on the Internet.

11. A media device for generating a user profile for a given user from at least one first playlist including a first sequence of content and being associated with the given user and stored on the media device, the media device comprising:

a searching element adapted to automatically search for at least one first playlist associated with the given user among a plurality of playlists, wherein the plurality of playlists includes at least one of a second playlist and a third playlist, wherein the second playlist has a second sequence of content and is associated with a different user and the third playlist has a third sequence of content and is associated with the given user, and each playlist of the plurality of playlists including at least one identifying characteristic of content stored on the media device;

an analyzing element adapted to analyze the at least one firstplay list and automatically derive from the at least one analyzed first playlist at least one playlist feature expressing at least one property of the at least one first playlist, the at least one playlist feature comprising an occurrence frequency or at least a content relationship of the plurality of playlists; and

a generating element adapted to automatically generate the user profile based on the analyzed at least one first playlist and the derived at least one playlist feature.

15. The media device of claim 11, further comprising distinguishing between manually created playlists and commercially available playlists.

16. The media device of claim 15, wherein the analyzing element checks for existence of a playlist on the Internet, or tags a playlist during manual creation.

17. The media device of claim 11, wherein the searching element, the analyzing element, and the generating element are embodied in computerized hardware including a processing element.