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

• US 20060242661A1
• Filed: 05/26/2004
• Published: 10/26/2006
• 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, De Mooij, Arnout Michiel, Verhaegh, Wilhelmus Franciscus Johannes
• Granted Patent: US 8,490,123 B2
• Time in Patent Office: Days
• 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

This invention relates to a method (and corresponding device) of generating a user profile on the basis of playlists, wherein 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. Additionally, the process (i.e. said method) is automated and uses known information. Aspects taken into account are 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 (22) on a media device (20) which has automatically obtained a first set of playlists comprising at least one playlist belonging to said given user (22), said method comprising the steps of:

analyzing (200) said first set of playlists and deriving a number of playlist features expressing properties of the playlist and

generating (300) the user profile on the basis of said analyzed first set of playlists and said derived playlist features.

2. A method as claimed in claim 1, wherein said method further comprises the step of selecting said first set of playlists from a second set of playlists, the second set of playlists comprising at least one playlist belonging to the user (22).

3. A method as claimed in claim 1, wherein said number of playlist features 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.

4. A method as claimed in claim 1, said method further comprising the step of:

generating (400) at least one recommended playlist on the basis of said user profile.

5. A method as claimed in claim 4, wherein a Bayesian analysis and recommendation method is used.

6. A method as claimed in claim 1, characterized in that each playlist of said first set comprises an ordered list of content items, such as songs or videos, said content items comprising metadata.

7. A method as claimed in claim 6, characterized in that said metadata comprises title, artist(s), genre, tempo and release year.

8. A method as claimed in claim 1, characterized in that said generated user profile comprises collections of examples of content items, such as songs or videos, liked and/or disliked by said user, collections of transitions liked and/or disliked by said user and collections of playlists liked and/or disliked by said user.

9. A method as claimed in claim 1, characterized in that said user profile further comprises counts and/or percentages of categorical content-metadata in playlists, and means and/or variances of numerical content-metadata in playlists.

10. A method as claimed in claim 1, characterized in that said media device is a jukebox, a set-top box, a TV, a PC, a DVD player, a (portable) hard disk recorder, a solid-state device, a radio or a VCR.

11. A method as claimed in claim 1, characterized in that each content item 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 (e.g. MP3, WMA, Real Audio, WAV, etc.);

a given digital movie format (e.g. DivX, DVD/MPEG2, Avi, wmf, MOV, Real Video, etc.);

a given picture format (e.g. JPEG, GIF, BMP, TIFF, etc.); and

/or

any such format that is capable of causing said media device to emit a picture, and/or sound signal, e.g. G72x, aiff, real.

13. A computer system for performing the method as claimed in claim 1.

14. A computer program product comprising program code means stored on a computer-readable medium (23) for performing the method of claim 1 when the computer program is run on a computer.

12. A media device (20) for generating a user profile, the media device (20) automatically having obtained a first set of playlists comprising at least one playlist belonging to said given user (22), the media device (20) comprising:

means (24) for analyzing (200) said first set of playlists and deriving a number of playlist features expressing properties of the whole playlist; and

means (24) for generating (300) the user profile based on said analyzed first set of playlists and said derived playlist features.