System and method for dynamic playlist of media

• US 6,748,395 B1
• Filed: 07/13/2001
• Issued: 06/08/2004
• Est. Priority Date: 07/14/2000
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Picker, Saar, Flannery, Frank, Carreno, Michael J.
• Primary Examiner(s): LE, UYEN T
• Application Number:
  US09/905,011
• Time in Patent Office: 1,061 Days
• Field of Search: 707/100, 707/102, 707/104.1, 709/203
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0209 Incentive being awarded or redeemed in connection with the playing of a video game
• CPC Class Codes: G10H 1/0008 Associated control or indicating means
• CPC Class Codes: G10H 2210/036 of musical genre, i.e. analysing the style of musical pieces, usually for selection, filtering or classification
• CPC Class Codes: G10H 2240/131 Library retrieval, i.e. searching a database or selecting a specific musical piece, segment, pattern, rule or parameter set
• CPC Class Codes: H04H 60/06 Arrangements for scheduling broadcast services or broadcast-related services
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A system and methods for the dynamic generation of playlists to a user are provided. In connection with a system that convergently merges perceptual and digital signal processing analysis of media entities for purposes of classifying the media entities, various means are provided to a user for automatically generating playlists of closely related and/or similarly situated media entities for distribution to participating users. Techniques for providing a dynamic recommendation engine and techniques for rating media entities are also included. In an illustrative implementation, the playlists may be generated and stored allowing for user persistence from experience to experience.

Claims

1. A method for dynamically generating target playlists of media comprising the steps of:

defining underlying characteristics of said target playlists using human classification techniques and digital signal processing (DSP) techniques, said underlying characteristics representative of characteristics inherent of desired media;

generating media sets having said defined underlying characteristics; and

merging said media sets according to predefined interactions between perceptual analysis and acoustic DSP analysis to generate said target playlists.

2. The method as recited in claim 1, further comprising weighting the media elements contained in said media sets according to at least one weighting randomization algorithm to generate said target playlists.

3. The method as recited in claim 1, further comprising the step of filtering said target playlists according to predefined restrictions.

4. The method as recited in claim 1, further comprising the step of distributing said generated target playlists to participating users over a network.

5. A dynamic playlist generation process in accordance with the method of claim 1 in which target playlists are dynamically generated responsive to a user request for a playlist, wherein said request contains parameters defining scope of said requested playlist.

6. A dynamic playlist generation process in accordance with the method of claim 1 wherein said interactions used by said merging step comprise at least one of artist, album, song, genre, or sub-genre.

7. A dynamic playlist generation process in accordance with the method of claim 1, further comprising the step of filtering said target playlists according to predefined restrictions, wherein said filter predefined restrictions comprise any of Recording Industry Association of America (RIAA) restrictions and user restrictions.

8. A dynamic playlist generation process in accordance with the method of claim 1 in which said merging step further comprises the step of applying predefined media parameters to merge media entities from said media sets, said media parameters comprising any of tempo, mood, and feel.

9. A computer readable medium bearing computer executable instructions for carrying out the method of claim 1.

10. A modulated data signal carrying computer executable instructions for carrying out the method of claim 1.

11. A computing device comprising means for carrying out each of the steps of the method of claim 1.

12. A system providing dynamic generation of target media playlists comprising:

an object and media parts processing system providing characteristics of target playlists using human classification techniques and digital signal processing (DSP) techniques, said object and media parts processing system executing instructions to categorize media entities into categorization data sets and to define characteristics for said target media playlists,

wherein said categorization data sets generated by said object and media parts processing system contain at least one media element having at least one characteristic in accordance with definitions of said categorization data sets; and

a merge system cooperating with said object and media parts to merge media entities from said generated categorization data sets according to at least one weighted randomization algorithm and perceptual analysis and acoustic DSP analysis to generate said target playlists.

13. The system as recited in claim 12, further comprising a filter system that filters said generated target playlists according to predefined restrictions to remove media entities not satisfying said restrictions.

14. The system as recited in claim 12, wherein said merge system further employs media parameters to generate said target playlists.

15. The system as recited in claim 14, wherein said media parameters comprise any of feel, tempo, and mood.

16. The system as recited in claim 12, wherein said merge system employs interactions among media entities from said categorization data sets to aggregate similar media entities to generate said target playlists.

17. The system as recited in claim 16, wherein said interactions comprise at least one of media entities'"'"' artist, album, song, genre, or sub-genre.

18. The system as recited in claim 14, further comprising a distribution means for leveraging generated target playlists to participating users.

19. A dynamic playlist generation system in accordance with the system as recited in claim 12, wherein said playlist generation is performed responsive to request for at least one media entity from participating users.

20. A method for matching a user'"'"'s musical preferences by dynamically generating at least one playlist in accordance with said user'"'"'s musical preferences, comprising:

providing a specific choice of user preferences in song content to a content provider;

mapping the specific choice of user preferences in a song analysis and matching system using a set of fundamental musical properties that captures the user'"'"'s preferences in song content using human classification techniques and digital signal processing (DSP) techniques;

scanning a database using the song analysis and matching system to find other songs that have a similar mapping of musical properties; and

generating at least one target playlist having media entities that have a similar mapping of musical properties by using predefined interactions between perceptual analysis and acoustic DSP analysis.

21. A one step song personalization process in accordance with the method of claim 20 in which the user requests a particular song which the user finds pleasing and the song analysis and matching system automatically plays a set of songs with similar fundamental musical properties as the chosen song.

22. The method as recited in claim 20, further comprising the step of distributing said generated target playlist to said user.

23. The method as recited in claim 20, wherein said generating step further comprises the steps of:

categorizing media entities according to predefined categorization schemes by a music matching and analysis system responsive to instructions from a calling object to generate categorization data sets, said calling object instructions providing one or more characteristics of said media entities for use in categorization; and

merging said categorization data sets according to at least one weighted randomization algorithm to generate said target playlists.

24. The method as recited in claim 23, further comprising the step of filtering said generated target playlists according to predefined restrictions to remove media entities not satisfying said predefined restrictions.