Auto playlist generator

• US 6,993,532 B1
• Filed: 05/30/2001
• Issued: 01/31/2006
• Est. Priority Date: 05/30/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Platt, John C., Weare, Christopher B., Burges, Christopher, Zheng, Alice, Swnson, Steven E.
• Primary Examiner(s): ALAM, SHAHID AL
• Application Number:
  US09/870,292
• Time in Patent Office: 1,707 Days
• Field of Search: 707/2, 707/3, 707/10, 707/102, 707/200, 707/104.1, 706/12, 715/532, 846/09
• US Class Current: 707/736
• 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
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: Y10S 707/916 Audio
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• 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 method for generating a list is provided. The system includes a seed item input subsystem, an item identifying subsystem, a descriptive metadata similarity determining subsystem and a list generating subsystem that builds a list based, at least in part, on similarity processing performed on seed item descriptive metadata and user item descriptive metadata and user selected thresholds applied to such similarity processing. The method includes inexact matching between identifying metadata associated with new user items and identifying metadata stored in a reference metadata database. The method further includes subjecting candidate user items to similarity processing, where the degree to which the candidate user items are similar to the seed item is determined, and placing user items in a list of items based on user selected preferences for (dis)similarity between items in the list and the seed item.

Claims

1. A system that facilitates generating one or more lists, the system comprising:

a user data store that stores user items;

an identifying system that associates descriptive metadata with user items; and

a list generation system to receive at least one seed item generated from descriptive metadata associated with a selected user item, the list generation system analyzing the at least one seed item at least in part by comparing the at least one seed item to one or more candidate items generated from the descriptive metadata associated with the user items to determine a degree of similarity between the at least one seed item and the one or more candidate items, wherein the analysis is facilitated by a similarity subsystem designed at least in part by a machine learning technique that learns from descriptive metadata associated with a training set of items, the list generation system outputting one or more lists corresponding to a subset of user items that are similar to the selected user item.

2. The system of claim 1 where the user data store resides on a client computing system.

3. The system of claim 2 where the list generation system resides on the client computing system.

4. The system of claim 1 where the one or more list items are songs.

5. The system of claim 4 where the songs are identifiable by at least one of an artist name, an album name and a track name.

6. The system of claim 5 where the descriptive metadata comprises information concerning at least one of a genre, a subgenre, a style, a mood, a vocal coding, a rhythm type and a rhythm description.

7. The system of claim 6 where the list corresponding to the subset of user items is a song playlist.

8. The system of claim 1 where the list items comprise at least one of movies, documents, books, music videos and sound recordings.

9. The system of claim 1, wherein the identifying system associates descriptive metadata with user items by performing inexact matching between identifying metadata associated with a user item to be added to a media library and identifying metadata associated with items in a reference metadata database.

10. A computer implemented method for generating one or more lists, the method comprising:

providing a plurality of metadata attributes relating to the content of a media object;

generating a seed feature vector from the plurality of metadata attributes;

providing at least one candidate feature vector, the at least one candidate feature vector generated from metadata relating to the content of a candidate object;

comparing the seed feature vector to the at least one candidate feature vector according to a similarity function, wherein the similarity function is determined at least in part by a machine leaning algorithm employing metadata attributes of a test set of media objects and wherein the similarity function returns an output indicative of the degree of similarity between the seed feature vector and the at least one candidate feature vector; and

generating a list of candidate items based on the output of the similarity function.

11. The method of claim 10, wherein comparing the seed feature vector to the candidate feature vector comprises producing a difference vector.

12. The method of claim 10, wherein the seed feature vector has at least 7 subjective metadata attributes.

13. The method of claim 11, wherein the at least 7 subjective metadata attributes comprise a genre attribute, a subgenre attribute, a style attribute, a mood attribute, a vocal coding attribute, a rhythm type attribute and a rhythm description attribute.

14. The method of claim 10, wherein the machine learning algorithm utilizes a sparse quadratic program.

15. Computer-executable instructions for implementing the method of claim 10 stored on computer-readable storage media.

16. A data packet stored on a storage medium, the data packet comprising computer executable instructions for performing the method of claim 10.