Auto playlist generator

• US 7,296,031 B1
• Filed: 03/11/2005
• Issued: 11/13/2007
• Est. Priority Date: 05/30/2001
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Platt, John C., Weare, Christopher B., Burges, Christopher, Swenson, Steven E., Zheng, Alice
• Primary Examiner(s): ALAM, SHAHID AL
• Application Number:
  US11/078,625
• Time in Patent Office: 977 Days
• Field of Search: 707/3, 707/10, 707/101, 707/102, 707/5, 707/6, 707/104.1, 715/501.1, 709/203, 709/217, 709/229, 725/39, 725/44, 725/53, 846/01, 846/09, 369/30.38, 386/40, 386/70
• US Class Current: 375/240.12
• 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 lists, the system comprising:

a media library data store that stores client items;

a reference metadata database that stores descriptive metadata associated with client items;

an identifying system operable to associate descriptive metadata with client items; and

a list generation system operably connected to the media library data store and the client item descriptive metadata data store, the list generation system comprising;

a seed item input subsystem adapted to receive at least one seed item;

a similarity subsystem operable to produce a similarity value that characterizes the degree to which a candidate client item and the seed item are similar, wherein the similarity subsystem accepts as inputs a feature vector associated with a candidate user item and a feature vector associated with the seed item and produces a difference vector, where the difference vector can be input to a similarity value generator, the similarity value generator producing the similarity value; and

a list generating subsystem operably connected to the similarity subsystem, the list generating subsystem producing a list based, at least in part, on the degree to which candidate client items are related to the at least one seed item.

2. The system of claim 1 where an item is identifiable by one or more item identifying fields.

3. The system of claim 1 where the at least one seed item is identifiable by one or more item identifying fields.

4. The system of claim 1 where the media library data store, reference metadata database and the list generation system reside on a client computer system.

5. The system of claim 1, where the reference metadata database and the item identifying system reside on a server computer and the list generating system resides on a client computer.

6. The system of claim 1 where the media library data store, the list generation system reside and the reference metadata database reside on a server computer.

7. The system of claim 1 where the similarity value generator accesses one or more similarity value data structures whose values were generated by machine learning techniques to convert the difference vector to the similarity value.

8. The system of claim 7 where the list items are at least one of songs, music videos, movies, documents, books, and images.

9. The system of claim 8 where the item identifying fields comprise at least one of an artist field, a collection field and a title field.

10. The system of claim 9 where list items are songs and the list item 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.

11. The system of claim 10 where a feature vector comprises one or more fields associated with at least one of 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.

12. A computer readable storage medium containing computer executable components for a system that facilitates generating lists, the components comprising:

a seed item input component adapted to receive at least one seed item;

an identifying component adapted to associate descriptive metadata with user items stored in a media library;

a similarity component that produces a similarity value that characterizes the degree to which a candidate user item and the at least one seed item are similar, the similarity component accepts as inputs a feature vector associated with a candidate user item and a feature vector associated with the seed item and produces a difference vector, where the difference vector can be input to a similarity value generator, the similarity value generator producing the similarity value; and

a list generating component that produces a list based, at least in part, on the degree to which candidate client items are related to the at least one seed item.

13. The computer readable medium of claim 12, where the client items are at least one of songs, music videos, movies, documents, books, and images.