Reducing genre metadata

• US 20070094215A1
• Filed: 08/03/2005
• Published: 04/26/2007
• Est. Priority Date: 08/03/2005
• Status: Abandoned Application

• Current Assignee: Delphi Technologies, Inc. (Aptiv PLC)
• Original Assignee: Delphi Technologies, Inc. (Aptiv PLC)
• Inventors: Toms, Mona, Welk, Douglas
• Application Number:
  US11/196,580
• Publication Number:
  US 20070094215A1
• Time in Patent Office: Days
• US Class Current: 706/52
• 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: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/329 on a disc [VTOC]

Abstract

A genre set is reduced from a large set of distinct genre classifications to a smaller set of broader genre classifications. The genre set may be reduced using statistical classification techniques, such as, for example, similarity matrices or may be arbitrarily defined a priori.

Claims

1. A method to classify a plurality of audio files, the method comprising the steps of:

receiving as input metadata associated with the audio files, the metadata comprising a set of original genre entries;

correlating the set of original genre entries with a set of consolidated genre entries, the number of consolidated genre entries being less than the number of original genre entries; and

associating the consolidated genre entries with the audio files as a function of the correlation of the set of original genre entries with the set of consolidated genre entries.

2. The method of claim 1, wherein the step of correlating the set of original genre entries with the set of consolidated genre entries comprises the step of correlating the set of original genre entries with the set of consolidated genre entries using a similarity matrix.

3. The method of claim 1, wherein the step of correlating the set of original genre entries with the set of consolidated genre entries comprises the step of correlating the set of original genre entries with the set of consolidated genre entries using a statistical classification technique.

4. The method of claim 3, wherein the statistical classification technique comprises cluster analysis.

5. The method of claim 4, further comprising the steps of:

identifying a plurality of cluster solutions as a function of the cluster analysis, each cluster solution comprising a candidate set of consolidated genre entries; and

identifying one of the cluster solutions as a preliminary cluster solution.

6. The method of claim 4, further comprising the step of generating a preliminary association of consolidated genre entries with respective original genre entries as a function of the cluster analysis.

7. The method of claim 4, further comprising the steps of:

receiving a user selection of at least one consolidated genre entry of the candidate set of consolidated genre entries; and

changing a level of granularity of the at least one selected consolidated genre entry.

8. A processor-readable medium having processor-executable instructions for:

receiving as input metadata associated with a plurality of audio files, the metadata comprising a set of original genre entries;

correlating the set of original genre entries with a set of consolidated genre entries, the number of consolidated genre entries being less than the number of original genre entries; and

associating the consolidated genre entries with the audio files as a function of the correlation of the set of original genre entries with the set of consolidated genre entries.

9. The processor-readable medium of claim 8, further having processor-executable instructions for correlating the set of original genre entries with the set of consolidated genre entries using a similarity matrix.

10. The processor-readable medium of claim 8, further having processor-executable instructions for correlating the set of original genre entries with the set of consolidated genre entries using a statistical classification technique.

11. The processor-readable medium of claim 10, wherein the statistical classification technique comprises cluster analysis.

12. The processor-readable medium of claim 11, further having processor-executable instructions for:

identifying a plurality of cluster solutions as a function of the cluster analysis, each cluster solution comprising a candidate set of consolidated genre entries; and

identifying one of the cluster solutions as a preliminary cluster solution.

13. The processor-readable medium of claim 11, further having processor-executable instructions for generating a preliminary association of consolidated genre entries with respective original genre entries as a function of the cluster analysis.

14. The processor-readable medium of claim 11, further having processor-executable instructions for:

receiving a user selection of at least one consolidated genre entry of the candidate set of consolidated genre entries; and

changing a level of granularity of the at least one selected consolidated genre entry.

15. An entertainment system comprising:

a media subsystem configured to retrieve data from a data storage medium storing a plurality of audio files;

a microprocessor operatively coupled to the media subsystem and configured to

receive as input metadata associated with the audio files, the metadata comprising a set of original genre entries,

correlate the set of original genre entries with a set of consolidated genre entries, the number of consolidated genre entries being less than the number of original genre entries, and

associate the consolidated genre entries with the audio files as a function of the correlation of the set of original genre entries with the set of consolidated genre entries.

16. The entertainment system of claim 15, wherein the microprocessor is further configured to correlate the set of original genre entries with the set of consolidated genre entries using a similarity matrix.

17. The entertainment system of claim 15, wherein the microprocessor is further configured to correlate the set of original genre entries with the set of consolidated genre entries using a statistical classification technique.

18. The entertainment system of claim 17, wherein the statistical classification technique comprises cluster analysis.

19. The entertainment system of claim 18, wherein the microprocessor is further configured to:

identify a plurality of cluster solutions as a function of the cluster analysis, each cluster solution comprising a candidate set of consolidated genre entries; and

identify one of the cluster solutions as a preliminary cluster solution.

20. The entertainment system of claim 18, wherein the microprocessor is further configured to generate a preliminary association of consolidated genre entries with respective original genre entries as a function of the cluster analysis.

21. The entertainment system of claim 18, wherein the microprocessor is further configured to:

receive a user selection of at least one consolidated genre entry of the candidate set of consolidated genre entries; and

change a level of granularity of the at least one selected consolidated genre entry.