METHODS AND APPARATUS FOR DETERMINING A MOOD PROFILE ASSOCIATED WITH MEDIA DATA

• US 20100325135A1
• Filed: 06/23/2009
• Published: 12/23/2010
• Est. Priority Date: 06/23/2009
• Status: Active Grant

• Current Assignee: Gracenote, Inc. (RR Donnelley & Sons Company)
• Original Assignee: Gracenote, Inc. (RR Donnelley & Sons Company)
• Inventors: Chen, Ching-Wei, Lee, Kyogu, DiMaria, Peter C., Cremer, Markus K.
• Granted Patent: US 8,805,854 B2
• Time in Patent Office: Days
• US Class Current: 707/759
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/4387 by the use of playlists
• CPC Class Codes: G10H 1/0008 Associated control or indicating means
• CPC Class Codes: G10H 2240/085 Mood, i.e. generation, detection or selection of a particular emotional content or atmosphere in a musical piece
• 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

Abstract

In an embodiment, a method is provided for determining a mood profile of media data. In this method, mood is determined across multiple elements of mood for the media data to create a mood profile associated with the media data. In some embodiments, the mood profile is then used to determine congruencies between one or more pieces of media data.

Claims

1. A method for identifying a congruency of media data, the method comprising:

using a processor to compare a first mood profile digest to a second mood profile digest to produce a measure of similarity representative of a mood relationship between the first and second mood profile digests; and

determining the first and second mood profile digests are congruent based on the measure of similarity and a threshold similarity.

2. The method of claim 1, wherein each mood profile digest is associated with a respective piece of media data and the determination of congruency compares the moods of the media data.

3. The method of claim 2, wherein each mood profile digest is associated with a respective piece of media data, each mood profile digest including a plurality of mood categories and each mood category includes an associated mood score.

4. The method of claim 3, wherein the first piece of media data and the second piece of media data are considered congruent when the first mood score and the second mood score meet the threshold similarity.

5. The method of claim 3, wherein a first piece of media data is associated with the first mood profile digest and a second piece of media data is associated with the second mood profile digest, and wherein the method further comprises:

comparing at least one mood score of the first mood profile digest with at least one mood score of the second mood profile digest.

6. The method of claim 4, wherein the plurality of mood categories and associated mood scores define a mood profile.

7. The method of claim 1, wherein comparing the first mood profile digest with the second mood profile digest further comprises using a correlates matrix to correlate different mood categories.

8. The method of claim 1, wherein comparing the first mood profile digest with the second mood profile digest further comprises using a correlates matrix to determine a first set of one or more normalized values associated with the first mood profile digest and to determine a second set of one or more normalized values associated with the second mood profile digest, and wherein the first and second sets of one or more normalized values are compared to produce the measure of similarity.

9. The method of claim 8, further comprising:

deriving a first composite value from the first set of one or more normalized values and a second composite value from the second set of one or more normalized values; and

calculating the measure of similarity based on a comparison of the first and second composite values.

10. The method of claim 1, further comprising:

communicating at least one audio identifier to a remote location; and

receiving at least one mood profile digest associated with the audio identifier from the remote location.

11. The method of claim 1, wherein the audio data includes a plurality of audio recordings, the method further comprising:

communicating a plurality of audio identifiers to a remote location, each audio identifier identifying an audio recording accessible by a media player;

receiving a plurality of mood profile digests from the remote location, each mood profile digest identifying at least one mood associated with a corresponding audio recording; and

selecting at least the first or the second mood profile digest from the plurality of mood profile digests received from the remote server.

12. The method of claim 11, wherein the each mood profile digest received from the remote location includes a plurality of mood categories, each mood category having an associated mood score.

13. The method of claim 12, wherein the plurality of mood categories received from the remote location is a subset of a total number of mood categories provided at the remote location.

14. The method of claim 1, wherein each mood profile digest includes a plurality of mood categories, each mood category including an associated mood score, the method further comprising comparing mood scores associated with different mood categories when determining the congruency of audio data.

15. The method of claim 1, further comprising using the identified congruency to suggest audio data associated with the second mood profile digest.

16. The method of claim 1, further comprising using the identified congruency to add audio data associated with the second mood profile digest to a playlist.

17. The method of claim 1, further comprising using the identified congruency to retrieve audio data associated with the second mood profile digest from a location.

18. The method of claim 1, wherein the first mood profile digest is associated with a first piece of audio data and the second mood profile digest is associated with a second piece of audio data.

20. The method of claim 1, wherein the first mood profile digest is a first predominant mood category associated with the first piece of audio data and the second mood profile digest is a second predominant mood category associated with the second piece of audio data.

21. The method of claim 1, wherein the first mood profile digest is a subset of a first mood profile and a second mood profile digest is a subset of a second mood profile.

22. The method of claim 1, wherein the first mood profile digest includes the entire first mood profile of a first piece of audio data, and the second mood profile digest includes the entire second mood profile of a second piece of audio data.

23. The method of claim 1, wherein the first mood profile digest is identified pursuant to a user selection.

24. The method of claim 1, wherein the first mood profile digest is derived from a first mood profile and the second mood profile digests is derived from a second mood profile, and wherein the first and second mood profile digests are identified pursuant to a dimensionality reduction technique.

26. Apparatus comprising:

a mood determining module, implemented by a processor, to compare a first mood profile digest to a second mood profile digest of audio data to produce a measure of similarity representative of a mood relationship between the first and second mood profile digests; and

an indicator providing module to identify the congruency between the audio data based on the measure of similarity and a threshold similarity.

27. A method for creating a playlist of media data, the method comprising:

using a processor to compare a first mood profile digest associated with a first piece of media data to a second mood profile digest associated with a second piece of media data to produce a measure of similarity representative of a mood relationship between the first and second pieces of media data;

using a correlates matrix to correlate different mood categories;

identifying a congruency based on the measure of similarity and a threshold similarity; and

adding the second piece of media data to the playlist when the measure of similarity exceeds the threshold similarity.