USER INTERFACE TO MEDIA FILES

• US 20130178962A1
• Filed: 01/06/2012
• Published: 07/11/2013
• Est. Priority Date: 01/06/2012
• Status: Active Grant

• Current Assignee: Gracenote, Inc. (RR Donnelley & Sons Company)
• Original Assignee: Gracenote, Inc. (RR Donnelley & Sons Company)
• Inventors: DiMaria, Peter C., Chen, Ching-Wei, Brenner, Vadim
• Granted Patent: US 8,855,798 B2
• Time in Patent Office: Days
• US Class Current: 700/94
• CPC Class Codes: G06F 16/44 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G10H 2220/131 for abstract geometric visualisation of music, e.g. for interactive editing of musical parameters linked to abstract geometric figures
• CPC Class Codes: G10H 2240/085 Mood, i.e. generation, detection or selection of a particular emotional content or atmosphere in a musical piece

Abstract

A user interface generator is configured to access a media file that stores acoustic data representative of sounds. The user interface generator determines a mood category of the media file, based on a mood vector calculated from the acoustic data. The mood category characterizes the media file as being evocative of a mood described by the mood category. The user interface generator generates a user interface that depicts a grid or map (e.g., a “mood grid” or a “mood map”) of multiple zones. One of the zones may occupy a position in the grid or map that corresponds to the mood category. The user interface may then be presented by the user interface generator (e.g., to a user). In the presented user interface, the zone that corresponds to the mood category may be operable (e.g., by the user) to perform one or more actions pertinent to the mood category.

Claims

1. A method comprising:

accessing a media file from a plurality of media files, the media file storing acoustic data representative of sounds;

determining a mood category of the media file based on a predominant component of a mood vector calculated from the acoustic data representative of the sounds of the media file,

the predominant component of the mood vector being one of multiple components of the mood vector,

the determined mood category characterizing the media file as evocative of a mood described by the mood category;

generating a two-dimensional user interface to the plurality of media files,

the two-dimensional user interface depicting a grid that includes a zone whose position in the grid corresponds to the mood category determined based on the predominant component of the mood vector calculated from the media file,

the generating of the two-dimensional user interface being performed by a processor of a machine; and

presenting the two-dimensional user interface that depicts the grid with the zone whose position corresponds to the mood category.

2. The method of claim 1, wherein:

the determining of the mood category of the media file includes;

summing weights of the multiple components of the mood vector; and

accessing a database that correlates the mood category with a largest weight among the summed weights.

3. The method of claim 1, wherein:

the determining of the mood category of the media file includes accessing a database that correlates the mood category with the predominant component of the mood vector.

4. The method of claim 3, wherein:

the database that correlates the mood category with the predominant component of the mood vector is a first localized database among multiple localized databases that reference the predominant component of the mood vector.

5. The method of claim 1, wherein:

the determining of the mood category of the media file includes accessing a predetermined human-generated lookup table that maps the multiple components of the mood vector to a plurality of mood categories that includes the mood category.

6. The method of claim 1, wherein:

the determining of the mood category of the media file includes accessing a lookup table that correlates the mood category with the position of the zone in the grid.

7. The method of claim 1, wherein:

the presenting of the two-dimensional user interface includes displaying the two-dimensional user interface on a display,

the zone whose position in the grid corresponds to the mood category overlaps an interactive portion of a controller that is operable to initiate an action with respect to the mood category.

8. The method of claim 7, wherein:

the interactive portion of the controller is operable to initiate the action selected from a group consisting of;

generation of a playlist for the mood category,

modification of the playlist for the mood category,

modification of a parameter that defines the playlist for the mood category,

generation of a recommendation from the mood category,

modification of a preference that influences recommendations from the mood category, and

identification of a user related to the mood category.

9. The method of claim 7, wherein:

the interactive portion of the controller is operable to initiate the action with respect to a further mood category that corresponds to a further zone adjacent to the zone in the grid.

10. The method of claim 7, wherein:

the controller is configured to receive at least one of a touch input, a gesture input, or a voice input.

11. The method of claim 7, wherein:

the controller is configured to receive a sequence of inputs that specifies multiple zones in the grid as a selection of multiple mood categories in sequential order.

12. The method of claim 1 further comprising:

generating a playlist based on the mood category,

the playlist identifying a subset of the plurality of media files that includes the media file and characterizing the subset as evocative of the mood described by the mood category,

the playlist corresponding to the zone whose position in the grid corresponds to the mood category; and

presenting the playlist in response to a user-generated selection of the position of the zone within the two-dimensional user interface.

13. The method of claim 1 further comprising:

receiving a user-generated selection of the zone whose position corresponds to the mood category; and

initiating playback of a playlist that references the media file and that corresponds to the mood category,

the initiating of the playback of the playlist being in response to the user-generated selection of the zone.

14. The method of claim 1 further comprising:

receiving a user-generated selection of the zone whose position corresponds to the mood category; and

initiating playback of a representative audio file that is evocative of the mood described by the mood category,

the initiating of the playback of the representative audio file being in response to the user-generated selection of the zone.

15. The method of claim 1, wherein:

the generating of the two-dimensional user interface includes coloring the zone based on a count of media files characterized by the mood category.

16. The method of claim 15, wherein:

the coloring of the zone is based on the count representing a number of new media files characterized by the mood category within a period of time.

17. The method of claim 1, wherein:

the generating of the two-dimensional user interface includes indicating that the zone corresponds to a preferred mood category of a user.

18. The method of claim 1, wherein:

the mood category is identified by a mood descriptor that describes the mood of which the media file is characterized as being evocative; and

the generating of the two-dimensional user interface is based on a set of mood descriptors inclusive of the mood descriptor and localized to a geographic region.

19. The method of claim 1, wherein:

the mood category corresponds to an energy level within a range of energy levels descriptive of musical calmness; and

the grid includes an axis that represents the range of energy levels.

20. The method of claim 19, wherein:

the range of energy levels includes a low energy level that indicates high musical calmness and includes a high energy level that indicates low musical calmness.

21. The method of claim 19 further comprising:

receiving a user-generated selection of the axis for display of the range of energy levels; and

wherein

the generating of the two-dimensional user interface generates the two-dimensional user interface with the axis in response to the user-generated selection of the axis for display.

22. The method of claim 1, wherein:

the mood category corresponds to a valence level within a range of valence levels, the valence level being descriptive of musical darkness; and

the grid includes an axis that represents the range of valence levels.

23. The method of claim 22, wherein:

the range of valence levels includes a low positivity level that indicates a high musical darkness and that includes a high positivity level that indicates a low musical darkness.

24. The method of claim 22 further comprising:

receiving a user-generated selection of the axis for display of the range of valence levels; and

wherein

the generating of the two-dimensional user interface generates the two-dimensional user interface with the axis in response to the user-generated selection of the axis for display.

25. The method of claim 1, wherein:

the generating of the two-dimensional user interface that depicts the grid includes generating the grid as an arrangement of multiple zones that include the zone whose position in the grid corresponds to the mood category; and

the multiple zones of the grid correspond to multiple playlists that identify multiple subsets of the plurality of media files.

26. The method of claim 25, wherein:

the generating of the grid with the multiple zones includes determining a uniform size of the multiple playlists that correspond to the multiple zones; and

generating the multiple playlists based on the uniform size.

27. The method of claim 25, wherein:

the generating of the grid with the multiple zones is based on weather data indicative of weather at a location.

28. The method of claim 25, wherein:

the generating of the grid with the multiple zones is based on speed data indicative of a speed of a vehicle.

29. The method of claim 25, wherein:

the generating of the grid with the multiple zones is based on location data indicative of a location.

30. The method of claim 25, wherein:

the generating of the grid with the multiple zones is based on time data indicative of a time of day at a location.

31. The method of claim 25, wherein:

the generating of the grid with the multiple zones is based on a preference of a user.

32. The method of claim 25, wherein:

the generating of the grid with multiple zones is based on drowsiness data indicative of a level of drowsiness of a driver of a vehicle.

33. The method of claim 32 further comprising:

initiating playback of a playlist among the multiple playlists,

the playlist referencing the media file and corresponding to the mood category that characterizes the media file as evocative of the mood described by the mood category,

the initiating of the playback of the playlist being based on the drowsiness data that indicates the level of drowsiness of the driver of the vehicle.

34. The method of claim 32 further comprising:

generating the drowsiness data from an image that depicts an eye of the driver of the vehicle.

35. The method of claim 34 further comprising:

capturing the image that depicts the eye of the driver from a camera in the vehicle that is pointed at the eye of the driver of the vehicle.

36. The method of claim 1 further comprising:

calculating the mood vector of the media file by performing an analysis of the acoustic data representative of the sounds of the media file; and

determining the predominant component of the mood vector based on the analysis of the acoustic data.

37. The method of claim 36, wherein:

the analysis of the acoustic data that represents the sounds of the media file includes a determination of at least one of a tempo histogram, a chroma histogram, an audio spectrum envelope, an audio spectral flatness, a mel-frequency cepstral coefficient, a modulation of mel-frequency cepstral coefficients, a spectral correlation, a proportion of percussive sounds, a modulation of percussive sounds, a strength of percussive sounds, a strength of non-percussive sounds, a periodicity of percussive sounds, a periodicity of non-percussive sounds, a standard deviation of percussive sounds, a chroma flatness, a chroma eccentricity, a harmonic transition strength, a major key, a minor key, a harmonic feature, a standard deviation of harmonic features, a local tempo, or a standard deviation of local tempos,

the determination being based on the acoustic data that represents the sounds of the media file.

38. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

accessing a media file from a plurality of media files, the media file storing acoustic data representative of sounds;

determining a mood category of the media file based on a predominant component of a mood vector calculated from the acoustic data representative of the sounds of the media file,

the predominant component of the mood vector being one of multiple components of the mood vector,

the determined mood category characterizing the media file as evocative of a mood described by the mood category;

generating a two-dimensional user interface to the plurality of media files,

the two-dimensional user interface depicting a grid that includes a zone whose position in the grid corresponds to the mood category determined based on the predominant component of the mood vector calculated from the media file,

the generating of the two-dimensional user interface being performed by the one or more processors of the machine; and

presenting the two-dimensional user interface that depicts the grid with the zone whose position corresponds to the mood category.

39. The non-transitory machine-readable storage medium of claim 38, wherein the operations further comprise:

generating a playlist based on the mood category,

the playlist identifying a subset of the plurality of media files that includes the media file and characterizing the subset as evocative of the mood described by the mood category,

the playlist corresponding to the zone whose position in the grid corresponds to the mood category; and

presenting the playlist in response to a user-generated selection of the position of the zone within the two-dimensional user interface.

40. A system comprising:

an access module configured to access a media file from a plurality of media files, the media file storing acoustic data representative of sounds;

the category module configured to determine a mood category of the media file based on a predominant component of a mood vector calculated from the acoustic data representative of the sounds of the media file,

the predominant component of the mood vector being one of multiple components of the mood vector,

the determined mood category characterizing the media file as evocative of a mood described by the mood category;

a processor configured by a generation module to generate a two-dimensional user interface to the plurality of media files,

the two-dimensional user interface depicting a grid that includes a zone whose position in the grid corresponds to the mood category determined based on the predominant component of the mood vector calculated from the media file; and

a presentation module configured to present the two-dimensional user interface that depicts the grid with the zone whose position corresponds to the mood category.

41. The system of claim 40 further comprising:

a player module configured to generate a playlist based on the mood category,

the playlist identifying a subset of the plurality of media files that includes the media file and characterizing the subset as evocative of the mood described by the mood category, and

the playlist corresponding to the zone whose position in the grid corresponds to the mood category; and

wherein

the presentation module is configured to present the playlist in response to a user-generated selection of the position of the zone within the two-dimensional user interface.