Machine-led mood change

Patent metadata

Field	Value
Publication number	US-9792084-B2
Application number	US-201514980650-A
Country	US
Kind code	B2
Filing date	Dec 28, 2015
Priority date	Jan 2, 2015
Publication date	Oct 17, 2017
Grant date	Oct 17, 2017

Abstract

A machine is configured to identify a media file that, when played to a user, is likely to modify an emotional or physical state of the user to or towards a target emotional or physical state. The machine accesses play counts that quantify playbacks of media files for the user. The playbacks may be locally performed or detected by the machine from ambient sound. The machine accesses arousal scores of the media files and determines a distribution of the play counts over the arousal scores. The machine uses one or more relative maxima in the distribution in selecting a target arousal score for the user based on contextual data that describes an activity of the user. The machine selects one or more media files based on the target arousal score. The machine may then cause the selected media file to be played to the user.

First claim

What is claimed is:

1. A method comprising:
accessing, by one or more processors of a machine, play counts that quantify playbacks of media files played for a user, the play counts being accessed from a playback history database of the user;
accessing, by one or more processors of the machine, arousal scores of the media files played for the user, the arousal scores indicating emotional energy levels that are represented within a three-dimensional pleasure-arousal-dominance model of emotional states and are humanly perceivable in the playbacks of the media files;
generating, by one or more processors of the machine, a distribution of the play counts over the arousal scores, the distribution pairing play counts to corresponding arousal scores, the distribution including one or more relative maximum of play counts that each correspond to a different arousal score among the arousal scores;
detecting a biometric measurement of the user via a biometric sensor;
determining, by one or more processors of the machine, a current arousal score of the user based on the biometric measurement of the user;
selecting, by one or more processors of the machine, a target arousal score for the user based on contextual data that describes an activity in which the user is engaged;
identifying, by one or more processors of the machine, a first relative maximum of the one or more relative maximum having a first arousal score closest to the target arousal score and based on the current arousal score of the user; and
selecting, by one or more processors of the machine, a media file for playback to the user based on the media file having an arousal score at or near the first arousal score of the first relative maximum.

2. The method of claim 1 , wherein the biometric measurement includes at least one of:
a force applied by the user to a portion of a car seat,
a frequency at which the force applied by the user to the portion of the car seat fluctuates,
a duration of a blink of an eye of the user,
a frequency at which the eye of the user blinks,
a frequency at which the eye of the user moves,
a blood glucose level of the user,
a heart rate of the user,
a frequency at which the heart rate of the user fluctuates,
a galvanic skin response measurement of the user,
a force applied by the user to a portion of a steering wheel,
a frequency at which the force applied by the user to the portion of the steering wheel fluctuates,
a frequency at which a brake pedal is pressed by the user,
a speed of a vehicle being operated by the user,
a frequency at which the vehicle changes direction,
an electroencephalogram of the user, or
an electrocardiogram of the user.

3. The method of claim 1 , wherein:
the biometric measurement of the user indicates that the user is drowsy;
the contextual data indicates that the activity in which the user is engaged is driving a vehicle; and
the selected target arousal score and the first arousal score that corresponds to the first relative maximum are higher than the current arousal score; and
the identifying of the first relative maximum is based on the first arousal score that corresponds to the first relative maximum being higher than the current arousal score.

4. The method of claim 1 , wherein:
the biometric measurement of the user indicates that the user is agitated;
the contextual data indicates that the activity in which the user is engaged is driving a vehicle; and
the selected target arousal score and the first arousal score that corresponds to the first relative maximum are lower than the current arousal score; and
the identifying of the first relative maximum is based on the first arousal score that corresponds to the first relative maximum play count being lower than the current arousal score.

5. The method of claim 1 , wherein:
the selecting of the media file includes determining that a candidate media file among the media files played for the user has a candidate arousal score within a threshold tolerance of the first arousal score that corresponds to the first relative maximum; and
the selecting of the media file selects the candidate media file based on the candidate arousal score being within the threshold tolerance of the first arousal score that corresponds to the first relative maximum.

6. The method of claim 1 , wherein:
the selecting of the media file includes determining that a candidate media file in a group of media files from which the media files played for the user are absent has a candidate arousal score within a threshold tolerance of the first arousal score that corresponds to the first relative maximum; and
the selecting of the media file selects the candidate media file from the group of media files from which the media files played for the user are absent.

7. The method of claim 1 , wherein the selecting of the target arousal score includes:
detecting the contextual data via a sensor; and
accessing a context database that maps the contextual data to the target arousal score.

8. The method of claim 1 , wherein the identification of the first relative maximum having the first arousal score is based on the first arousal score being between the current arousal score and the target arousal score.

9. The method of claim 8 , wherein the identification of the first relative maximum having the first arousal score is based on a calculated difference between the target arousal score and the current arousal score.

10. The method of claim 8 , wherein 8 the selecting of the first arousal score that corresponds to the first relative maximum play count includes:
calculating differences between the target arousal score and each of the arousal scores that correspond to the relative maximum in the distribution; and
determining a smallest difference among the differences between the target arousal score and each of the arousal scores that correspond to the relative maximum.

11. The method of claim 1 , wherein the selecting of the media file includes:
determining that the first relative maximum play count transgresses a threshold play count; and
selecting the first arousal score that corresponds to the first relative maximum play count based on the first relative maximum play count transgressing the threshold play count.

12. The method of claim 1 , further including causing the selected media file to be played to the user.

13. 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 play counts that quantify playbacks of media files played for a user, the play counts being accessed from a playback history database of the user;
accessing arousal scores of the media files played for the user, the arousal scores indicating emotional energy levels that are represented within a three-dimensional pleasure-arousal-dominance model of emotional states and are humanly perceivable in the playbacks of the media files;
generating a distribution of the play counts over the arousal scores, the distribution pairing play counts to corresponding arousal scores, the distribution including one or more relative maximum of play counts that each correspond to a different arousal score among the arousal scores;
determining a current arousal score of the user based on a biometric measurement of the user detected using a biometric sensor;
selecting a target arousal score for the user based on contextual data that describes an activity in which the user is engaged;
identifying a first relative maximum of the one or more relative maximum having a first arousal score closest t

Assignees

• Gracenote Inc

Inventors

• Vartakavi Aneesh
• Dimaria Peter C
• Gubman Michael
• Cremer Markus K
• Summers Cameron Aubrey
• Tronel Gregoire

Classifications

• G06F16/639 Primary

  using playlists · CPC title

• G06F3/165 Primary

  Management of the audio stream, e.g. setting of volume, audio stream path · CPC title

• G06F17/30772

  Physics · mapped topic

• H04L67/535

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title