System and method for using biometrics to predict and select music preferences

Patent metadata

Field	Value
Publication number	US-9507326-B2
Application number	US-201514837910-A
Country	US
Kind code	B2
Filing date	Aug 27, 2015
Priority date	Oct 25, 2012
Publication date	Nov 29, 2016
Grant date	Nov 29, 2016

Abstract

Systems and methods for using biometrics to select music preference are provided. A system for using biometrics to select music preferences for a user in a vehicle, comprises a music selection module electrically coupled to at least one biometric sensor in the vehicle, wherein the at least one biometric sensor senses a characteristic of the user and outputs data for the sensed characteristic to the music selection module, and wherein the music selection module selects a music selection for the user based on the sensed characteristic data, and a controller module electrically coupled to the music selection module to control playing of the music selection, wherein the controller module receives an output including the music selection from the music selection module.

First claim

We claim:

1. A method for using biometrics to select music preferences for a user in a vehicle, the method comprising:
monitoring the vehicle for an input from a biometric sensor;
determining whether any inputs from the biometric sensor have been detected;
determining whether a music selection is being played;
interpreting the input from the biometric sensor to predict whether the sensory input indicates satisfaction with the music selection being played;
selecting another music selection other than the music selection being played based on the interpretation of the input from the biometric sensor;
categorizing the music selection being played as one the user likes or dislikes based on the interpretation of the input from the biometric sensor; and
analyzing models of biometric data applied on a filter;
wherein the filter outputs a prediction of music selections for the user based on the models; and
wherein the models are developed from reaction variant patterns, and the method further comprises:
respectively categorizing existing reaction variant patterns under different music selections;
detecting uncategorized reaction variant patterns;
determining to which categorized reaction variant patterns the uncategorized reaction variant patterns are closest; and
categorizing the uncategorized reaction variant patterns under the same music selections as their closest categorized reaction variant patterns.

2. The method of claim 1 , further comprising playing the other music selection in place of the music selection being played if it is determined that the sensory input indicates dissatisfaction with the music selection being played, and the categorization of the music selection being played as one the user dislikes.

3. The method of claim 1 , further comprising playing the other music selection after the music selection being played ends in response to a determination that the sensory input indicates satisfaction with the music selection being played, and the categorization of the music selection being played as one the user likes.

4. The method of claim 1 , wherein the input from the biometric sensor comprises at least one of a pulse rate, a body temperature, a facial expression and a body movement.

5. The method of claim 1 , wherein the biometric sensor comprises at least one of a pressure sensor, a motion sensor, a pulse rate sensor, a temperature sensor and a camera.

6. The method of claim 1 , further comprising analyzing environmental data and selecting the other music selection based on the interpretation of the input from the biometric sensor and the environmental data.

7. The method of claim 6 , wherein the environmental data is at least one of a day of a week, a time of the day, weather, season and driving route.

8. The method of claim 1 , further comprising selecting the other music selection based on the interpretation of the input from the biometric sensor and previously analyzed biometric data.

9. The method of claim 1 , further comprising searching at least one of a database and FM frequencies for a matching or similar music selection to the other music selection.

10. The method of claim 9 , wherein the searching is performed according to a music classification pattern.

11. The method of claim 1 , wherein the reaction variant patterns are based on linear combinations of other patterns.

12. The method of claim 1 , wherein the models include personalized user models developed during a training phase.

13. The method of claim 1 , further comprising:
denoting the existing reaction variant patterns as a matrix, wherein the determining to which categorized reaction variant patterns the uncategorized reaction variant patterns are closest comprises determining which music selections most overlap with nonzero entries when solving a linear equation based on the matrix.

14. The method of claim 1 , wherein the input from the biometric sensor comprises at least one of a facial expression and a body movement, and is captured by at least one of a motion sensor and a camera.

15. The method of claim 1 , further comprising:
detecting a conversation between the user and another occupant in the vehicle;
decreasing a volume of the music selection being played based on the detection of the conversation; and
increasing the volume of the music selection being played to a point prior to the decreasing upon detecting ceasing of the conversation.

16. A method for using biometrics to select music preferences for a user in a vehicle, the method comprising:
monitoring the vehicle for an input from a biometric sensor;
determining whether any inputs from the biometric sensor have been detected;
determining whether a music selection is being played;
interpreting the input from the biometric sensor to predict whether the sensory input indicates satisfaction with the music selection being played;
selecting another music selection other than the music selection being played based on the interpretation of the input from the biometric sensor; and
categorizing the music selection being played as one the user likes or dislikes based on the interpretation of the input from the biometric sensor, wherein:
the vehicle includes another user;
the input from the biometric sensor comprises biometric information of the user and the other user; and
the method further comprises determining overlapping music selections liked by both the user and the other user.

17. A method for using biometrics to select music preferences for a user in a vehicle, the method comprising:
monitoring the vehicle for an input from a biometric sensor;
determining whether any inputs from the biometric sensor have been detected;
interpreting the input from the biometric sensor;
analyzing environmental data;
categorizing a music selection being played as one the user likes or dislikes based on the interpretation of the input from the biometric sensor; and
selecting another music selection based on the interpretation of the input from the biometric sensor and the environmental data, wherein:
the vehicle includes another user;
the input from the biometric sensor comprises biometric information of the user and the other user; and
the method further comprises determining overlapping music selections liked by both the user and the other user.

18. A method for using biometrics to select music preferences for a user in a vehicle, the method comprising:
monitoring the vehicle for an input from a plurality of biometric sensors;
determining whether any inputs from the biometric sensors have been detected;
interpreting the inputs from the biometric sensors to develop models of biometric data;
applying and analyzing the models of the biometric data on a filter;
categorizing music selections as those the user likes or dislikes based on the models;
outputting a prediction of music selections for the user based on the models, wherein the models are developed from reaction variant patterns;
respectively categorizing existing reaction variant patterns under different music selections;
detecting uncategorized reaction variant patterns;
determining to which categorized reaction variant patterns the uncategorized reaction variant patterns are closest; and
categorizing the uncategorized reaction variant patterns under the same music selections as their closest categorized reaction variant patterns.

Assignees

• IBM

Inventors

• Caskey Sasha P
• Kanevsky Dimitri
• Maskey Sameer R
• Sainath Tara N

Classifications

• G06F17/30778

  Physics · mapped topic

• G06K9/00926

  Physics · mapped topic

• G06F3/165

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

• G06F17/30764

  Physics · mapped topic

• G05B1/01 Primary

  electric · CPC title