Music recommendation based on biometric and motion sensors on mobile device
First Claim
Patent Images
1. A method implemented by a mobile device for music recommendation to a user of the mobile device, the method comprising:
- acquiring one or more measurements from at least one biometric sensor to obtain biometric information of the user;
acquiring at least one measurement from one or more motion sensors to obtain physical motion data of the user;
determining, based on the biometric information, a biometric identifier as a classification of a biometric state of the user;
determining, based on the physical motion data, an activity identifier as a classification of physical motion of the user, wherein the classification of the physical motion is one of a plurality of physical activities;
determining a life index identifier jointly based on the activity identifier and the biometric identifier;
mapping the life index identifier to a mood classifier using a set of initial conditions to generate a music recommendation, wherein the mood classifier identifies at least one mood of a plurality of moods, and wherein the music recommendation includes a music associated with the at least one mood;
recommending the music to the user for playing based on the music recommendation;
updating, using a machine-learning algorithm, the mapping of the life index identifier to the mood classifier based on user feedback, wherein the user feedback indicates a preference of the user regarding previous music recommended to the user; and
recommending future music to the user for playing based on music recommendations via the updated mapping.
1 Assignment
0 Petitions
Accused Products
Abstract
A method implemented by a mobile device for music recommendation to a user of the mobile device, the method comprising acquiring one or more measurements from at least one biometric sensor to obtain biometric information of the user, determining a music based at least in part on the biometric information, and recommending the music to the user for playing.
12 Citations
16 Claims
-
1. A method implemented by a mobile device for music recommendation to a user of the mobile device, the method comprising:
-
acquiring one or more measurements from at least one biometric sensor to obtain biometric information of the user; acquiring at least one measurement from one or more motion sensors to obtain physical motion data of the user; determining, based on the biometric information, a biometric identifier as a classification of a biometric state of the user; determining, based on the physical motion data, an activity identifier as a classification of physical motion of the user, wherein the classification of the physical motion is one of a plurality of physical activities; determining a life index identifier jointly based on the activity identifier and the biometric identifier; mapping the life index identifier to a mood classifier using a set of initial conditions to generate a music recommendation, wherein the mood classifier identifies at least one mood of a plurality of moods, and wherein the music recommendation includes a music associated with the at least one mood; recommending the music to the user for playing based on the music recommendation; updating, using a machine-learning algorithm, the mapping of the life index identifier to the mood classifier based on user feedback, wherein the user feedback indicates a preference of the user regarding previous music recommended to the user; and recommending future music to the user for playing based on music recommendations via the updated mapping. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A mobile device comprising:
a processor configured to couple to at least one biometric sensor and further configured to; acquire one or more measurements from the at least one biometric sensor to obtain biometric information of a user; couple to one or more motion sensors; acquire at least one measurement from the one or more motion sensors to obtain physical motion data of the user; determine, based on the biometric information, a biometric identifier as a classification of a biometric state of the user; determine, based on the physical motion data, an activity identifier as a classification of physical motion of the user, wherein the classification of the physical motion is one of a plurality of physical activities; determine a life index identifier jointly based on the activity identifier and the biometric identifier; map the life index identifier to a mood classifier using a set of initial conditions to generate a music recommendation, wherein the mood classifier identifies at least one mood of a plurality of moods, and wherein the music recommendation includes a music associated with the at least one mood; recommend the music to the user for playing based on the music recommendation; update, using a machine-learning algorithm, the mapping of the life index identifier to the mood classifier based on user feedback, wherein the user feedback indicates a preference of the user regarding previous music recommended to the user; and recommend future music to the user for playing based on music recommendations via the updated mapping. - View Dependent Claims (7, 8, 9, 10, 11)
-
12. A computer program product comprising computer executable instructions stored on a non-transitory computer readable medium such that when executed by a processor cause a mobile device to:
-
acquire one or more measurements from at least one sensor to obtain physical condition data of a user using the mobile device, wherein the physical condition data includes physical motion data and biometric information of the user; determine, based on the biometric information, a biometric identifier as a classification of a biometric state of the user; determine, based on the physical motion data, an activity identifier as a classification of physical motion of the user, wherein the classification of the physical motion is one of a plurality of physical activities; determine a life index identifier jointly based on the activity identifier and the biometric identifier; map the life index identifier to a mood classifier using a set of initial conditions to generate a music recommendation, wherein the mood classifier identifies at least one mood of a plurality of moods, and wherein the music recommendation includes a music associated with the at least one mood; recommend the music to the user for playing based on the music recommendation; update, using a machine-learning algorithm, the mapping of the life index identifier to the mood classifier based on user feedback, wherein the user feedback indicates a preference of the user regarding previous music recommended to the user, and recommend future music to the user for playing based on the music recommendation via the updated mapping. - View Dependent Claims (13, 14, 15, 16)
-
Specification