System and method for biometrics-based music recommendation

• US 10,078,691 B2
• Filed: 12/27/2013
• Issued: 09/18/2018
• Est. Priority Date: 12/27/2013
• Status: Active Grant

• Current Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Futurewei Technologies Incorporated (Huawei Investment & Holding Co., Ltd.)
• Inventors: Zhang, Jianyu, Chong, Chia Chin
• Primary Examiner(s): Chen, Alan S
• Application Number:
  US14/142,249
• Publication Number:
  US 20150186780A1
• Time in Patent Office: 1,726 Days
• CPC Class Codes: G06F 16/636 by using biological or physiological data
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

Abstract

Embodiments are provided herein for providing biometrics-based music recommendations to users. The biometric-based music recommendations take into account the changing music preferences of users from time to time as their biometrics change, such as due to users wellness states, being in different moods, engagement in different activities, and/or entering different environments. The schemes herein are implemented on user devices equipped or coupled to wearable devices capable of collecting biometrics data from users, such as heart rate, perspiration, and skin temperature data. The biometrics data of a user are collected and then processed into biometrics information. The biometrics information is then classified into a current wellness state of the user. A music recommendation is then provided to the user according to the biometrics information and the current wellness state of the user.

Claims

1. A method by a user device for providing biometrics based music recommendation to a user, the method comprising:

determining biometrics information for the user according to physical biometrics data of the user;

classifying the biometrics information into a current user biometric identifier representing a current music-independent physically-based wellness state of the user;

classifying a current or recent user music selection by the user into a current user mood classifier representing a current user emotional mood;

mapping the current user biometric identifier to the current user mood classifier; and

providing a music recommendation to the user according to the mapping between the current user biometric identifier and the current user mood classifier, the current user biometric identifier and the current user mood classifier being different from each other.

2. The method of claim 1 further comprising collecting the physical biometrics data using a biometric sensor embedded in the user device.

3. The method of claim 1 further comprising receiving, at the user device, the physical biometrics data from a separate device comprising a biometric sensor via a connection between the user device and the separate device.

4. The method of claim 1, wherein classifying the biometrics information into the current user biometric identifier includes selecting the current user biometric identifier from a plurality of biometric identifiers representing a plurality of corresponding predefined music-independent physically-based wellness states of the user.

5. The method of claim 4, wherein providing the music recommendation to the user according to the current user biometric identifier and the current user mood classifier includes providing the current user biometric identifier and the current user mood classifier to a music recommender.

6. The method of claim 1, wherein classifying the current or recent user music selection by the user into a current user mood classifier includes selecting the current user mood classifier from a plurality of mood classifiers representing a plurality of corresponding predefined user emotional moods.

7. The method of claim 1, further comprising learning a mapping between user biometrics identifiers and user mood classifiers according to music selection feedback and behavior of the user.

8. The method of claim 1, further comprising changing the music recommendation to the user from time to time according to changes in at least one of the current user mood classifier or the physical biometrics data.

9. A method by a user device for providing biometrics based music recommendation to a user, the method comprising:

receiving a current user biometric identifier representing a current music-independent physically-based wellness state of the user based on physical biometrics data for the user;

receiving a current user mood classifier representing a current emotional mood of the user based on a current or recent user music selection by the user;

determining a music recommendation according to a predefined mapping between the current user mood classifier and the current user biometric identifier, the current user biometric identifier and the current user mood classifier being different from each other; and

indicating the music recommendation to the user.

10. The method of claim 9 further comprising establishing the predefined mapping between the current user biometric identifier and the current user mood classifier in accordance with music preferences and learning a music selection behavior of the user.

11. The method of claim 9 further comprising:

receiving the physical biometrics data collected from one or more biometric sensor devices;

determining biometrics information of the user according to the physical biometrics data; and

classifying the biometrics information into the current user biometric identifier representing the current music-independent physically-based wellness state of the user.

12. The method of claim 9 further comprising:

collecting music files from one or more user storages; and

classifying, using audio analysis, the music files into mood-based classifications representing emotional moods of the user.

13. A user device for providing biometrics based music recommendation to a user, the user device comprising:

at least one processor; and

a non-transitory computer readable storage medium storing programming for execution by the at least one processor, the programming including instructions to;

determine biometrics information for the user according to physical biometrics data of the user;

classify the biometrics information into a current user biometric identifier representing a current music-independent physically-based wellness state of the user;

classify a current or recent user music selection by the user into a current user mood classifier representing a current user emotional mood;

mapping the current user biometric identifier to the current user mood classifier; and

provide a music recommendation to the user according to the mapping between the current user biometric identifier and the current user mood classifier, wherein the current user biometric identifier and the current user mood classifier are different from each other.

14. The user device of claim 13, wherein the user device further comprises an embedded biometric sensor, and wherein the programming includes further instructions to collect the physical biometrics data using the embedded biometric sensor.

15. The user device of claim 14, wherein the embedded biometric sensor is one of a temperature sensor, a heart rate sensor, or a sweat sensor.

16. The user device of claim 13, wherein the user device is connected to a separate device with biometric sensing capability, and wherein the programming includes further instructions to receive the physical biometrics data from the separate device.

17. The user device of claim 13, wherein the programming includes further instructions to learn a mapping between user biometric identifiers and user mood classifiers according to music selection feedback and behavior of the user.

18. The user device of claim 17, wherein the instructions to determine the current user emotional mood according to current or recent user music selection includes instructions to:

collect music files from one or more user storages; and

classify, using audio analysis, the music files into mood-based classifications representing emotional moods of the user.