Recommending sports instructional content based on motion sensor data

• US 9,409,074 B2
• Filed: 08/27/2014
• Issued: 08/09/2016
• Est. Priority Date: 08/27/2014
• Status: Active Grant

• Current Assignee: Beijing Shunyuan Kaihua Technology Limited
• Original Assignee: Zepp Labs, Inc. (Zepp Health Corporation)
• Inventors: Han, Zheng, Xu, Jie
• Primary Examiner(s): Chan, Allen
• Application Number:
  US14/470,482
• Publication Number:
  US 20160059103A1
• Time in Patent Office: 713 Days
• Field of Search: 700/91, 463/9, 463/40
• US Class Current: 1/1
• CPC Class Codes: A61B 2503/10 Athletes
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/1121 Determining geometric values, e.g. centre of rotation or angular range of movement
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A63B 69/36 for golf
• CPC Class Codes: G06F 16/78 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06Q 10/0639 Performance analysis of employees; Performance analysis of enterprise or organisation operations
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising

Abstract

A solution is provided for recommending sports video content samples to users of a recommendation service with enhanced user experience. The recommendation service generates voting scores for sports video content samples according to a voting method, and selects from among the sports content samples according to the voting scores for the sports video content samples. The voting method is based on in part on motion data for a user'"'"'s sports motion and the motion data is captured by a motion data device. The sports video content samples, e.g., golf videos, can be classified into multiple classes, e.g., golf swing power related videos, and each class is related to a different aspect of the sports motion.

Claims

1. A computer-implemented method for recommending a sports video content sample related to a user'"'"'s sports motion, the method comprising:

selecting a voting method based on motion data of the user'"'"'s sports motion, the voting method measuring one aspect of the user'"'"'s sports motion, and the motion data captured by at least one motion data device and the motion data characterized by a plurality of motion parameters;

generating a voting score for each sports video content sample of a plurality of sports video content samples according to the selected voting method, a voting score for a sports video content sample indicating a measurement of performance of a player performing a sports motion captured by the sports video content sample;

ranking the plurality of sports video content samples based on the voting scores associated with the plurality of sports video content samples; and

selecting at least one sports video content sample from the plurality of sports video content samples based on the ranking.

2. The computer-implemented method of claim 1, wherein each sports video content sample of the plurality of sports video content samples has an associated sports motion characterized by a plurality of motion parameters.

3. The computer-implemented method of claim 1, wherein the sports motion is a swing of a sports equipment that contacts a ball.

4. The computer-implemented method of claim 3, wherein the swing is one of a swing of a golf club, a swing of a racquet, and a swing of a bat.

5. The computer-implemented method of claim 3, wherein the swing is characterized by a plurality of motion parameters, the motion parameters including a speed of a user'"'"'s hand holding the sports equipment and a speed of the sports equipment.

6. The computer-implemented method of claim 1, wherein the motion data device is attached to a sports equipment.

7. The computer-implemented method of claim 1, wherein the motion data device is attached to a user'"'"'s hand holding a sports equipment.

8. The computer-implemented method of claim 1, wherein the motion data device comprises at least one of the following:

a micro-electromechanical (MEMS) sensor;

an electromyography (EMG) sensor; and

a digital camera.

9. The computer-implemented method of claim 1, wherein the plurality of sports video content samples are classified into different classes, each class relating to a different aspect of the sports motion, and the selected sports video content sample having a highest voting score in the aspect of the sports motion measured by the selected voting method.

10. The computer-implemented method of claim 9, wherein the sports motion is a swing of a golf club, and the classes include at least one of the following:

speed of a head of the golf club;

swing plane of the golf club;

hand plane of the swing;

tempo of the swing;

backswing of the swing;

speed of a hand holding the golf club; and

hip motion.

11. The computer-implemented method of claim 1, wherein at least a portion of the plurality of the sports video content samples are instructional videos illustrating various aspects of the sports motion.

12. The computer-implemented method of claim 1, wherein at least a portion of the plurality of the sports video content samples are videos of professional sports players, coaches or instructors illustrating various aspects of the sports motion.

13. The computer-implemented method of claim 1, further comprising:

generating a plurality of voting scores for each sports video content sample of the sports video content samples according to a plurality of other voting methods;

generating an aggregated voting score for each sports video content sample of the sports video content samples by combining the voting scores of the sports video content sample generated according to the plurality of the other voting methods;

ranking the plurality of sports video content samples based on the aggregated voting scores associated with the sports video content samples; and

selecting one or more sports video content samples from the sports video content samples based on the ranking.

14. The computer-implemented method of claim 13, wherein the plurality of other voting methods include at least one of the following:

a measurement of frequency data associated with each sports video content sample;

a measurement of difference between each sports video content sample and other sports video content samples;

a measurement of consistency of each sports video content sample with respect to other sports video content samples;

a measurement of user ratings of each sports video content sample; and

a measurement of duplication of each sports video content sample.

15. The computer-implemented method of claim 13, wherein generating an aggregated voting score for each sports video content sample of the sports video content samples comprises:

applying scaling factors associated with the plurality of other voting methods, the scaling factor associated with a voting method indicating a relative importance of the voting method, wherein the scaling factors are configurable for different sports motions.

16. A non-transitory computer readable medium storing executable computer program instructions for recommending a sports video content sample related to a user'"'"'s sports motion, the computer program instructions comprising instructions for:

selecting a voting method based on motion data of the user'"'"'s sports motion, the voting method measuring one aspect of the user'"'"'s sports motion, and the motion data captured by at least one motion data device and the motion data characterized by a plurality of motion parameters;

generating a voting score for each sports video content sample of a plurality of sports video content samples according to the selected voting method, a voting score for a sports video content sample indicating a measurement of performance of a player performing a sports motion captured by the sports video content sample;

ranking the plurality of sports video content samples based on the voting scores associated with the plurality of sports video content samples; and

selecting at least one sports video content sample from the plurality of sports video content samples based on the ranking.

17. The computer-readable storage medium of claim 16, wherein each sports video content sample of the plurality of sports video content samples has an associated sports motion characterized by a plurality of motion parameters.

18. The computer-readable storage medium of claim 16, wherein the sports motion is a swing of a sports equipment that contacts a ball, and the swing is one of a swing of a golf club, a swing of a racquet, and a swing of a bat.

19. The computer-readable storage medium of claim 18, wherein the swing is characterized by a plurality of motion parameters, the motion parameters including a speed of a user'"'"'s hand holding the sports equipment and a speed of the sports equipment.

20. The computer-readable storage medium of claim 16, wherein the motion data device is attached to a sports equipment.

21. The computer-readable storage medium of claim 16, wherein the plurality of sports video content samples are classified into different classes, each class relating to a different aspect of the sports motion, and the selected sports video content sample having a highest voting score in the aspect of the sports motion measured by the selected voting method.

22. The computer-readable storage medium of claim 21, wherein the sports motion is a swing of a golf club, and the classes include at least one of the following:

speed of a head of the golf club;

swing plane of the golf club;

hand plane of the swing;

tempo of the swing;

backswing of the swing;

speed of a hand holding the golf club; and

hips motion.

23. The computer-readable storage medium of claim 16, wherein at least a portion of the plurality of the sports video content samples are instructional videos illustrating various aspects of the sports motion.

24. The computer-readable storage medium of claim 16, wherein at least a portion of the plurality of the sports video content samples are videos of professional sports players, coaches or instructors illustrating various aspects of the sports motion.

25. The computer-readable storage medium of claim 16, further comprising computer program instructions for:

generating a plurality of voting scores for each sports video content sample of the sports video content samples according to a plurality of other voting methods;

generating an aggregated voting score for each sports video content sample of the sports video content samples by combining the voting scores of the sports video content sample generated according to the plurality of the other voting methods;

ranking the plurality of sports video content samples based on the aggregated voting scores associated with the sports video content samples; and

selecting at least one sports video content sample from the plurality of sports video content samples based on the ranking.

26. The computer-readable storage medium of claim 25, wherein the plurality of other voting methods include at least one of the following:

a measurement of frequency data associated with each sports video content sample;

a measurement of difference between each sports video content sample and other sports video content samples;

a measurement of consistency of each sports video content sample with respect to other sports video content samples;

a measurement of user ratings of each sports video content sample; and

a measurement of duplication of each sports video content sample.

27. The computer-readable storage medium of claim 25, wherein the computer program instructions for generating an aggregated voting score for each sports video content sample of the sports video content samples comprise instructions for:

applying scaling factors associated with the plurality of other voting methods, the scaling factor associated with a voting method indicating a relative importance of the voting method, wherein the scaling factors are configurable for different sports motions.

28. A computer-implemented method for selecting sports video content samples related to a user'"'"'s sports motion, the method comprising:

receiving a plurality of sports video content samples and a plurality of voting methods, each sports video content sample having a sports motion defined by one or more motion parameters;

applying the plurality of voting methods to each sports video content sample of the plurality of sports video content samples, a voting method applied to a sports video content sample measuring a player'"'"'s performance of performing the sports motion of the sports video content sample;

generating a plurality of voting scores for each sports video content sample of the sports video content samples according to the plurality of voting methods, a voting score of a sports video content sample generated according to a voting method indicating a measurement of the player'"'"'s performance measured by the voting method;

selecting a voting method from the plurality of voting methods based on motion data of the user'"'"'s sports motion captured by at least one motion data device, the motion data characterized by a plurality of motion parameters, and the selected voting method measuring one aspect of the user'"'"'s sports motion;

ranking the plurality of sports video content samples based on the voting scores of the plurality of sports video content samples generated according to the selected voting method; and

selecting one or more sports video content samples for the selected voting method based on the ranking.

29. The method of claim 28, further comprising:

selecting another voting method based on one or more motion parameters describing another aspect of the user'"'"'s sports motion;

generating a voting score for each sports video content sample of the sports video content samples according to the selected another voting method;

ranking the plurality of sports video content samples based on the voting scores associated with the sports video content samples generated according to the selected another voting method; and

selecting one or more sports video content samples from the sports video content samples based on the ranking.

30. The method of claim 28, further comprising:

generating a voting score for a sports video content sample of the plurality of sports video content samples based on a shifted standard deviation of the sports content sample with respect to all other sports video content samples having a same type of sports motion as the sports video content sample.