Smart fitness system

Patent metadata

Field	Value
Publication number	US-11514813-B2
Application number	US-201816152527-A
Country	US
Kind code	B2
Filing date	Oct 5, 2018
Priority date	Oct 5, 2018
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

Methods, systems, and computer program products for analysis of movement patterns and corrective actions are provided. Aspects include capturing, via a camera, movement data associated with a user, analyzing the movement data to identify a movement pattern of the user, accessing, from a database, a model movement pattern for the movement pattern of the user, comparing the model movement pattern to the movement pattern of the user, determining a fault in the movement pattern of the user, and displaying, via a display screen, video data comprising a corrected movement pattern for the user based at least on the fault in the movement pattern of the user.

First claim

What is claimed is:

1. A computer-implemented method for analysis of movement patterns and corrective actions, the method comprising:
capturing, via a camera, movement data associated with a user performing a movement pattern;
analyzing the movement data to identify the movement pattern of the user;
accessing, from a database, a model movement pattern for the movement pattern of the user;
comparing the model movement pattern to the movement pattern of the user;
based on determining a fault in the movement pattern of the user, displaying, via a display screen arranged behind a two-way mirror, an alert to the user indicating that the movement pattern of the user is improper; and
responsive to the user acknowledging the alert, displaying, via the display screen arranged behind the two-way mirror, video data comprising a corrected movement pattern for the user, wherein the corrected movement pattern includes an indication of the fault in the movement pattern of the user.

2. The computer-implemented method of claim 1 , wherein capturing the movement data associated with the user is responsive to a detection, by the camera, of a presence of the user within a predefined range of the display screen.

3. The computer-implemented method of claim 1 , further comprising building a user profile comprising one or more characteristics of the user, wherein the model movement pattern is accessed based at least in part on the one or more characteristics of the user.

4. The computer-implemented method of claim 3 , wherein the one or more characteristics of the user comprise height of the user, weight of the user, and age of the user.

5. The computer-implemented method of claim 3 , wherein the one or more characteristics are inputted by the user.

6. The computer-implemented method of claim 3 , wherein the one or more characteristics are determined from the movement data of the user.

7. The computer-implemented method of claim 1 , further comprises:
obtaining historical movement data of the user;
comparing the movement pattern of the user to the historical movement data of the user to identify an improvement to the movement pattern of the user; and
storing the improvement to the movement pattern of the user in a memory.

8. The computer-implemented method of claim 1 , wherein the movement data comprises video of the user performing a physical movement.

9. The computer-implemented method of claim 1 , wherein the movement data comprises one or more images of the user performing a physical movement.

10. The computer-implemented method of claim 1 , wherein the determining the fault in the movement pattern of the user comprises:
extracting, by a machine learning model, a first plurality of features from the movement pattern of the user to generate a first feature vector;
extracting, by the machine learning model, a second plurality of features from the model movement pattern to generate a second feature vector;
comparing the first feature vector to the second feature vector to determine a difference score, wherein the fault is determined based on the difference score exceeding a threshold difference score.

11. The computer-implemented method of claim 1 , further comprising:
operating the camera to adjust at least one characteristic of the camera to capture one or more images of the movement pattern of the user.

12. The computer-implemented method of claim 11 , wherein the at least one characteristic comprises a pan, a tilt, and a zoom for the camera.

13. The computer-implemented method of claim 1 , further comprising:
analyzing the movement pattern of the user to identify a hazardous condition; and
transmitting an alert based on the hazardous condition.

14. The computer-implemented method of claim 1 , wherein the movement pattern comprises an exercise performed by the user.

15. The computer-implemented method of claim 1 , wherein the display screen is arranged behind a mirror.

16. A system for analysis of movement patterns and corrective actions, the system comprising:
a processor communicative coupled to a memory, the processor configured to:
capture, via a camera, movement data associated with a user performing a movement pattern;
analyze the movement data to identify the movement pattern of the user;
access, from a database, a model movement pattern for the movement pattern of the user;
compare the model movement pattern to the movement pattern of the user;
based on a determination that a fault exists in the movement pattern of the user, display, via a display screen arranged behind a two-way mirror, an alert to the user indicating that the movement pattern of the user is improper; and
responsive to the user acknowledging the alert, display, via the display screen arranged behind the two-way mirror, video data comprising a corrected movement pattern for the user, wherein the corrected movement pattern includes an indication of the fault in the movement pattern of the user.

17. The system of claim 16 , wherein the determining the fault in the movement pattern of the user comprises:
extracting, by a machine learning model, a first plurality of features from the movement pattern of the user to generate a first feature vector;
extracting, by the machine learning model, a second plurality of features from the model movement pattern to generate a second feature vector;
comparing the first feature vector to the second feature vector to determine a difference score, wherein the fault is determined based on the difference score exceeding a threshold difference score.

18. A computer program product for analysis of movement patterns and corrective actions, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising:
capturing, via a camera, movement data associated with a user performing a movement pattern;
analyzing the movement data to identify the movement pattern of the user;
accessing, from a database, a model movement pattern for the movement pattern of the user;
comparing the model movement pattern to the movement pattern of the user;
based on determining a fault in the movement pattern of the user, displaying, via a display screen arranged behind a two-way mirror, an alert to the user indicating that the movement pattern of the user is improper; and
responsive to the user acknowledging the alert, displaying, via the display screen arranged behind the two-way mirror, video data comprising a corrected movement pattern for the user, wherein the corrected movement pattern includes an indication of the fault in the movement pattern of the user.

19. The computer program product of claim 18 , further comprises:
obtaining historical movement data of the user;
comparing the movement pattern of the user to the historical movement data of the user to identify an improvement to the movement pattern of the user; and
storing the improvement to the movement pattern of the user in a memory.

20. The computer program product of claim 18 , wherein the determining the fault in the movement pattern of the user comprises:
extracting, by a machine learning model, a first plurality of features from the movement pattern of the user to generate a first feature vector;
extracting, by the machine learning model, a second plurality of features from the model movement pattern to

Assignees

• IBM

Inventors

• Bell Denise
• Jenkins Jana H
• Kusnitz Jeffrey A
• Morales Adriana

Classifications

• G09B19/003 Primary

  Repetitive work cycles; Sequence of movements · CPC title

• G16H20/30

  relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising · CPC title

• A61B5/11

  Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb {(A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721)} · CPC title

• A63B21/0724

  Bar-bells; Hand bars · CPC title

• G09B5/02

  with visual presentation of the material to be studied, e.g. using film strip · CPC title