# US 2020/0206568 A1 · Posture coaching system and method for weight training by motion pattern

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0206568 A1
- Document ID: US20200206568A1
- Status: Published application
- Kind: A1
- Application number: 16/555,851
- Filed: 2019-08-29
- Published: 2020-07-02
- Earliest claimed: 2018-12-27
- Inventors: Junho Hong; Yoon Jin KIM
- Web page: https://patentgrep.com/patent/US20200206568A1

## CPC

- A63B 24/0006: {Computerised comparison for qualitative assessment of motion sequences or the course of a movement}
- G09B 19/0038: {Sports}
- A63B 21/072: Dumb-bells, bar-bells or the like {, e.g. weight discs having an integral peripheral handle}
- A63B 24/0062: {Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance}
- A63B 2024/0012: {Comparing movements or motion sequences with a registered reference}
- A63B 2024/0068: {Comparison to target or threshold, previous performance or not real time comparison to other individuals}
- A63B 2208/02: posture
- A63B 2220/10: Positions
- A63B 2220/16: Angular positions
- A63B 2220/20: Distances or displacements
- A63B 2220/34: Angular speed
- A63B 2220/40: Acceleration
- A63B 2220/803: Motion sensors
- A63B 2220/833: Sensors arranged on the exercise apparatus or sports implement
- A63B 2220/836: Sensors arranged on the body of the user
- A63B 2220/89: Field sensors, e.g. radar systems
- A63B 2225/50: Wireless data transmission, e.g. by radio transmitters or telemetry
- A63B: APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT (apparatus for passive exercising, massage A61H)
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)

## Abstract

Disclosed is a posture coaching method for weight training, which includes sensing an exercising motion of a user by a sensor module that is attached to a part of the body of the user or exercise equipment gripped by the user for exercising; calculating an inherent angle of the sensor module and a linear acceleration of each axis of a user-based coordinate system based on the user by using the sensed value; analyzing an exercising posture of the user by detecting and classifying a pattern of the linear acceleration and the inherent angle; and generating exercising posture correction data based on the classified pattern.

## Claims

### Claim 1

A posture coaching method for weight training, comprising:
sensing an exercising motion of a user by a sensor module that is attached to a part of the body of the user or exercise equipment gripped by the user for exercising;
calculating an inherent angle of the sensor module and a linear acceleration of each axis of a user-based coordinate system based on the user by using the sensed value;
analyzing an exercising posture of the user by detecting and classifying a pattern of the linear acceleration and the inherent angle; and
generating exercising posture correction data based on the classified pattern.

### Claim 2 (depends on 1)

The posture coaching method for weight training according to claim 1,
wherein the sensor module includes a geomagnetic sensor, a gyro sensor and an acceleration sensor, and
wherein the step of calculating an inherent angle of the sensor module and a linear acceleration of each axis of a user-based coordinate system based on the user includes calculating the inherent angle based on a quaternion calculated based on sensor values measured by the geomagnetic sensor, the gyro sensor and the acceleration sensor.

### Claim 3 (depends on 2)

The posture coaching method for weight training according to claim 2,
wherein the sensor module includes a distance sensor, and
wherein the posture coaching method further comprises:
calculating a distance from a reference surface based on the distance sensor; and
detecting a distance pattern from the reference surface.

### Claim 4 (depends on 2)

The posture coaching method for weight training according to claim 2,
wherein the step of calculating an inherent angle of the sensor module and a linear acceleration of each axis of a user-based coordinate system based on the user includes calculating a front direction of the user according to an initial value sensed by the sensor module and deriving each axis of the user-based coordinate system based on the calculated front direction.

### Claim 5 (depends on 4)

The posture coaching method for weight training according to claim 4,
wherein the front direction is derived to be present on a reference plane of a user-based coordinate system that is derived by the geomagnetic sensor.

### Claim 6 (depends on 4)

The posture coaching method for weight training according to claim 4,
wherein the front direction is derived based on an exercise type input by the user and the sensed initial value.

### Claim 7 (depends on 2)

The posture coaching method for weight training according to claim 2,
wherein the step of analyzing an exercising posture of the user by detecting and classifying a pattern of the linear acceleration and the inherent angle includes:
sensing a first user exercising posture by a motion sensor and the sensor module;
sensing a second user exercising posture by a motion sensor and the sensor module;
obtaining a motion coefficient by calculating through a neural network the data collected in the steps of sensing the first and second user exercising postures by the motion sensor and the sensor module; and
detecting and classifying a pattern of the linear acceleration and the inherent angle based on the motion coefficient.

### Claim 8 (depends on 7)

The posture coaching method for weight training according to claim 7,
wherein the step of obtaining a motion coefficient obtains the motion coefficient by means of backpropagation by inputting the data obtained by sensing the first user exercising posture and the second user exercising posture by the motion sensor into an input terminal of the neural network and inputting the data obtained by sensing the first user exercising posture and the second user exercising posture by the sensor module into an output terminal of the neural network.

### Claim 9

A posture coaching system for weight training, comprising:
a posture measuring module having a sensor module attached to a part of the body of a user or exercise equipment gripped by the user for exercising to sense an exercising motion of the user;
a pattern detecting module configured to calculate an inherent angle of the sensor module and a linear acceleration of each axis of a user-based coordinate system based on the user by using the sensed value and to analyze an exercising posture of the user by detecting and classifying a pattern of the linear acceleration and the inherent angle; and
a posture analyzing module having a guide module configured to generate exercising posture correction data based on the detected and classified pattern.
