Exercise evaluation improvement system, and exercise evaluation improvement method
AssigneeNippon Telegraph and Telephone Corporation
InventorsShingo Tsukada, Hiroshi Nakashima, Tetsuomi Sogawa
Life of this patent
Estimating the term…
Abstract
An exercise rating and improvement system comprising: a feature amount extraction unit for extracting, from information obtained from a subject, a feature amount about exercise efficiency; an rating unit for rating exercise efficiency of the subject by comparing the extracted feature amount and a feature amount to be compared; and an improvement information providing unit for providing, on the basis of the rating result, information such that the feature amount of the subject approaches the feature amount to be compared.
Claims20
A computer-implemented method for rating an operation using electrical signals, the method comprising:
- receiving the electrical signals from one or more sensors attached to a subject exercising a sport, wherein the electrical signals are associated with the subject in operation associated with exercising the sport, the electrical signals relating to one or more of biological data and movement data of the subject represented by the electrical signals from the one or more sensors attached to the subject while exercising the sport;
- extracting from the electrical signals associated with the subject exercising the sport, based on a trained machine learning model, a feature amount of exercise efficiency of the subject exercising the sport, wherein the trained machine learning model is trained using supervised training data associated with an advanced player exercising the sport, wherein the supervised training data includes the feature amount of the exercise efficiency of the subject indicating rating indices corresponding to at least one of motion, position, timing between motions, strength, or tension associated with exercising the sport, and wherein the advanced player is distinct from the subject;
- determining a rating associated with the exercise efficiency of the subject based at least on a comparison between the feature amount of the exercise efficiency of the subject and a target feature amount of exercise efficiency associated with the advanced player exercising the sport;
- generating information associated with the rating including the exercise efficiency of the subject, wherein the information is associated with eliminating a difference between the feature amount of the exercise efficiency of the subject and the target feature amount of exercise efficiency;
- and
- outputting at least one of sound or light based on the rating associated with the exercise efficiency of the subject and the information.
A system for rating an operation using electrical signals, the system comprising:
- a processor;
- and
- a memory storing computer-executable instructions that when executed by the processor cause the system to:
- receive the electrical signals from one or more sensors attached to a subject exercising a sport, wherein the electrical signals are associated with the subject in operation associated with exercising the sport, the electrical signals relating to one or more of biological data and movement data of the subject represented by the electrical signals from the one or more sensors attached to the subject while exercising the sport;
- extract from the electrical signals associated with the subject exercising the sport, based on a trained machine learning model, a feature amount of exercise efficiency of the subject exercising the sport, wherein the trained machine learning model is trained using supervised training data associated with an advanced player exercising the sport, wherein the supervised training data includes the feature amount of the exercise efficiency of the subject indicating rating indices corresponding to at least one of motion, position, timing between motions, strength, or tension associated with exercising the sport, and wherein the advanced player is distinct from the subject;
- determine a rating associated with the exercise efficiency of the subject based at least on a comparison between the feature amount of the exercise efficiency of the subject and a target feature amount of exercise efficiency associated with the advanced player exercising the sport;
- generate information associated with the rating including the exercise efficiency of the subject, wherein the information is associated with eliminating a difference between the feature amount of the exercise efficiency of the subject and the target feature amount of exercise efficiency associated with the advanced player exercising the sport;
- and
- output at least one of sound or light based on the rating associated with the exercise efficiency of the subject and the information.
A computer-readable non-transitory recording medium storing computer-executable instructions that when executed by a processor cause a computer system to:
- receive electrical signals from one or more sensors attached to a subject exercising a sport, wherein the electrical signals are associated with the subject in operation associated with exercising the sport, the electrical signals relating to one or more of biological data and movement data of the subject represented by the electrical signals from the one or more sensors attached to the subject while exercising the sport;
- extract from the electrical signals associated with the subject exercising the sport based on a trained machine learning model, a feature amount of exercise efficiency of the subject exercising the sport, wherein the trained machine learning model is trained using supervised training data associated with an advanced player exercising the sport, wherein the supervised training data includes the feature amount of the exercise efficiency of the subject indicating rating indices associated with exercising the sport, and wherein the advanced player is distinct from the subject determine a rating associated with the exercise efficiency of the subject based at least on a comparison between the feature amount of the exercise efficiency of the subject and a target feature amount of exercise efficiency associated with the advanced player exercising the sport;
- generate information associated with the rating including the exercise efficiency of the subject, wherein the information is associated with eliminating a difference between the feature amount of the exercise efficiency of the subject and the target feature amount of exercise efficiency;
- and
- output at least one of sound or light based on the rating associated with the exercise efficiency of the subject and the information.
Dependencies are inferred from the claim text.