US-12616892-B2 - Information processing device, information processing method, and non-transitory computer-readable storage medium storing program

US12616892B2US 12616892 B2US12616892 B2US 12616892B2US-12616892-B2

Abstract

An information processing device includes a control unit, provided that information indicating evaluation about a first exercise is evaluation information, inputting input information including the evaluation information about a first person and respective pieces of the evaluation information about a plurality of model persons to a trained machine learning model being configured to, when the input information is input, output model person information indicating a model person appropriate for a goal of the first person among the plurality of model persons, and outputting output information including the model person information output from the machine learning model.

Inventors

Shinichi Kobayashi

Assignees

SEIKO EPSON CORPORATION

Dates

Publication Date: 20260505
Application Date: 20230817
Priority Date: 20220818

Claims (11)

1 . An information processing device comprising a control unit configured to, provided that information indicating evaluation about a first exercise is evaluation information, input information including the evaluation information about a first person and respective pieces of the evaluation information about a plurality of model persons to a machine learning model trained, and output information including model person information indicating a model person, among the plurality of model persons, corresponding to similar evaluation information output from the machine learning model, the machine learning model being configured to, when the input information is input, output, as the similar evaluation information, a piece of the evaluation information that, among the respective pieces of the evaluation information about the plurality of model persons, is estimated to be most easily approachable by the evaluation information about the first person; a motion capture sensor configured to detect movement data of a human body performing the first exercise; and a myoelectric sensor configured to detect electrical activity data from at least one part of the human body during performance of the first exercise, wherein the control unit is further configured to generate the evaluation information as waveform data based on the movement data from the motion capture sensor and the electrical activity data from the myoelectric sensor, and the machine learning model is trained using evaluation change information indicating changes in evaluation information resulting from users performing different training exercises, the machine learning model being configured to output the evaluation information that is estimated to be most achievable by the first person based on the evaluation change information.
2 . The information processing device according to claim 1 , wherein when the input information is input, the machine learning model outputs practice menu information indicating a practice menu appropriate for the first person among a plurality of practice menus for the first exercise, together with the model person information.
3 . The information processing device according to claim 1 , wherein information indicating an attribute is used as attribute information, and each of the plurality of model persons is associated with the attribute information about the model person, and the control unit identifies one or more model persons associated with the attribute information matching the attribute information about the first person from among the plurality of model persons in accordance with a received operation, and generates the input information including the evaluation information about each of the one or more model persons identified and the evaluation information about the first person.
4 . The information processing device according to claim 3 , wherein the attribute information includes at least one of age group information indicating an age group or physique information indicating a physique.
5 . The information processing device according to claim 1 , wherein the evaluation change information indicates changes in the evaluation information caused by respective practices of a plurality of practice menus for the first exercise.
6 . The information processing device according to claim 5 , wherein the evaluation information includes waveform data indicating how to use a human body for an action to be analyzed in the first exercise, the evaluation change information indicates a change caused in the waveform data, and when the input information is input, the machine learning model identifies, from among respective pieces of the waveform data about the plurality of model persons, the waveform data most easily approachable by the waveform data about the first person included in the input information that is input, and identifies, as the similar evaluation information, the evaluation information including the waveform data identified.
7 . The information processing device according to claim 6 , wherein the waveform data is data based on first information about a movement of an object for the action and second information about how to use a first part of the human body in the action, and the object is the human body or a tool used in the first exercise.
8 . The information processing device according to claim 6 , wherein the waveform data includes first waveform data based on first information about a movement of an object for the action and second information about how to use a first part of the human body in the action, and second waveform data based on the first information and third information about how to use a second part of the human body in the action, and the object is the human body or a tool used in the first exercise.
9 . The information processing device according to claim 1 , wherein when the input information is input and the evaluation information about a second person different from the first person is included in the input information, the machine learning model outputs the similar evaluation information indicating evaluation different from evaluation indicated by the similar evaluation information output when the evaluation information about the first person is included in the input information.
10 . An information processing method comprising: provided that information indicating evaluation about a first exercise is evaluation information, inputting input information including the evaluation information about a first person and respective pieces of the evaluation information about a plurality of model persons to a machine learning model trained, and outputting output information including model person information indicating a model person, among the plurality of model persons, corresponding to similar evaluation information output from the machine learning model, the machine learning model being configured to, when the input information is input, output, as the similar evaluation information, a piece of the evaluation information that, among respective pieces of the evaluation information of the plurality of model persons, is estimated to be most easily approachable by the evaluation information about the first person; detecting, by a motion capture sensor, movement data of a human body performing the first exercise; detecting, by a myoelectric sensor, electrical activity data from at least one part of the human body during performance of the first exercise; and generating the evaluation information as waveform data based on the movement data and the electrical activity data, wherein the machine learning model is trained using evaluation change information indicating changes in evaluation information resulting from users performing different training exercises, the machine learning model being configured to output the evaluation information that is estimated to be most achievable by the first person based on the evaluation change information.
11 . A non-transitory computer-readable storage medium storing a program, the program causing a computer to execute: provided that information indicating evaluation about a first exercise is evaluation information, inputting input information including the evaluation information about a first person and respective pieces of the evaluation information about a plurality of model persons to a machine learning model trained, and outputting output information including model person information indicating a model person, among the plurality of model persons, corresponding to similar evaluation information output from the machine learning model, the machine learning model being configured to, when the input information is input, output, as the similar evaluation information, a piece of the evaluation information that, among respective pieces of the evaluation information of the plurality of model persons, is estimated to be most easily approachable by the evaluation information about the first person; detecting, by a motion capture sensor, movement data of a human body performing the first exercise; detecting, by a myoelectric sensor, electrical activity data from at least one part of the human body during performance of the first exercise; and generating the evaluation information as waveform data based on the movement data and the electrical activity data, wherein the machine learning model is trained using evaluation change information indicating changes in evaluation information resulting from users performing different training exercises, the machine learning model being configured to output the evaluation information that is estimated to be most achievable by the first person based on the evaluation change information.

Description

The present application is based on, and claims priority from JP Application Serial Number 2022-130584, filed Aug. 18, 2022, the disclosure of which is hereby incorporated by reference herein in its entirety. BACKGROUND 1. Technical Field This disclosure relates to an information processing device, an information processing method, and a non-transitory computer-readable storage medium storing a program. 2. Related Art Technologies for supporting people to perform exercises have been researched and developed. In this regard, a known information processing device acquires data about an exercise of a user, calculates a difference between the acquired data and data about an exercise of a possible model person of the user, and outputs information indicating advice for compensating for the calculated difference (see JP-A-2022-061784). However, the information processing device described in JP-A-2022-061784 cannot output a desired person of the user as the possible model person of the user. Thus, the information processing device may cause the user to aspire to be a person different from a person whom the user should aspire to be. SUMMARY According to an aspect of the present disclosure for solving the above problem, an information processing device includes a control unit configured to use information indicating evaluation about a first exercise as evaluation information, input input information including the evaluation information about a first person and respective pieces of the evaluation information about a plurality of model persons to a machine learning model trained, and output output information including model person information indicating a model person, among the plurality of model persons, corresponding to similar evaluation information output from the machine learning model, the machine learning model being configured to, when the input information is input, output, as the similar evaluation information, a piece of the evaluation information that, among respective pieces of the evaluation information of the plurality of model persons, is estimated to be most easily approachable by the evaluation information about the first person. According to another aspect of the present disclosure, an information processing method includes, provided that information indicating evaluation about a first exercise is evaluation information, inputting input information including the evaluation information about a first person and respective pieces of the evaluation information about a plurality of model persons to a machine learning model trained, and outputting output information including model person information indicating a model person, among the plurality of model persons, corresponding to similar evaluation information output from the machine learning model, the machine learning model being configured to, when the input information is input, output, as the similar evaluation information, a piece of the evaluation information that, among respective pieces of the evaluation information of the plurality of model persons, is estimated to be most easily approachable by the evaluation information about the first person. According to still another aspect of the present disclosure, a non-transitory computer-readable storage medium stores a program, the program causing a computer to execute, provided that information indicating evaluation about a first exercise is evaluation information, inputting input information including the evaluation information about a first person and respective pieces of the evaluation information about a plurality of model persons to a machine learning model trained, and outputting output information including model person information indicating a model person, among the plurality of model persons, corresponding to similar evaluation information output from the machine learning model, the machine learning model being configured to, when the input information is input, output, as the similar evaluation information, a piece of the evaluation information that, among respective pieces of the evaluation information of the plurality of model persons, is estimated to be most easily approachable by the evaluation information about the first person. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a diagram illustrating an example of a configuration of an information processing device 1. FIG. 2 is a diagram illustrating an example of input and output of a machine learning model M. FIG. 3 is a diagram illustrating graphs in which waveforms indicated by waveform data generated based on first information and second information are plotted. FIG. 4 is a diagram illustrating another example of a graph G1 illustrated in FIG. 3. FIG. 5 is a diagram illustrating an example of a flowchart of processing of outputting output information by the information processing device 1. FIG. 6 is a diagram illustrating another example of the configuration of the information processing device 1. FIG. 7 is a diagram illustrating an