IP Library Granted Patent US 12,485,313
Granted Patent B2
US 12,485,313 · App. 18/269,130 · Granted Dec 2, 2025

Exercise assisting apparatus, exercise assisting method, and recording medium for decision making

Inventors: Makoto Yasukawa (Tokyo, JP); Kosuke Nishihara (Tokyo, JP); Yuji Ohno (Tokyo, JP)
Assignee: NEC Corporation
A63B24/0062A61B5/1128A61B5/7267A63B24/0006A63B2024/0012A63B2220/05A63B2220/805A63B2220/836A63B2225/52
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,485,313
App. No.
18/269,130
Granted
Dec 2, 2025
Kind
B2
Abstract

An exercise assisting apparatus 1 includes: a division unit 312 configured to divide sample motion information 3231 indicating motions of a sample person doing exercise into a plurality of pieces of motion element information 3235 , according to regularity of the motions of the sample person; and a generation unit 314 configured to generate an inference model by causing a pre-trained model 322 to learn time-series antecedent dependency of the plurality of pieces of motion element information, the inference model inferring motions of a target person, based on target motion information 3211 indicating the motions of the target person doing exercise.

Claims (47)

1 . An exercise assisting apparatus comprising:

a non-transitory computer readable recording medium; and

a computation apparatus configured to executed a computer program on the non-transitory computer readable recording medium to:

divide sample motion information indicating motions of a sample person doing exercise into a plurality of pieces of motion element information, according to regularity of the motions of the sample person;

generate an inference model by causing a pre-trained model to learn time-series antecedent dependency of the plurality of pieces of motion element information by machine learning, the inference model inferring motions of a target person, based on target motion information indicating the motions of the target person doing exercise;

acquire one or more images of the target person who is repeating same exercise from an image pickup apparatus;

divide motions of the target person in the acquired one or more images into a plurality of pieces of motion element information;

infer a difference between the motions of the target person and exemplary motions by processing the inference model based on the plurality of pieces of motion element information; and

display the inferred difference in a superimposed manner on an image in which the target person appears.

2 . The exercise assisting apparatus according to claim 1 , wherein

the pre-trained model is a model generated through learning time-series antecedent dependency of a plurality of pieces of first motion element information that is the plurality of pieces of motion element information,

the plurality of pieces of first motion element information is generated by dividing, according to the regularity of the motions of the sample person, first sample motion information that is the sample motion information indicating the motions of the sample person doing a first type of exercise,

the computation apparatus is configured to execute the computer program to:

divide second sample motion information into a plurality of pieces of second motion element information, the second sample motion information being the sample motion information indicating the motions of the sample person doing a second type of exercise that is different from the first type of exercise, the plurality of pieces of second motion element information being the plurality of pieces of motion element information, and

generate the inference model by causing the pre-trained model to additionally learn time-series antecedent dependency of the plurality of pieces of second motion element information.

3 . The exercise assisting apparatus according to claim 2 , wherein

the inference model is a model inferring the motions of the target person, based on the target motion information indicating the motions of the target person doing the second type of exercise.

4 . The exercise assisting apparatus according to claim 2 , wherein

the first sample motion information indicates exemplary motions of the sample person doing the first type of exercise, and different motions of the sample person doing the first type of exercise, the different motions being different from the exemplary motions, and

the second sample motion information indicates exemplary motions of the sample person doing the second type of exercise.

5 . The exercise assisting apparatus according to claim 2 , wherein

the first type of exercise and the second type of exercise are exercises belonging to an identical category, and

the category is set based on a body part that is moved by exercise or a body part on which exercise places an impact.

6 . The exercise assisting apparatus according to claim 2 , wherein

the computation apparatus is configured to execute the computer program to:

divide the first sample motion information into the plurality of pieces of first motion element information, and

generate the pre-trained model through learning time-series antecedent dependency of the plurality of pieces of first motion element information.

7 . The exercise assisting apparatus according to claim 1 , wherein

the computation apparatus is configured to execute the computer program to:

infer the motions of the target person by using the generated inference model and the target motion information.

8 . An exercise assisting apparatus comprising:

at least one memory configured to store instructions; and

at computation apparatus is configured to execute the computer program to:

acquire an inference model capable of inferring motions of a target person from target motion information indicating the motions of the target person doing exercise; and

infer the motions of the target person by using the inference model and the target motion information,

wherein the inference model is a model generated by dividing sample motion information indicating motions of a sample person doing exercise into a plurality of pieces of motion element information, according to a flow of changes in motion of the sample person, and by causing a pre-trained model to learn time-series antecedent dependency of the plurality of pieces of motion element information.

9 . The exercise assisting apparatus according to claim 8 , wherein

the sample motion information indicates the motions of the sample person doing a first type of exercise, and

the target motion information indicates the motions of the target person doing a second type of exercise that is different from the first type of exercise.

10 . The exercise assisting apparatus according to claim 8 , wherein

the computation apparatus is configured to execute the computer program to:

display notification information, in a superimposing manner, on an image of the target person when the inferred motions of the target person are displaced from exemplary motions, the notification information notifying a body part of the target person that is displaced from the exemplary motions.

11 . The exercise assisting apparatus according to claim 10 , wherein

the computation apparatus is configured to execute the computer program to display the notification information to optimize the motions of the target person so that the motions of the target person is closer to the exemplary motions.

12 . An exercise assisting method comprising:

dividing sample motion information indicating motions of a sample person doing exercise into a plurality of pieces of motion element information, according to regularity of the motions of the sample person; and

generating an inference model by causing a pre-trained model to learn time-series antecedent dependency of the plurality of pieces of motion element information, the inference model inferring motions of a target person, based on target motion information indicating the motions of the target person doing exercise.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 22, 2023
From: YASUKAWA, MAKOTO; NISHIHARA, KOSUKE; OHNO, YUJI
To: NEC CORPORATION
Reel/Frame 064031/0238 →
Continuity (1)
Related Publication 20240082636A1 · Mar 14, 2024
References Cited (16)
US 10956673B1 · Ramezani et al. · 2021 [cited by applicant]
US 20040219498A1 · Davidson · 2004 [cited by examiner]
US 20160314352A1 · Matsunaga et al. · 2016 [cited by applicant]
US 20160314818A1 · Kirk et al. · 2016 [cited by applicant]
US 20190022492A1 · Takahashi et al. · 2019 [cited by applicant]
US 20190179297A1 · Kuroda · 2019 [cited by examiner]
US 20210082412A1 · Kennewick · 2021 [cited by applicant]
JP 2016041142A · 2016 [cited by applicant]
JP 2016208516A · 2016 [cited by applicant]
JP 2017055913A · 2017 [cited by applicant]
JP 2017215685A · 2017 [cited by applicant]
JP 2018000230A · 2018 [cited by applicant]
JP 2020005766A · 2020 [cited by applicant]
JP 2020194569A · 2020 [cited by applicant]
WO 2015098260A1 · 2015 [cited by applicant]
International Search Report for PCT Application No. PCT/JP2021/012504, mailed on Jun. 8, 2021. [cited by applicant]