Back to results
US 12,485,314 B2Granted
Generating inference model for decision making regarding rehabilitation from motions of sample person
AssigneeNEC Corporation
InventorsMakoto Yasukawa, Kosuke Nishihara, Yuji Ohno
Life of this patent
Estimating the term…
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.
Claims8
An exercise assisting apparatus comprising:
- a non-transitory computer readable recording medium;
- and
- a computation apparatus configured to execute a computer program on the non-transitory computer readable recording medium to:
- acquire one or more images of a sample person who is exercising in exemplary motions for rehabilitation in first phase of recovery from an image pickup apparatus;
- divide first sample motion information, indicating motions of the sample person in the acquired one or more images, into a plurality of pieces of motion element information, according to regularity of the motions of the sample person;
- generate an inference model for the rehabilitation in the first phase of recovery by causing a pre-trained model to learn time-series antecedent dependency of the plurality of pieces of motion element information by machine learning, wherein the pre-trained model is generated by using second sample motion information for rehabilitation in second phase of recovery, and wherein the inference model infers motions of a target person, based on target motion information indicating the motions of the target person doing exercise for the rehabilitation in the first phase of recovery;
- acquire one or more images of the target person who is repeating same exercise from an image pickup apparatus;
- divide the 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.
8 more elements
An exercise assisting method comprising:
- acquiring one or more images of a sample person who is exercising in exemplary motions for rehabilitation in first phase of recovery from an image pickup apparatus;
- dividing the first sample motion information, indicating motions of the sample person in the acquired one or more images, into a plurality of pieces of motion element information, according to regularity of the motions of the sample person;
- generating an inference model for the rehabilitation in the first phase of recovery by causing a pre-trained model to learn time-series antecedent dependency of the plurality of pieces of motion element information by machine learning, wherein the pre-trained model is generated by using second sample motion information for rehabilitation in second phase of recovery, and wherein the inference model infers motions of a target person, based on target motion information indicating the motions of the target person doing exercise for the rehabilitation in the first phase of recovery;
- acquiring one or more images of the target person who is repeating same exercise from an image pickup apparatus;
- dividing the motions of the target person in the acquired one or more images into a plurality of pieces of motion element information;
- inferring 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
- displaying the inferred difference in a superimposed manner on an image in which the target person appears.
5 more elements
A non-transitory recording medium storing a computer program causing a computer to execute an exercise assisting method,
- the exercise assisting method including:
- acquiring one or more images of a sample person who is exercising in exemplary motions for rehabilitation in first phase of recovery from an image pickup apparatus;
- dividing the first sample motion information, indicating motions of the sample person in the acquired one or more images, into a plurality of pieces of motion element information, according to regularity of the motions of the sample person;
- and
- generating an inference model for the rehabilitation in the first phase of recovery by causing a pre-trained model to learn time-series antecedent dependency of the plurality of pieces of motion element information by machine learning, wherein the pre-trained model is generated by using second sample motion information for rehabilitation in second phase of recovery, and wherein the inference model infers motions of a target person, based on target motion information indicating the motions of the target person doing exercise for the rehabilitation in the first phase of recovery;
- acquiring one or more images of the target person who is repeating same exercise from an image pickup apparatus;
- dividing the motions of the target person in the acquired one or more images into a plurality of pieces of motion element information;
- inferring 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
- displaying the inferred difference in a superimposed manner on an image in which the target person appears.
7 more elements
Dependencies are inferred from the claim text.