JP2020099534A - Function improvement support device and system - Google Patents

Abstract

To provide a function improvement support device for determining an exercise program for efficiently improving a function of an object user such as a person requiring care.SOLUTION: A function improvement support device 20 comprises: an acquisition part 28 for acquiring a feature amount related to a function of an object user; and an exercise program determination part 23 for determining an exercise program for improving a function of the object user from the acquired feature amount, on the basis of a learned model. The learned model is subjected to machine learning with feature amounts related to functions of a plurality of users and exercise programs executed by respective users as learning data, and outputs identification information of the exercise program corresponding to the feature amount.SELECTED DRAWING: Figure 2

Description

The present invention relates to a function improvement support device, a function improvement support system, and a terminal device that support improvement of a target user's function.

In recent years, the aging of population has progressed rapidly, and the number of persons requiring care including the elderly is increasing. Therefore, it is necessary to control the increase in the number of persons requiring care or reduce the number of persons requiring care.

As an example of the above-mentioned measures, for example, Patent Document 1 discloses a dementia care support system that improves cognitive function by having a person requiring care for dementia play a game.

Further, Patent Document 2 discloses a user health maintenance and activation support and watching system that improves exercise function by providing an exercise program to a care recipient and having the person perform an operation according to the program. There is.

JP, 2016-071897, A JP, 2010-140119, A

However, caregivers have a wide range of problems, and even if problems are identified, it is difficult for a rehabilitation professional to select the most effective program from the numerous exercise programs. In other words, it is extremely difficult for ordinary care workers to select such a program.

Also in the systems described in Patent Documents 1 and 2, it is difficult to select the optimum game or exercise program, and the same problem occurs.

The present invention has been made in view of such circumstances, and a function improvement support device and a function improvement support capable of determining an exercise program for effectively improving the function of a target user such as a care recipient. It is intended to provide a system and a terminal device.

(1) In order to achieve the above object, a function improvement support apparatus according to an aspect of the present invention includes an acquisition unit that acquires a feature amount related to a function of a target user and an acquired unit based on a learned model. An exercise program determining unit that determines an exercise program for improving the function of the target user from a feature amount, wherein the learned model has a feature amount related to the function for a plurality of users, and The model is machine-learned using the executed exercise program as learning data, and outputs identification information of the exercise program corresponding to the feature amount.

According to this configuration, the exercise program for improving the function of the target user can be determined by inputting the feature amount related to the function of the target user into the learned model. The learned model is a model obtained by machine learning the feature amounts of a plurality of users and the exercise program executed by each user as learning data. Therefore, by inputting the feature amount of the target user into the learned model, the exercise program expected to have the highest degree of improvement for the target user is output. This makes it possible to determine an exercise program for effectively improving the function of the target user such as a care recipient.

(2) Preferably, the function is a function related to exercise or life of the user, and the acquisition unit acquires a distance image indicating a distance to the target user as the feature amount, and determines the exercise program. Based on the learned model, the section determines a problem related to the exercise or life of the user and an exercise program for improving the problem from the acquired feature amount, and the learned model is , For a plurality of users, the distance image of each user, a problem related to exercise or life of each user, and an exercise program executed by each user are machine-learned as learning data, and the problem corresponding to the feature amount It is a model that outputs identification information of points and the exercise program.

According to this configuration, by inputting the distance image of the target user into the learned model, the problem of the target user can be extracted and the exercise program for improving the problem can be determined. For example, even for target users who cannot get up, there is a difference in the degree to which they cannot get up. However, this configuration does not provide the same exercise program to a plurality of target users who cannot get up, but determines and provides the most effective exercise program for each target user according to the degree that they cannot get up. can do.

(3) Further, the function is a function related to a user's language or oral cavity, and the acquisition unit is configured to answer the question of the target user's language or oral cavity and the inspection item, and the target user's language or The evaluation by the oral profession to the evaluation item of the oral cavity is obtained as the feature amount, and the learned model is, for a plurality of users, the answer to the question item and inspection item of the language or oral cavity of each user, depending on the oral profession Machine evaluation is performed on the evaluation items of each user, and the management guidance items and exercise programs executed by each user as learning data, and the identification information of the management guidance items and the identification information of the exercise program corresponding to the feature amount are identified. It is a model to be output, and the exercise program determination unit may determine a management instruction item and an exercise program for improving the function of the target user from the acquired feature amount based on the learned model. ..

According to this configuration, the answer to the question item and the inspection item of the target user's language or oral cavity, and the target user's evaluation by the oral profession are acquired, and the acquired answer and evaluation are input to the learned model, Management guidance and exercise programs can be determined to improve language or oral related functions of the target user. Thereby, for example, instead of providing the same management guidance item and exercise program to a plurality of target users with language impairment, determine the most effective management guidance item and exercise program for each target user, Can be provided.

(4) Further, the function improvement support device further includes a machine learning unit that machine-learns the learned model, and the machine learning unit further executes the exercise program determined by the exercise program determination unit. The learned model may be machine-learned using the feature amount of the target user and the identification information of the exercise program as learning data.

With this configuration, the learned model can be re-learned using the feature amount of the target user and the exercise program provided to the target user as learning data. This makes it possible to determine and provide an effective exercise program with a higher degree of improvement to other target users.

(5) A function improvement support system according to another aspect of the present invention includes a distance image sensor that acquires a distance image indicating a distance to a target user, the function improvement support device according to (2), and the function improvement support. A terminal device that acquires a problem related to exercise or life of the target user and an exercise program for improving the function of the target user from the device, and presents the acquired problem and the exercise program.

With this configuration, the terminal device can present the problem and exercise program determined by the function improvement support device. Therefore, for example, the target user who uses the terminal device can execute the training for improving the function based on the most effective exercise program after knowing the problems of the target user. In addition, the caregiver of the target user can make the target user perform the training for improving the function based on the most effective exercise program after knowing the problem of the target user.

(6) A function improvement support system according to another aspect of the present invention is a function improvement support device according to (3), and management guidance items and exercises for improving the function of a target user from the function improvement support device. A terminal device that acquires a program and presents the acquired management instruction items and the exercise program is provided.

With this configuration, the exercise program determined by the above-described function improvement support device can be presented to the terminal device. Therefore, for example, the target user who uses the terminal device can execute the training for improving the function based on the most effective management guidance item and the exercise program. Further, the caregiver of the target user can cause the target user to execute the training for improving the function based on the most effective management guidance item and the exercise program.

A terminal device according to another aspect of the present invention is an exercise program acquisition unit that acquires an exercise program for improving the function of a target user from the function improvement support device described above, and the exercise acquired by the exercise program acquisition unit. An exercise program presenting unit that presents a program.

With this configuration, the exercise program determined by the function improvement support device can be presented. Therefore, for example, the target user who uses the terminal device or the caregiver of the target user can execute the training for improving the function based on the most effective exercise program.

According to the present invention, it is possible to effectively improve the function of a target user such as a care recipient.

It is a figure which shows the structure of the function improvement support system which concerns on Embodiment 1 of this invention. It is a block diagram which shows the structure of the function improvement support apparatus which concerns on Embodiment 1 of this invention. It is a figure which shows an example of the user information memorize|stored in the memory|storage part. It is a block diagram which shows the structure of the terminal device which concerns on Embodiment 1 of this invention. 5 is a flowchart showing an example of a processing procedure of the function improvement support device according to the first embodiment of the present invention. 5 is a flowchart showing an example of a processing procedure of the function improvement support device according to the first embodiment of the present invention. It is a figure which shows the other structure of a function improvement support system. FIG. 6 is a block diagram showing a configuration of a function improvement support device according to a second embodiment. It is a figure which shows an example of the questionnaire which contains the question item, test item, and answer item with respect to a language or an oral cavity. It is a figure which shows an example of the evaluation document which includes the evaluation item regarding a language or an oral cavity, and the evaluation of the oral specialist for the said item. It is a figure which shows an example of the user information memorize|stored in the memory|storage part. 9 is a flowchart showing an example of a processing procedure of the function improvement support device according to the second embodiment of the present invention. It is a figure which shows an example of the management guidance plan of the oral function improvement service created based on the content of the management guidance item and the exercise program transmitted to the terminal device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that at least a part of the embodiments described below may be arbitrarily combined.

[Embodiment 1]
<Functional improvement support system configuration>
FIG. 1 is a diagram showing a configuration of a function improvement support system according to the first embodiment of the present invention.

The function improvement support system 1 is a system for improving the function of a target user 50 such as a care recipient, and includes a distance image sensor 10, a function improvement support device 20, and a terminal device 40.

The distance image sensor 10 generates a distance image in which the brightness value of each pixel indicates the distance to the subject by measuring the distance to the plurality of points of the subject. That is, the distance image sensor 10 is a camera including a plurality of LEDs (Light Emitting Diodes) regularly arranged on the front surface of the camera and a lens, and light emitted from the plurality of LEDs at once is a subject. The reflected light (eg, near infrared light) is collected by the lens. At this time, the time from when the LED emits light to when the reflected light reaches the lens varies depending on the position of the subject. That is, the closer the subject is to the camera, the shorter the arrival time of the reflected light, and the farther the subject is from the camera, the longer the arrival time of the reflected light. The range image sensor 10 outputs the distance to the object for each pixel by measuring the arrival time for each pixel. That is, the distance image sensor 10 outputs a distance image in which the distance to the subject is represented by the brightness value in the pixel.

The function improvement support device 20 acquires a distance image from the distance image sensor 10. The function improvement support device 20 determines a problem regarding the function of the target user 50 and an exercise program for improving the problem from the distance image based on the learned model that is machine-learned in advance.

For example, the improvement target function is a function related to the exercise or life of the target user 50.

The learned model is machine-learned by using distance images for a plurality of users, problems regarding functions of each user, and an exercise program executed by each user as learning data, and identifies problems and exercise programs corresponding to the distance image. It is a model that outputs information (exercise program name).

That is, the learned model is machine-learned for a plurality of users using the distance image of each user, the problem of each user, the attribute of each user, and the exercise program executed by each user as learning data, and the model of the target user 50 is acquired. It is a model that outputs the problem of the target user 50 and the identification information (exercise program name) of the exercise program corresponding to the distance image and the attributes of the target user 50.

The model can be created by, for example, deep learning. Here, the distance image of the user is input and the distance image of the user and the attribute of the user are input by performing deep learning with a teacher using the learning data that outputs the problem of the user and the exercise program name. As, it is possible to create a model that outputs problems and exercise program names. The model can be represented by a neural network by performing deep learning.

The function improvement support device 20 transmits the determined problem and exercise program to the terminal device 40 via the network 2.

The terminal device 40 is, for example, a computer device including a display screen such as a tablet terminal, a smartphone, or a laptop computer. The terminal device 40 is operated by, for example, a caregiver, a caregiver, or a care worker who assists the target user 50 in improving the function. The target user 50 itself may operate the terminal device 40.

The terminal device 40 receives the problem and the exercise program from the function improvement support device 20. The terminal device 40 displays the received exercise program on the display screen. As a result, the caregiver or the like informs the target user 50 of the problem and causes the target user 50 to execute an exercise program to improve the problem, or the target user 50 knows the problem by himself and provides an exercise program to improve the problem. It can be carried out.

<Configuration of function improvement support device>
FIG. 2 is a block diagram showing the configuration of the function improvement support device according to the first embodiment of the present invention.

The function improvement support device 20 includes a distance image acquisition unit 21, an exercise program determination unit 23, a storage unit 24, a learning data acquisition unit 26, a machine learning unit 27, and a user attribute acquisition unit 28.

The function improvement support device 20 can be realized by a general computer including a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), an HDD (Hard Disk Drive), a communication interface, and the like. .. For example, the computer programs stored in the HDD or the ROM are loaded into the RAM and executed on the CPU, whereby the respective processing units 21, 23, and 26 to 28 of the function improvement support device 20 are functionally realized. .. However, some or all of the processing units 21, 23, and 26 to 28 may be realized by hardware such as a semiconductor device.

The distance image acquisition unit 21 acquires the distance image output from the distance image sensor 10 as the feature amount of the target user 50.

Note that the distance image acquisition unit 21 may perform labeling processing for attaching the same label to the three-dimensional coordinates within a predetermined distance range based on the three-dimensional coordinates indicated by the distance image. The distance image acquisition unit 21 may extract the region of the target user 50 from the result of the labeling process. For example, the distance image acquiring unit 21 may extract the largest area existing in the area as the area of the target user 50 by previously designating the area in which the target user 50 exists.

The distance image acquisition unit 21 stores the acquired distance image in the storage unit 24 as user information 25A in association with the user ID of the target user 50.

The user attribute acquisition unit 28 acquires, for example, the attribute of the target user 50 input by operating the keyboard or the terminal device 40, and additionally registers it in the user information 25A stored in the storage unit 24. The attributes include, for example, information such as the gender, age, weight, and height of the target user 50.

The exercise program determination unit 23 uses the distance image acquired by the distance image acquisition unit 21 and the attribute of the target user 50 acquired by the user attribute acquisition unit 28 based on the learned model 25B stored in the storage unit 24. , A problem related to the function of the target user 50 and an exercise program for improving the problem are determined. The exercise program determination unit 23 additionally registers the determined problem and the exercise program name, which is the identification information of the exercise program, in the user information 25A stored in the storage unit 24.

The problems determined by the exercise program determination unit 23 include, for example, problem 1 showing a large classification of problems such as being unable to turn over, being unable to stand up, and being unable to crouch, and more detailed problems. There is problem 2 shown. For example, Problem 2 for Problem 1 “I can't turn over” includes “Neck is not raised”, “Arms are not raised”, “Shoulders are not raised”, “Body is not twisted”, etc. Be done.

The exercise program is prepared, for example, for each of the problem 2 and, for a user who does not have a raised neck, a neck flexion exercise that tilts the neck downward diagonally, and for a user who does not have a raised shoulder, does not move the abdomen. It also includes various exercise programs such as reach exercise to move the scapula and straightening exercise to extend the elbow and lie the abdomen for the user who does not have a twist in the body.

The exercise program determining unit 23 transmits the determined problem and the determined content or exercise program name of the exercise program to the terminal device 40 and registers it in the user information 25A.

The storage unit 24 is composed of an HDD, a flash memory, or the like, and stores user information 25A and a learned model 25B.

FIG. 3 is a diagram illustrating an example of user information stored in the storage unit.
The user information 25A is stored in association with the user ID, sex, age, weight, height, distance image, problem 1, problem 2, and exercise program name.

For example, the gender of the target user 50 with the user ID “u1” is “male”, the age is “81” years old, the weight is “72” kg, the height is “168” cm, the distance image is “img1”, and the target user 50 is Problem 1 is that "rolling over" is not possible, and problem 2 of the target user 50 is that "the neck is not raised" and "the left arm is not raised". The name of the exercise program determined to improve the above is “p1”. Similar information is also stored in the storage unit 24 for the target users 50 such as the user IDs “u2” and “u3”.

The learning data acquisition unit 26 acquires learning data for retraining the learned model 25B. Specifically, the learning data acquisition unit 26 reads the user information 25A from the storage unit 24.

For example, the learning data acquisition unit 26 acquires the user information about the target user 50 having the user ID “u1” shown in FIG. 3 as the learning data. The learning data acquisition unit 26 similarly acquires user information as learning data for other target users 50 such as user IDs “u2” and “u3”.

The machine learning unit 27 updates the learned model 25B by further machine learning the learned model 25B based on the learning data acquired by the learning data acquisition unit 26. As described above, for machine learning, deep learning can be used as an example.
The machine learning unit 27 stores the updated learned model 25B in the storage unit 24.

<Terminal device configuration>
FIG. 4 is a block diagram showing the configuration of the terminal device according to Embodiment 1 of the present invention.
The terminal device 40 includes an exercise program acquisition unit 41 and an exercise program presentation unit 42.

The exercise program acquisition unit 41 acquires a problem and an exercise program from the function improvement support device 20 via the network 2. When the content of the exercise program is stored in the storage unit of the exercise program acquisition unit 41, the exercise program acquisition unit 41 acquires the exercise program name from the function improvement support device 20 and corresponds to the exercise program name from the storage unit. The exercise program may be acquired by reading the exercise program.

The exercise program presenting unit 42 presents the problem and exercise program acquired by the exercise program acquiring unit 41 to the target user 50 or a caregiver of the target user 50 by displaying the problem and the exercise program on the display screen.

<Operation mode>
FIG. 5 is a flowchart showing an example of a processing procedure of the function improvement support device according to the first embodiment of the present invention. FIG. 5 shows a processing procedure of the function improvement support device 20 in the operation mode in which the exercise program of the target user 50 is determined from the distance image obtained by capturing the target user 50.

The distance image acquisition unit 21 acquires the distance image output from the distance image sensor 10 (S1).

The exercise program determination unit 23 inputs the distance image acquired by the distance image acquisition unit 21 and the attribute (sex, age, weight, height) of the target user 50 into the learned model 25B, and the probability is highest (function improvement). (Probability of) and the exercise program name are determined (S2).

The exercise program determination unit 23 transmits the determined problems and the content of the exercise program to the terminal device 40 (S3). The exercise program determining unit 23 may transmit the exercise program name to the terminal device 40 instead of the content of the exercise program.

Thereby, the terminal device 40 can receive and display the problem and the content of the exercise program transmitted from the function improvement support device 20. Therefore, the caregiver using the terminal device 40 can notify the target user 50 of the problem of the target user 50 and execute the exercise program most effective for improving the function.

<Learning mode>
FIG. 6 is a flowchart showing an example of a processing procedure of the function improvement support device according to the first embodiment of the present invention. FIG. 6 shows a processing procedure of the function improvement support device 20 in the learning mode for re-learning the learned model for determining the exercise program.

The learning data acquisition unit 26 acquires the user information 25A by reading it from the storage unit 24 (S11).

The machine learning unit 27 uses the user information 25A acquired by the learning data acquisition unit 26 as learning data, and machine-learns the learned model 25B stored in the storage unit 24 again (S13). In the example illustrated in FIG. 3, the machine learning unit 27 machine-learns the learned model 25B using the sex, age, weight, height, distance image, problem 1, problem 2 and exercise program name of each user as learning data. To do. The machine learning unit 27 overwrites the learned model 25B after the opportunity learning in the storage unit 24.
The learning mode process is performed, for example, every predetermined period (for example, one month).

<Effect of Embodiment 1>
As described above, according to the first embodiment of the present invention, the exercise program for improving the function of the target user 50 by inputting the feature amount related to the function of the target user 50 into the learned model 25B. Can be determined. The learned model 25B is a model obtained by machine-learning the feature amounts of a plurality of users, the problems of each user, and the exercise program executed by each user as learning data. Therefore, by inputting the feature amount and the problem of the target user 50 into the learned model 25B, the exercise program expected to have the highest degree of improvement for the target user 50 is output. Thereby, the exercise program for effectively improving the function of the target user 50 such as the care recipient can be determined. Further, conventionally, a rehabilitation professional has, for example, measured motion elements such as the bending angle of the neck of the target user 50 and the rotation angle in the body axis, and determined an exercise program based on the measurement result. According to this embodiment, such measurement work is unnecessary.

More specifically, the problem can be extracted based on the distance image, and the exercise program for improving the problem can be determined. For example, even for the target users 50 who cannot get up, there is a difference in the degree to which the target users 50 cannot get up. However, in this configuration, the same exercise program is not provided to a plurality of target users 50 who are unable to get up, but the most effective exercise program is determined for each target user 50 according to the degree that they cannot get up. , Can be provided.

Further, the learned model 25B can be re-learned using the distance image and the problem of the target user 50 and the exercise program provided to the target user 50 as learning data. This makes it possible to determine and provide an effective exercise program with a higher degree of improvement to the other target users 50.

[Modification 1 of Embodiment 1]
In the first embodiment described above, the model learning is performed by machine learning with a teacher, but it is also possible to perform the model learning by reinforcement learning.

For example, the distance image of the user and the attribute of the user are set to the state in the reinforcement learning, the problem of the user and the exercise program name are the actions in the reinforcement learning, and the degree of improvement is the reward in the reinforcement learning. A model that outputs a problem and an exercise program name that maximize the degree of improvement can be created by inputting the distance image and the user attribute. The reinforcement learning can be deep reinforcement learning, and the model can be expressed by a neural network by performing the deep reinforcement learning.

The learning data acquisition unit 26 of the function improvement support device 20 illustrated in FIG. 2 reads the user information 25A from the storage unit 24. Further, the learning data acquisition unit 26 acquires the degree of improvement of the function after executing the exercise program having the exercise program name indicated in the user information 25A. The learning data acquisition unit 26 receives, for example, the degree of improvement input by the caregiver operating the keyboard or the terminal device 40. The degree of improvement is, for example, numerically expressed in five stages of 1 to 5, where 1 is the highest degree of improvement, the higher the number, the lower the degree of improvement, and 5 is the lowest degree of improvement.

For example, the learning data acquisition unit 26 executes the user information about the target user 50 with the user ID “u1” shown in FIG. 3 and the target user 50 after executing the exercise program name “p1” shown in the user information. The degree of improvement of the function of is acquired as learning data. The learning data acquisition unit 26 similarly acquires the user information and the improvement degree of the function as learning data for the other target users 50 such as the user IDs “u2” and “u3”.

The machine learning unit 27 again machine-learns the learned model 25B stored in the storage unit 24, using the user information 25A and the degree of improvement acquired by the learning data acquisition unit 26 as learning data. In the example illustrated in FIG. 3, the machine learning unit 27 learns the sex, age, weight, height, distance image, problem 1, problem 2, and exercise program name of each user, and the degree of improvement in the function of the user. The learned model 25B is machine-learned as use data. The machine learning unit 27 overwrites the learned model 25B after the opportunity learning in the storage unit 24.

[Modification 2 of Embodiment 1]
The function of the distance image sensor 10 may be provided in the terminal device 40, or the distance image sensor 10 is prepared as an attachment of the terminal device 40, and the distance image sensor 10 is connected to the terminal device 40 for use. You may.

FIG. 7 is a diagram showing another configuration of the function improvement support system.
The function improvement support system 1 is a system for improving the function of a target user 50 such as a care recipient, and includes a distance image sensor 10, a function improvement support device 20, and a terminal device 40. The distance image sensor 10 is miniaturized, for example, and is configured to be connectable to the terminal device 40.

The terminal device 40 executes the same processing as that of the above-described embodiment. In addition, the terminal device 40 transmits the distance image generated by the distance image sensor 10 to the function improvement support device 20 via the network 2.

The function improvement support device 20 performs the same processing as that of the above-described embodiment based on the distance image received from the terminal device 40.

[Second Embodiment]
In the first embodiment, improvement of functions related to exercise or life of the user has been described. However, the function to be improved is not limited to this. For example, a function related to the user's language or oral cavity may be the function to be improved.

In the second embodiment, improvement of a function related to a user's language or oral cavity will be described. In the following, points different from those of the first embodiment will be mainly described, and detailed description of the same points will not be repeated.

The function improvement support system according to the second embodiment does not include the distance image sensor 10 in the function improvement support system 1 shown in FIG.

<Configuration of function improvement support device>
FIG. 8 is a block diagram showing the configuration of the function improvement support device according to the second embodiment.
The function improvement support device 20 includes an answer acquisition unit 29 and an evaluation acquisition unit 30 instead of the distance image acquisition unit 21 in the configuration of the function improvement support device 20 according to the first embodiment shown in FIG. The answer acquisition unit 29 and the evaluation acquisition unit 30 are functionally realized by executing a computer program on the CPU, similarly to the distance image acquisition unit 21. However, the answer acquisition unit 29 and the evaluation acquisition unit 30 may be realized by hardware such as a semiconductor device.

The answer acquisition unit 29 acquires answers to the question item and the inspection item of the language or oral cavity of the target user 50 as feature quantities related to the function of the target user 50.

FIG. 9 is a diagram showing an example of an inquiry sheet including question items, examination items, and answer items for language or oral cavity. The inquiry sheet shows question items and inspection items and answer options. For example, the item IDs "Q1" to "Q10" show a set of question item and answer choices, and the item ID "Q11" and later show a set of examination item and answer choices.

Here, the question item is an item that the target user 50 himself/herself mainly answers subjectively. However, if the answer by the target user 50 is difficult, a caregiver or the like may answer. The inspection item is an item for objectively observing the target user 50, and is also called an observation item. Therefore, in principle, the caregiver or the like answers the inspection item, not the target user 50 itself.

For example, “1. No” and “2. Yes” are prepared as answers to the question item “Is it hard to eat hard food?” with the item ID “Q1”. In addition, "1. Good", "2. Slightly good", "3. Normal", "4. Slightly bad" and as answers to the question item "How is your oral health?" of item ID "Q10" and "5. Bad" is prepared.

Moreover, “1. none”, “2. yes” and “3. many” are prepared as answers to the inspection item “dirt of teeth or artificial teeth” of the item ID “Q11”. Further, “1. None”, “2. Yes” and “3. Many” are prepared for the inspection item “Tongue stain” of the item ID “Q12”.

The answer acquisition unit 29 acquires, for each target user 50, a set of item IDs and answers of the questionnaire as shown in FIG. 9. The answer acquisition unit 29 acquires, for example, a set of item IDs and their answers input by operating the keyboard or the terminal device 40 from the keyboard or the terminal device 40, and associates them with the user ID of the target user 50. , User information 25A is stored in the storage unit 24.

The evaluation acquisition unit 30 acquires the evaluation by the oral specialist for the language or oral evaluation items of the target user 50 as a feature amount related to the function of the target user 50.

FIG. 10: is a figure which shows an example of the evaluation document which includes the evaluation item regarding a language or an oral cavity, and the evaluation of the oral specialist with respect to the said item. The evaluation report shows evaluation items and evaluation options.

Here, the evaluation item is an item that a speech hearing specialist, a dental hygienist, or a nurse who is an oral specialist makes an evaluation while observing the target user 50 on a daily basis.

For example, “1. None”, “2. Small amount”, and “3. Large amount” are prepared as evaluations for the evaluation item “salting” (evaluation item for drooling) of the item ID “E1”. In addition, as the evaluation for the evaluation item “cervical flexion range of motion” (evaluation item for the range of vertical movement of the neck) of the item ID “E2”, “1. no limit”, “2. move slightly”, “3. immovable” Is prepared.

The evaluation acquisition unit 30 acquires, for each target user 50, a set of item IDs and evaluations of the evaluation document as shown in FIG. 10. The evaluation acquisition unit 30 acquires, for example, a group of item IDs input by operating the keyboard or the terminal device 40 and the evaluation thereof from the keyboard or the terminal device 40, and associates them with the user ID of the target user 50. , User information 25A is stored in the storage unit 24.

The exercise program determination unit 23, based on the learned model 25B stored in the storage unit 24, sets of item IDs and answers acquired by the answer acquisition unit 29, and item IDs and evaluations acquired by the evaluation acquisition unit 30. From the group, management guidance items and exercise programs for improving the function of the target user 50 are determined. The exercise program determining unit 23 additionally registers the management instruction item name, which is the identification information of the determined management instruction item, and the exercise program name, which is the identification information of the exercise program, in the user information 25A stored in the storage unit 24. The management guidance items include, for example, various guidance items such as provision of information regarding oral function improvement and assistance for cleaning the oral cavity. Further, the exercise program includes various programs such as oral gymnastics, swallowing gymnastics, salivary gland massage, and functional training such as breathing and swallowing. The management guidance item determined by the exercise program determination unit 23 is a combination of the various guidance items described above, and the exercise program determined by the exercise program determination unit 23 is a combination of the various programs described above. It is a thing.

The exercise program determination unit 23 transmits the determined contents of the management guidance item and the contents of the exercise program, or the management guidance item name and the exercise program name to the terminal device 40 and registers them in the user information 25A.

The learned model 25B stored in the storage unit 24 includes, for a plurality of users, a group of item IDs and answers of each user, a group of item IDs and evaluations, user attributes, and management instruction items executed by each user. Machine learning is performed using the exercise program as learning data, and the management instruction item name and exercise program name corresponding to the item ID and answer set of the target user 50, the item ID and evaluation set, and the attribute of the target user 50 are set. This is the model to output.

For example, the model can be created using deep learning. Here, learning data in which a feature amount (a set of item ID and answer, a set of item ID and evaluation) and an attribute related to a user's function are input, and a management instruction item name and an exercise program name are output is used. Then, a model can be created by performing deep learning with a teacher. The model can be represented by a neural network by performing deep learning.

FIG. 11 is a diagram showing an example of user information stored in the storage unit.
The user information 25A is stored in association with a user ID, gender, age, weight, height, item ID of question item and inspection item, answer, item ID of evaluation item, evaluation, management instruction item name, and exercise program name. ing.

For example, the gender of the target user 50 of the user ID "u1" is "male", the age is "81", the weight is "72" kg, the height is "168" cm, and the answer for the item ID "Q1" is "1". , Item ID “Q2” has an answer of “3”, item ID “Q3” has an answer of “2”, item ID “E1” has an evaluation of “2”, item ID “E2” has an evaluation of “3”, item The evaluation of the ID “E3” is “1”, the name of the management instruction item determined to improve the function of the target user 50 is “m1”, and the exercise program determined to improve the function of the target user 50. Is "t1". Similar information is also stored in the storage unit 24 for the target user 50 such as the user ID “u2”.

The learning data acquisition unit 26 acquires learning data for retraining the learned model 25B. For example, the learning data acquisition unit 26 acquires the user information about the target user 50 having the user ID “u1” shown in FIG. 9 as the learning data. The learning data acquisition unit 26 similarly acquires user information as learning data for other target users 50 such as user IDs “u2” and “u3”.

The machine learning unit 27 updates the learned model 25B by further machine learning the learned model 25B based on the learning data acquired by the learning data acquisition unit 26. As described above, for machine learning, deep learning can be used as an example.
The machine learning unit 27 stores the updated learned model 25B in the storage unit 24.
The configuration of the terminal device 40 is similar to that of the first embodiment.

<Operation mode>
FIG. 12 is a flowchart showing an example of the processing procedure of the function improvement support device according to the second embodiment of the present invention. FIG. 12 shows a processing procedure of the function improvement support device 20 in the operation mode in which the exercise program of the target user 50 is determined from the question and the answer to the target user 50.

The answer acquisition unit 29 acquires the answers to the question item and the inspection item of the language or oral cavity of the target user 50 as the feature quantities related to the function of the target user 50 (S21). That is, the answer acquisition unit 29 acquires a set of item IDs of the questionnaire and the answers thereof as shown in FIG.

The evaluation acquisition unit 30 acquires the evaluation of the language or oral cavity evaluation item of the target user 50 by the oral professional as a feature amount related to the function of the target user 50 (S22). That is, the evaluation acquisition unit 30 acquires a set of item IDs and evaluations of the evaluation document as shown in FIG.

The exercise program determination unit 23 includes a group of item IDs and answers acquired by the answer acquisition unit 29, a group of item IDs and evaluations acquired by the evaluation acquisition unit 30, and attributes of the target user 50 (sex, age, weight, height). ) And are input to the learned model 25B to determine the management guidance item name and the exercise program name (S23).

The exercise program determination unit 23 transmits the determined management guidance item and the content of the exercise program to the terminal device 40 (S24). The exercise program determining unit 23 may transmit the management instruction item name and the exercise program name to the terminal device 40 instead of the content of the management instruction item and the exercise program.

Note that, also in the second embodiment, the function improvement support device 20 re-learns the learned model in the learning mode. The process flow is the same as that shown in FIG. 6 except that the barycentric position and the amount of exercise are changed to the item ID and answer group and the item ID and evaluation group.

FIG. 13 is a diagram showing an example of the management guidance plan of the oral function improvement service created based on the content of the management guidance items and the exercise program transmitted to the terminal device 40.

In the management guidance plan, management guidance items and exercise programs to be carried out on the target user 50 are shown. For example, “Providing information on improvement of oral function” by a professional is shown as a management instruction item. In addition, as an exercise program, "oral and swallowing exercises" and "salivary gland massage" by professionals, "oral and swallowing exercises" by related employees, and "oral and swallowing exercises" at home by the individual are shown. Has been done.

<Effect of Embodiment 2>
As described above, according to the second embodiment of the present invention, the answers to the question item and the examination item of the language or the oral cavity of the target user 50, and the evaluation by the oral profession to the language or the oral cavity evaluation item of the target user 50. Are acquired, and the acquired answers and evaluations are input to the learned model 25B, whereby a management instruction item and an exercise program for improving the function related to the language or the oral cavity of the target user 50 can be determined. .. Thereby, for example, instead of providing the same management guidance item and exercise program to a plurality of target users 50 having a language disorder, the most effective management guidance item and exercise program is determined for each target user 50. Can be provided.

[Modification of Second Embodiment]
In the above-described second embodiment, the model learning is performed by supervised machine learning, but it is also possible to perform the model learning by reinforcement learning.

For example, the model can be created using reinforcement learning. Here, the feature amount (the set of item ID and answer, the set of item ID and evaluation) and the attribute related to the function of the user are the states in the reinforcement learning, and the management instruction item name and the exercise program name are the actions in the reinforcement learning. A model can be created by performing reinforcement learning with the degree of improvement as a reward in reinforcement learning. The reinforcement learning can be deep reinforcement learning, and the model can be expressed by a neural network by performing the deep reinforcement learning.

The learning data acquisition unit 26 of the function improvement support device 20 illustrated in FIG. 2 acquires learning data for relearning the learned model 25B. For example, the learning data acquisition unit 26 includes the user information about the target user 50 with the user ID “u1” shown in FIG. The degree of improvement in the function of the target user 50 after executing the exercise program of “t1” is acquired as learning data. The learning data acquisition unit 26 similarly acquires the user information and the improvement degree of the function as learning data for the other target users 50 such as the user IDs “u2” and “u3”. The degree of improvement is, for example, numerically expressed in five stages of 1 to 5, where 1 is the highest degree of improvement, the higher the number, the lower the degree of improvement, and 5 is the lowest degree of improvement.

The machine learning unit 27 updates the learned model 25B by further machine learning the learned model 25B based on the learning data acquired by the learning data acquisition unit 26. As described above, for machine learning, for example, reinforcement learning or deep reinforcement learning can be used.
The machine learning unit 27 stores the updated learned model 25B in the storage unit 24.

[Appendix]
Although the embodiment of the function improvement support system according to the present invention has been described above, the present invention is not limited to the above embodiment.

For example, in the above-described first embodiment, the center of gravity position and the amount of exercise of the target user 50 are used as the feature amount, but the feature amount is not limited to this. For example, the distance from the ground to the center of gravity of the target user 50, the distance from the distance image sensor 10 to the center of gravity of the target user 50, or the like may be used as the feature amount. In addition, if more detailed information regarding the motor function of the target user 50 can be obtained, that information may be used as the feature amount. For example, an index related to neck flexion angle, the rise of in-body rotation, or an index related to the rising of the center of gravity such as forward movement, vertical movement, or downward movement, moving the rear leg backward, or Values of various indexes such as indexes related to crouching such as bending of the knee may be used as the feature amount of the target user 50. These index values may be automatically calculated based on the distance image, or may be input to the function improvement support device 20 by a caregiver or the like. Also, these feature quantities may be used in combination.

Further, in the above-described second embodiment, the management guidance plan and the exercise program for improving the function related to the language or the oral cavity of the target user 50 is determined. However, for example, either one of the management guidance plan and the exercise program is determined. It may be decided.

Note that some or all of the functions of the function improvement support device 20 described above may be provided by cloud computing. That is, some or all of the functions of the function improvement support device 20 may be realized by the cloud server. For example, in the function improvement support device 20, the functions of the exercise program determination unit 23, the storage unit 24, the learning data acquisition unit 26, and the machine learning unit 27 may be realized by a cloud server. The function improvement support device 20 may acquire the exercise program or exercise program name most effective in improving the function of the target user 50 by transmitting the feature amount and the attribute of the target user 50 to the cloud server. ..

In addition, the respective modifications of the first and second embodiments described above can be expressed as the following supplementary notes 1 to 4.

<Appendix 1>
An acquisition unit that acquires a feature amount related to the function of the target user,
An exercise program determining unit that determines an exercise program for improving the function of the target user from the acquired feature amount based on a learned model;
The learned model is machine-learned using a feature amount related to a function for a plurality of users, an exercise program executed by each user, and a degree of improvement of the function after execution of the exercise program as learning data to obtain the feature amount. A function improvement support device, which is a model that outputs identification information of the corresponding exercise program.

<Appendix 2>
The function is a function related to exercise or life of the user,
The acquisition unit acquires a distance image indicating the distance to the target user as the feature amount,
The exercise program determination unit, based on the learned model, from the acquired feature amount, determines a problem related to the exercise or life of the user, and an exercise program for improving the problem,
The learned model indicates, for a plurality of users, the distance image of each user, a problem associated with each user's exercise or life, an exercise program executed by each user, and an improvement degree of the function after the exercise program is executed. The function improvement support device according to appendix 1, which is a model that is machine-learned as learning data and that outputs the identification information of the problem and the exercise program corresponding to the feature amount.

<Appendix 3>
The function is a function related to a user's language or oral cavity,
The acquisition unit acquires the answer to the target user's language or oral question item and the inspection item, and the evaluation by the oral professional for the target user's language or oral evaluation item as the feature amount,
The learned model is, for a plurality of users, answers to the question items and examination items of the language or oral cavity of each user, evaluation of each user's evaluation items by the oral profession, management guidance items and exercise programs executed by each user. , And the management guidance item and the degree of improvement of the function after execution of the exercise program are machine-learned as learning data, and the identification information of the management guidance item and the identification information of the exercise program corresponding to the feature amount are output. Is a model,
The function improvement support according to appendix 1, wherein the exercise program determination unit determines a management instruction item and an exercise program for improving the function of the target user from the acquired feature amount based on the learned model. apparatus.

<Appendix 4>
Furthermore, a machine learning unit for machine learning the learned model is provided,
The machine learning unit further learns the characteristic amount of the target user who has executed the exercise program determined by the exercise program determination unit, identification information of the exercise program, and the degree of improvement of the function after execution of the exercise program. 4. The function improvement support device according to any one of appendices 1 to 3, which machine-learns the learned model as usage data.

The embodiments disclosed this time are to be considered as illustrative in all points and not restrictive. The scope of the present invention is defined not by the meanings described above but by the claims, and is intended to include meanings equivalent to the claims and all modifications within the scope.

1 Function Improvement Support System 2 Network 10 Distance Image Sensor 20 Function Improvement Support Device 21 Distance Image Acquisition Unit 23 Exercise Program Determination Unit 24 Storage Unit 25A User Information 25B Learned Model 26 Learning Data Acquisition Unit 27 Machine Learning Unit 28 User Attribute Acquisition Part 29 Answer acquisition part 30 Evaluation acquisition part 40 Terminal device 41 Exercise program acquisition part 42 Exercise program presentation part 50 Target user

Claims (7)

An acquisition unit that acquires a feature amount related to the function of the target user,
An exercise program determining unit that determines an exercise program for improving the function of the target user from the acquired feature amount based on a learned model;
The learned model is machine-learned using the feature amount related to the functions of a plurality of users and the exercise program executed by each user as learning data, and outputs identification information of the exercise program corresponding to the feature amount. A function improvement support device that is a model. The function is a function related to exercise or life of the user,
The acquisition unit acquires a distance image indicating the distance to the target user as the feature amount,
The exercise program determination unit, based on the learned model, from the acquired feature amount, determines a problem related to the exercise or life of the user, and an exercise program for improving the problem,
The learned model is machine-learned for a plurality of users by using the distance image of each user, a problem related to the exercise or life of each user, and an exercise program executed by each user as learning data, and the feature amount The function improvement support apparatus according to claim 1, wherein the function improvement support apparatus is a model for outputting the identification information of the problem and the exercise program corresponding to. The function is a function related to a user's language or oral cavity,
The acquisition unit acquires the answer to the target user's language or oral question item and the inspection item, and the evaluation by the oral professional for the target user's language or oral evaluation item as the feature amount,
The learned model includes, for a plurality of users, answers to the question items and examination items of the language or oral cavity of each user, evaluation of evaluation items of each user by an oral profession, and management guidance items and exercises executed by each user. A model that is machine-learned using a program as learning data, and outputs identification information of the management instruction item and identification information of the exercise program corresponding to the feature amount,
The function improvement according to claim 1, wherein the exercise program determination unit determines a management guidance item and an exercise program for improving the function of the target user from the acquired feature amount based on the learned model. Support device. Furthermore, a machine learning unit for machine learning the learned model is provided,
The machine learning unit further machine-learns the learned model using the feature amount of the target user who has executed the exercise program determined by the exercise program determination unit and the identification information of the exercise program as learning data. The function improvement support device according to any one of claims 1 to 3. A distance image sensor that acquires a distance image indicating the distance to the target user,
A function improvement support device according to claim 2;
A terminal that acquires a problem related to exercise or life of the target user and an exercise program for improving the function of the target user from the function improvement support device, and presents the acquired problem and the exercise program A function improvement support system equipped with a device. A function improvement support device according to claim 3;
A function improvement support system, comprising: a management instruction item and an exercise program for improving the function of a target user, and a terminal device that presents the acquired management instruction item and exercise program from the function improvement assistance device. An exercise program acquisition unit that acquires an exercise program for improving the function of the target user from the function improvement support device according to any one of claims 1 to 4.
An exercise program presenting unit that presents the exercise program acquired by the exercise program acquiring unit.

Images