Program and system for controlling device for supporting motion of target site of subject, and method for configuring device for supporting motion of target site of subject

Abstract

To provide a program or the like for controlling a device for supporting the movement of an object part of a subject.SOLUTION: A program for controlling an apparatus for assisting movement of a target part of a subject, the program being executed in a computer system comprising a processor unit, the program being configured to receive a first signal when the subject is attempting to move the target part with a first movement, the program comprising: The first signal causes the processor unit to perform a process including: indicating at least a first biological signal when the subject part is going to be moved by the first movement, the self-movable range of the subject part when the subject part is going to be moved by the first movement, and the magnitude of the force when the subject part is going to be moved by the first movement; selecting a mode for controlling the device on the basis of the received first signal; and controlling the device in the selected mode.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a system for assisting the movement of a target part of a subject, a program for controlling an apparatus for assisting the movement of a target part of a subject, and a method for configuring an apparatus for assisting the movement of a target part of a subject. [Background technology]

[0002] BACKGROUND ART For finger rehabilitation (also simply referred to as "rehabilitation"), assist devices that are attached to the fingers and assist the movements of a subject are known (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2018-108359 Summary of the Invention [Problem to be solved by the invention]

[0004] The inventors have performed rehabilitation of a subject by combining biosignals obtained from the subject with a device for assisting the subject's movements. Specifically, the inventors have performed rehabilitation of the subject by recognizing the subject's intended movements from the biosignals obtained from the subject and driving a device to assist the subject's intended movements.

[0005] However, the magnitude of the movement of the target part of the subject, the type of force output, the strength of the biosignal, etc., differ from subject to subject, and depending on the subject, it may be difficult to properly recognize the intended movement from the biosignal. For subjects with difficulty in recognizing such intended movement, the device for assisting the subject's movement must be configured differently, or it may not even be possible to use the device for assisting the subject's movement.

[0006] The present invention has been made in consideration of the above circumstances, and aims to provide a program, a system, and a method for configuring a device for assisting the movement of a target part of a subject, so that the device for assisting the movement of a target part of a subject can be adapted to multiple subjects. [Means for solving the problem]

[0007] The present invention provides, for example, the following items.

[0008] (Item 1) A program for controlling a device for assisting movement of a target part of a subject, the program being executed in a computer system including a processor unit, the program comprising: Receiving a first signal when the subject is attempting to move the target part with a first movement, the first signal indicating at least a first biological signal when the subject is attempting to move the target part with the first movement, a range of unassisted movement of the target part when the subject is attempting to move the target part with the first movement, and a magnitude of force when the subject is attempting to move the target part with the first movement; selecting a mode for controlling the device based on the received first signal; controlling the device in the selected mode; and A program that causes the processor unit to perform processing including the steps of: (Item 2) determining that the magnitude of the force is less than a predetermined threshold; if the magnitude of the force is less than the predetermined threshold, receiving a biological signal labeled with an indication of an intended first movement as a first biological signal; Item 1. The program according to item 1, further comprising: (Item 3) Selecting a mode for controlling the device comprises: selecting a movement sensing mode when the subject moves the target body part within the unassisted range of motion; Controlling the device in the motion sensing mode includes: sensing movement of the subject by the target area; controlling the device based on the sensed movement to avoid interfering with the movement; Item 3. The program according to item 1 or 2, comprising: (Item 4) Selecting a mode for controlling the device comprises: selecting a biological signal sensing mode when the subject moves the target part outside the range of unassisted movement, Controlling the device in the biosignal sensing mode includes: receiving a biological signal acquired when the subject intends to move the target part; determining, based on the biological signal, that the intended movement of the subject is the first movement; controlling the device to assist the first movement; 4. The program according to any one of items 1 to 3, comprising: (Item 5) receiving a second signal when the subject is attempting to move the target part with a second movement, the second signal indicating at least a second biological signal when the subject is attempting to move the target part with the second movement, a range of unassisted movement of the target part when the subject is attempting to move the target part with the second movement, and a magnitude of force when the subject is attempting to move the target part with the second movement; and selecting a mode for controlling the device further comprises: 5. The program according to any one of items 1 to 4, further comprising selecting a mode for controlling the device based on the first signal and the second signal. (Item 6) Selecting a mode for controlling the device comprises: determining whether the first biological signal and the second biological signal can be distinguished from each other based on their feature amounts; selecting a first mode when the first biological signal and the second biological signal can be distinguished by their feature amounts; Item 6. The program according to Item 5, comprising: (Item 7) When the first mode is selected, the feature amount of the first biological signal and the feature amount of the second biological signal are learned. and controlling the device in the first mode further comprises: receiving a biological signal acquired when the subject intends to move the target part; determining whether the movement intended by the subject is the first movement or the second movement based on the learned feature; controlling the device to assist the determined movement; and Item 7. The program according to Item 6, comprising: (Item 8) Selecting a mode for controlling the device comprises: determining whether the first biological signal and the second biological signal can be distinguished from each other based on their feature amounts; When the first biological signal and the second biological signal cannot be distinguished from each other based on their feature amounts, determining whether or not the biological signal when the subject is in a relaxed state can be distinguished from the first biological signal or the second biological signal based on their intensities; selecting a second mode when the biological signal when the subject is in a relaxed state can be distinguished from the first biological signal or the second biological signal based on their intensities; selecting a third mode when it is not possible to distinguish between the biological signal when the subject is in a relaxed state and the first biological signal or the second biological signal based on their intensities; 8. The program according to any one of items 5 to 7, comprising: (Item 9) Controlling the device in the second mode comprises: receiving a biological signal acquired when the subject intends to move the target part; determining whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the intensity of the biological signal; controlling the device to assist one of the first movement and the second movement when it is determined that the movement intended by the subject is the first movement or the second movement; controlling the device to assist the other of the first movement and the second movement when the movement intended by the subject is determined to be a weakness movement; Item 9. The program according to Item 8, comprising: (Item 10) When the third mode is selected, the feature amount of the first biological signal or the feature amount of the second biological signal and the feature amount of the biological signal in the relaxed state are learned. and controlling the device in the third mode further comprises: receiving a biological signal acquired when the subject intends to move the target part; determining whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the feature amount of the biological signal; controlling the device to assist one of the first movement and the second movement when it is determined that the movement intended by the subject is the first movement or the second movement; controlling the device to assist the other of the first movement and the second movement when the movement intended by the subject is determined to be a weakness movement; 10. The program according to item 8 or 9, comprising: (Item 11) Selecting a mode for controlling the device comprises: determining whether the first biological signal and the second biological signal can be distinguished based on their intensities; selecting a fourth mode when the first biological signal and the second biological signal can be distinguished based on their intensities; 11. The program according to any one of items 5 to 10, comprising: (Item 12) Controlling the device in the fourth mode comprises: receiving a biological signal acquired when the subject intends to move the target part; determining whether the intended movement of the subject is the first movement or the second movement based on the strength of the biological signal; controlling the device to assist the determined movement; and Item 12. The program according to Item 11, comprising: (Item 13) 13. The program according to any one of items 1 to 12, wherein the target area is an upper body area. (Item 14) Item 14. The program according to item 13, wherein the target site is a finger. (Item 15) 13. The program according to any one of items 5 to 12, wherein the first movement is a movement of clenching the hand, and the second movement is a movement of opening the hand. (Item 16) A system for assisting movement of a target part of a subject, comprising: A device for assisting the movement of a target part of a subject; acquiring means for acquiring a biological signal from the subject; sensing means for sensing movement of the subject; a control means for controlling the device; The control means comprises: receiving a first signal from the acquisition means and the sensing means when the subject is attempting to move the target part with a first movement, the first signal indicating at least a first biological signal when the subject is attempting to move the target part with the first movement, the range of unassisted movement of the target part when the subject is attempting to move the target part with the first movement, and the magnitude of force when the subject is attempting to move the target part with the first movement; selecting a mode for controlling the device based on the received first signal; controlling the device in the selected mode; and A system that is configured to: (Item 17) 1. A method for configuring a device for assisting movement of a target region of a subject, the method comprising: Receiving a first signal when the subject is attempting to move the target part with a first movement, the first signal indicating at least a first biological signal when the subject is attempting to move the target part with the first movement, a range of unassisted movement of the target part when the subject is attempting to move the target part with the first movement, and a magnitude of force when the subject is attempting to move the target part with the first movement; selecting a mode for controlling the device based on the received first signal; setting the device to the selected mode; A method comprising: [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a program, a system, and a method for configuring a device for assisting the movement of a target part of a subject, for controlling the device, and thereby the device for assisting the movement of a target part of a subject can be adapted to multiple subjects, even if the magnitude of the movement, the force output, the strength of the biosignal, etc., differs among the multiple subjects. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a system 10 for assisting the movement of a target part of a subject. [Figure 2A] FIG. 2 shows an example of the configuration of control means 200. [Figure 2B] FIG. 1 is a diagram showing an example of the configuration of a control means 200′, which is an alternative embodiment of the control means 200. [Figure 3] 1 is a diagram showing the relationship between a myoelectric signal as a biosignal, which is an example of a signal received by the receiving means 210, and the angle of the arm 112 relative to the base 111. [Figure 4] 1 is a flowchart showing an example of a process (process 400) performed by the system 10 for assisting the movement of a target part of a subject. [Figure 5] A flowchart showing an example of the detailed flow of step S401 in the process 400 when performed by the control means 200'. [Figure 6] 6 is a flowchart showing another example of a process (process 600) performed by the system 10 for assisting the movement of a target part of a subject. [Figure 7A] 6 is a flowchart showing an example of a detailed flow of step S603 in process 600. [Figure 7B] 6 is a flowchart showing an example of a detailed flow of step S603 in process 600. [Figure 8] 8 is a flowchart showing an example of a process (process 800) performed by the system 10 for assisting the movement of a target part of a subject. DETAILED DESCRIPTION OF THE INVENTION

[0011] The present invention will be described below.Unless otherwise specified, it should be understood that the terms used in this specification are used in the meanings generally used in the relevant field.Therefore, unless otherwise defined, all technical terms and scientific terms used in this specification have the same meaning as those generally understood by those skilled in the art to which this invention belongs.In the event of any discrepancy, this specification (including definitions) shall prevail.

[0012] (Definition of terms) In this specification, the term "biological signal" refers to a signal obtained from a living organism. Examples of biological signals include, but are not limited to, electromyographic signals indicating muscle activity of a living organism, electrocardiographic signals indicating cardiac activity of a living organism, electroencephalograms indicating brain activity of a living organism, nerve signals transmitted in nerve cells, muscle sound signals indicating muscle activity of a living organism, and muscle hardness signals indicating muscle hardness of a living organism.

[0013] As used herein, "subject" refers to a person receiving movement assistance.

[0014] In this specification, the term "target part" refers to a body part that is the target of receiving movement assistance. The target part may be a part of the body or the entire body.

[0015] As used herein, "about" means ±10% of the preceding numerical value.

[0016] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0017] (Configuration of a system for assisting the movement of a target part of a subject) FIG. 1 shows an example of the configuration of a system 10 for assisting the movement of a target part of a subject.

[0018] The system 10 includes a device 100 for assisting the movement of a target part of a subject, a control means 200 for controlling the device 100, an acquisition means 300 for acquiring a biosignal from the subject, and a sensing means 400 for sensing the movement of the subject.

[0019] The device 100 is configured to be attachable to a part of the subject's body that is to be rehabilitated (target part). The device 100 is attached to the target part and can support the movement of the target part by applying force to the target part.

[0020] The target part may be any part of the body. The target part may be, for example, a finger, an arm, a shoulder, a leg, a knee, an ankle, an upper body, a lower body, etc. Preferably, the target part may be a part of the body that performs voluntary movement. The part of the body that performs voluntary movement may be, for example, a part of the upper body.

[0021] 1, the target area is shown as fingers. The device 100 is attached to the fingers and can assist the flexion and extension of each finger by applying force around the joints of each finger.

[0022] The device 100 can be attached to the target site by any attachment means. The material and shape of the attachment means are not particularly limited as long as it allows the device 100 to be attached to the target site. For example, the attachment means may be made of cloth, leather, resin, paper, or rubber. The shape of the attachment means may be flat, belt-like, or annular.

[0023] In the example shown in FIG. 1, the device 100 is worn on the finger by wrapping a belt-like wearing means around the finger.

[0024] The device 100 includes a portion 110 that is attached to the target site, and the portion 110 that is attached to the target site includes a base portion 111 and an arm portion 112 that can move relative to the base portion 111. By attaching both the base portion 111 and the arm portion 112 to the target site and driving the arm portion 112 so that the arm portion 112 moves relative to the base portion 111, a force can be applied to the target site.

[0025] The device 100 can drive the arm unit 112 by any driving means. The driving means may be, for example, a wire, a link mechanism, or a rack and pinion. In the example shown in FIG. 1, a wire 120 is shown as the driving means. The driving unit that drives the wire or the like may be any means capable of driving the wire or the like. For example, it may be a motor, or an air or hydraulic cylinder. Furthermore, the driving unit may be provided in the part 110 that is attached to the target site, or may be provided remotely from the part 110 that is attached to the target site.

[0026] In the example shown in FIG. 1, the driving unit 130 that drives the wire 120 is provided remotely from the portion 110 that is attached to the target site.

[0027] The device 100 is controlled by a control means 200. The control means 200 may be any means capable of controlling the device 100. The control means 200 may be, for example, a dedicated controller or a general-purpose information processing device. The control means 200 may be, for example, an information processing device of a desktop type, a laptop type, a tablet type, a smartphone type, or the like. The control means 200 may be, for example, installed remotely from the target site, or may be attached to the target site together with the device 100. The control means 200 may be, for example, implemented as a means separate from the device 100, or may be implemented as a means mounted within the device 100.

[0028] In the example shown in FIG. 1, the control means 200 is shown as a laptop-type information processing device.

[0029] The control means 200 can transmit a control signal to the driving unit 130 to control the driving unit 130 and, ultimately, the device 100. The control means 200 and the device 100 (or the driving unit 130) can be connected in any manner. For example, the control means 200 and the device 100 (or the driving unit 130) can be connected by wire or wirelessly. For example, the control means 200 and the device 100 (or the driving unit 130) can be connected via a network (e.g., the Internet, a LAN, etc.).

[0030] The control means 200 can receive the biosignal acquired by the acquisition means 300. The acquisition means 300 can be any means capable of acquiring the biosignal from the subject. For example, the acquisition means 300 can be a myoelectric device equipped with an electromyographic sensor capable of detecting the myoelectric signal of a living body, an electroencephalograph equipped with an electroencephalogram sensor capable of detecting the electroencephalogram of a living body, a nerve signal meter equipped with a nerve signal sensor capable of directly acquiring the nerve signal of a living body, a muscle sound meter equipped with a muscle sound sensor capable of detecting the muscle sound signal of a living body, a muscle hardness meter capable of measuring the hardness of the muscle of a living body, etc.

[0031] The obtaining means 300 may, for example, comprise a detecting unit and a transmitting unit.

[0032] The detector may be any means configured to detect a biological signal, such as an electromyographic sensor capable of detecting a biological myoelectric signal, an electrocardiographic sensor capable of detecting a biological electrocardiographic signal, an electroencephalogram sensor capable of detecting a biological electroencephalogram, an electroencephalogram sensor capable of detecting a biological electroencephalogram, a nerve signal sensor capable of directly acquiring a biological nerve signal, or a muscle sound sensor capable of detecting a biological muscle sound signal.

[0033] The transmitting unit is configured to be able to transmit a signal to the outside of the acquiring means 300. The transmitting unit transmits the signal to the outside of the acquiring means 300 wirelessly or via a wired connection. The transmitting unit may transmit the signal, for example, using a wireless LAN such as Wi-Fi. The transmitting unit may transmit the signal using a short-range wireless communication such as Bluetooth (registered trademark). The transmitting unit transmits, for example, a biological signal detected by the detecting unit to the control means 200.

[0034] The acquiring means 300 and the control means 200 are connected in any manner. For example, the acquiring means 300 and the control means 200 may be connected by wire or wirelessly. For example, the acquiring means 300 and the control means 200 may be connected via a network (for example, the Internet, a LAN, etc.).

[0035] The acquisition unit 300 can be placed at any position on the subject's body as long as it is a position where a biosignal generated when the subject intends to move the target part can be detected. For example, if the acquisition unit 300 acquires an electromyographic signal, the acquisition unit 300 can be placed on or near a muscle that moves the target part. For example, if the acquisition unit 300 acquires an electroencephalogram, the acquisition unit 300 can be placed on the subject's head.

[0036] 1, one acquisition means 300 is attached to the body, but any number of acquisition means 300 may be used depending on the biosignals to be acquired. For example, at least two acquisition means 300 may be used, including a first acquisition means that acquires biosignals mainly due to a first movement and a second acquisition means that acquires biosignals mainly due to a second movement.

[0037] For example, two acquisition means 300 can be used to acquire biosignals when the target region is bent and biosignals when the target region is stretched. In this case, one of the two acquisition means 300 can acquire biosignals when the target region is bent, and the other of the two acquisition means 300 can acquire biosignals when the target region is stretched. In this case, for example, three or more acquisition means 300 can be used, with some of the three or more acquisition means 300 acquiring biosignals when the target region is bent and some other of the three or more acquisition means 300 acquiring biosignals when the target region is stretched.

[0038] The sensing means 400 is configured to sense the movement of the subject. The sensing means 400 may be provided within the device 100 or may be provided external to the device 100. In the example shown in Figure 1, the sensing means 400 is provided within the device 100.

[0039] The sensing means 400 can sense the movement of the subject, for example, by sensing the relative movement of the arm unit 112 with respect to the base unit 111. The sensing means 400 includes, for example, but is not limited to, an angle sensor capable of sensing the angle of the arm unit 112 with respect to the base unit 111, a position sensor capable of sensing the position of the arm unit 112 with respect to the base unit 111, and a force sensor capable of sensing the force applied to the base unit 111.

[0040] The sensing means 400 can, for example, sense the movement of the subject and output a signal indicating the range of independent movement of the subject's target part when the subject is moving the target part. The sensing means 400 can also output, for example, a signal indicating that the subject is moving the target part within the range of independent movement and / or a signal indicating that the subject is moving the target part outside the range of independent movement.

[0041] The sensing means 400 can, for example, sense the movement of the subject, thereby outputting a signal indicating the magnitude of force exerted when the subject moves the target region. The signal indicating the magnitude of force exerted when the subject moves the target region may be, for example, a binary signal indicating whether or not force is being exerted, or a multi-value signal indicating the magnitude of force numerically. The sensing means 400 can, for example, apply a constant torque to the arm unit 112 and sense a change in the angle of the arm unit 112 relative to the base unit 111, thereby outputting a signal indicating the magnitude of force exerted when the subject moves the target region. If a change in angle is detected, this indicates that the subject is exerting a force at least large enough to overcome the applied torque.

[0042] The sensing means 400 can, for example, capture images of the subject's movements and sense the subject's movements from the captured images (e.g., multiple still images or video images). This can be achieved, for example, by known motion capture techniques.

[0043] FIG. 2A shows an example of the configuration of the control means 200.

[0044] The control means 200 comprises a receiving section 210 , a processor section 220 , a memory section 230 and an output section 240 .

[0045] The receiving unit 210 is configured to be able to receive signals from outside the control means 200. The receiving unit 210 receives signals from outside the control means 200 wirelessly or via a wired connection. The receiving unit 210 may receive signals using, for example, a wireless LAN such as Wi-Fi. The receiving unit 210 may receive signals using short-range wireless communication such as Bluetooth (registered trademark). The receiving unit 210, for example, receives from the acquiring unit 300 a biosignal detected by the acquiring unit 300. The receiving unit 210, for example, receives from the sensing unit 400 a signal acquired by the sensing unit 400. The receiving unit 210, for example, receives a signal including the biosignal received from the acquiring unit 300 and the signal received from the sensing unit 400. The receiving unit 210, for example, receives an input from a user (for example, a doctor, a physical therapist, an occupational therapist, a rehabilitation trainer, a test subject, etc.).

[0046] FIG. 3 shows the relationship between a myoelectric signal as a biosignal, as an example of a signal received by the receiving means 210, and the angle of the arm 112 relative to the base 111.

[0047] In FIG. 3, the vertical axis indicates the myoelectric potential (EMG) of an electromyographic signal, and the horizontal axis indicates the angle (deg) of the arm part 112 with respect to the base part 111.

[0048] 3(a) and 3(b) show an example of the relationship between the angle and the myoelectric signal obtained when opening the hand. Fig. 3(a) shows the relationship between the myoelectric signal obtained from the myoelectric sensor placed at the position of the muscle (extensor muscle) that generates myoelectricity when the target part is extended, and the angle of the arm part 112 relative to the base part 111. Fig. 3(b) shows the relationship between the angle of the arm part 112 relative to the base part 111 and the myoelectric signal obtained from the myoelectric sensor placed at the position of the muscle (flexor muscle) that generates myoelectricity when the target part is flexed.

[0049] Figures 3(c) and 3(d) show examples of the relationship between the myoelectric signal obtained when a hand is clenched and the angle. Figure 3(c) shows the relationship between the myoelectric signal obtained from the myoelectric sensor placed at the position of the muscle (extensor muscle) that generates myoelectricity when the target part is extended and the angle of the arm part 112 relative to the base part 111. Figure 3(d) shows the relationship between the myoelectric signal obtained from the myoelectric sensor placed at the position of the muscle (flexor muscle) that generates myoelectricity when the target part is flexed and the angle of the arm part 112 relative to the base part 111.

[0050] The signals shown in Figures 3(a) and 3(b) can be labeled as "hand opening movements" because they contain EMG signals obtained when the hand is opened. The signals shown in Figures 3(c) and 3(d) can be labeled as "hand opening movements" because they contain EMG signals obtained when the hand is closed.

[0051] For example, if a predetermined threshold is set, it can be determined that the extensor muscles are being exerted because the myoelectric signal acquired from the myoelectric sensor placed at the position of the extensor muscles shown in Figure 3(a) exceeds the threshold (indicated by the dash-dotted line), while the myoelectric signal acquired from the myoelectric sensor placed at the position of the flexor muscles shown in Figure 3(b) does not exceed the threshold (indicated by the dash-dotted line).For example, it can be determined that the flexor muscles are being exerted because the myoelectric signal acquired from the myoelectric sensor placed at the position of the extensor muscles shown in Figure 3(c) does not exceed the threshold (indicated by the dash-dotted line), while the myoelectric signal acquired from the myoelectric sensor placed at the position of the flexor muscles shown in Figure 3(d) exceeds the threshold (indicated by the dash-dotted line).

[0052] The biological signal received by the receiving means 210 may also include a time component, that is, the biological signal received by the receiving means 210 may indicate a time-series change of the biological signal.

[0053] For example, the biological signal received by the receiving means 210 can be represented in a three-dimensional graph by adding a time axis to the graph shown in FIG.

[0054] When the biosignal includes a time component, the processor unit 220 can extract the feature of the biosignal by frequency analysis of the biosignal. The frequency analysis can be, for example, a Fourier transform, but is not limited to this. Any method can be used for the frequency analysis as long as it can extract the feature.

[0055] A feature can have any dimension. For example, the dimension of a feature can be 2, 4, 8, 9, 16, 18, 27, 32, etc. An n-dimensional feature can be represented as a vector with n components (n is an integer).

[0056] For example, if the acquisition means 300 has a first acquisition means (e.g., an acquisition means for acquiring a biosignal from an extensor muscle) and a second acquisition means (e.g., an acquisition means for acquiring a biosignal from a flexor muscle), feature amounts can be extracted from the biosignals acquired by the first acquisition means and the biosignals acquired by the second acquisition means. In one embodiment, when extracting feature amounts from myoelectric signals as biosignals, for example, feature amounts related to extensor muscles and feature amounts related to flexor muscles can be extracted from myoelectric signals acquired from myoelectric sensors placed at the positions of extensor muscles and flexor muscles, respectively. In this case, the number of dimensions of the feature amounts can be, for example, 27.

[0057] The feature amount may be extracted for each stage of the subject's movement. For example, in the example shown in FIG. 3, the feature amount may be extracted for each angle of the arm unit 112 with respect to the base unit 111. The angle may be, for example, in increments of 1 degree, 10 degrees, 30 degrees, or 45 degrees. For example, in the case of increments of 30 degrees, the feature amount when the angle θ of the arm unit 112 with respect to the base unit 111 is 0 degrees, the feature amount when θ=30 degrees, the feature amount when θ=60 degrees, the feature amount when θ=90 degrees, the feature amount when θ=120 degrees, etc. may be extracted.

[0058] As described above, the signal can be labeled with the intended movement. Therefore, in one embodiment, the signal received by the receiving means 210 can be represented by a vector of (intended movement, angle of the arm unit 112 relative to the base unit 111, n-dimensional feature vector). In one example, a biometric signal when the subject's fingers are at 30 degrees relative to the base unit 111 when opening their hand can be represented by (hand opening, 30 degrees, 27-dimensional feature vector). In another embodiment, the biometric signal received by the receiving means 210 can be represented by a vector of (intended movement, angle of the arm unit 112 relative to the base unit 111, n-dimensional feature vector related to the extensor muscles, m-dimensional feature vector related to the flexor muscles). In one example, a biometric signal when the subject's fingers are at 30 degrees relative to the base unit 111 when opening their hand can be represented by (hand opening, 30 degrees, 9-dimensional feature vector related to the extensor muscles, 18-dimensional feature vector related to the flexor muscles).

[0059] The signal data labeled as described above can be processed as data when an attempt is made to move a target region. For example, it is possible to compare (comparison of strength, comparison of feature amount, etc.) data when an attempt is made to move a target region with a first movement (e.g., opening the hand) with data when an attempt is made to move the target region with a second movement (e.g., clenching the hand). For example, it is possible to compare (comparison of strength, etc.) data related to flexor muscles when an attempt is made to move a target region with a first movement (e.g., opening the hand) with data related to extensor muscles when an attempt is made to move the target region with the first movement, and to compare (comparison of strength, etc.) data related to flexor muscles when an attempt is made to move a target region with a second movement (e.g., clenching the hand) with data related to extensor muscles when an attempt is made to move the target region with the second movement. Furthermore, it is possible to compare data obtained when attempting to move a target body part with a first movement (e.g., opening the hand), data obtained when attempting to move a target body part with a second movement (e.g., clenching the hand), and data obtained when the target body part is relaxed (or when no attempt is made to move the target body part). For example, it is also possible to compare (e.g., compare strength) data obtained when the flexor muscles are relaxed (or when no attempt is made to move the target body part) with data obtained when the extensor muscles are relaxed (or when no attempt is made to move the target body part). For example, it is possible to perform machine learning on data obtained when attempting to move a target body part with a first movement and data obtained when attempting to move the target body part with a second movement, or on data obtained when attempting to move a target body part with a first movement, data obtained when attempting to move the target body part with a second movement, and data obtained when the target body part is relaxed.

[0060] 2A again, the processor unit 220 controls the overall operation of the control means 200. The processor unit 220 reads out a program stored in the memory unit 230 and executes the program, thereby making it possible for the control means 200 to function as a device that executes desired steps.

[0061] The memory unit 230 stores programs required for executing processes, data required for executing the programs, and the like. For example, the memory unit 230 may store a program for implementing processes for assisting the movement of a target part of a subject (for example, processes described later in FIGS. 4, 5, 6, 7A, 7B, and 8). Here, how the program is stored in the memory unit 230 does not matter. For example, the program may be pre-installed in the memory unit 230. Alternatively, the program may be installed in the memory unit 230 by being downloaded via a network, or may be installed in the memory unit 230 via a storage medium such as an optical disk or USB.

[0062] The output unit 240 is configured to be able to output a signal to the outside of the control means 200. The control means 200 is able to output a signal to the device 100. There is no restriction on how the output unit 240 outputs the signal. For example, the output unit 240 may transmit the signal to the outside of the control means 200 via a wired connection or wirelessly. For example, the output unit 240 may convert the signal into a format that can be handled by the device 100 to which the signal is output, or may adjust the response speed to be able to be handled by the device 100 to which the signal is output, and then transmit the signal.

[0063] The processor section 220 includes a mode selection means 221 and a control signal generation means 222 .

[0064] The mode selection means 221 is configured to select a mode for controlling the device 100 from among a plurality of modes.

[0065] The multiple modes include, for example, a motion sensing mode. In the motion sensing mode, the control means 200 controls the device 100 based on the subject's motion sensed by the sensing means 400. In the motion sensing mode, the control means 200 can control the device 100 so as not to interfere with the sensed subject's motion. That is, in the motion sensing mode, the device 100 is driven to counteract resistance inherent in the device 100 due to interference between the components of the device 100, etc. This allows the subject to move the target body part as if they were not wearing the device 100. Controlling the device 100 in the motion sensing mode is preferably performed, for example, when the subject is moving the target body part within its range of independent movement. This allows the device 100 to assist the subject's movement of the target body part without interfering with the subject's movement within the range of independent movement. This leads to more efficient rehabilitation of the subject. Furthermore, within the range of independent movement of the subject, controlling the device in the motion sensing mode rather than the biosignal sensing mode described below can reduce erroneous recognition related to biosignal sensing.

[0066] The plurality of modes includes, for example, a biosignal sensing mode. The biosignal sensing mode is a mode in which the control means 200 controls the device 100 based on the biosignal acquired by the acquisition means 300. In the biosignal sensing mode, a movement intended by the subject is recognized based on the biosignal, and the device 100 can be controlled to support the recognized movement. For example, in the biosignal sensing mode, the control means 200 can determine whether the movement intended by the subject is a specific movement and control the device 100 to support the determined specific movement. Alternatively, for example, in the biosignal sensing mode, the control means 200 can determine whether the movement intended by the subject is a first movement or a second movement among multiple movements and control the device 100 to support the determined first movement or second movement.

[0067] The first and second movements may be, for example, paired movements of a target part of a subject. Examples of paired movements include, but are not limited to, flexion-extension, adduction-abduction, internal rotation-external rotation, pronation-supination, etc. For example, if the target part is a finger, the paired movement may be, for example, clenching-opening (fist-open).

[0068] Although the present specification describes the multiple movements as including a first movement and a second movement different from the first movement, it should be understood that the multiple movements are not limited to the first and second movements. The multiple movements may include any number of movements greater than or equal to three, such as a third movement, a fourth movement, etc. That is, in the biosignal sensing mode, the control means 200 can determine whether the movement intended by the subject is the first movement, the second movement, etc., or the nth movement (n≧3) of the multiple movements, and control the device 100 to assist the determined first movement, the second movement, etc., or the nth movement.

[0069] For example, the device 100 is controlled to drive the arm unit 112 relative to the base unit 111 in the direction of the recognized movement, thereby allowing the subject to achieve the intended movement even if the movement is outside the range of their own movement.

[0070] The biosignal sensing mode includes, for example, a first mode. In the first mode, the control means 200 determines whether the movement intended by the subject is a first movement or a second movement among multiple movements based on the feature amount of the biosignal, and controls the device 100 to assist the determined movement. In the first mode, the control means 200 determines whether the movement intended by the subject is a first movement or a second movement based on the feature amount of the biosignal acquired during movement assistance execution, and controls the device 100 to assist the first movement if the movement intended by the subject is determined to be the first movement, and controls the device 100 to assist the second movement if the movement intended by the subject is determined to be the second movement. In the first mode, the control means 200 may also determine based on the feature amount of the biosignal that the movement intended by the subject is a relaxation movement (or that the subject does not intend a movement). In this case, the control means 200 can prevent the device 100 from being controlled. This can prevent the device 100 from moving when the subject intends a relaxation movement (or when the subject does not intend a movement).

[0071] That is, in the first mode, the control means 200 controls the device 100 to assist the first movement when the subject intends the first movement, to assist the second movement when the subject intends the second movement, and not to assist the movement when the subject intends the relaxation movement (or when no movement is intended), by determining three states: (1) the first movement, (2) the second movement, and (3) the relaxation movement (or no movement is intended) based on the features of the biological signals acquired during the assistance execution.

[0072] The feature of the biosignal is extracted by frequency analysis of the biosignal including a time component. The frequency analysis may be, for example, but is not limited to, a Fourier transform. Any method can be used for the frequency analysis as long as it can extract the feature. The feature can have any dimension. For example, the dimension of the feature can be 2, 4, 8, 9, 16, 18, 27, 32, etc. An n-dimensional feature can be represented as a vector having n components (n is an integer).

[0073] The feature amount may be extracted for each stage of the subject's movement, for example. The feature amount can be extracted for each angle of a joint related to a target part of the living body, for example. The angle may be in increments of 1 degree, 10 degrees, 30 degrees, or 45 degrees. For example, in the case of increments of 30 degrees, the feature amount when the joint angle θ=0 degrees, the feature amount when θ=30 degrees, the feature amount when θ=60 degrees, the feature amount when θ=90 degrees, the feature amount when θ=120 degrees, etc. can be extracted.

[0074] In the first mode, the control means 200 distinguishes between the first movement and the second movement based on the feature amount of the biological signal by using a machine learning model prepared in advance to distinguish between the first movement and the second movement. The prepared machine learning model may be a model that has learned the feature amount of the biological signal and the label attached to the biological signal.

[0075] The machine learning model may be, for example, a neural network model. The neural network may have an input layer, a hidden layer, and an output layer. The neural network may have one or more hidden layers. The number of nodes in the input layer of the neural network corresponds to the number of dimensions of the input data. The number of nodes in the output layer of the neural network corresponds to the number of dimensions of the output data. The hidden layer of the neural network may include any number of nodes. The weight coefficient of each node in the hidden layer of the neural network may be calculated using training data. The training data may be features extracted from biosignals and labels attached to the biosignals. For example, the weight coefficient of each node may be calculated so that when features extracted from biosignals are input to the input layer, the value of the output layer corresponds to the label attached to the biosignal. When 27-dimensional features extracted from biosignals are input and two possible output states, a first movement or a second movement, are output, the number of nodes in the input layer is 27 and the number of nodes in the output layer is 2. For example, as described below, when the subject's movement stage is also input, one additional node is added to the input layer. For example, as will be described later, if three types of movement are output, namely, the first movement, the second movement, and the relaxed movement, the number of nodes in the output layer will be three.

[0076] For example, to enable a machine learning model to distinguish between an opening hand movement and a clenching hand movement, a set of training data (input training data, output training data) for training the machine learning model may be (feature values ​​extracted from biosignals obtained when the subject makes an opening hand movement, a value indicating the opening hand movement), and (feature values ​​extracted from biosignals obtained when the subject makes a closing hand movement, a value indicating the closing hand movement). It is preferable to acquire training data from multiple subjects and train the multiple training data. When feature values ​​extracted from biosignals obtained when the subject makes a certain movement are input to the machine learning model prepared in this manner, the machine learning model can output either a value indicating that the movement is a first movement or a value indicating that the movement is a second movement.

[0077] In one embodiment, multiple machine learning models may be prepared for each stage of the subject's movement. For example, a series of movements of the subject may be divided into multiple stages, and a machine learning model may be prepared for each of the multiple stages. In one embodiment, when a target part of a living organism is moved around a joint associated with that part, multiple machine learning models may be prepared for each joint angle. For example, multiple machine learning models may be prepared, including a first machine learning model applicable to joint angles of 0 degrees ≦ θ < 30 degrees, a second machine learning model applicable to joint angles of 30 degrees ≦ θ < 60 degrees, a third machine learning model applicable to joint angles of 60 degrees ≦ θ < 90 degrees, and a fourth machine learning model applicable to joint angles of 90 degrees ≦ θ. This allows a machine learning model appropriate for each stage of the subject's movement to be used, thereby improving the accuracy of movement recognition.

[0078] In another embodiment, the machine learning model may also learn the stage of the subject's movement. In this case, the training data may be a value indicating which stage of the subject's movement sequence the subject is in, a feature extracted from the biosignal obtained at that stage, and a label attached to the biosignal. For example, in order for the machine learning model to be able to distinguish between hand opening movements and hand clenching movements, a set of training data (input training data, output training data) for training the machine learning model may be ((value indicating that joint angle θ=0 degrees, value of feature quantity extracted from biosignals obtained when the hand was opened at a joint angle θ=0 degrees), value indicating hand opening movements), ((value indicating that joint angle θ=30 degrees, value of feature quantity extracted from biosignals obtained when the hand was opened at a joint angle θ=30 degrees), value indicating hand opening movements), ((value indicating that joint angle θ=60 degrees, value of feature quantity extracted from biosignals obtained when the hand was opened at a joint angle θ=60 degrees), value indicating hand opening movements), ((value indicating that joint angle θ=90 degrees, value of feature quantity extracted from biosignals obtained when the hand was opened at a joint angle θ=90 degrees) The training data may be, for example, ((a value indicating a joint angle θ=0°, a value indicating a joint angle θ=0° of a feature extracted from a biosignal obtained when the hand was closed, at a joint angle θ=30°), a value indicating a hand closing movement), ((a value indicating a joint angle θ=60°, a value indicating a joint angle θ=60° of a feature extracted from a biosignal obtained when the hand was closed, at a joint angle θ=90°), a value indicating a hand opening movement), ((a value indicating a joint angle θ=0°, a value indicating a hand closing movement), a value indicating a hand closing movement), ((a value indicating a joint angle θ=0°, a value indicating a hand closing movement), a value indicating a hand closing movement), etc. It is preferable to acquire training data from a plurality of subjects and train a plurality of training data.When the machine learning model prepared in this way is input with the features extracted from the biosignals acquired when the subject makes a certain movement and the joint angles at that time, the machine learning model can output a value indicating whether the movement is a first movement or a second movement.

[0079] The machine learning model described above was a two-state discrimination model that distinguishes between the first and second movements. For example, a three-state discrimination model is used to distinguish between three states, (1) the first movement, (2) the second movement, and (3) a relaxed movement (or no movement intended), as described above.

[0080] In the first mode, the first movement and the second movement (and the relaxation movement) are distinguished based on the feature amount of the biosignal, so that even if there is only a small difference in the strength of the biosignal due to the difference in the movement, the first movement and the second movement (and the relaxation movement) can be distinguished with high accuracy and the first movement or the second movement can be supported. The first mode is particularly useful, for example, when the strength of the biosignal is so similar or weak that the first movement and the second movement (and the relaxation movement) cannot be distinguished from the strength of the biosignal.

[0081] For example, when assisting with a clenching movement and an opening movement of the hands, if the biosignals resulting from the clenching movement and the opening movement of the hands can be distinguished by their feature amounts, device 100 can be controlled to assist the clenching movement when it is determined that the movement intended by the subject is a clenching movement based on the feature amounts of the biosignals acquired during movement assistance execution, and can assist the opening movement when it is determined that the movement intended by the subject is an opening movement of the hands. Alternatively, for example, when the biosignals resulting from the clenching movement, the opening movement of the hands, and the relaxing movement of the hands can be distinguished by their feature amounts, device 100 can be controlled to assist the clenching movement when it is determined that the movement intended by the subject is a clenching movement based on the strength of the biosignals acquired during movement assistance execution, can assist the opening movement when it is determined that the movement intended by the subject is an opening movement of the hands, and can not assist the movement when it is determined that the movement intended by the subject is a relaxing movement.

[0082] The biosignal sensing mode includes, for example, a second mode. In the second mode, the control means 200 determines whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the intensity of the biosignal, and controls the device 100 to assist either the first movement or the second movement based on the determination. In the second mode, the control means 200 determines whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the intensity of the biosignal acquired during movement assistance execution, and controls the device 100 to assist either the first movement or the second movement if it is determined that the movement intended by the subject is the first movement or the second movement, and controls the device 100 to assist the other of the first movement or the second movement if it is determined that the movement intended by the subject is a relaxation movement. When the movement intended by the subject is determined to be the first movement or the second movement, whether the movement to be assisted will be the first movement or the second movement can be set, for example, by a user (e.g., a doctor, physical therapist, occupational therapist, rehabilitation trainer, subject, etc.).

[0083] In the second mode, the control means 200 can, for example, determine whether the strength of the biosignal exceeds a preset threshold, and determine that the movement is the first or second movement if it is determined that the strength of the biosignal exceeds the threshold, and determine that the movement is a relaxation movement if it is determined that the strength of the biosignal does not exceed the threshold. Alternatively, the control means 200 can, for example, determine whether the strength of the biosignal acquired by a first acquisition means that acquires a biosignal mainly due to the first movement and the strength of the biosignal acquired by a second acquisition means that acquires a biosignal mainly due to the second movement each exceed a threshold, and determine that the movement is the first or second movement if it is determined that the strength of either biosignal exceeds the threshold, and determine that the movement is a relaxation movement if it is determined that the strength of neither biosignal exceeds the threshold.

[0084] The threshold may be any value. The threshold may be a preset fixed value or a variable value. If the threshold is a variable value, for example, the threshold may be varied for each subject. The threshold may be set, for example, based on the maximum and / or minimum values ​​of the intensity of the biosignal acquired from the subject. For example, when the minimum value of the intensity of the biosignal is 0% and the maximum value of the intensity of the biosignal is 100%, the threshold may be a value between about 50% and about 95%, or a value between about 60% and about 90%, such as about 60%, about 70%, or about 80%. The threshold may be set, for example, based on the maximum and / or minimum values ​​of the intensity of the biosignal when a load is applied to the target site. For example, the threshold may be set based on the maximum and / or minimum values ​​of the intensity of the biosignal when a maximum load, a load half the maximum load, a minimum load, or the like is applied to the target site.

[0085] The second mode distinguishes between the first movement, the second movement, and relaxation, and therefore can assist the first movement or the second movement even when the biosignal due to the first movement cannot be distinguished from the biosignal due to the second movement. Whether the supported movement is the first movement or the second movement can be set by an external input. The second mode is particularly useful, for example, when the biosignal strengths and feature quantities are so similar or weak that the first movement and the second movement cannot be distinguished from each other.

[0086] For example, when assisting with a clenching movement and an opening movement of the hands, if it is not possible to distinguish between the biosignals resulting from the clenching movement and the opening movement of the hands, device 100 can be controlled to assist the clenching movement of the hands when it is determined that the movement intended by the subject is a clenching movement (or an opening movement of the hands) based on the strength of the biosignals acquired during movement assistance execution, and can assist the opening movement of the hands when it is determined that the movement intended by the subject is a relaxing movement. Similarly, device 100 can be controlled to assist the opening movement of the hands when it is determined that the movement intended by the subject is an opening movement of the hands (or a clenching movement of the hands), and can assist the clenching movement of the hands when it is determined that the movement intended by the subject is a relaxing movement. Whether to assist the clenching movement or the opening movement of the hands when it is determined that the clenching movement (or the opening movement of the hands) is to be supported can be set by a doctor or the like depending on the condition of the subject.

[0087] The biosignal sensing mode includes, for example, a third mode. In the third mode, the control means 200 determines whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the feature amount of the biosignal, and controls the device 100 to assist either the first movement or the second movement based on the determination. In the third mode, the control means 200 determines whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the feature amount of the biosignal acquired during movement assistance execution, and controls the device 100 to assist either the first movement or the second movement if the movement intended by the subject is determined to be the first movement or the second movement, and controls the device 100 to assist the other of the first movement or the second movement if the movement intended by the subject is determined to be a relaxation movement. When the movement intended by the subject is determined to be the first movement or the second movement, whether the movement to be assisted will be the first movement or the second movement can be set, for example, by a user (e.g., a doctor, physical therapist, occupational therapist, rehabilitation trainer, subject, etc.).

[0088] In the third mode, the control means 200 distinguishes between the first or second movement and the relaxation movement based on the feature amount of the bio-signal by using a machine learning model prepared in advance to distinguish between the first or second movement and the relaxation movement. The prepared machine learning model may be a model that has learned the feature amount of the bio-signal and the label attached to the bio-signal.

[0089] The machine learning model is similar to the machine learning model used in the first mode, but differs from the machine learning model used in the first mode in that it has been trained to distinguish between two states: the first or second movement, and the relaxed movement.

[0090] For example, to enable a machine learning model to distinguish between an open hand movement or a clenched hand movement and a relaxed hand movement, a set of training data (input training data, output training data) for training the machine learning model may be (feature values ​​extracted from biosignals obtained when the subject makes an open hand movement or a clenched hand movement, a value indicating that the movement is either an open hand movement or a clenched hand movement) or (feature values ​​extracted from biosignals obtained when the subject makes a relaxed hand movement, a value indicating that the movement is either an open hand movement or a clenched hand movement). It is preferable to acquire training data from multiple subjects and train the multiple training data. When feature values ​​extracted from biosignals obtained when the subject makes a certain movement are input to the machine learning model prepared in this way, the machine learning model can output either a value indicating that the movement is either an open hand movement or a clenched hand movement, or a value indicating that the movement is either an open hand movement or a clenched hand movement.

[0091] In one embodiment, similar to the machine learning model used in the first mode, multiple machine learning models may be prepared for each stage of the subject's movement.

[0092] In another embodiment, the machine learning model may also be trained to learn the stages of the subject's movement, similar to the machine learning model used in the first mode.

[0093] The third mode distinguishes between the first movement, the second movement, and a relaxation movement based on the feature amount of the biosignal, and therefore can accurately distinguish between the first movement, the second movement, and a relaxation movement, even when the strength of the biosignal is weak, and can assist the first movement or the second movement. Whether the movement to be assisted is the first movement or the second movement can be set by external input (e.g., a clenching movement of the hand or an opening movement of the hand). The third mode is particularly useful, for example, when the biosignals are so similar or weak that the first and second movements cannot be distinguished from the strength and feature amount of the biosignals, and when the biosignals are so similar or weak that the first and second movements cannot be distinguished from the strength and feature amount of the biosignals.

[0094] For example, when assisting with a hand clenching movement and a hand opening movement, if it is not possible to distinguish between a biosignal due to a hand clenching movement and a biosignal due to a hand opening movement, device 100 can be controlled to assist the hand clenching movement if it is determined that the movement intended by the subject is a hand clenching movement (or a hand opening movement) based on the feature amount of the biosignal acquired during movement assistance execution, and can assist the hand opening movement if it is determined that the movement intended by the subject is a hand relaxation movement. Similarly, device 100 can be controlled to assist the hand clenching movement if it is determined that the movement intended by the subject is a hand opening movement (or a hand clenching movement), and can assist the hand clenching movement if it is determined that the movement intended by the subject is a hand relaxation movement. Whether to assist the hand clenching movement or the hand opening movement if it is determined that the hand clenching movement (or hand opening movement) is to be supported can be set by a doctor or the like depending on the condition of the subject.

[0095] The biosignal sensing mode includes, for example, a fourth mode. In the fourth mode, the control means 200 determines whether the movement intended by the subject is a first movement or a second movement among multiple movements based on the strength of the biosignal and controls the device 100 to assist the determined movement. In the fourth mode, the control means 200 determines whether the movement intended by the subject is a first movement or a second movement based on the strength of the biosignal acquired during movement assistance execution, and controls the device 100 to assist the first movement if the movement intended by the subject is determined to be the first movement, and controls the device 100 to assist the second movement if the movement intended by the subject is determined to be the second movement. In the fourth mode, the control means 200 may also determine whether the movement intended by the subject is a relaxation movement based on the strength of the biosignal. In this case, the control means 200 can prevent the device 100 from being controlled. This can prevent the device 100 from moving when the subject intends to perform a relaxation movement.

[0096] That is, in the fourth mode, the control means 200 controls the device 100 to assist the first movement when the subject intends the first movement, to assist the second movement when the subject intends the second movement, and not to assist the movement when the subject intends the relaxation movement (or when no movement is intended), by determining three states: (1) the first movement, (2) the second movement, and (3) the relaxation movement (or no movement is intended) based on the strength of the biological signal obtained during the assistance execution.

[0097] In the second mode, the control means 200 can, for example, determine whether the strength of the biological signal exceeds a predetermined threshold, determine that the movement is a first movement when it is determined that the strength of the biological signal exceeds the threshold, and determine that the movement is a second movement when it is determined that the strength of the biological signal does not exceed the threshold. Alternatively, the control means 200 can, for example, determine whether either the strength of the biological signal acquired by a first acquisition means that acquires a biological signal mainly due to the first movement exceeds a threshold or the strength of the biological signal acquired by a second acquisition means that acquires a biological signal mainly due to the second movement exceeds a threshold, and determine that the movement is a first movement when it is determined that the strength of the biological signal acquired by the first acquisition means exceeds the threshold and the strength of the biological signal acquired by the second acquisition means does not exceed the threshold, and determine that the movement is a second movement when it is determined that the strength of the biological signal acquired by the first acquisition means does not exceed the threshold and the strength of the biological signal acquired by the second acquisition means exceeds the threshold. If it is determined that both the strength of the biosignal acquired by the first acquisition means and the strength of the biosignal acquired by the second acquisition means exceed the threshold value or both do not exceed the threshold value, it can be determined that the movement is indeterminable or that it is a relaxation movement.

[0098] The threshold may be any value. The threshold may be a preset fixed value or a variable value. If the threshold is a variable value, for example, the threshold may be varied for each subject. The threshold may be set, for example, based on the maximum and / or minimum values ​​of the intensity of the biosignal acquired from the subject. For example, when the minimum value of the intensity of the biosignal is 0% and the maximum value of the intensity of the biosignal is 100%, the threshold may be a value between about 50% and about 95%, or a value between about 60% and about 90%, such as about 60%, about 70%, or about 80%. The threshold may be set, for example, based on the maximum and / or minimum values ​​of the intensity of the biosignal when a load is applied to the target site. For example, the threshold may be set based on the maximum and / or minimum values ​​of the intensity of the biosignal when a maximum load, a load half the maximum load, a minimum load, or the like is applied to the target site.

[0099] In the fourth mode, the first movement and the second movement are distinguished based on the strength of the biosignal, so that, for example, it can be determined whether it is the first movement or the second movement when the strength of the biosignal exceeds a threshold. This allows for support of the first movement or the second movement with high responsiveness. The more responsively the first movement or the second movement is supported, the greater the rehabilitation effect.

[0100] In the fourth mode, for example, in order to exclude a state in which both the first movement and the second movement are supported, when determining the second movement, if the strength of the biological signal indicating the first movement exceeds a threshold, it can be determined not to be the second movement regardless of the strength of the biological signal indicating the second movement.

[0101] For example, when assisting with a hand clenching movement and a hand opening movement, if the biosignal resulting from the hand clenching movement and the biosignal resulting from the hand opening movement can be distinguished by their intensity, device 100 can be controlled to assist the hand clenching movement when it is determined that the movement intended by the subject is a hand clenching movement based on the intensity of the biosignal acquired during movement assistance execution, or to assist the hand opening movement when it is determined that the movement intended by the subject is an hand opening movement. For example, device 100 can be controlled to assist the hand clenching movement when the intensity of the biosignal acquired during movement assistance execution exceeds a threshold related to the hand clenching movement, or to assist the hand opening movement when the intensity of the biosignal acquired during movement assistance execution exceeds a threshold related to the hand opening movement. Alternatively, for example, when the biosignals resulting from the movement of clenching the hands, the biosignals resulting from the movement of opening the hands, and the biosignals resulting from the movement of relaxing the hands can be distinguished by their intensity, the device 100 can be controlled based on the intensity of the biosignals acquired during the execution of movement assistance to assist the movement of clenching the hands when it is determined that the movement intended by the subject is a movement of opening the hands, to assist the movement of opening the hands, and not to assist the movement when it is determined that the movement intended by the subject is a movement of relaxing the hands.

[0102] In addition, in order to exclude an antagonistic state in which both the muscles for clenching the hands and the muscles for opening the hands are contracting, for example, when determining whether a hand is being clenched, if the strength of the biosignal for the opening the hands exceeds a certain threshold, it can be determined that the movement is a clenching of the hands, regardless of the strength of the biosignal for the clenching of the hands.

[0103] The control signal generating means 222 is configured to generate a control signal for controlling the device 100. The control signal generating means 222 generates a control signal for controlling the device 100 in the mode selected by the mode selecting means 221.

[0104] For example, when the motion sensing mode is selected by the mode selection means 221, the control signal generation means 222 can generate a control signal based on the subject's motion sensed by the sensing means 400 to control the device 100 so as not to interfere with the sensed subject's motion.

[0105] For example, when the mode selection means 221 selects the biosignal sensing mode, the control signal generation means 222 can recognize a movement intended by the subject based on the biosignal acquired by the acquisition means 300, and generate a control signal for controlling the device 100 to assist the recognized movement. For example, when the mode selection means 221 selects the first mode, the control signal generation means 222 can recognize whether the movement intended by the subject is a first movement or a second movement based on the feature amount of the biosignal acquired by the acquisition means 300, and generate a control signal for controlling the device 100 to assist the first movement or the second movement. As described above, the control signal generation means 222 can recognize whether the movement intended by the subject is the first movement or the second movement based on the feature amount of the biosignal by utilizing a machine learning model prepared in advance. For example, when the second mode is selected by the mode selection means 221, the control signal generation means 222 can recognize whether the movement intended by the subject is the first movement, the second movement, or the relaxation movement based on the intensity of the biosignal acquired by the acquisition means 300, and generate a control signal for controlling the device 100 to assist the first movement or the second movement. For example, when the third mode is selected by the mode selection means 221, the control signal generation means 222 can recognize whether the movement intended by the subject is the first movement, the second movement, or the relaxation movement based on the feature amount of the biosignal acquired by the acquisition means 300, and generate a control signal for controlling the device 100 to assist the first movement or the second movement. As described above, the control signal generation means 222 can recognize whether the movement intended by the subject is the first movement, the second movement, or the relaxation movement based on the feature amount of the biosignal by utilizing a machine learning model prepared in advance. For example, when the fourth mode is selected by the mode selection means 221, the control signal generation means 222 can recognize whether the movement intended by the subject is the first movement or the second movement based on the strength of the biosignal acquired by the acquisition means 300, and generate a control signal for controlling the device 100 to assist the first movement or the second movement.In the first and fourth modes, in addition to recognizing whether the intended movement of the subject is the first movement or the second movement, the subject can also recognize that the intended movement is a relaxation movement. When the intended movement of the subject is recognized as a relaxation movement, the control signal generating means 222 can either not generate a control signal or generate a control signal for controlling the device 100 not to move.

[0106] The generated control signal is transmitted to the device 100 via the output unit 240, and the device 100 is controlled in accordance with the control signal.

[0107] 2B shows an example of the configuration of a control means 200' that is an alternative embodiment of the control means 200. The control means 200' differs from the control means 200 in that a processor unit 220' includes a determination means 223. The same components as those described with reference to FIG. 2A are given the same reference numerals, and detailed description thereof will be omitted here.

[0108] The control means 200 ′ comprises a receiving section 210 , a processor section 220 ′, a memory section 230 and an output section 240 .

[0109] The processor unit 220' controls the overall operation of the control means 200'. The processor unit 220' reads out a program stored in the memory unit 230 and executes the program. This allows the control means 200' to function as a device that executes desired steps.

[0110] The memory unit 230 stores programs required for executing processes, data required for executing the programs, and the like. For example, the memory unit 230 may store a program for implementing processes for assisting the movement of a target part of a subject (for example, processes described later in FIGS. 4, 5, 6, 7A, 7B, and 8). Here, how the program is stored in the memory unit 230 does not matter. For example, the program may be pre-installed in the memory unit 230. Alternatively, the program may be installed in the memory unit 230 by being downloaded via a network, or may be installed in the memory unit 230 via a storage medium such as an optical disk or USB.

[0111] The processor section 220 ′ includes a determining means 223 , a mode selecting means 221 , and a control signal generating means 222 .

[0112] The determination means 223 is configured to determine whether the magnitude of the force indicated by the received signal is less than a predetermined threshold. The predetermined threshold may be any numerical value, but is preferably a value that can determine that no force is being exerted. For example, the predetermined threshold may be a value greater than 0. The determination means 223 can determine whether the magnitude of the force is less than the predetermined threshold, for example, based on a signal indicating an angular change of the arm unit 112 relative to the base unit 111 when a certain torque is applied to the arm unit 112. For example, if there is an angular change, the determination means 223 can determine that the magnitude of the force is greater than the predetermined threshold, and if there is no angular change, the determination means 223 can determine that the magnitude of the force is less than the predetermined threshold. This allows the determination means 223 to determine whether or not the subject is exerting force.

[0113] If the determination means 223 determines that the magnitude of the force indicated by the received signal is equal to or greater than a predetermined threshold, it can be assumed that the subject is exerting force. In this case, the received signal can be used directly for subsequent processing. This is because, as shown in Figure 3, it is possible to identify what movement the biosignal contained in the received signal represents.

[0114] In this case, the output from the determining means 223 is passed to the mode selecting means 221 .

[0115] If the determination means 223 determines that the magnitude of the force indicated by the received signal is less than a predetermined threshold, it can be assumed that no force is being exerted by the subject. In this case, the received signal cannot be used for subsequent processing, because it is not possible to identify what movement the biosignal contained in the received signal represents.

[0116] In this case, a separate process is required to label the biosignals acquired from the subject as biosignals representing the intended movement.

[0117] The process of labeling a biosignal can be performed by any known method. For example, a subject can be instructed to perform a certain action (e.g., by speaking out loud or showing an illustration), and a label of that action can be attached to a biosignal obtained when the subject attempts the action in response to the instruction. For example, a subject can be instructed to open their hand (e.g., by speaking out loud or showing an illustration), and a label of "hand opening action" can be attached to a biosignal obtained when the subject attempts to open their hand in response to the instruction. The biosignal in this case can be, for example, a signal from the rising edge to the falling edge of the signal. For example, a subject can be instructed to perform a relaxation action (e.g., by speaking out loud or showing an illustration), and a label of "relaxation" can be attached to a biosignal obtained when the subject attempts to perform the relaxation action in response to the instruction. The biosignal in this case can be, for example, a signal from the falling edge to the rising edge of the signal. The labeled biosignal can be used for comparison (comparison of intensity, comparison of features, etc.), machine learning, etc.

[0118] The processing for labeling the biological signals may be performed by the control means 200′ or by a means other than the control means 200′. The other means may be a means within the system 10 or a means external to the system 10. The above example assumes that a biosignal can be detected from the subject. If a biosignal cannot be detected from the subject, therapy and / or rehabilitation can be performed on the subject using any known method. For example, therapy and / or rehabilitation can be performed on the subject using imagery training in which the subject imagines moving a target area at a constant rhythm, and / or therapy in which electrical stimulation is applied to the target area.

[0119] In the example shown in Figures 2A and 2B, each component of the control means 200 is provided within the control means 200, but the present invention is not limited to this. Any of the components of the control means 200 can also be provided outside the control means 200. For example, if the processor unit 220 and the memory unit 230 are each configured with separate hardware components, the hardware components may be connected via any network. In this case, the type of network does not matter. The hardware components may be connected, for example, via a LAN, wirelessly, or wired.

[0120] 2A and 2B, the components of the processor unit 220 are provided in the same processor unit 220, but the present invention is not limited to this. A configuration in which the components of the processor unit 220 are distributed across multiple processor units is also within the scope of the present invention. In this case, the multiple processor units may be located in the same hardware component, or in separate hardware components located nearby or remotely.

[0121] (Processing by a system to assist the subject in moving the target part) 4 is a flowchart showing an example of a process (process 400) performed by the system 10 for assisting the movement of a target part of a subject. The process 400 is performed by the processing means 200.

[0122] Before performing step S401, the subject performs a preparatory movement to acquire a first signal. First, the subject wears device 100 on the target body part. Next, the subject moves the target body part with a first movement while device 100 is controlled so as not to interfere with the movement of the target body part. As a result, the subject moves the target body part with the first movement within the unassisted movement range, and sensing means 400 senses the unassisted movement range of the target body part when the subject is about to move the target body part with the first movement.

[0123] Optionally, the subject may move the target part with the second movement (and the third movement, ..., the nth movement) under control of the device 100 so as not to interfere with the movement of the target part. This allows the subject to move the target part with the second movement (and the third movement, ..., the nth movement) within the unassisted range of movement, and the sensing means 400 senses the unassisted range of movement of the target part when the subject is attempting to move the target part with the second movement (and the third movement, ..., the nth movement).

[0124] Next, with the device 100 controlled to apply a load to the target region, the subject moves the target region with a first movement. The acquisition means 300 acquires a biosignal when the subject is attempting to move the target region with the first movement, and the sensing means 400 senses the movement or force of the target region when the subject is attempting to move the target region with the first movement. The load is applied in a direction opposite to the direction of the first movement. For example, if the first movement and the second movement are paired movements, the load may be applied in a direction that moves the target region with the second movement. This step preferably involves multiple samplings, such as varying the magnitude of the load during the first movement or performing this step multiple times with different loads. This increases the amount of data available for subsequent processing.

[0125] At this time, a biological signal may be acquired when the subject is in a relaxed state before and after the subject is about to move the target part with the first movement.

[0126] Optionally, the subject moves the target region with a second movement (and a third movement, ..., nth movement) while the device 100 is controlled to apply a load to the target region. At this time, the acquisition means 300 acquires a biological signal when the subject is attempting to move the target region with the second movement (and the third movement, ..., nth movement), and the sensing means 400 senses the movement or force of the target region when the subject is attempting to move the target region with the second movement (and the third movement, ..., nth movement). The load is applied in a direction opposite to the direction of the second movement (and the third movement, ..., nth movement). For example, if the first movement and the second movement are paired movements, the load may be applied in a direction that moves the target region with the first movement. It is preferable to perform multiple samplings in this step by varying the magnitude of the load during the second movement or by performing this step multiple times with different loads. This is because it is possible to increase the amount of data available for subsequent processing.

[0127] In this case, biosignals may be acquired when the subject is in a relaxed state before and after the subject attempts to move the target area with the second movement (and the third movement, ... the nth movement).

[0128] In step S401, the receiving unit 210 of the processing means 200 receives a first signal. The first signal is a signal obtained when the subject is attempting to move the target part with a first movement, and may indicate a biosignal obtained when the subject is attempting to move the target part with the first movement, the range of unassisted movement of the target part when the subject is attempting to move the target part with the first movement, and the magnitude of force when the subject is attempting to move the target part with the first movement. If multiple samplings are performed during the preparatory movement before performing step S401, the first signal may include data from the multiple samplings. The first signal may include a biosignal obtained when the subject is in a relaxed state before and after attempting to move the target part with the first movement.

[0129] The first signal may be received from the acquiring means 300 and the sensing means 400. The first signal may, for example, be received directly from the acquiring means 300 and the sensing means 400, or may be received indirectly from another device in communication with the acquiring means 300 and the sensing means 400. Once the first signal is received, the receiving unit 210 passes the first signal to the processor unit 220 for further processing.

[0130] When the processor unit 220 receives the first signal, in step S402, the mode selection means 221 of the processor unit 210 selects a mode for controlling the device based on the first signal. The mode selection means 221 can select a mode for controlling the device 100 from among a plurality of modes. The plurality of modes may include, for example, a motion sensing mode and a biological signal sensing mode. The plurality of modes may include a first mode, a second mode, a third mode, and a fourth mode.

[0131] In step S403, the control signal generating means 222 of the processor unit 220 generates a control signal for controlling the device 100 in the selected mode, and controls the device 100 in the selected mode by transmitting the generated control signal to the device 100 via the output unit 240. This causes the device 100 to assist the first movement of the subject.

[0132] Process 400 enables device 100 to operate in different modes for each subject, enabling movement assistance according to the subject's condition. Furthermore, a mode suitable for the subject can be automatically selected, reducing the burden on doctors, physical therapists, occupational therapists, rehabilitation trainers, and others assisting with rehabilitation. Furthermore, since the only movement required by the subject is the preparatory movement before step S401, the mode setting of device 100 can be performed with a simple operation, reducing the burden on the subject.

[0133] In the above example, the process 400 is performed by the control means 200, but the process 400 can also be performed by the control means 200' in the same way.

[0134] Fig. 5 is a flowchart showing an example of the detailed flow of step S401 in the process 400 when performed by the control means 200'. The process shown in Fig. 5 is performed to identify subjects who are unable to generate force from the target body part or are unable to move the target body part.

[0135] In step S501, the receiving unit 210 of the processing means 200′ receives a first signal. The first signal is a signal received when the subject is attempting to move the target body part with a first movement, and may indicate a biosignal received when the subject is attempting to move the target body part with the first movement, the range of unassisted movement of the target body part when the subject is attempting to move the target body part with the first movement, or the magnitude of force applied when the subject is attempting to move the target body part with the first movement.

[0136] The first signal may be received from the acquiring means 300 and the sensing means 400. The first signal may, for example, be received directly from the acquiring means 300 and the sensing means 400, or may be received indirectly from another device in communication with the acquiring means 300 and the sensing means 400. Once the first signal is received, the receiving unit 210 passes the first signal to the processor unit 220′ for further processing.

[0137] In step S502, the determination means 223 of the processor unit 220′ determines whether the magnitude of the force indicated by the received first signal is less than a predetermined threshold. The predetermined threshold may be any numerical value, but is preferably a value that can determine that no force is being exerted. For example, the predetermined threshold may be a value greater than 0. The determination means 223 may determine whether the magnitude of the force is less than the predetermined threshold, for example, based on a signal indicating an angular change of the arm unit 112 relative to the base unit 111 when a certain torque is applied to the arm unit 112. For example, if there is an angular change, the determination means 223 may determine that the magnitude of the force is greater than the predetermined threshold, and if there is no angular change, the determination means 223 may determine that the magnitude of the force is less than the predetermined threshold. In this way, in step S502, it is determined whether or not the subject is exerting force.

[0138] If it is determined in step S502 that the magnitude of the force indicated by the received first signal is equal to or greater than the predetermined threshold, the process proceeds to step S402 described above, because the first signal received in step S501 can also be used in subsequent steps.

[0139] If it is determined in step S502 that the magnitude of the force indicated by the received first signal is less than the predetermined threshold, the process proceeds to step S503. This is because it is not possible to identify the intended movement of the biosignal contained in the first signal received in step S501, and therefore the biosignal cannot be used in subsequent steps.

[0140] In step S503, a label is attached to the biosignal acquired from the subject. Step S503 may be performed in the processor unit 220′, but can also be performed by means other than the processor unit 220′. The process for attaching a label to the biosignal acquired from the subject can be performed by any known method. In the process for attaching a label to the biosignal acquired from the subject, a label indicating that the first movement was intended is attached to the biosignal acquired when the subject was made to attempt a first movement.

[0141] In step S504, the processing means 200' receives the labeled biosignal. If step S503 is performed by means other than the processor unit 220', the receiving unit 210 of the processing means 200' receives the labeled biosignal. The labeled biosignal will be used in place of the first biosignal included in the first signal. The received biosignal is passed to the processor unit 220' for further processing, and the process proceeds to step S402.

[0142] The above-described processing identifies subjects who are unable to generate force from the target body part or who are unable to move the target body part, and by acquiring biosignals separately for such subjects, even subjects who are unable to generate force from the target body part or who are unable to move the target body part can receive movement assistance from the device 10. Furthermore, it is possible to automatically identify subjects whose biosignals need to be acquired separately, thereby reducing the burden on doctors, physical therapists, occupational therapists, rehabilitation trainers, and others who assist with rehabilitation.

[0143] 6 is a flowchart showing another example of a process (process 600) performed by system 10 to assist the movement of a target part of a subject. Process 600 differs from process 400 in that a second signal is used in addition to a first signal. In the following, process 600 will be described as being performed in control means 200, but process 600 can also be performed in control means 200' in the same way.

[0144] In step S601, the receiving unit 210 of the processing means 200 receives a first signal. Step S601 is similar to step S401, and therefore description thereof will be omitted here. As with step S401, the subject may perform preparatory movements before performing step S601. If multiple samplings are performed in the preparatory movements before performing step S601, the first signal may include data from the multiple samplings.

[0145] In step S602, the receiving unit 210 of the processing means 200 receives a second signal. The second signal is a signal obtained when the subject is attempting to move the target part with the second movement, and may indicate a biosignal obtained when the subject is attempting to move the target part with the second movement, the range of independent motion of the target part when the subject is attempting to move the target part with the second movement, and the magnitude of force when the subject is attempting to move the target part with the second movement. If multiple samplings are performed during the preparatory movement before performing step S601, the second signal may include data from the multiple samplings. The second signal may include a biosignal obtained when the subject is in a relaxed state before and after attempting to move the target part with the second movement.

[0146] The second signal may be received from the acquiring means 300 and the sensing means 400. The second signal may, for example, be received directly from the acquiring means 300 and the sensing means 400, or may be received indirectly from another device in communication with the acquiring means 300 and the sensing means 400. Once the second signal is received, the receiving unit 210 passes the second signal to the processor unit 220 for further processing.

[0147] Note that step S602 may be performed by steps similar to steps S501 to S504 shown in FIG.

[0148] Alternatively, after receiving the first and second signals in steps S601 and S602, instead of step S502, the intensity of the first signal may be compared with the intensity of the second signal. This allows for determining whether the intensities of the first and second signals are sufficiently different to distinguish them. The comparison may include, for example, determining whether the difference between the intensities of the first and second signals exceeds a predetermined threshold, or determining whether the difference in the outputs of a neural network is greater than a certain value, or determining the distance or information entropy of information vectors in information theory. The predetermined threshold may be any value, such as between about 1% and about 50% of the intensity of the first or second signal, or between about 10% and about 40%, e.g., about 5%, about 10%, or about 15%.

[0149] If it is determined that the strength of the first signal and the strength of the second signal are significantly different, or that the difference between the strength of the first signal and the strength of the second signal is equal to or greater than a predetermined threshold, the process proceeds to step S603, because the first signal and the second signal received in step S601 and step S602 can be used in subsequent steps.

[0150] If it is determined that the strength of the first signal and the strength of the second signal are not significantly different, or that the difference between the strength of the first signal and the strength of the second signal is less than the predetermined threshold, the process proceeds to step S503 because the first signal and the second signal received in steps S601 and S602 cannot be distinguished from each other and therefore cannot be used in subsequent steps.

[0151] In step S503, labels are attached to the biosignals acquired from the subject. In the process of labeling the biosignals acquired from the subject, a label indicating that the first movement was intended is attached to the biosignal acquired when the subject was made to attempt a first movement, and a label indicating that the second movement was intended is attached to the biosignal acquired when the subject was made to attempt a second movement.

[0152] In step S504, the processing means 200' receives the labeled biosignal. If step S503 is performed by a means other than the processor unit 220', the receiving unit 210 of the processing means 200' receives the labeled biosignal. The labeled biosignal will be used in place of the first biosignal contained in the first signal and the second biosignal contained in the second signal. The received biosignal is passed to the processor unit 220' for further processing, and the process proceeds to step S603.

[0153] When the processor unit 220 receives the first signal and the second signal, in step S603, the mode selection means 221 of the processor unit 210 selects a mode for controlling the device based on the first signal and the second signal. The mode selection means 221 can select a mode for controlling the device 100 from among a plurality of modes. The plurality of modes can include, for example, a motion sensing mode and a biological signal sensing mode. The plurality of modes can include a first mode, a second mode, a third mode, and a fourth mode.

[0154] In step S604, the control signal generating means 222 of the processor unit 220 generates a control signal for controlling the device 100 in the selected mode, and controls the device 100 in the selected mode by transmitting the generated control signal to the device 100 via the output unit 240. This causes the device 100 to assist the subject in the first movement or the second movement.

[0155] Process 600 enables device 100 to operate in different modes for each subject, enabling movement assistance according to the subject's condition. Also, a mode suitable for the subject can be automatically selected, reducing the burden on doctors, physical therapists, occupational therapists, rehabilitation trainers, and others who assist with rehabilitation.

[0156] Fig. 7A is a flowchart showing an example of the detailed flow of step S603 in process 600. The process shown in Fig. 7A is performed by mode selection means 221 of processor unit 220 to select a mode for controlling device 100 from the first to fourth modes.

[0157] In step S701, the mode selection means 221 determines whether or not the first and second biological signals can be distinguished from each other based on their intensities.

[0158] Whether the first biosignal and the second biosignal can be distinguished by their intensities can be determined, for example, by whether either the intensity of the first biosignal or the intensity of the second biosignal exceeds a threshold. For example, if the intensity of the first biosignal exceeds a threshold but the intensity of the second biosignal does not, or if the intensity of the second biosignal exceeds a threshold but the intensity of the first biosignal does not, it can be determined that the first biosignal and the second biosignal can be distinguished by their intensities. On the other hand, if the intensity of the first biosignal does not exceed a threshold and the intensity of the second biosignal does not exceed a threshold, or if the intensity of the first biosignal exceeds a threshold and the intensity of the second biosignal also exceeds a threshold, it can be determined that the first biosignal and the second biosignal cannot be distinguished by their intensities. Alternatively, whether the first biosignal and the second biosignal can be distinguished by their intensities can be determined, for example, by the intensity P of the first biosignal acquired by a first acquisition means that mainly acquires biosignals due to a first movement. 11 , the intensity P of the first biological signal acquired by the second acquisition means for acquiring a biological signal mainly due to the second movement. 12 , the intensity P of the second biological signal acquired by the first acquisition means 21 , and the intensity P of the second biological signal acquired by the second acquisition means 22 Determine whether each of these exceeds a threshold, and 11 ,P 12 )=(1,0) and (P 21 ,P 22)=(0,1) or (P 11 ,P 12 )=(0,1) and (P 21 ,P 22 )=(1,0), it can be determined that the first and second biological signals can be distinguished from each other by their intensities. Here, 1 indicates that the intensity exceeds the threshold, and 0 indicates that the intensity does not exceed the threshold. On the other hand, when (P 11 ,P 12 )=(1,1) or (P 11 ,P 12 )=(0,0) or (P 21 ,P 22 )=(1,1) or (P 21 ,P 22 )=(0,0), it can be determined that the first and second biological signals cannot be distinguished from each other based on their intensities. 11 ,P 12 ) and (P 21 ,P 22 ) are different, it can be determined that the first biological signal and the second biological signal can be distinguished by their intensities, and (P 11 ,P 12 ) and (P 21 ,P 22 ) are the same, it can be determined that the first and second biological signals cannot be distinguished from each other based on their intensities.

[0159] The threshold may be set separately for the first biosignal and the second biosignal, or may be set commonly for the first biosignal and the second biosignal. The threshold may be set separately for the biosignal acquired by the first acquisition means and the biosignal acquired by the second acquisition means, or may be set commonly for the first biosignal and the second biosignal. The threshold may be set, for example, based on the maximum and / or minimum intensity of the first biosignal or the second biosignal, or the average intensity of the first biosignal or the second biosignal. The threshold may be, for example, a value between 50% and 95%, or a value between 60% and 90%, such as 60%, 70%, or 80%, when the minimum intensity of the first biosignal or the second biosignal is 0% and the maximum intensity of the first biosignal or the second biosignal is 100%.

[0160] If it is determined in step S701 that the first biosignal and the second biosignal can be distinguished by their intensities, proceed to step S707; if it is determined that the first biosignal and the second biosignal cannot be distinguished by their intensities, proceed to step S702.

[0161] In step S702, the mode selection means 221 determines whether or not the first biological signal and the second biological signal can be distinguished from each other based on their feature amounts.

[0162] Whether the first and second biological signals can be distinguished from each other based on their feature quantities is determined, for example, by whether a pre-prepared machine learning model can distinguish between the first and second biological signals. The pre-prepared machine learning model may be a model that learns the feature quantities of biological signals and the labels attached to the biological signals, and specifically, may be a two-state discrimination model capable of distinguishing between two states. For example, if there is a significant difference between the output when the feature quantities of the first biological signal are input to the machine learning model and the output when the second biological signal is input to the machine learning model, it can be determined that the first and second biological signals can be distinguished from each other based on their feature quantities. For example, if there is no significant difference between the output when the feature quantities of the first biological signal are input to the machine learning model and the output when the second biological signal is input to the machine learning model, it can be determined that the first and second biological signals cannot be distinguished from each other based on their feature quantities. Here, the criterion for a significant difference may be any criterion, and may be, for example, a strict or lenient criterion depending on the condition of the subject. In one example, the accuracy rate of predictions made by a machine learning model is calculated, and if the accuracy rate is equal to or greater than a predetermined threshold, it is determined that there is a significant difference, and if it is less than the predetermined threshold, it is determined that there is no significant difference.

[0163] If it is determined in step S702 that the first biosignal and the second biosignal can be distinguished by their features, proceed to step S703; if it is determined that the first biosignal and the second biosignal cannot be distinguished by their features, proceed to step S704.

[0164] In step S703, the mode selection means 221 selects the first mode. In the first mode, the control means 200 determines whether the movement intended by the subject is a first movement or a second movement among multiple movements based on the feature of the biosignal, and controls the device 100 to assist the determined movement. The first mode is possible because the first biosignal and the second biosignal can be distinguished based on their feature. When the first mode is selected, the machine learning model used in step S702 may be trained to learn the feature of the first biosignal and the feature of the second biosignal, thereby tuning the pre-prepared machine learning model to suit the subject. In the control in the first mode, the tuned machine learning model may be used to recognize the movement.

[0165] In step S704, the mode selection means 221 determines whether the biosignal in the relaxed state can be distinguished from the first or second biosignal based on their intensities. The biosignal in the relaxed state can be received together with the first or second signal in step S601 or S602.

[0166] Whether the biosignal in the relaxed state can be distinguished from the first or second biosignal based on their intensities can be determined, for example, by determining whether either the intensity of the first or second biosignal or the intensity of the biosignal in the relaxed state exceeds a threshold. For example, if the intensity of the first or second biosignal exceeds the threshold but the intensity of the biosignal in the relaxed state does not, or if the intensity of the first or second biosignal does not exceed the threshold but the intensity of the biosignal in the relaxed state does not exceed the threshold, it can be determined that the first or second biosignal can be distinguished from the biosignal in the relaxed state based on their intensities. On the other hand, for example, when the intensity of the first biosignal or the second biosignal does not exceed the threshold and the intensity of the biosignal in the relaxed state also does not exceed the threshold, or when the intensity of the first biosignal or the second biosignal exceeds the threshold and the intensity of the biosignal in the relaxed state also exceeds the threshold, it can be determined that the first biosignal or the second biosignal and the biosignal in the relaxed state cannot be distinguished by their intensities. Alternatively, whether the first biosignal and the second biosignal can be distinguished by their intensities can be determined, for example, by the intensity P of the first biosignal acquired by the first acquisition means that mainly acquires the biosignal due to the first movement. 11 , the intensity P of the first biological signal acquired by the second acquisition means for acquiring a biological signal mainly due to the second movement. 12 , the intensity P of the second biological signal acquired by the first acquisition means 21 , the intensity P of the second biological signal acquired by the second acquisition means 22 , the biological signal P in the relaxed state acquired by the first acquisition means 31 , the biological signal P in the relaxed state acquired by the second acquisition means 32 Determine whether each of these exceeds a threshold, and 11 ,P 12 ) and / or (P 21 ,P 22 ) and (P 31 ,P 32) are different, it can be determined that the first biological signal or the second biological signal and the biological signal in the relaxed state can be distinguished by their intensities, and (P 11 ,P 12 ) and (P 21 ,P 22 ) and (P 31 ,P 32 ) are the same, it can be determined that the first biological signal or the second biological signal cannot be distinguished from the biological signal in the relaxed state based on their intensities.

[0167] The threshold may be set separately for the first biosignal, the second biosignal, and the biosignal in the state of relaxation, or may be set commonly for the first biosignal, the second biosignal, and the biosignal in the state of relaxation. The threshold may be set separately for the biosignal acquired by the first acquisition means and the biosignal acquired by the second acquisition means, or may be set commonly for the first biosignal, the second biosignal, and the biosignal in the state of relaxation. The threshold may be set, for example, based on the maximum and / or minimum intensity of the first biosignal or the second biosignal, or the average intensity of the first biosignal or the second biosignal. The threshold may be, for example, a value between 50% and 95%, or a value between 60% and 90%, such as 60%, 70%, or 80%, when the minimum intensity of the first biosignal or the second biosignal is 0% and the maximum intensity of the first biosignal or the second biosignal is 100%.

[0168] If it is determined in step S704 that the biosignal in the relaxed state can be distinguished from the first biosignal or the second biosignal based on their intensities, proceed to step S705; if it is determined that the biosignal in the relaxed state cannot be distinguished from the first biosignal or the second biosignal based on their intensities, proceed to step S706.

[0169] In step S705, the mode selection means 221 selects the second mode. In the second mode, the control means 200 determines whether the movement intended by the subject is the first movement, the second movement, or a movement of relaxation based on the intensity of the biosignal, and controls the device 100 to support either the first movement or the second movement based on the determination. The second mode is possible because the biosignal in a state of relaxation can be distinguished from the first biosignal or the second biosignal based on their intensities. When the second mode is selected, the threshold and conditions for distinguishing between the biosignal in a state of relaxation and the first biosignal or the second biosignal may be determined to suit the subject.

[0170] In step S706, the mode selection means 221 selects the third mode. In the third mode, the control means 200 determines whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the feature amount of the biosignal, and controls the device 100 to assist either the first movement or the second movement based on the determination. When the third mode is selected, a machine learning model (two-state discrimination model) capable of distinguishing between the biosignal of the first movement or the second movement and the biosignal in a relaxation state may be trained to learn the feature amount of the first biosignal or the second biosignal and the feature amount in a relaxation state, thereby tuning the machine learning model to suit the subject. In the control in the third mode, the tuned machine learning model may be used to recognize the movement.

[0171] The third mode is possible when the biosignal in the state of weakness can be distinguished from the first biosignal or the second biosignal based on their feature amounts, but if the biosignal in the state of weakness cannot be distinguished from the first biosignal or the second biosignal based on their feature amounts, the subject may undergo another form of rehabilitation before receiving movement support from the device 100. The other form of rehabilitation is, for example, practice so that the subject can distinguish between the first movement or the second movement and weakness.

[0172] In step S707, the mode selection means 221 selects the fourth mode. The fourth mode is a mode in which the control means 200 determines whether the movement intended by the subject is the first movement or the second movement based on the strength of the bio-signal, and controls the device 100 to support the determined movement. The fourth mode is possible because the first bio-signal and the second bio-signal can be distinguished from each other based on their strengths. When the fourth mode is selected, the threshold and conditions for distinguishing between the first bio-signal and the second bio-signal may be determined to suit the subject. In this way, the mode for controlling the device 100 can be selected according to the strength or feature of the biological signal from the subject. This enables flexible movement assistance according to the subject's condition. Furthermore, the mode suitable for the subject can be automatically selected, reducing the burden on doctors, physical therapists, occupational therapists, rehabilitation trainers, and others who assist with rehabilitation.

[0173] FIG. 7B is a flowchart showing another example of the detailed flow (S603′) of step S603 in the process 600.

[0174] In step S701', the mode selection means 221 determines whether the first biosignal, the second biosignal, and the biosignal in the relaxed state can be distinguished based on their intensities. The biosignal in the relaxed state can be received together with the first signal or the second signal in step S601 or step S602.

[0175] Whether or not the first biological signal, the second biological signal, and the biological signal in the relaxed state can be distinguished by their intensities can be determined by, for example, determining the intensity P of the first biological signal acquired by the first acquisition means that mainly acquires the biological signal due to the first movement. 11 , the intensity P of the first biological signal acquired by the second acquisition means for acquiring a biological signal mainly due to the second movement. 12, the intensity P of the second biological signal acquired by the first acquisition means 21 , the intensity P of the second biological signal acquired by the second acquisition means 22 , the biological signal P in the relaxed state acquired by the first acquisition means 31 , the biological signal P in the relaxed state acquired by the second acquisition means 32 Determine whether each of these exceeds a threshold, and 11 ,P 12 ) and (P 21 ,P 22 ) and (P 31 ,P 32 ) are different, it can be determined that the first biological signal, the second biological signal, and the biological signal in the relaxed state can be distinguished from each other based on their intensities, and (P 11 ,P 12 ) and (P 21 ,P 22 ) and (P 31 ,P 32 ) are the same, it can be determined that the first biological signal, the second biological signal, and the biological signal in the relaxed state cannot be distinguished by their intensities.

[0176] The threshold may be set separately for the first biosignal, the second biosignal, and the biosignal in the state of relaxation, or may be set commonly for the first biosignal, the second biosignal, and the biosignal in the state of relaxation. The threshold may be set separately for the biosignal acquired by the first acquisition means and the biosignal acquired by the second acquisition means, or may be set commonly for the first biosignal, the second biosignal, and the biosignal in the state of relaxation. The threshold may be set, for example, based on the maximum and / or minimum intensity of the first biosignal or the second biosignal, or the average intensity of the first biosignal or the second biosignal. The threshold may be, for example, a value between 50% and 95%, or a value between 60% and 90%, such as 60%, 70%, or 80%, when the minimum intensity of the first biosignal or the second biosignal is 0% and the maximum intensity of the first biosignal or the second biosignal is 100%.

[0177] If it is determined in step S701' that the first bio-signal, the second bio-signal, and the bio-signal in a state of relaxation can be distinguished by their intensities, proceed to step S707'; if it is determined that the first bio-signal, the second bio-signal, and the bio-signal in a state of relaxation cannot be distinguished by their intensities, proceed to step S702'.

[0178] For example, in step S702', the mode selection means 221 determines whether or not it is possible to distinguish between the first biological signal, the second biological signal, and the biological signal in the relaxed state based on the feature amounts thereof.

[0179] Whether the first biosignal, the second biosignal, and the biosignal in the relaxation state can be distinguished from each other using their feature amounts is determined, for example, by whether a pre-prepared machine learning model can distinguish between the first biosignal, the second biosignal, and the biosignal in the relaxation state. The pre-prepared machine learning model may be a model that learns the feature amounts of the biosignals and the labels attached to the biosignals, and specifically may be a three-state discrimination model that can distinguish between three states. For example, if there is a significant difference between the output when the feature amounts of the first biosignal are input to the machine learning model, the output when the feature amounts of the second biosignal are input to the machine learning model, and the output when the feature amounts of the biosignal in the relaxation state are input to the machine learning model, it can be determined that the first biosignal, the second biosignal, and the biosignal in the relaxation state can be distinguished from each other using their feature amounts. For example, if there is no significant difference between the output when the feature amount of a first biological signal is input to a machine learning model, the output when the feature amount of a second biological signal is input to the machine learning model, and the output when the feature amount of a biological signal in a relaxed state is input to the machine learning model, it can be determined that the first biological signal, the second biological signal, and the biological signal in a relaxed state cannot be distinguished using these feature amounts. Here, the criterion for a significant difference can be any criterion, for example, a strict criterion or a lenient criterion depending on the condition of the subject. In one example, the accuracy rate of predictions made by the machine learning model is calculated, and if the accuracy rate is equal to or greater than a predetermined threshold, it can be determined that there is a significant difference, and if it is less than the predetermined threshold, it can be determined that there is no significant difference.

[0180] If it is determined in step S702' that the first bio-signal, the second bio-signal, and the bio-signal in a state of relaxation can be distinguished by their feature amounts, proceed to step S703'; if it is determined that the first bio-signal, the second bio-signal, and the bio-signal in a state of relaxation cannot be distinguished by their feature amounts, proceed to step S704.

[0181] Step S703′ is the same as step S703 shown in FIG. 7A. In step S703′, the mode selection unit 221 selects the first mode. In the first mode, the control unit 200 determines whether the subject's intended movement is the first movement, the second movement, or a relaxation movement based on the feature quantities of the biosignals, and controls the device 100 to support the determined movement. The first mode is possible because the first biosignal, the second biosignal, and the biosignal in the relaxation state can be distinguished based on their feature quantities. When the first mode is selected, the machine learning model used in step S702′ may be trained to learn the feature quantities of the first biosignal, the feature quantities of the second biosignal, and the biosignal in the relaxation state, thereby tuning the pre-prepared machine learning model to suit the subject. In the control in the first mode, the tuned machine learning model may be used to recognize the movement.

[0182] Step S704 is the same as step S704 shown in FIG. 7A, and therefore a description thereof will be omitted here.

[0183] Step S707' is the same as step S707 shown in FIG. 7B.

[0184] In step S707', the mode selection means 221 selects the fourth mode. The fourth mode is a mode in which the control means 200 determines whether the movement intended by the subject is the first movement, the second movement, or a relaxation movement based on the intensity of the bio-signal, and controls the device 100 to support the determined movement. The fourth mode is possible because the first bio-signal, the second bio-signal, and the bio-signal in a relaxation state can be distinguished based on their intensities.

[0185] In the above example, a determination is made for each step for the first and second biosignals as a whole, and a mode is selected. However, the present invention is not limited to this. For example, the first and second biosignals may be divided into multiple stages, and a determination may be made for each of the multiple stages, and an appropriate mode may be selected for each of the multiple stages. For example, the fourth mode may be selected for the first and second biosignals for which a Yes determination is made in step S701 or S701′, the first mode may be selected for the first and second biosignals for which a Yes determination is made in step S702 or S702′, the second mode may be selected for the first and second biosignals for which a Yes determination is made in step S704, and the third mode may be selected for the first and second biosignals for which a No determination is made in step S704. This allows an appropriate mode to be selected depending on the subject's movement state.

[0186] 8 is a flowchart showing an example of processing (process 800) by the system 10 for assisting the movement of a target part of a subject. Process 800 is processing for selecting a mode for controlling the device 100 while movement assistance is being performed. In the following, it will be described that process 800 is performed by the control means 200, but process 800 can also be performed by the control means 200' in the same way.

[0187] In step S801, the receiving unit 210 of the processing means 200 receives a first signal. Step S801 is performed before the execution of motion support. Step S801 is the same as step S401, and therefore a description thereof will be omitted here.

[0188] Like step S401, step S801 may be replaced by steps S501 to S504 as shown in FIG.

[0189] Step S802 is performed while movement assistance is being performed, and in step S802, the receiving unit 210 of the processing means 200 receives a signal when the subject is attempting to move a target part while movement assistance is being performed. The signal when the subject is attempting to move a target part while movement assistance is being performed indicates a biosignal when the subject is attempting to move a target part while movement assistance is being performed, and indicates the movement when the subject is attempting to move a target part while movement assistance is being performed.

[0190] A signal indicating that the subject is attempting to move the target part during movement assistance execution can be received from the acquiring means 300 and the sensing means 400. A signal indicating that the subject is attempting to move the target part during movement assistance execution may be received directly from the acquiring means 300 and the sensing means 400, for example, or may be received indirectly from another device that communicates with the acquiring means 300 and the sensing means 400. When a signal indicating that the subject is attempting to move the target part during movement assistance execution is received, the receiving unit 210 passes the signal to the processor unit 220 for subsequent processing.

[0191] When the processor unit 220' receives the first signal and a signal indicating that the subject is about to move the target body part during execution of movement assistance, step S803 is performed. In step S803, the mode selection means 221 of the processor unit 220 selects a mode for controlling the device.

[0192] Step S803 includes step S831 and step S832 or step S833.

[0193] In step S831, the mode selection means 221 determines whether the subject's movement, indicated by the signal when the subject is attempting to move the target part during movement assistance, is within the unassisted range of motion. This can be performed by comparing the signal with the unassisted range of motion indicated by the first signal. Because the subject's range of motion may change due to fatigue or the like, the determination region may be set larger or smaller than the range of motion measured in advance, or a slight force assist may be performed in the first or second direction when the subject approaches the determination boundary surface.

[0194] If it is determined that the subject's movement is within the unaided movement range, the process proceeds to step S832; if it is determined that the subject's movement is not within the unaided movement range, the process proceeds to step S833.

[0195] In step S832, the mode selection means 221 selects the motion sensing mode. The motion sensing mode is a mode in which the control means 200 controls the device 100 based on the subject's motion. In the motion sensing mode, the control means 200 can control the device 100 so as not to interfere with the sensed motion of the subject. That is, in the motion sensing mode, the device 100 is driven to cancel out the resistance inherent in the device 100 due to interference between the components of the device 100, etc. This allows the subject to move the target body part as if they were not wearing the device 100.

[0196] In step S833, the mode selection means 221 selects a biosignal sensing mode. The biosignal sensing mode is a mode in which the device 100 is controlled based on the biosignal of the subject. In the biosignal sensing mode, a movement intended by the subject is recognized based on the biosignal, and the device 100 can be controlled to assist the recognized movement. Here, the biosignal sensing mode can be one of a first mode, a second mode, a third mode, and a fourth mode. One of the first mode, the second mode, the third mode, and the fourth mode can be selected in step S833, for example, by performing a process similar to the process shown in FIG. 7A or 7B. Alternatively, one of the first mode, the second mode, the third mode, and the fourth mode can be selected, for example, after step S801 and before step S802, i.e., before the execution of the movement assistance, by performing a process similar to the process shown in FIG. 7A or 7B.

[0197] When a mode is selected in step S803, in step S804, the control signal generating means 222 of the processor unit 220 generates a control signal for controlling the device 100 in the selected mode, and controls the device 100 in the selected mode by transmitting the generated control signal to the device 100 via the output unit 240. This causes the device 100 to assist the subject in the first movement or the second movement.

[0198] Steps S802 to S804 can be repeated during the execution of motion assistance, thereby making it possible to always select a suitable mode during the execution of motion assistance.

[0199] For example, in step S803, step 833 may select different modes depending on the stage of the same movement of the target body part during movement assistance. For example, even for a hand-opening movement, different modes can be selected for each stage (e.g., angle around the finger joints). For example, at a stage where the first and second movements can be distinguished based on the strength of the biosignal, the fourth mode can be selected; at a stage where the first and second movements can be distinguished based on the feature amount of the biosignal, the first mode can be selected; at a stage where the first or second movements can be distinguished from the relaxation movement based on the strength of the biosignal, the second mode can be selected; and at a stage where the first or second movements can be distinguished from the relaxation movement based on the feature amount of the biosignal, the third mode can be selected. In this way, even for a single movement, selecting a mode appropriate for the stage of that movement improves the accuracy of movement recognition, which in turn leads to improved rehabilitation efficiency.

[0200] For example, when the first mode or the third mode is selected in step S833, in step S804, the movement of the target part can be recognized using a machine learning model appropriate for the stage of movement of the target part during movement assistance execution. This improves the accuracy of movement recognition and enables more efficient rehabilitation. For example, when a target part of a living body is moved around a joint associated with that part, a first machine learning model may be used to recognize the movement of the target part when the joint angle is 0 degrees ≦ θ < 30 degrees, a second machine learning model may be used to recognize the movement of the target part when the joint angle is 30 degrees ≦ θ < 60 degrees, a third machine learning model may be used to recognize the movement of the target part when the joint angle is 60 degrees ≦ θ < 90 degrees, and a fourth machine learning model may be used to recognize the movement of the target part when the joint angle is 90 degrees ≦ θ.

[0201] Process 800 makes it possible to switch modes depending on the subject's range of self-movement, enabling movement assistance according to the subject's condition and movement. Furthermore, within the range in which the subject can move on his or her own, control is performed in the movement sensing mode rather than the biosignal sensing mode described below, thereby reducing the number of times the biosignal sensing mode is used and reducing erroneous recognition related to biosignal sensing.

[0202] In the above example, the steps of processes 400, 600, and 800 are described as being performed in a particular order, but the described order is merely an example. The steps of processes 400, 600, and 800 can be performed in any order that is logically possible. For example, in process 600, step S602 can be performed before step S601. For example, in step S603, steps S701, S704, and S707 can be performed in parallel.

[0203] Additionally, each step of processes 400, 600, and 800 may be omitted in one embodiment, or may be replaced with another step in another embodiment.

[0204] In the examples described above with reference to Figures 4, 5, 6, 7A, 7B, and 8, it has been explained that the processing of each step shown in Figures 4, 5, 6, 7A, 7B, and 8 is realized by the processor unit 120 and a program stored in the memory unit 130, but the present invention is not limited to this. At least one of the processing of each step shown in Figures 4, 5, 6, 7A, 7B, and 8 may be realized by a hardware configuration such as a control circuit.

[0205] The present invention is not limited to the above-described embodiments. It is understood that the scope of the present invention should be interpreted only by the claims. It is understood that a person skilled in the art can implement an equivalent scope based on the description of the present invention and common technical knowledge from the description of specific preferred embodiments of the present invention. [Industrial Applicability]

[0206] The present invention is useful for providing a program, a system for controlling an apparatus for assisting the movement of a target part of a subject, and a method for configuring an apparatus for assisting the movement of a target part of a subject. [Explanation of symbols]

[0207] 10. System for assisting subject in moving a target part 100 Device for assisting movement of a target part of a subject 200 Control Means 300 Acquisition method 400 Sensing means

Claims

[Claim 1] The invention described in this specification.

Images