Relaxation state determination system and relaxation state determination method

Abstract

To enable easy and highly accurate detection of a relaxed state. [Solution] The system includes a muscle displacement detection sensor 10 or 20 that detects muscle displacement at a specific location of the subject, and a relaxation state determination unit 105 that determines whether the subject is in a relaxed state or a tense state based on the muscle displacement detected by the muscle displacement detection sensor 10 or 20. The relaxation state determination unit 105 determines whether the subject is in a relaxed state based on the results of comparing the muscle displacement data with a threshold, or machine learning of the muscle displacement data. The specific location is one or a combination of the following muscle parts: calf, neck, upper arm, back, chin, head, forearm, shoulder, thigh, waist and buttocks, or abdomen.

Description

Technical Field

[0001] The present invention relates to a relaxation state determination system and a relaxation state determination method for determining that a subject is in a relaxed state.

Background Art

[0002] Conventionally, various methods for measuring the physical and mental health state have been proposed. For example, Patent Document 1 proposes a technique for determining the relaxation state of a subject based on the detected facial expression and the detected value of the heart rate detected from the face image of the subject. Further, Patent Document 2 proposes a technique for determining the relaxation state of a subject from electroencephalogram.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the changes in facial expressions and heart rate vary greatly among individuals. Even if a value indicating the relaxation state is detected by detecting a face image or heart rate using the technique described in Patent Document 1, the detected value is relative, and it has been difficult to detect a highly accurate relaxation degree. Also, as described in Patent Document 2, it is possible to detect the relaxation degree from electroencephalogram, but a large-scale configuration is required for the detection and analysis of electroencephalogram, and it has been difficult to determine a highly accurate relaxation state with a simple configuration.

[0005] An object of the present invention is to provide a relaxation state determination system and a relaxation state determination method that can accurately and easily determine the relaxation state. [Means for solving the problem]

[0006] The relaxation state determination system of the present invention comprises a muscle displacement detection sensor that detects muscle displacement at a specific location of a subject, and a relaxation state determination unit that determines whether the subject is in a relaxed state or a tense state based on the muscle displacement detected by the muscle displacement detection sensor. Of these, the specific areas mentioned above are composed of the following: gastrocnemius muscle, soleus muscle, tibialis anterior muscle, peroneal muscle, sternocleidomastoid muscle, scalene muscle, upper arm muscle, latissimus dorsi muscle, jaw muscle, head muscle, forearm muscle, deltoid muscle, thigh muscle, lower back and gluteal muscle, or abdominal muscle, either individually or in combination.

[0007] Furthermore, the relaxation state determination method of the present invention includes a muscle displacement detection process that detects muscle displacement at a specific location of the subject, and a relaxation state determination process that determines whether the subject is in a relaxed state or a tense state based on the muscle displacement detected by the muscle displacement detection process. Of these, the specific areas mentioned above are composed of the following: gastrocnemius muscle, soleus muscle, tibialis anterior muscle, peroneal muscle, sternocleidomastoid muscle, scalene muscle, upper arm muscle, latissimus dorsi muscle, jaw muscle, head muscle, forearm muscle, deltoid muscle, thigh muscle, lower back and gluteal muscle, or abdominal muscle, either individually or in combination.

[0008] The inventors of this invention have found a correlation between tasks performed by people and muscle displacement in specific parts of the human body. First, the inventors positioned "mental arithmetic" and "writing" as high-tension tasks, and "relaxing," "appreciation," and "casual conversation" as low-tension tasks. Then, the inventors collected output values ​​from muscle displacement detection sensors from specific parts of multiple subjects performing "mental arithmetic" or "writing." In addition, the inventors collected output values ​​from muscle displacement detection sensors from specific parts of multiple subjects performing "relaxing," "appreciation," or "casual conversation."

[0009] The inventor then divided the collected output values ​​from the muscle displacement detection sensor into training data and test data, classified the training data into tasks with high tension and tasks with low tension, and trained an SVM (Support Vector Machine) model. Next, the inventor input the remaining test data into the trained SVM and evaluated the model. As a result, the inventor confirmed that, at each specific location, tasks with high tension and tasks with low tension were classified with high accuracy. The table below shows the accuracy of classification at several specific locations (accuracy is highest on a scale of 1).

[0010] [Table 1]

[0011] The present invention is based on the correlation between muscle displacement and tension at a specific location, as discovered in this manner. [Effects of the Invention]

[0012] According to the present invention, it is possible to easily and appropriately determine whether a person is in a relaxed state or a tense state. [Brief explanation of the drawing]

[0013] [Figure 1] This is a diagram showing an example of a relaxation state determination system according to one embodiment of the present invention. [Figure 2] This figure shows an example of how to mount a sensor device used in a relaxation state determination system according to one embodiment of the present invention. [Figure 3] This is a perspective view showing an example (front view) of a sensor device used in a relaxation state determination system according to one embodiment of the present invention. [Figure 4] This is a perspective view showing an example (rear view) of a sensor device used in a relaxation state determination system according to one embodiment of the present invention. [Figure 5] This flowchart shows an example of the initial setup procedure for a relaxation state determination system according to one embodiment of the present invention. [Figure 6] It is a figure showing an example of a screen at the time of initial setting in a relaxation state determination system according to an exemplary embodiment of the present invention. [Figure 7] It is a flowchart showing an example of a determination processing procedure (example of threshold comparison) by a relaxation state determination system according to an exemplary embodiment of the present invention. [Figure 8] It is a flowchart showing an example of a determination processing procedure (example of machine learning) by a relaxation state determination system according to an exemplary embodiment of the present invention. [Figure 9] It is a figure showing an example of display of a determination result by a relaxation state determination system according to an exemplary embodiment of the present invention. [Figure 10] It is a configuration diagram showing an example of a relaxation state determination system according to a second exemplary embodiment of the present invention. [Figure 11] It is a flowchart showing an example of a determination processing procedure (example of threshold comparison) by the relaxation state determination system of FIG. 10. [Figure 12] It is a flowchart showing an example of a determination processing procedure (example of machine learning) by the relaxation state determination system of FIG. 10.

Mode for Carrying Out the Invention

[0014] [First Embodiment] Hereinafter, a relaxation state determination system and a relaxation state determination method according to an exemplary embodiment of the present invention (hereinafter referred to as "this example") will be described with reference to the accompanying drawings. The relaxation state determination system and the relaxation state determination method of this example are used for a process of detecting muscle displacement data from a single muscle part (specific location) and determining a tension state. In the relaxation state determination system of this example, the calf or the corrugator supercilii muscle will be described as an example of a specific location for detecting muscle displacement. However, the application of this example is not limited to the calf and the corrugator supercilii muscle.

[0015] The relaxation state assessment system described in this example can also be applied to the calves (gastrocnemius, soleus, tibialis anterior, and peroneal muscles), neck (sternocleidomastoid and scalene muscles), and upper arms. Furthermore, the relaxation state assessment system described in this example can also be applied to the back (trapezius and latissimus dorsi muscles), jaw (masseter and depressor anguli oris muscles), and head (frontalis and temporalis muscles from the temples to the forehead).

[0016] Furthermore, the relaxation state determination system in this example can also be applied to the forearm (flexor and extensor muscles of the hand and fingers, and pronator muscles involved in rotation), the shoulder (deltoid muscle), and the thigh (quadriceps femoris and hamstring muscles). In addition, the relaxation state determination system in this example can also be applied to the waist and buttocks (erector spinae muscles and gluteal muscles) and the abdominal area (rectus abdominis and oblique muscles). Here, "area" includes the area surrounding the muscle.

[0017] [Configuration of the relaxation state determination system] Figure 1 is a diagram showing an example of the relaxation state determination system in this example. As shown in Figure 1, the relaxation state determination system in this example consists of a calf sensor 10 or trapezius muscle sensor 20 attached to the subject's body B, and a terminal 100 that determines and displays the relaxation state based on the muscle displacement (calf muscle or trapezius muscle) detected by the calf sensor 10 or trapezius muscle sensor 20. The calf sensor 10 and the trapezius muscle sensor 20 are muscle displacement detection sensors that detect muscle displacement at the location where they are attached. In this example, it is sufficient to attach either the calf sensor 10 or the trapezius muscle sensor 20 to body B.

[0018] The terminal 100 can be a smartphone or a smartwatch. Examples of the configurations for the calf sensor 10 and trapezius muscle sensor 20 will be described later. The calf sensor 10 or trapezius muscle sensor 20 is a sensor that detects muscle displacement in multiple channels. The muscle displacement data detected by the calf sensor 10 or trapezius muscle sensor 20 is supplied to the terminal 100 by wired or wireless transmission.

[0019] The terminal 100, in terms of hardware configuration, consists of a CPU (Central Processing Unit) 111, memory 112, sensor interface 113, display unit 106, and communication interface 107, as shown in the lower part of Figure 1. The terminal 100 then realizes each of the processing units described below by executing the application program implemented in the memory 112 using the CPU 111.

[0020] First, let's describe the configuration from the perspective of the functions performed by terminal 100. Terminal 100 includes a muscle displacement data acquisition unit 101, a threshold determination unit 102, a machine learning unit 103, an initial setting unit 104, a relaxation state determination unit 105, and a display unit 106. The muscle displacement data acquisition unit 101 acquires muscle displacement data from the calf sensor 10 or the trapezius muscle sensor 20. In this case, the muscle displacement data acquisition unit 101 acquires 14 channels of muscle displacement data. The threshold determination unit 102 compares the muscle displacement data of 14 channels with a preset threshold and supplies the number of channels in which it determines that the muscle displacement data has deviated above the threshold to the relaxation state determination unit 105.

[0021] The machine learning unit 103 classifies the 14 channels of muscle displacement data using machine learning processing, determining whether the muscle displacement data for each channel indicates a state of tension or relaxation. The machine learning unit 103 then supplies the classified data to the relaxation state determination unit 105. The initial setup unit 104 performs the initial setup when the calf sensor 10 or trapezius muscle sensor 20 is attached to the subject's body B. Here, the machine learning unit 103 may use deep learning with a deep neural network to classify whether the multi-channel muscle displacement data is in a state of tension or relaxation. The relaxation state determination unit 105 determines whether the subject is in a relaxed state or a tense state based on either or both of the output data from the threshold determination unit 102 and the output data from the machine learning unit 103.

[0022] The display unit 106 displays the result of the relaxation state determination unit 105. Furthermore, the results of the relaxation state determination unit 105 may be transmitted to a server or another terminal via the internet or other means. In Figure 1, terminal 100 is configured to include both a threshold determination unit 102 and a machine learning unit 103, but terminal 100 may be configured to include only one of them.

[0023] [Sensor configuration and installation examples] Figure 2 shows an example in which the calf sensor 10 is attached to the calf of one leg f of body B. As shown in Figure 2, the calf sensor 10 is attached to detect muscle displacement data, for example, the displacement (tension) of the posterior muscle (gastrocnemius muscle) slightly above the ankle (for example, about 10 centimeters above).

[0024] Figures 3 and 4 are perspective views showing an example configuration of the calf sensor 10 as it is attached as shown in Figure 2. Figure 3 shows the front side of the calf sensor 10, and Figure 4 shows the back side of the calf sensor 10. The calf sensor 10 consists of a main body 11 and a belt 12. The belt 12 is made of a flexible resin such as silicone rubber. By joining one end 12a and the other end 12b of the belt 12, the calf sensor 10 is attached around the calf as shown in Figure 2. The main body 11 of the calf sensor 10 contains a circuit board for detecting muscle displacement and a battery.

[0025] Furthermore, as shown in Figure 4, 14 sensor members 13 are arranged in a row along the longitudinal direction of the belt 12 on the back side of the calf sensor 10. Each sensor member 13 is equipped with a lens, and these lenses detect the displacement of the calf muscles (gastrocnemius muscle). As the sensor member 13, for example, an optical distance sensor that detects distance using infrared light is used. Each sensor member 13 performs muscle displacement detection processing based on the detected distance. When attaching the calf sensor 10, 14 sensor members 13 are arranged on the posterior side of the calf. The posterior side of the calf is an area where muscles are concentrated.

[0026] The 14 channels of muscle displacement data detected by the 14 sensor members 13 are digitized by a circuit in the main unit 11 and then wirelessly transmitted to the terminal 100. Alternatively, the calf sensor 10 and the terminal 100 may be connected by a wire, and the muscle displacement data may be transmitted to the terminal 100 via the wire.

[0027] Although the configuration of the trapezius muscle sensor 20 is not shown in the diagram, the trapezius muscle sensor 20 is configured to detect muscle displacement using the same principle as the calf sensor 10. Specifically, the trapezius muscle sensor 20 is attached to the area from the neck to the upper back of the subject's body B. The area from the neck to the upper back of the subject's body B is where the trapezius muscle is concentrated. The trapezius muscle sensor 20 has 14 sensor members, similar to the sensor member 13 of the calf sensor 10 shown in Figure 4, arranged on its mounting surface to detect 14 channels of trapezius muscle displacement. Similar to the sensor member 13 of the calf sensor 10, the detected trapezius muscle displacement data is transmitted to the terminal 100 wirelessly or via wired connection.

[0028] [Initial setup process] When using the relaxation state determination system in this example to determine the state of relaxation, initial setup is required on the terminal 100 after attaching the calf sensor 10 or trapezius muscle sensor 20 to the subject's body B. As already explained in Figure 1, the initial setup is performed by the initial setup unit 104.

[0029] Figure 5 is a flowchart showing the initial setup process by the initial setup unit 104. First, when the initial setup unit 104 starts the initial setup, it displays a message on the display unit 106 instructing the subject to exert force (step S11). For example, when using the calf sensor 10, it instructs the subject to exert force in their legs, and when using the trapezius muscle sensor 20, it instructs the subject to exert force in their shoulders.

[0030] After the instructions are given in step S11, the initial setup unit 104 learns the muscle displacement data detected by the calf sensor 10 or trapezius muscle sensor 20 as muscle displacement data during tension (step S12). In step S12, the initial setup unit 104 calculates, for example, the maximum value and average value from among the 14 channels of muscle displacement data to determine the muscle displacement data during tension. Here, even when using the average value of muscle displacement data during tension, it is not necessarily a simple average of all 14 channels of muscle displacement data; it could be the average of a predetermined number of top channels, for example. Alternatively, when using muscle displacement data during tension for machine learning, all 14 channels of muscle displacement data may be used.

[0031] Next, the initial setup unit 104 instructs the subject to relax by displaying a message on the display unit 106 (step S13). Here, the initial setup unit 104 instructs the subject to relax their legs if the calf sensor 10 is used, and to relax their shoulders if the trapezius muscle sensor 20 is used. After the instruction is given in step S13, the initial setup unit 104 learns the muscle displacement data detected by the calf sensor 10 or the trapezius muscle sensor 20 as muscle displacement data during relaxation (step S14). Here, the initial setup unit 104 calculates, for example, the maximum value or average value from the 14 channels of muscle displacement data to use as muscle displacement data during relaxation. Alternatively, the initial setup unit 104 may use the values ​​of all 14 channels of muscle displacement as muscle displacement data during relaxation for machine learning.

[0032] Then, the initial setup unit 104 sets the threshold determination unit 102 and the machine learning unit 103 based on the muscle displacement data values ​​during tension learned in step S12 and the muscle displacement data values ​​during relaxation learned in step S13 (step S15). In other words, the threshold determination unit 102 sets a threshold TH1 for determination between the value of muscle displacement data during tension and the value of muscle displacement during relaxation. Furthermore, the machine learning unit 103 is configured to use the obtained muscle displacement data values ​​during tension and the muscle displacement data values ​​during relaxation as training signals for machine learning.

[0033] Figure 6 shows an example of the display screen of the display unit 106 during initial setup. Figure 6 shows an example of the instruction screen when the calf sensor 10 is used to instruct the subject to exert force in step S11. At this time, the screen in Figure 6 displays the message 201, "Pull your foot towards you and keep tensing your calf muscles," and an image 202 showing the position of the foot at that time.

[0034] Furthermore, the screen in Figure 6 also displays a "Measuring" button 203 and an "End" button 204, allowing the subject to touch the screen to start or end the measurement. When instructing the subject to relax in step S13, the same screen will display instructions for relaxing. After the initial setup described above is complete, the relaxation state determination process in this example's relaxation state determination system will begin.

[0035] [Relaxation state determination process based on threshold judgment] Figure 7 is a flowchart showing the process by which the relaxation state determination unit 105 determines the relaxation state based on the determination result in the threshold determination unit 102. First, the muscle displacement data acquisition unit 101 acquires 14 channels of muscle displacement data and supplies the acquired 14 channels of muscle displacement data to the threshold determination unit 102 (step S21). The threshold determination unit 102 compares the acquired muscle displacement data values ​​from the 14 channels with the threshold TH1 set in the initial setup process (step S22).

[0036] Then, the threshold determination unit 102 determines, based on the results obtained from the comparison in step S22, whether more than half of the 14 channels, i.e., 7 or more channels, meet the threshold TH1 (step S23). In step S23, if more than half of the channels are above the threshold TH1 (Yes in step S23), the relaxation state determination unit 105 determines that the subject is in a state of tension (step S24). Also, in step S23, if more than half of the channels are not above the threshold TH1 (No in step S23), the relaxation state determination unit 105 determines that the subject is in a relaxed state (step S25).

[0037] Then, the relaxation state determination unit 105 displays a screen on the display unit 106 based on the determination result (step S26). For example, the display unit 106 may display "You are in a relaxed state" or "You are in a tense state" based on the determination result. Alternatively, the relaxation state determination unit 105 may transmit the determination result to a server or the like via the communication unit of the terminal 100, and the server may register whether the subject is in a relaxed state or a tense state.

[0038] [Machine learning-based relaxation state detection process] Figure 8 is a flowchart showing the process by which the relaxation state determination unit 105 determines the relaxation state based on the classification results from the machine learning unit 103. First, the muscle displacement data acquisition unit 101 acquires 14 channels of muscle displacement data and supplies the acquired 14 channels of muscle displacement data to the machine learning unit 103 (step S31). The machine learning unit 103 classifies the acquired 14-channel muscle displacement data values ​​using the training signal obtained during the initial setup (step S32).

[0039] Then, the relaxation state determination unit 105 obtains the results of the classification in step S32 and determines whether or not the classification result was classified as a state of tension (step S33). In step S33, if the classification result is a state of tension (Yes in step S33), the relaxation state determination unit 105 determines that the subject is in a state of tension (step S34). Also, in step S33, if the subject is not in a state of tension (No in step S33), the relaxation state determination unit 105 determines that the subject is in a relaxed state (step S35).

[0040] Then, the relaxation state determination unit 105 displays a screen based on the determination result on the display unit 106 (step S36). In this case as well, the relaxation state determination unit 105 may also transmit the determination result to a server or the like via the communication unit of the terminal 100, so that the server can register whether the subject is in a relaxed state or a tense state.

[0041] [Example of displaying a relaxed state] Figure 9 shows an example of the display screen of terminal 100 showing relaxed and stressed states. The example in Figure 9 shows that terminal 100 displays the relaxed or tense state obtained from the calf sensor 10 or trapezius muscle sensor 20 connected to terminal 100. However, it is also possible to display the relaxed or tense state obtained from another terminal other than terminal 100.

[0042] In other words, Figure 9 displays the facial images of subjects A1 and A2. In the example on the left of Figure 9, a rain symbol M1 is displayed next to subject A1's face, and the face itself is displayed in a dark color. This indicates that subject A1 is in a state of tension. In the example on the right of Figure 9, a sun symbol M2 is displayed next to subject A2's face, and the face itself is displayed in a bright color. This indicates that subject A2 is in a relaxed state.

[0043] As explained above, the relaxation state determination system in this example can accurately determine and display whether a subject is in a relaxed or tense state based on muscle displacement data from the calf or trapezius muscle. In particular, by determining the state from the calf or trapezius muscle, the accuracy of detecting relaxation and tension in this relaxation state determination system can be greatly improved.

[0044] [Second Embodiment] Next, a relaxation state determination system and relaxation state determination method of a second embodiment of the present invention (hereinafter referred to as "this example") will be described with reference to the attached drawings. In this example of a relaxation state determination system, muscle displacement data is simultaneously detected from combinations of multiple muscle areas (specific locations) to determine the state of tension. In this example of a relaxation state determination system, the calf and trapezius muscles are used as examples to explain specific locations for detecting muscle displacement. However, the application of this example is not limited to the combination of the calf and trapezius muscles. Furthermore, this example can be applied not only to combinations of two locations, but also to combinations of three or more locations.

[0045] The relaxation state determination system in this example can include the calf (gastrocnemius, soleus, tibialis anterior, and peroneal muscles), neck (sternocleidomastoid and scalene muscles), or upper arm in its combination. Furthermore, the relaxation state determination system in this example can include the back (trapezius and latissimus dorsi muscles), chin (masseter and depressor anguli oris muscles), or head (frontalis and temporalis muscles from the temples to the forehead) in its combination.

[0046] Furthermore, the relaxation state determination system in this example can include the forearm region (flexor and extensor muscles of the hand and fingers, and pronator muscles involved in rotation), the shoulder region (deltoid muscle region), or the thigh (quadriceps femoris region, hamstring muscle region) in its combination. Additionally, the relaxation state determination system in this example can include the waist and buttocks (erector spinae muscle region, gluteal muscle region) or the abdominal region (rectus abdominis muscle region, oblique abdominal muscle region) in its combination. Here, "region" includes the area surrounding the muscle.

[0047] In the following description of this example (second embodiment), the same reference numerals are used for parts identical to those in the first embodiment, and redundant explanations are omitted.

[0048] [Configuration of the relaxation state determination system] As shown in Figure 10, the relaxation state determination system in this example consists of a calf sensor 10 and a trapezius muscle sensor 20 attached to the subject's body B, and a terminal 100 that determines and displays the relaxation state based on the muscle displacement (calf muscles and trapezius muscles) detected by the calf sensor 10 and trapezius muscle sensor 20. The calf sensor 10 and trapezius muscle sensor 20 are muscle displacement detection sensors that detect muscle displacement at the location where they are attached. In the relaxation state determination system in this example, both the calf sensor 10 and the trapezius muscle sensor 20 are attached to body B.

[0049] The muscle displacement data acquisition unit 101 simultaneously acquires muscle displacement data from the calf sensor 10 and the trapezius muscle sensor 20. Here, 14 channels of muscle displacement data are acquired from each sensor, for a total of 28 channels of muscle displacement data. The threshold determination unit 102 compares the muscle displacement data of 28 channels with a preset threshold and supplies the number of channels in which it determines that the muscle displacement data has deviated above the threshold to the relaxation state determination unit 105.

[0050] The machine learning unit 103 classifies the muscle displacement data of the 28 channels using machine learning processing, determining whether the muscle displacement data for each channel indicates a state of tension or relaxation. The machine learning unit 103 then supplies the classified data to the relaxation state determination unit 105. The initial setup unit 104 performs the initial setup when the calf sensor 10 and trapezius muscle sensor 20 are attached to the subject's body B. Here, the machine learning unit 103 may use deep learning with a deep neural network to classify whether the multi-channel muscle displacement data is in a state of tension or relaxation. The relaxation state determination unit 105 determines whether the subject is in a relaxed state or a tense state based on either or both of the output data from the threshold determination unit 102 and the output data from the machine learning unit 103.

[0051] The display unit 106 displays the result of the relaxation state determination unit 105. Furthermore, the results of the relaxation state determination unit 105 may be transmitted to a server or another terminal via the internet or other means. In Figure 10, the terminal 100 is configured to include both the threshold determination unit 102 and the machine learning unit 103, but the terminal 100 may be configured to include only one of them.

[0052] [Initial setup process] The initial setup process is the same as in the first embodiment. However, in this example, since both the calf sensor 10 and the trapezius muscle sensor 20 are used in the process, the initial setup process is performed for both the calf sensor 10 and the trapezius muscle sensor 20.

[0053] The threshold determination unit 102 sets a threshold TH1 for determination based on the output of the calf sensor 10, between the value of the muscle displacement data during tension and the value of the muscle displacement data during relaxation. Similarly, the threshold determination unit 102 sets a threshold TH2 for determination based on the output of the trapezius muscle sensor 20, between the value of the muscle displacement data during tension and the value of the muscle displacement data during relaxation. Furthermore, the machine learning unit 103 sets the values ​​of muscle displacement data obtained from both the calf sensor 10 and the trapezius muscle sensor 20 during tension, and the values ​​of muscle displacement data during relaxation, to be used as training signals for machine learning.

[0054] [Relaxation state determination process based on threshold judgment] Figure 11 is a flowchart showing the process by which the relaxation state determination unit 105 determines the relaxation state based on the determination result from the threshold determination unit 102. First, the muscle displacement data acquisition unit 101 acquires 14 channels of muscle displacement data from the calf sensor 10 and 14 channels of muscle displacement data from the trapezius muscle sensor 20, and supplies the acquired 28 channels of muscle displacement data to the threshold determination unit 102 (step S41). The threshold determination unit 102 compares the values ​​of the 14 channels of muscle displacement data acquired from the calf sensor 10 with the threshold TH1 set in the initial setup process, and also compares the values ​​of the 14 channels of muscle displacement data acquired from the trapezius muscle sensor 20 with the threshold TH2 set in the initial setup process (step S42).

[0055] Then, the threshold determination unit 102 determines, based on the results obtained from the comparison in step S42, whether more than half of the total 28 channels of the calf sensor 10 and trapezius muscle sensor 20, i.e., 14 channels or more, are at or above threshold TH1 or threshold TH2 (step S43).

[0056] In step S43, if more than half of the channels are at or above the threshold TH1 or threshold TH2 (Yes in step S43), the relaxation state determination unit 105 determines that the subject is in a state of tension (step S44). Also, in step S43, if more than half of the channels are not at or above the threshold TH1 or threshold TH2 (No in step S43), the relaxation state determination unit 105 determines that the subject is in a relaxed state (step S45).

[0057] Then, the relaxation state determination unit 105 displays a screen on the display unit 106 based on the determination result (step S46). For example, the display unit 106 may display "You are in a relaxed state" or "You are in a tense state" based on the determination result. Alternatively, the relaxation state determination unit 105 may transmit the determination result to a server or the like via the communication unit of the terminal 100, and the server may register whether the subject is in a relaxed state or a tense state.

[0058] [Machine learning-based relaxation state detection process] Figure 12 is a flowchart showing the process by which the relaxation state determination unit 105 determines the state of relaxation based on the classification results from the machine learning unit 103. First, the muscle displacement data acquisition unit 101 acquires a total of 28 channels of muscle displacement data from the calf sensor 10 and the trapezius muscle sensor 20, and supplies the acquired 28 channels of muscle displacement data to the machine learning unit 103 (step S51). The machine learning unit 103 classifies the acquired 28 channels of muscle displacement data using the training signal obtained in the initial setup (step S52).

[0059] Then, the relaxation state determination unit 105 obtains the results of the classification in step S52 and determines whether or not the classification result was classified as a state of tension (step S53). In step S53, if the classification result is a state of tension (Yes in step S53), the relaxation state determination unit 105 determines that the subject is in a state of tension (step S54). Also, in step S53, if the subject is not in a state of tension (No in step S53), the relaxation state determination unit 105 determines that the subject is in a relaxed state (step S55).

[0060] Then, the relaxation state determination unit 105 displays a screen based on the determination result on the display unit 106 (step S56). In this case as well, the relaxation state determination unit 105 may also transmit the determination result to a server or the like via the communication unit of the terminal 100, so that the server can register whether the subject is in a relaxed state or a tense state.

[0061] As explained above, the relaxation state determination system in this example determines whether a subject is in a relaxed state or a tense state based on muscle displacement data from two locations, the calf and the trapezius muscle, i.e., muscle displacement data from multiple specific locations. Therefore, it can make a more accurate determination compared to making a determination based on muscle displacement data from only one location.

[0062] [Differentiation] It should be noted that the embodiments described above are detailed explanations provided to make the present invention easier to understand, and the configurations and processes described in the above embodiments can be modified or changed in various ways. For example, in the relaxation state determination system of this example, 14 channels of muscle displacement data are acquired from the calf sensor 10 or the trapezius muscle sensor 20, and the relaxation state is determined from the 14 channels of muscle displacement data. However, the relaxation state may also be determined from muscle displacement data with fewer channels. However, since the threshold determination unit 102 performs a majority vote to determine if more than half of the channels are above the threshold, it is preferable that at least 3 channels of muscle displacement data are acquired. However, it is also possible to determine tension if one of the 2 channels of muscle displacement data exceeds the threshold, or if the muscle displacement data of 1 channel exceeds the threshold. In the relaxation state determination system of this example, the determination was made based on whether the threshold is "above" the threshold and whether more than half of the channels are "above" the threshold. Instead, the determination could be made based on whether the threshold is "exceeded" and whether more than half of the channels are "above" the threshold.

[0063] Furthermore, while initial setup is preferably performed when the calf sensor 10 or trapezius muscle sensor 20 is attached, after the initial setup has been performed, the same subject may be assessed using the data obtained during the initial setup, even after attaching or detaching the calf sensor 10 or trapezius muscle sensor 20. In addition, the training signals for machine learning may be improved by obtaining setting values ​​from a large number of subjects.

[0064] Furthermore, while the example shown in Figure 1 uses a terminal 100 such as a smartphone to determine the state of relaxation, the calf sensor 10 or trapezius muscle sensor 20 may also incorporate a processing unit such as a microcontroller that performs the determination process shown in the flowchart in Figure 7 or Figure 8. Alternatively, muscle displacement data obtained from the calf sensor 10 or trapezius muscle sensor 20 may be transmitted to an external server, where the server may determine the state of relaxation or tension. In this case, the server would implement a program that performs the determination process shown in the flowchart in Figure 7 or Figure 8.

[0065] Furthermore, as mentioned above, the specific locations on the human body from which the muscle displacement detection sensor detects muscle displacement are not limited to the calf and trapezius muscles. The muscle displacement detection sensor can detect muscle displacement data from each of the specific locations mentioned above. In addition, while the second embodiment showed an example of determining the tension state by simultaneously acquiring muscle displacement data from two muscle sites, it is also possible to simultaneously acquire muscle displacement data from three or more muscle sites and perform majority voting based on thresholds or classification using a machine learning model.

[0066] Furthermore, the form of the sensor that acquires muscle displacement data is not limited to the belt-like form shown in Figures 2 to 4. Muscle displacement detection sensors may be placed on the surface of objects that are close to the body, such as chairs or beds, to acquire muscle displacement data at specific locations. Muscle displacement detection sensors may also be placed on fabric that closely wraps around the body, such as a bodysuit, to acquire muscle displacement data at specific locations. In addition, muscle displacement detection sensors may be placed at specific locations using means of attachment to the body, such as stickers or suction cups.

[0067] Furthermore, the tension level can be expressed numerically. For example, when determining the tension level by comparing muscle displacement data with a threshold, the tension level can be expressed as the ratio of the number of channels that exceed the threshold to the total number of channels. Alternatively, the tension level can be expressed numerically and reflected in the number of hearts, as shown in Figure 9. [Explanation of Symbols]

[0068] 10...Calf sensor, 11...Main unit, 12...Belt, 13...Sensor component, 20...Trapezius muscle sensor, 100...Terminal, 101...Muscle displacement data acquisition unit, 102...Threshold determination unit, 103...Machine learning unit, 104...Initial setup unit, 105...Relaxation state determination unit, 106...Display unit, 107...Communication interface, 111...CPU, 112...Memory, 113...Sensor interface, 201...Message display, 202...Image display, 203...Measurement in progress button, 204...End button

Claims

1. A muscle displacement detection sensor that detects muscle displacement in a specific area of ​​the subject, The system includes a relaxation state determination unit that determines whether the subject is in a relaxed state or a tense state based on the muscle displacement detected by the muscle displacement detection sensor, The aforementioned specific area is one or a combination of the following muscle groups: gastrocnemius, soleus, tibialis anterior, peroneal, sternocleidomastoid, scalene, upper arm, latissimus dorsi, jaw, head, forearm, deltoid, thigh, hip and gluteal muscles, or abdominal muscles. Relaxation state detection system.

2. Furthermore, the system includes a threshold determination unit that compares the value of the muscle displacement detected by the muscle displacement detection sensor with a predetermined threshold. The relaxation state determination unit determines that the subject is relaxed if the muscle displacement value determined by the threshold determination unit is less than the threshold, and determines that the subject is tense if the value exceeds the threshold. The relaxation state determination system according to claim 1.

3. The muscle displacement detection sensor detects muscle displacement of a specific location (including the trapezius muscle) or a combination of muscle parts using N channels (where N is 2 or more). The threshold determination unit determines that the person is relaxed if the muscle displacement values ​​of more than half of the N channels are below the predetermined threshold, and determines that the person is tense if the muscle displacement values ​​of more than half of the channels exceed the threshold. The relaxation state determination system according to claim 2.

4. As an initial setting, when the subject is instructed to apply force to the specific area, the muscle displacement detection sensor detects the value of the muscle displacement, and when the subject is instructed to release the force at the specific area, The system measures the muscle displacement values ​​detected by the muscle displacement detection sensor and sets the threshold values ​​based on the measured values ​​of each muscle displacement. The relaxation state determination system according to claim 2.

5. Furthermore, the system includes a machine learning unit that performs machine learning based on the muscle displacement values ​​of the specific location (including the trapezius muscle) or combinations of muscle parts detected by the muscle displacement detection sensor. The relaxation state determination unit determines whether the subject is in a relaxed state or a tense state based on the results of machine learning processing performed by the machine learning unit. The relaxation state determination system according to claim 1.

6. A muscle displacement detection process that detects muscle displacement in specific areas of the subject, This includes a relaxation state determination process that determines whether the subject is in a relaxed state or a tense state based on the muscle displacement detected by the muscle displacement detection process, The aforementioned specific location is one or a combination of the following muscle groups: gastrocnemius, soleus, tibialis anterior, peroneal, sternocleidomastoid, scalene, upper arm, latissimus dorsi, jaw, head, forearm, deltoid, thigh, hip and gluteal muscles, or abdominal muscles. Method for determining a relaxed state.

Images