Mental state estimation device, mental state estimation system, and mental state estimation method

Abstract

This invention provides a mental and physical state estimation device, a mental and physical state estimation system, and a mental and physical state estimation method for estimating a subject's mental and physical state from the subject's walking movements in daily life. [Solution] A mental and physical state estimation device 3 for estimating the mental and physical state of subject P. The mental and physical state estimation device 3 comprises an input unit that receives walking data of subject P and environmental information of subject P, a storage unit that stores walking data in association with environmental information, a calculation unit that estimates the mental and physical state of subject P from the walking data and environmental information received by the input unit, and an output unit that outputs the mental and physical state of the subject estimated by the calculation unit. The calculation unit extracts walking data for a specific walking state based on the environmental information and estimates the mental and physical state of subject P from the extracted walking data based on estimation criteria set by the environmental information.

Description

Technical Field

[0001] The present disclosure relates to a psychosomatic state estimation device, a psychosomatic state estimation system, and a psychosomatic state estimation method.

Background Art

[0002] There is disclosed in Japanese Unexamined Patent Application Publication No. 2024-032633 (Patent Document 1) an emotion estimation device capable of estimating the emotion of a subject from walking data obtained by measuring the walking motion of the subject. In this device, correspondence data associating a plurality of walking indices included in the walking data with emotion data is obtained, the emotion of the subject is estimated from the received walking data, and the estimated emotion of the subject is output.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the device disclosed in Japanese Unexamined Patent Application Publication No. 2024-032633 (Patent Document 1) estimates emotions such as "happy", "angry", and "depressed" of the subject, and mainly estimates the psychological state of the subject. Therefore, with this device, it is not possible to estimate the physical state of the subject in addition to the psychological state of the subject. In recent years, there has been a demand for a device that can estimate the psychosomatic state of businesspersons, including physical states such as physical fatigue in addition to psychological states such as mental fatigue.

[0005] The present disclosure has been made to solve such problems, and an object thereof is to provide a psychosomatic state estimation device, a psychosomatic state estimation system, and a psychosomatic state estimation method for estimating the psychosomatic state of a subject from the walking motion of the subject in daily life.

Means for Solving the Problems

[0006] A mental and physical state estimation device according to a certain aspect of this disclosure is a mental and physical state estimation device for estimating the mental and physical state of a subject. The mental and physical state estimation device comprises an input unit that receives the subject's walking data and the subject's environmental information, a storage unit that stores the walking data in association with the environmental information, a calculation unit that estimates the subject's mental and physical state from the walking data and environmental information received by the input unit, and an output unit that outputs the subject's mental and physical state estimated by the calculation unit. The calculation unit extracts walking data for a specific walking state based on the environmental information and estimates the subject's mental and physical state from the extracted walking data based on estimation criteria set by the environmental information.

[0007] A mental and physical state estimation system according to a certain aspect of this disclosure comprises a measuring device for measuring walking data and the mental and physical state estimation device described above.

[0008] A method for estimating a mental and physical state according to a certain aspect of this disclosure is a method for estimating the mental and physical state of a subject. The method for estimating a mental and physical state includes the steps of: receiving walking data of a subject measured by a measuring device and environmental information of the subject; storing the walking data in a storage unit in association with the environmental information; setting estimation criteria based on the environmental information; extracting walking data for a specific walking state based on the environmental information; estimating the mental and physical state of the subject from the extracted walking data based on the set estimation criteria; and outputting the estimated mental and physical state of the subject. [Effects of the Invention]

[0009] According to this disclosure, walking data for specific walking states is extracted based on environmental information, and the subject's physical and mental state is estimated from the extracted walking data based on estimation criteria set by the environmental information, thereby enabling a highly accurate estimation of the subject's physical and mental state. [Brief explanation of the drawing]

[0010] [Figure 1]This is a schematic diagram showing the configuration of a mental and physical state estimation system, including a mental and physical state estimation device according to an embodiment. [Figure 2] This is a schematic diagram illustrating a smart shoe according to an embodiment. [Figure 3] This is a block diagram showing the configuration of a mental and physical state estimation device according to an embodiment. [Figure 4] This is a flowchart illustrating the fatigue estimation process performed by the mental and physical state estimation device according to the embodiment. [Figure 5] This is a diagram to explain the ground contact angle in walking data. [Figure 6] This diagram illustrates the proportion of stance phase time in gait data. [Figure 7] This diagram illustrates how gait indices change depending on the environment. [Figure 8] This diagram explains the conditions for excluding data from the walking data used for fatigue estimation. [Figure 9] This diagram illustrates the processing of walking data used for fatigue estimation. [Figure 10] This diagram illustrates the change in walking indicators in relation to walking speed. [Figure 11] This diagram illustrates the estimation criteria used for estimating fatigue in outdoor environments. [Figure 12] This figure illustrates the differences in the regression lines for the ratio of stance phase time to walking speed in different environments. [Figure 13] This diagram illustrates another estimation criterion used for estimating fatigue in outdoor environments. [Figure 14] This figure shows an example of changes in walking indicators used to estimate fatigue. [Figure 15] This figure shows an example of the estimation results obtained by performing fatigue estimation. [Modes for carrying out the invention]

[0011] In the present disclosure, examples of a psychosomatic state estimation device, a psychosomatic state estimation system, and a psychosomatic state estimation method for estimating a subject's psychosomatic state from walking data of the subject's walking motion (which may include running motion) obtained from a sensor provided on the subject will be described. Here, the psychosomatic state includes a mental state and a physical state. The mental state includes emotions such as "happy", "angry", "depressed", mental fatigue, stress, etc., and the physical state includes physical fatigue and physical complaints, etc. In the following examples, as an example of estimating the psychosomatic state of a subject, a case where a sensor is provided on shoes and fatigue of the psychosomatic state (including mental fatigue and physical fatigue) is estimated from the walking data of the subject will be described.

[0012] However, the psychosomatic state estimation device, the psychosomatic state estimation system, and the psychosomatic state estimation method are not limited to fatigue estimation, and can be similarly used for estimating the psychosomatic state (such as emotions and stress) of the subject. Also, the attachment position of the sensor for acquiring the subject's walking data is not limited to shoes, and it may be attached to the leg with a supporter or the like. Furthermore, if the subject's walking motion can be continuously measured daily, there is no limitation on the type and number of sensors.

[0013] [[ID=⑧]]Hereinafter, the psychosomatic state estimation device, the psychosomatic state estimation system, and the psychosomatic state estimation method according to the embodiment will be described based on the drawings. In the following description, the same components are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated.

[0014] (Embodiment) [Configuration of Psychosomatic State Estimation System] FIG. 1 is a schematic diagram showing the configuration of a mental and physical state estimation system 100 including a mental and physical state estimation device 3 according to an embodiment. The mental and physical state estimation system 100 includes a mobile terminal 1, smart shoes 2, and a mental and physical state estimation device 3. The mobile terminal 1 transmits the walking data acquired by the smart shoes 2 to the mental and physical state estimation device 3, and receives and displays the estimation result of the fatigue of the subject P estimated by the mental and physical state estimation device 3. The smart shoes 2 include sensors that measure the movement of the subject P during walking or running. The smart shoes 2 including the sensors function as a measuring device that measures walking data.

[0015] The mental and physical state estimation device 3 estimates the fatigue of the subject P from the walking data acquired by the smart shoes 2 by executing a fatigue estimation program. The mental and physical state estimation device 3 receives the environmental information of the subject P in addition to the walking data of the subject P. Here, as the environmental information, for example, it includes at least one of the time zone of walking, the place of walking, the weather at the time of walking, and the temperature and humidity at the time of walking. Specifically, the mental and physical state estimation device 3 acquires the information of the time zone of walking from the time when the walking data of the subject P is received by the mobile terminal 1, and also receives the position information of a GPS (Global Positioning System) receiver (not shown) provided in the mobile terminal 1 as the information of the place of walking. Further, the mental and physical state estimation device 3 acquires the information of the weather at the time of walking and the temperature and humidity at the time of walking at the position from the position information received from the mobile terminal 1 via the Internet or the like.

[0016] The mental and physical state estimation device 3 has been described as acquiring the time information and the position information from the mobile terminal 1 in addition to the walking data of the subject P, and acquiring the information of the weather at the time of walking and the temperature and humidity at the time of walking from the Internet or the like from the information. However, the mobile terminal 1 may add the time information, the position information, the weather at the time of walking, and the temperature and humidity at the time of walking to the walking data acquired by the smart shoes 2 as the environmental information of the subject P and transmit it to the mental and physical state estimation device 3. Further, if the sensors of the smart shoes 2 include a clock function and a GPS function, the time information and the position information may be included in the walking data of the subject P transmitted from the smart shoes 2 to the mobile terminal 1.

[0017] The mental and physical state estimation device 3 was explained to estimate the fatigue of subject P from walking data acquired by smart shoes 2 by executing a fatigue estimation program. However, the fatigue estimation program may also be executed on the mobile terminal 1, and the mobile terminal 1 may function as a mental and physical state estimation device by executing the fatigue estimation program.

[0018] Furthermore, the mental and physical state estimation device 3 can also estimate the fatigue of subject P from walking data, taking into account the attributes of subject P received by the mobile terminal 1 (for example, gender, age, body type, height, etc.). For example, the mental and physical state estimation device 3 may estimate the fatigue of subject P from walking data based on fatigue estimation criteria set for each attribute of subject P received. The mental and physical state estimation device 3 may also store the fatigue estimation criteria set for each attribute.

[0019] [Smart Shoes] First, we will describe the smart shoes 2, which include sensors for measuring walking or running movements in the mental and physical state estimation system 100. Figure 2 is a schematic diagram illustrating the smart shoes 2 according to an embodiment. The smart shoes 2 shown in Figure 2 incorporate a sensor module 21 (an example of a sensor), and this sensor module 21 measures the walking data of the subject P.

[0020] Although not shown in the diagram, the sensor module 21 includes an acceleration sensor, an angular velocity sensor, a calculation circuit that calculates gait indicators from the measurements of these sensors, and a communication circuit for wirelessly transmitting gait data, including the gait indicators and measurements calculated by the calculation circuit, to the mobile terminal 1. The acceleration sensor can measure acceleration in the three axes X, Y, and Z, for example, and the angular velocity sensor can measure angular velocity in each of the three axes X, Y, and Z. Therefore, the sensor module 21 can include gait indicators such as stride, walking speed, cadence, time taken per step, stance phase duration, swing phase duration, stance phase duration, toe angle at ground contact (ground contact angle), pronation, maximum foot height, and landing impact (force at ground contact) as gait data of subject P, based on the measurements of the acceleration sensor and the angular velocity sensor. Here, landing impact is the force applied to the foot at the time of landing and is an example of a gait indicator estimated based on the maximum value of the vertical acceleration at the time of landing.

[0021] Although it has been explained that walking data is transmitted from the sensor module 21 to the mobile terminal 1 via wireless communication, this is not the only method. For example, walking data may be transmitted from the sensor module 21 to the mobile terminal 1 via wired communication or using a recording medium (e.g., a memory chip, USB memory, etc.).

[0022] Furthermore, although it has been explained that the sensor module 21 calculates a gait index from the measured values ​​of the acceleration sensor and the angular velocity sensor, it is not limited to this. For example, the sensor module 21 may simply transmit the measured values ​​of the acceleration sensor (3-axis acceleration values) and the measured values ​​of the angular velocity sensor (3-axis angular velocity values) to the mobile terminal 1 or the mental state estimation device 3, and the mobile terminal 1 or the mental state estimation device 3 may calculate a gait index from the measured values ​​of the acceleration sensor and the angular velocity sensor obtained from the sensor module 21.

[0023] [Configuration of the mental and physical state estimation device] In this disclosure, the mental and physical state estimation device 3 estimates the fatigue of subject P from walking data acquired by smart shoes 2 by executing a fatigue estimation program. Figure 3 is a block diagram showing the configuration of the mental and physical state estimation device 3 according to an embodiment. As shown in Figure 3, the mental and physical state estimation device 3 comprises a processor 11, memory 12, storage 13, input interface 14, output interface 15, communication interface 16, and media reader 17. These components are connected via a processor bus 18.

[0024] The processor 11 is a computer that reads programs (for example, an OS (Operating System) 130, a fatigue estimation program 131) stored in the storage 13, loads the read programs into memory 12, and executes them. The processor 11 is composed of, for example, a CPU (Central Processing Unit), an FPGA (Field Programmable Gate Array), a GPU (Graphics Processing Unit), or an MPU (Multi Processing Unit). The processor 11 may also be composed of processing circuits.

[0025] Memory 12 consists of volatile memory such as DRAM (Dynamic Random Access Memory) or SRAM (Static Random Access Memory), or non-volatile memory such as ROM (Read Only Memory) or flash memory.

[0026] The storage 13 consists of, for example, a non-volatile storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). In addition to the OS 130 and the fatigue estimation program 131, the storage 13 stores walking data 133, estimation criteria 134, etc. The fatigue estimation program 131 is a program for estimating the fatigue of subject P from walking data. The walking data 133 is stored in the storage 13 in association with environmental information.

[0027] The input interface 14 (an example of an input unit) accepts input operations from keyboards, mice, and touch devices. The output interface 15 (an example of an output unit) outputs the estimated fatigue results of subject P to a display, speaker, etc.

[0028] The communication interface 16 (an example of an input or output unit) receives walking data and environmental information from the mobile terminal 1 via wired or wireless communication, and outputs the estimated fatigue results of subject P to the mobile terminal 1. Furthermore, the communication interface 16 receives location information from a GPS receiver installed in the mobile terminal 1 by communicating with the mobile terminal 1.

[0029] The media reader 17 accepts storage media such as removable disks, memory chips, and USB memory sticks, and acquires data stored on the removable disks, memory chips, USB memory sticks, etc. The media reader 17 may also read programs stored on the removable disk, or store the estimated fatigue results of subject P on the removable disk or other media and output them.

[0030] [Method for Estimating Mental and Physical State] Next, the fatigue estimation process performed by the mental and physical state estimation device 3 will be explained with reference to the figures. Figure 4 is a flowchart illustrating the fatigue estimation process performed by the mental and physical state estimation device 3 according to the embodiment. Each step shown in Figure 4 is realized by the processor 11 of the mental and physical state estimation device 3 executing the fatigue estimation program 131.

[0031] First, the mental and physical state estimation device 3 receives walking data from the smart shoes 2 (sensor module 21) via the mobile terminal 1 (step S1). The mobile terminal 1 continuously receives walking data from the smart shoes 2 and can cumulatively store walking data for a certain period (for example, several days or several months), and transmits the walking data to the mental and physical state estimation device 3 at regular intervals, for example, every few hours or every day. Of course, the mobile terminal 1 may also transmit the walking data received from the smart shoes 2 to the mental and physical state estimation device 3 in real time.

[0032] Furthermore, the mental and physical state estimation device 3 receives environmental information of subject P from the mobile terminal 1 (step S2). This environmental information of subject P includes, for example, the time when the mobile terminal 1 received walking data from the smart shoes 2 (the time of day when walking) and the location information of subject P identified by the GPS receiver of the mobile terminal 1 (the place where walking takes place). In addition, based on the location information of subject P, the mental and physical state estimation device 3 may receive at least one piece of information from the internet via the communication interface 16, which includes the weather during walking and the temperature and humidity during walking.

[0033] Here, we consider the relationship between subject P's walking motion and subject P's fatigue. For example, subject P's walking speed is thought to decrease as subject P's fatigue increases, and subject P's stride is thought to decrease as subject P's fatigue increases. Also, subject P's cadence is thought to decrease as subject P's fatigue increases, and subject P's ground contact angle is thought to decrease as subject P's fatigue increases. Note that cadence is the number of steps per minute. Figure 5 is a diagram to explain the ground contact angle of the walking data. When subject P's fatigue is low, the ground contact angle a shown in Figure 5 is large, and the foot is sufficiently raised relative to the floor, while conversely, when subject P's fatigue is high, the ground contact angle a is small, and the foot is not sufficiently raised relative to the floor.

[0034] Furthermore, it is thought that the proportion of stance time for subject P increases as subject P's fatigue increases. Figure 6 is a diagram illustrating the proportion of stance time in walking data. In human walking, as shown in Figure 6, when focusing on either the left or right foot, there is a stance phase, which is the period when the body is supported by the foot in question (the period when one foot is in contact with the floor), and a swing phase, which is the period when the body is not supported by the foot (the period when one foot is off the floor). The proportion of stance time indicates the proportion of time spent in the stance phase during one step of walking, and in natural walking, the average proportion of stance time is considered to be around 60%.

[0035] The relationship between subject P's walking motion and subject P's fatigue is basically as described above. However, subject P's walking motion is influenced not only by subject P's fatigue but also by the environment. For example, subject P's walking motion changes significantly when the environment, such as the time of day or location of walking, changes. Figure 7 is a diagram illustrating the environmental changes in walking data. Figure 7(a) shows walking indices indoors and outdoors. Figure 7(b) shows walking indices when commuting to work and when returning home. In Figures 7(a) and 7(b), the mean and standard deviation (SD) are shown, with the standard deviation indicated in parentheses.

[0036] As shown in Figure 7(a), walking speed (m / s), stride-to-height ratio, cadence (steps / min), and ground contact angle (°) are all lower indoors compared to outdoors. However, the percentage of stance phase time (%) hardly changes between indoors and outdoors. The changes in walking indicators shown in Figure 7(a) are thought to be influenced by the location where one is walking. Furthermore, as shown in Figure 7(b), walking speed (m / s), stride-to-height ratio, cadence (steps / min), ground contact angle (°), and percentage of stance phase time (%) are all lower when returning home compared to when commuting to work. Assuming the commuting route is the same and the location of walking does not affect the changes in walking indicators shown in Figure 7(b), it is thought that the changes in walking indicators shown are due to the effects of accumulated fatigue, etc., between commuting to work and returning home. Note that the stride-to-height ratio is a walking indicator calculated based on the stride of the walking indicator and the attributes of subject P.

[0037] Since subject P's walking motion is affected by the environment, fatigue cannot be accurately estimated unless the estimation criteria are changed depending on the environment, such as the time of day and location of walking. Therefore, the mental and physical state estimation device 3 changes the fatigue estimation criteria set by the environmental information and estimates fatigue based on walking data. Returning to Figure 4, the mental and physical state estimation device 3 sets the estimation criteria based on the received environmental information (step S3). The storage 13 of the mental and physical state estimation device 3 stores the fatigue estimation criteria 134 set by the environmental information. The mental and physical state estimation device 3 reads the estimation criteria 134 from the storage 13 based on the received environmental information and uses the read estimation criteria 134 to estimate subject P's fatigue in that environment. Specifically, the mental and physical state estimation device 3 estimates subject P's fatigue using the estimation criteria for commuting for walking data at commuting, and estimates subject P's fatigue using the estimation criteria for indoor walking data. Furthermore, the mental and physical state estimation device 3 sets estimation criteria for each environmental factor, such as weather (sunny, rainy, etc.), temperature, sunrise time, and sunset time, or for each combination thereof.

[0038] However, even walking data from commuting to work does not always include walking on flat, straight roads, but rather walking on sloped or winding roads, encompassing walking data from different environments. Similarly, indoor walking data includes walking data from different environments, such as going up and down stairs or turning corners. Therefore, in order to estimate the fatigue of subject P with high accuracy from the walking data, the mental and physical state estimation device 3 needs to process the data to extract specific walking states, such as walking in a straight line, based on environmental information.

[0039] The mental and physical state estimation device 3 extracts straight-line walking data from the walking data based on the received environmental information (step S4). Figure 8 is a diagram illustrating the conditions for data excluded from the walking data used for fatigue estimation. In other words, Figure 8 describes the conditions for extracting straight-line walking data used for fatigue estimation by excluding sitting walking data, stair climbing walking data, curved walking data, etc., from the walking data. Based on these conditions, the mental and physical state estimation device 3 can extract specific walking data from the walking data received from the mobile terminal 1, for example, stable straight-line walking data of about 15 steps.

[0040] Specifically, the mental and physical state estimation device 3, in order to prevent misidentification of seated data as standing data in the walking data received from the mobile terminal 1, determines walking data for a continuous period of 15 steps or more as straight-line walking data. In addition, to exclude abnormal walking, including running, from the walking data, the mental and physical state estimation device 3 determines walking data with a ground contact angle of 0 degrees or more (heel contact) and a stance phase time ratio of 50% to 70% as straight-line walking data. Furthermore, to exclude walking with different ground contact patterns, such as climbing stairs, from the walking data, the mental and physical state estimation device 3 determines walking data with a standard deviation of ground contact angle of 10° or less as straight-line walking data. In addition, to exclude walking with large fluctuations in walking speed and unstable walking from the walking data, the mental and physical state estimation device 3 determines walking data with a coefficient of variation of walking speed of 45% or less as straight-line walking data. Furthermore, the mental and physical state estimation device 3 excludes uphill or downhill walking from the walking data, and determines walking data where the start and end positions of the walk and the change in elevation are within a predetermined range as straight-line walking data.

[0041] The mental and physical state estimation device 3 extracts walking data from the mobile terminal 1 that satisfies all the conditions shown in Figure 8 as straight-line walking data. Note that the conditions shown in Figure 8 are just one example of conditions for extracting straight-line walking data, and other conditions may be added or replaced.

[0042] Next, we will explain the process of extracting walking data used for fatigue estimation from walking data received from mobile terminal 1 and calculating a walking index. Figure 9 is a diagram illustrating the processing of walking data used for fatigue estimation. The upper graph in Figure 9 shows the walking data for one day of subject P from the time of arrival at work until the time of return home, with the horizontal axis representing time and the vertical axis representing walking speed [m / s]. Of the walking data for one day, the gray period represents the sitting period and the black period represents the walking period. The mental and physical state estimation device 3 applies the conditions shown in Figure 8 to the walking data for one day shown in Figure 9 to extract walking data for straight-line walking. For example, the lower graph in Figure 9 is a graph of walking data for 50 steps of straight-line walking extracted from walking data around 4 PM. In this graph, the horizontal axis represents the number of steps and the vertical axis represents walking speed [m / s].

[0043] The mental and physical state estimation device 3 calculates the mean and variance of the walking index from the extracted 50-step straight-line walking data and stores it in the storage 13. When the mental and physical state estimation device 3 calculates the mean and variance of walking speed from the 50-step straight-line walking data shown in Figure 9, for example, it uses 15 steps as one window, calculates the mean and variance of the walking speed in that window, and then calculates the mean and variance of the multiple walking speeds calculated for each window by shifting the window, thereby obtaining the mean and variance of the walking index. The mental and physical state estimation device 3 extracts walking data as straight-line walking data from the walking data received from the mobile terminal 1 using a unit of 15 steps or more, but other numbers of steps such as 20 steps or more may be used as the unit, or time such as 10 seconds may be used as the unit in addition to the number of steps.

[0044] The mental and physical state estimation device 3 estimates the fatigue of subject P based on walking indicators calculated from extracted straight-line walking data, such as the average walking speed, and estimation criteria set by the environmental information at the time the walking data was acquired. Therefore, the mental and physical state estimation device 3 can estimate the fatigue of subject P, which is less affected by the environment. The mental and physical state estimation device 3 can also estimate the fatigue of subject P, which is less affected by the environment, by similarly processing other walking indicators (for example, stride-to-height ratio, cadence, ground contact angle, etc.).

[0045] This embodiment describes a process to further reduce the influence of the environment. In the aforementioned process, estimation criteria were set according to environmental information, and walking data for straight-line walking was extracted from walking data in various walking environments, in order to reduce the influence of the environment. Nevertheless, it is difficult to estimate the fatigue of subject P from walking indicators without any influence of the environment. For example, even if the commuting time, walking location, weather, and temperature and humidity at the time of walking are the same, the degree of road congestion may differ. If the road is congested, walking speed is likely to decrease even if other environmental conditions are the same, and walking indicators may also be affected by the road traffic environment.

[0046] In particular, walking speed is considered to be a walking indicator that is easily influenced by the environment, regardless of the subject P's fatigue. Therefore, walking indicators that have a high correlation with walking speed can be considered to be walking indicators that are easily influenced by the environment. Figure 10 is a diagram illustrating the changes in walking indicators with respect to walking speed. Figure 10 shows the correlation coefficients of each walking indicator with respect to walking speed. Specifically, five data points and their mean values ​​are shown for the correlation coefficients of stride-to-height ratio, cadence, ground contact angle, and stance phase time ratio with respect to walking speed. As can be seen from Figure 10, stride-to-height ratio, cadence, and ground contact angle show high correlations with walking speed with respect to walking speed, with a mean of 0.75 or higher, but the stance phase time ratio has a lower correlation with respect to walking speed compared to these walking indicators.

[0047] In other words, it is clear that the stance phase time ratio is a walking indicator that is less affected by the environment. Therefore, the mental and physical state estimation device 3 uses the stance phase time ratio as a walking indicator for fatigue estimation in order to further reduce the influence of the environment, and estimates the fatigue of subject P from the stance phase time ratio based on estimation criteria set by environmental information. Note that the walking indicator used to reduce the influence of the environment is not limited to the stance phase time ratio, but any walking indicator with a low correlation to walking speed may be used, for example, the coefficient of variation (variability) of walking speed or the coefficient of variation of other walking indicators.

[0048] Next, we will explain the process by which the mental and physical state estimation device 3 estimates the fatigue of subject P from the walking index based on the estimation criteria. Returning to Figure 4, the mental and physical state estimation device 3 determines in storage 13 whether there is a recall of the walking index from one time point in the same environment as the straight-line walking data extracted in step S4 (step S5). If there is no recall of the walking index from one time point in the same environment (NO in step S5), the mental and physical state estimation device 3 estimates the fatigue of subject P from the walking index based on calculation I (step S6). The walking index from one time point in the past refers to the walking index for the walking data from the closest past time period among the walking data from the same day and environment. For example, if the storage 13 stores outdoor walking data at 8:00 AM, outdoor walking data at 9:00 AM, indoor (office) walking data at 10:00 AM, and indoor (office) walking data at 2:00 PM, the walking data from one time point in the past for the indoor (office) walking data at 4:00 PM is the indoor walking data at 2:00 PM.

[0049] Calculation I estimates subject P's fatigue using only the gait indicators from the received gait data when the gait indicators from the previous time point in the same environment are not stored in storage 13. Figure 11 is a diagram illustrating the estimation criteria used for estimating fatigue in an outdoor environment. In the graph shown in Figure 11, the horizontal axis represents gait speed and the vertical axis represents the proportion of stance phase time, and the regression line K of the proportion of stance phase time to gait speed from previously measured outdoor gait data is shown.

[0050] In Calculation I, the stance phase time percentage is first extracted from the received walking data. Point A in Figure 11 represents the received stance phase time percentage data. Next, the stance phase time percentage on the regression line K with respect to walking speed is calculated. Point B in Figure 11 represents the stance phase time percentage data on the regression line K. Next, if the difference between point A and point B exceeds a threshold set by environmental information, subject P is estimated to be fatigued. The threshold set by environmental information is set as a range such as the standard deviation (σ) or twice the standard deviation (2σ) from the regression line K. In Figure 11, the standard deviation (σ) and twice the standard deviation (2σ) are shown as dashed lines.

[0051] When the mental and physical state estimation device 3 estimates the fatigue of subject P in calculation I, it uses a threshold set by environmental information as the estimation criterion, and based on that threshold, it estimates the fatigue of subject P from the proportion of stance phase time in the extracted walking data.

[0052] Figure 11 shows an example of estimating fatigue based on estimation criteria set in accordance with the outdoor environment. However, the regression lines for the ratio of stance phase time to walking speed in an outdoor environment are different from those for an indoor environment. Figure 12 is a diagram to explain the difference in the regression lines for the ratio of stance phase time to walking speed in different environments. Figure 12(a) shows the regression line K for the ratio of stance phase time to walking speed in an outdoor environment, and Figure 12(b) shows the regression line L for the ratio of stance phase time to walking speed in an indoor environment. Therefore, the estimation criterion used for estimating fatigue in an outdoor environment should be the regression line L shown in Figure 12(b), not the regression line K shown in Figure 12(a).

[0053] Returning to Figure 4, if there is a recall of the walking indicator from one time point in the same environment (YES in step S5), the mental state estimation device 3 estimates the fatigue of subject P from the walking indicator based on calculation II (step S7).

[0054] Calculation II estimates subject P's fatigue from the change between the received walking data and the walking index from the previous time point, assuming that the walking index from the previous time point in the same environment is stored in storage 13. Figure 13 is a diagram illustrating another estimation criterion used for fatigue estimation in an outdoor environment. In the graph shown in Figure 13, the horizontal axis represents walking speed and the vertical axis represents the proportion of the stance phase, with the regression line K of the proportion of the stance phase relative to walking speed from previously measured outdoor walking data.

[0055] In Calculation II, first, the stance phase time percentage is extracted from the received walking data, and the stance phase time percentage is extracted from the walking data from the previous time point. Point A1 in Figure 13 represents the received stance phase time percentage data, and point A2 represents the stance phase time percentage data from the previous time point. Next, the stance phase time percentage on the regression line K with respect to walking speed for the received stance phase time percentage, and the stance phase time percentage on the regression line K with respect to walking speed for the stance phase time percentage from the previous time point are calculated. Point B1 in Figure 13 represents the stance phase time percentage data for point A1 on the regression line K, and point B2 represents the stance phase time percentage data for point A2 on the regression line K. Next, the difference C1 between point A2 and point A1, and the difference C2 between point B1 and point B2 are calculated, and if the difference C1 between difference C2 exceeds a set threshold value, it is estimated that subject P is fatigued. The threshold value is set to, for example, twice the value of the difference C2, which is the change in the regression line K.

[0056] When the mental state estimation device 3 estimates the fatigue of subject P in calculation II, it uses the change in the stance phase time ratio under the same environmental information as the estimation criterion, and reads the stance phase time ratio of past walking data under the same environmental information as the stance phase time ratio of the extracted walking data from storage 13. Furthermore, based on the estimation criterion (difference C2), the mental state estimation device 3 estimates the fatigue of subject P from the change (difference C1) between the stance phase time ratio of the walking data read from storage 13 and the stance phase time ratio of the extracted walking data.

[0057] Here, we will explain the changes in walking speed and stance phase time percentage from the daily walking data of subject P. Figure 14 is a diagram showing an example of changes in walking indicators used for fatigue estimation. Figure 14(a) is a graph showing the changes in walking speed and stance phase time percentage with respect to the elapsed time since arrival at work, with the horizontal axis representing the elapsed time since arrival at work, the left vertical axis representing walking speed [m / s], and the right vertical axis representing stance phase time percentage [%]. The solid line graph shows the change in walking speed, and the dashed line graph shows the change in stance phase time percentage. Figure 14(b) is a graph showing the change in stance phase time percentage with respect to walking speed, with the horizontal axis representing walking speed [m / s] and the vertical axis representing stance phase time percentage [%].

[0058] The solid line graph in Figure 14(a) shows that walking speed decreases between 2 and 4 hours after arriving at work. This is because subject P's walking changed from walking outdoors during his commute to walking indoors during office work. On the other hand, the dashed line graph in Figure 14(a) shows that the proportion of stance phase time remains almost constant between 2 and 4 hours after arriving at work. This also indicates that the proportion of stance phase time, as a walking index, has a low correlation with walking speed, which is easily affected by the environment.

[0059] When the elapsed time from arrival at work exceeds 6 hours and reaches 8 hours, the walking speed decreases as shown by the solid line graph in Figure 14(a), and the proportion of stance phase time increases as shown by the dashed line graph in Figure 14(a). This is thought to be because 8 hours have passed since subject P arrived at the office, and fatigue has accumulated. As shown in the graph in Figure 14(b), arrow D, which shows the change in elapsed time from arrival at work between 6 and 8 hours, shows a significant change compared to arrow E, which corresponds to the regression line K obtained under the same environment, and subject P's fatigue can be estimated. In this way, the mental and physical state estimation device 3 can estimate subject P's fatigue with greater accuracy by estimating subject P's fatigue based on the change in the proportion of stance phase time.

[0060] Returning to Figure 4, if the mental / physical state estimation device 3 estimates the fatigue of the subject P in step S6 or step S7, it outputs the estimated fatigue result of subject P to the mobile terminal 1 (step S8). Figure 15 shows an example of the estimation result after fatigue estimation. In Figure 15(a), the display screen of the mobile terminal 1 shows a graph 1a showing the fatigue of the subject P estimated from changes in walking indicators (e.g., percentage of stance phase time) over one week, and displays the estimation result in the lower part of the graph 1a with the message 1b, "(Fatigue) Judging from your walking, you appear tired. Why not take a short break?". In another example of display, Figure 15(b), the estimation result is displayed in the lower part of the current time display with the message 1c, "(Fatigue) detected. Why not take a short break?".

[0061] [Differentiation] (1) In the above-described embodiment, it was explained that the mental and physical state estimation device 3 estimates fatigue based on walking data, taking into account the fatigue estimation criteria set by environmental information. However, it is not limited to this, and the mental and physical state estimation device 3 may set estimation criteria for each mental and physical state of subject P using environmental information, extract walking data using environmental information, and estimate subject P's mental and physical state from the walking data extracted based on the set estimation criteria. For example, subject P may be asked to select the mental and physical state they wish to estimate, and mental and physical state estimates such as emotion, fatigue, and stress may be estimated.

[0062] (2) In the above-described embodiment, the movements of subject P were measured using smart shoes 2 in which a sensor module 21 (including a 3-axis acceleration sensor and a 3-axis angular velocity sensor) was incorporated into the shoe. However, the position where the sensor module 21 is attached may be any position in which walking data of subject P can be acquired. Also, in the above-described embodiment, a total of two sensor modules 21 are used by providing one type of sensor in each of the left and right shoes. However, it may also be possible to use one sensor module 21 by providing it in either the left or right shoe. Furthermore, multiple sensors of different types may be used. Moreover, even if a sensor module 21 is provided in each of the left and right shoes, the mental state estimation device 3 may be configured to receive walking data from either one of the sensor modules 21.

[0063] (3) In the above-described embodiment, the movements of subject P were measured using smart shoes 2 in which a sensor module 21 (including a 3-axis acceleration sensor and a 3-axis angular velocity sensor) was incorporated into the shoes. However, walking data of subject P may be acquired using sensors built into the mobile terminal 1. In other words, the mobile terminal 1 may function as a measuring device.

[0064] [Aspect] (1) The mental and physical state estimation device relating to this disclosure is A mental and physical state estimation device for estimating the mental and physical state of a subject, An input unit that receives the subject's walking data and the subject's environmental information, A memory unit that stores walking data in relation to environmental information, It includes a calculation unit that estimates the subject's physical and mental state from walking data and environmental information received by the input unit, The calculation unit is, Based on environmental information, gait data for specific walking conditions is extracted, and the subject's physical and mental state is estimated from the extracted gait data based on estimation criteria set by the environmental information.

[0065] As a result, the mental and physical state estimation device relating to this disclosure extracts walking data for a specific walking state based on environmental information, and estimates the subject's mental and physical state from the extracted walking data based on estimation criteria set by the environmental information, thereby enabling a highly accurate estimation of the subject's mental and physical state.

[0066] (2) A mental and physical state estimation device as described in (1), Environmental information includes at least one of the following: time of day when walking, location of walking, weather conditions during walking, and temperature and humidity during walking.

[0067] (3) A mental and physical state estimation device as described in (1) or (2), The gait data includes at least one gait indicator from among stride, walking speed, cadence, time taken per step, stance phase duration, swing phase duration, percentage of stance phase duration, toe-up angle at landing, heel-up angle at take-off, pronation, maximum foot lift height, and impact on landing.

[0068] (4) A mental and physical state estimation device described in any one of items (1) to (3), A specific walking state is straight-line walking. The calculation unit extracts linear walking data from the walking data received by the input unit, in predetermined time intervals.

[0069] (5) A mental and physical state estimation device described in any one of items (1) to (4), The calculation unit uses a threshold set by environmental information as an estimation criterion, and estimates the subject's physical and mental state from the extracted walking data based on that threshold.

[0070] (6) A mental and physical state estimation device described in any one of items (1) to (4), The calculation unit uses changes in walking data under the same environmental information as an estimation criterion, reads past walking data under the same environmental information as the extracted walking data from the storage unit, and Based on estimation criteria, the subject's physical and mental state is estimated from the changes in extracted gait data read from the memory unit.

[0071] (7) A mental and physical state estimation device described in any one of items (1) to (6), The gait data used to estimate the physical and mental state of the subjects is a gait index that is less affected by the environment.

[0072] (8)(7) A mental and physical state estimation device, The gait index is an index that is less affected by changes in walking speed.

[0073] A mental and physical state estimation device described in any one of items (9)(1) to (8), An indicator that has little impact on changes in walking speed is one that shows the proportion of stance phase time to the total walking time.

[0074] A mental and physical state estimation device described in any one of items (10)(1) to (9), The system further includes an output unit that outputs the mental and physical state of the subject estimated by the calculation unit.

[0075] (11) The mental and physical state estimation system relating to this disclosure comprises a measuring device for measuring walking data and a mental and physical state estimation device described in any one of items (1) to (9).

[0076] (12)(11) A mental and physical state estimation system, The measuring device includes at least one sensor that measures 3-axis acceleration and 3-axis angular velocity.

[0077] (13)(12) A mental and physical state estimation system, The sensors are installed in the shoes worn by the subjects.

[0078] (14) The method for estimating the mental and physical state relating to this disclosure is: A method for estimating the mental and physical state of a subject, A step of receiving the subject's gait data measured by a measuring device, and the subject's environmental information, A step of storing walking data in a memory unit in association with environmental information, Steps include setting estimation criteria based on environmental information, Steps include: extracting walking data for a specific walking state based on environmental information; Based on the established estimation criteria, the physical and mental state of the subject is estimated from the extracted walking data. The process includes the step of outputting the estimated physical and mental state of the subject.

[0079] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims rather than by the foregoing description, and all modifications within the meaning and scope equivalent to the claims are intended to be included. [Explanation of Symbols]

[0080] 1 Mobile device, 2 Smart shoes, 3 Physical and mental state estimation device, 11 Processor, 12 Memory, 13 Storage, 14 Input interface, 15 Output interface, 16 Communication interface, 17 Media reader, 18 Processor bus, 21 Sensor module, 100 Physical and mental state estimation system, 131 Fatigue estimation program, 133 Walking data, 134 Estimation criteria.

Claims

1. A mental and physical state estimation device for estimating the mental and physical state of a subject, An input unit that receives the subject's walking data and the subject's environmental information, A storage unit that stores the walking data in relation to the environmental information, The system includes a calculation unit that estimates the physical and mental state of the subject from the walking data and environmental information received by the input unit, The aforementioned arithmetic unit, A mental and physical state estimation device that extracts walking data for a specific walking state based on the environmental information, and estimates the mental and physical state of the subject from the extracted walking data based on estimation criteria set by the environmental information.

2. The mental and physical state estimation device according to claim 1, wherein the environmental information includes at least one of the following: the time of day when walking, the location where walking takes place, the weather conditions during walking, and the temperature and humidity during walking.

3. The mental and physical state estimation device according to claim 1, wherein the walking data includes at least one walking indicator from among stride, walking speed, cadence, time taken for one step, stance phase duration, swing phase duration, percentage of stance phase duration, toe lift angle at landing, heel lift angle at lift-off, pronation, maximum foot lift height, and landing impact.

4. The aforementioned specific walking state is straight-line walking, The mental and physical state estimation device according to any one of claims 1 to 3, wherein the calculation unit extracts the walking data of straight walking from the walking data received by the input unit in predetermined period units.

5. The mental and physical state estimation device according to any one of claims 1 to 3, wherein the calculation unit uses a threshold set by the environmental information as the estimation standard, and estimates the mental and physical state of the subject from the extracted walking data based on the threshold.

6. The calculation unit uses the changes in the walking data in the same environmental information as the estimation criterion, and reads past walking data of the same environmental information as the extracted walking data from the storage unit. A mental and physical state estimation device according to any one of claims 1 to 3, which estimates the mental and physical state of the subject from the changes in the extracted walking data from the walking data read from the storage unit, based on the estimation criteria.

7. The mental and physical state estimation device according to any one of claims 1 to 3, wherein the walking data used to estimate the mental and physical state of the subject is a walking index that is less affected by the environment.

8. The mental and physical state estimation device according to claim 7, wherein the walking index is an index that has little influence on changes in walking speed.

9. An index that has little effect on changes in walking speed is an index that shows the ratio of the stance phase time to the walking period, the mental and physical state estimation device according to claim 8.

10. The mental and physical state estimation device according to any one of claims 1 to 3, further comprising an output unit that outputs the mental and physical state of the subject estimated by the calculation unit.

11. A measuring device for measuring the aforementioned walking data, A mental state estimation system comprising the mental state estimation device according to any one of claims 1 to 3.

12. The mental state estimation system according to claim 11, wherein the measuring device includes at least one sensor that measures three-axis acceleration and three-axis angular velocity.

13. The mental and physical state estimation system according to claim 12, wherein the sensor is provided in the shoes used by the subject.

14. A method for estimating the mental and physical state of a subject, A step of receiving the subject's walking data measured by the measuring device, and the subject's environmental information, The steps include storing the walking data in the storage unit in association with the aforementioned environmental information, A step of setting estimation criteria based on the aforementioned environmental information, A step of extracting walking data for a specific walking state based on the aforementioned environmental information, A step of estimating the subject's physical and mental state from the extracted walking data based on the set estimation criteria, A method for estimating a mental and physical state, comprising the step of outputting the estimated mental and physical state of the subject.

Images