Motion information acquisition device, control method and program for motion information acquisition device

Abstract

The present invention provides an exercise information acquisition device that does not require a separate sensor to measure the subject's body temperature when obtaining the results of determining the subject's body temperature risk. [Solution] An exercise information acquisition device comprising: a case member attached to a subject; a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires exercise data of the subject corrected with the temperature data; a control unit which acquires exercise information of the subject based on the exercise data of the subject corrected with the temperature data and acquires temperature information based on the temperature data; and a storage unit which stores a trained model that, when at least the exercise information and the temperature information are input, outputs the subject's body temperature estimated based on the exercise information and the temperature information, wherein the control unit determines the subject's body temperature risk based on the subject's body temperature output from the trained model.

Description

Technical Field

[0001] The present disclosure relates to an exercise information acquisition device, a control method for the exercise information acquisition device, and a program.

Background Art

[0002] Patent Document 1 describes a heatstroke prevention system that monitors a person's activity state, predicts the risk related to heatstroke, and provides information necessary for preventing heatstroke (see Patent Document 1). In this heatstroke prevention system, a body state sensor attached to a subject includes a body temperature measurement unit that measures the body temperature of the subject, and the risk of heatstroke of the subject is determined from the measurement result of the body temperature measurement unit.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology as described above, it is necessary to include a temperature measurement unit for measuring the body temperature of the subject, and reduction of the cost of the device has been desired.

Means for Solving the Problems

[0005] One embodiment is an exercise information acquisition device comprising: a case member attached to a subject; a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires exercise data of the subject corrected with the temperature data; a control unit which acquires exercise information of the subject based on the exercise data of the subject corrected with the temperature data and acquires temperature information based on the temperature data; and a storage unit which stores a trained model that, when at least the exercise information and the temperature information are input, outputs the subject's body temperature estimated based on the exercise information and the temperature information, wherein the control unit determines the subject's body temperature risk based on the subject's body temperature output from the trained model.

[0006] One embodiment is a control method for an exercise information acquisition device, comprising: a case member attached to a subject; and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires exercise data of the subject corrected with the temperature data, the control method for the exercise information acquisition device comprising: acquiring the temperature data within the exercise information acquisition device; acquiring the exercise data of the subject corrected with the temperature data; acquiring exercise information of the subject based on the exercise data of the subject corrected with the temperature data; acquiring temperature information based on the temperature data; inputting the exercise information and the temperature information to a trained model stored in a storage unit, which outputs the subject's body temperature estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input; and determining the subject's body temperature risk based on the subject's body temperature output from the trained model.

[0007] One embodiment is a control method for an exercise information acquisition device comprising: a case member attached to a subject; and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires exercise data of the subject corrected with the temperature data, the control method for the exercise information acquisition device comprising: acquiring the temperature data within the exercise information acquisition device; acquiring the exercise data of the subject corrected with the temperature data; acquiring exercise information of the subject based on the exercise data of the subject corrected with the temperature data; acquiring temperature information based on the temperature data; inputting the exercise information and the temperature information to a trained model stored in a storage unit, which outputs the subject's body temperature risk estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input; and acquiring the subject's body temperature risk output from the trained model.

[0008] One embodiment is a program for controlling a computer constituting an exercise information acquisition device, which comprises a case member attached to a subject, and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires exercise data of the subject corrected with the temperature data, and the program performs the steps of: acquiring exercise information of the subject based on the exercise data of the subject corrected with the temperature data; acquiring temperature information based on the temperature data; inputting the exercise information and the temperature information to a trained model stored in a storage unit, which outputs the subject's body temperature estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input; and determining the subject's body temperature risk based on the subject's body temperature output from the trained model.

[0009] One embodiment is a program for controlling a computer constituting an exercise information acquisition device, which comprises a case member attached to a subject, and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires exercise data of the subject corrected with the temperature data, and the program executes the steps of: acquiring exercise information of the subject based on the exercise data of the subject corrected with the temperature data; acquiring temperature information based on the temperature data; inputting the exercise information and the temperature information to a trained model stored in a storage unit, which outputs the subject's body temperature risk estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input; and acquiring the subject's body temperature risk output from the trained model. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an example configuration of an information processing system including a motion information acquisition device according to the embodiment. [Figure 2] This figure shows an example of the configuration of the first motion information acquisition device according to the first embodiment. [Figure 3] This figure shows an example of the input and output of the first simplified pre-trained model according to the first embodiment. [Figure 4] This figure shows an example of the input and output of the first simplified learning model according to the first embodiment. [Figure 5] This figure shows an example of the input and output of the first detailed trained model according to the first embodiment. [Figure 6] This figure shows an example of the procedure for processing performed by the first motion information acquisition device according to the first embodiment. [Figure 7] This figure shows an example of the configuration of the first A motion information acquisition device according to a modification of the first embodiment. [Figure 8] This figure shows an example of the configuration of the second motion information acquisition device according to the second embodiment. [Figure 9] This figure shows an example of the input and output of the second simplified pre-trained model according to the second embodiment. [Figure 10] It is a diagram showing an example of the input and output of the second easy-to-learn model according to the second embodiment. [Figure 11] It is a diagram showing an example of the input and output of the second detailed learned model according to the second embodiment. [Figure 12] It is a diagram showing an example of the procedure of the process performed by the second motion information acquisition device according to the second embodiment. [Figure 13] It is a diagram showing a configuration example of the second A motion information acquisition device according to a modification of the second embodiment. [Figure 14] It is a diagram showing a configuration example of the α information processing system including the α motion information acquisition device according to a modification of the embodiment.

Mode for Carrying Out the Invention

[0011] Hereinafter, embodiments will be described with reference to the drawings. Note that the names of each system, device, etc. are names for explanation and may be called by other names.

[0012] FIG. 1 is a diagram showing a configuration example of an information processing system 1 including a motion information acquisition device 10 according to an embodiment. The information processing system 1 includes a motion information acquisition device 10, an environment information providing device 21, an external communication device 31, a subject terminal 41, and an external terminal 42. FIG. 1 also shows a subject 51.

[0013] The motion information acquisition device 10 includes a case member 110. The case member 110 has, for example, a plastic material, but may be other materials. The case member 110 is attached to the subject 51 by being worn on a predetermined part of the subject 51. In the present embodiment, the motion information acquisition device 10 has a shape similar to a watch, and the case member 110 is worn on the wrist of the subject 51. Note that the motion information acquisition device 10 may have a watch function.

[0014] The motion information acquisition device 10 and the environmental information providing device 21 can communicate wirelessly. The motion information acquisition device 10 and the external communication device 31 can communicate wirelessly. The external communication device 31 and the subject terminal 41 can communicate either wired or wirelessly. The external communication device 31 and the external terminal 42 can communicate either wired or wirelessly. Here, the communication between one device and another device may be performed via a predetermined device in a predetermined network, for example. The predetermined device may be, for example, a base station device, a relay station device, or a server device, etc. Note that the environmental information providing device 21, the external communication device 31, the subject terminal 41, and the external terminal 42 are all devices external to the motion information acquisition device 10.

[0015] The environmental information providing device 21 provides predetermined environmental information. In the present embodiment, the environmental information includes information regarding temperature, information regarding humidity, and information regarding weather. Note that the environmental information may include information regarding other environments. The information regarding temperature may be, for example, information on the temperature itself, or may be other information related to the temperature. Note that as the temperature, for example, the outside air temperature is used. The information regarding humidity may be, for example, information on the humidity itself, or may be other information related to the humidity. The information regarding weather may be, for example, information on the weather itself, or may be other information related to the weather.

[0016] Here, in the present embodiment, for the sake of simplicity of explanation, a case where all environmental information is provided from the environmental information providing device 21 is shown. However, as another example, a plurality of environmental information providing devices may be provided, and information regarding each environment may be provided from each environmental information providing device. That is, the environmental information providing device 21 shown in FIG. 1 may be configured to be distributed among a plurality of devices. The environmental information provider 21 may also be a device that provides weather information, such as by the Japan Meteorological Agency. The environmental information provider 21 may also be a designated server device.

[0017] The external communication device 31 has the function of relaying communication between the motor information acquisition device 10 and the subject terminal 41, and the function of relaying communication between the motor information acquisition device 10 and the external terminal 42. The external communication device 31 may be any device, for example, a predetermined server device.

[0018] Target user terminal 41 is the terminal used by target user 51. The target terminal 41 is equipped with an output unit and receives notification target information sent from the motor information acquisition device 10 via the external communication device 31, and notifies by outputting the said information using the output unit. Here, the output unit may have one or more of the following: a display unit having a screen for displaying and outputting information, or a sound output unit for outputting information by sound. The sound may be speech. The target device 41 may be any device, such as a smartphone, tablet, or other computer.

[0019] External terminal 42 is an external terminal. The external terminal 42 is equipped with an output unit and receives notification target information sent from the motion information acquisition device 10 via the external communication device 31, and notifies by outputting the said information using the output unit. Here, the output unit may have one or more of the following: a display unit having a screen for displaying and outputting information, or a sound output unit for outputting information by sound. The sound may be speech. The external terminal 42 may be any device, such as a smartphone, tablet, or other computer.

[0020] In this embodiment, the communication between the exercise information acquisition device 10 and the subject terminal 41, and the communication between the exercise information acquisition device 10 and the external terminal 42, are shown to be relayed by the external communication device 31. However, as other examples, the exercise information acquisition device 10 and the subject terminal 41 may communicate directly, and the exercise information acquisition device 10 and the external terminal 42 may communicate directly.

[0021] Furthermore, in this embodiment, we have shown an example configuration in which information to be notified generated by the motion information acquisition device 10 can be notified via the target terminal 41. However, in other examples, the target terminal 41 may not be provided. Furthermore, in this embodiment, we have shown a configuration example in which information to be notified generated by the motion information acquisition device 10 can be notified by an external terminal 42. However, in other examples, the external terminal 42 may not be provided. Furthermore, in configurations where neither the target terminal 41 nor the external terminal 42 is provided, or where either one or both terminals are provided but the motor information acquisition device 10 communicates directly with the terminal, the external communication device 31 does not need to be provided.

[0022] The first embodiment will be described. In the first embodiment, we will describe a case in which the first motion information acquisition device 11 shown in Figure 2 is used as the motion information acquisition device 10 shown in Figure 1. The first motion information acquisition device 11 is an example of the motion information acquisition device 10.

[0023] Figure 2 shows an example of the configuration of the first motion information acquisition device 11 according to the first embodiment. The first motion information acquisition device 11 comprises a data acquisition unit 121, a communication unit 122, a notification unit 123, a first storage unit 124, and a first control unit 125. The data acquisition unit 121 includes a sensor unit 141 having a 6-axis motion sensor. The data acquisition unit 121 may be equivalent to the sensor unit 141.

[0024] The sensor unit 141 is an example of a measuring instrument. The sensor unit 141 comprises a first sensor section 151 and a second sensor section 152. The first sensor unit 151 includes an acceleration sensor C1 and an angular velocity sensor C2. The second sensor unit 152 includes a temperature sensor C3. The second sensor unit 152 may be equivalent to the temperature sensor C3.

[0025] The first control unit 125 includes a velocity calculation unit 161, a momentum calculation unit 162, a temperature information acquisition unit 163, a position information acquisition unit 164, a time acquisition unit 165, an environmental information acquisition unit 166, a wear information acquisition unit 167, a model selection unit 168, and a body temperature risk determination unit 169.

[0026] The components of the first motion information acquisition device 11 will now be described. In this embodiment, each component of the first motion information acquisition device 11 shown in Figure 2 is housed in a case member 110. In this embodiment, the sensor unit 141 consists of an IC (Integrated Circuit) chip, or a small device equipped with said chip. For example, an inertial measurement unit (IMU) may be used as the sensor unit 141.

[0027] The accelerometer C1 measures acceleration. The angular velocity sensor C2 measures angular velocity. The first sensor unit 151 acquires the movement data of the subject 51. The motion data may be, for example, acceleration data, or angular velocity data, or acceleration data and angular velocity data, or other data obtained based on the acceleration data and angular velocity data. Furthermore, measurement may also be called, for example, measurement or detection.

[0028] The temperature sensor C3 measures the temperature inside the case component 110. The second sensor unit 152 acquires temperature data, which is the data of the temperature in question.

[0029] The sensor unit 141 includes, for example, a processor (not shown), which corrects the acquired motion data with the acquired temperature data, thereby acquiring motion data corrected with the temperature data. In this embodiment, for the sake of explanation, the motion data corrected with temperature data will also be referred to as corrected motion data.

[0030] Here, there are no particular limitations on the method used to acquire motion data corrected for temperature data, and various methods may be used. For example, as a method different from this embodiment, the sensor unit 141 may use a method in which it adjusts one or both of the acceleration sensor C1 and the angular velocity sensor C2 based on the acquired temperature data to detect one or both of the acceleration data corrected by the temperature data and the angular velocity data corrected by the temperature data, thereby acquiring motion data corrected by the temperature data.

[0031] There are no particular limitations on the timing at which each sensor, such as the acceleration sensor C1, the angular velocity sensor C2, and the temperature sensor C3, measures each physical quantity. For example, it may be at periodic timings at predetermined time intervals. This time interval may be, for example, 10 milliseconds. Furthermore, the timing at which each sensor measures each physical quantity may be synchronized with each other, or it may not be synchronized.

[0032] Furthermore, the measured values ​​output from each sensor do not necessarily have to be the values ​​of each individual measurement; for example, they may be statistical values ​​of the results of a predetermined number of measurements. The predetermined number of times may be predetermined, for example, and may be the number of measurements taken at predetermined intervals. The statistical value in question may be, for example, an average value.

[0033] The communication unit 122 communicates with external devices. In this embodiment, the communication unit 122 communicates with the environmental information providing device 21. The communication unit 122 also communicates with the external communication device 31.

[0034] The notification unit 123 provides notification of the information to be notified. As an example, the notification unit 123 may have an output unit in the first motion information acquisition device 11 that outputs the information to be notified. This output unit may have one or more of the following: a display unit having a screen that displays and outputs the information, or a sound output unit that outputs the information by sound. The sound may be voice. As another example, the notification unit 123 may communicate with an external communication device 31 via the communication unit 122 and transmit the information to be notified to a predetermined terminal via the external communication device 31, thereby causing the terminal to notify the information. In this embodiment, the terminal is either the target terminal 41 or the external terminal 42, or both.

[0035] In this embodiment, for the sake of explanation, the notification unit 123 is shown to have the functions of notifying the first motion information acquisition device 11, causing the target terminal 41 to make a notification, and causing the external terminal 42 to make a notification. However, for example, a configuration may be used in which the necessary functions are included and the unnecessary functions are omitted.

[0036] The first memory unit 124 stores information. In this embodiment, the first storage unit 124 stores the information of the first trained model unit D. The first pre-trained model unit D includes the first simplified pre-trained model E and the first detailed pre-trained model F. Here, the first storage unit 124 may store any other information. The information may also be referred to as data.

[0037] The first simplified pre-trained model E is an example of a pre-trained model that uses simplified input data. The first detailed pre-trained model F is an example of a pre-trained model that uses detailed input data. In this embodiment, whether the input data is simple or detailed represents a relative relationship between the two, and the terms simple and detailed are merely convenient expressions for explanatory purposes.

[0038] The first control unit 125 includes, for example, a processor such as a CPU (Central Processing Unit), and performs predetermined processing by executing a predetermined program using the processor. The program may be stored, for example, in the first storage unit 124.

[0039] The velocity calculation unit 161 calculates the velocity based on the corrected motion data acquired by the data acquisition unit 121. This calculation may, for example, be an estimation calculation. For example, if the corrected motion data includes acceleration data, the velocity calculation unit 161 may calculate the velocity based on that acceleration data. For example, the velocity calculation unit 161 may pre-learn the relationship between acceleration norm and velocity using a learning model that takes acceleration norm as input and velocity as output, and then input the acceleration norm into the learned learning model, thereby obtaining the velocity output from the learning model as the calculation result. As another example, the velocity calculation unit 161 may pre-learn the relationship between the period and power obtained by frequency analysis of acceleration and the velocity using a learning model that takes the period and power obtained by frequency analysis of acceleration as input and outputs velocity. By inputting the period and power obtained by frequency analysis of acceleration into the learned learning model, the velocity output from the learning model may be used as the calculation result.

[0040] As another example, if the corrected motion data includes acceleration data and angular velocity data, the velocity calculation unit 161 may calculate the velocity based on the acceleration data and angular velocity data.

[0041] The momentum calculation unit 162 calculates momentum based on the velocity obtained by the velocity calculation unit 161. In this embodiment, momentum is expressed in METs, which is generally derived from velocity. Mets represent the intensity of physical activity.

[0042] In this embodiment, the momentum obtained by the momentum calculation unit 162 is a value based on the movement of the first motion information acquisition device 11, and is considered to be the momentum of the attachment position of the subject 51 to which the first motion information acquisition device 11 is attached. Furthermore, the movement of the first motion information acquisition device 11 may be considered, for example, as the movement of the first motion information acquisition device 11 itself.

[0043] In this embodiment, the momentum calculated by the momentum calculation unit 162 is an example of the motion information of the subject 51, which is obtained based on the motion data of the subject 51 corrected with temperature data.

[0044] The temperature information acquisition unit 163 acquires temperature information based on the temperature data acquired by the second sensor unit 152. Here, the temperature information may be, for example, information about the temperature itself represented by temperature data, or it may be other information related to the temperature represented by temperature data.

[0045] Furthermore, when the case member 110 of the first exercise information acquisition device 11 is in close contact with the subject's body 51, the temperature measured by the temperature sensor C3 is affected by the subject's body temperature. In other words, in this embodiment, the temperature information acquired by the temperature information acquisition unit 163 is information that is affected by the subject's body temperature. As another example, the temperature information acquisition unit 163 can acquire temperature information related to the body temperature of the subject 51, while removing the influence of the ambient temperature, by combining the temperature measured by the temperature sensor C3 with the ambient temperature. For reference, when measuring ambient temperature with a temperature sensor on a wearable device worn on the body, if the wearable device is in close contact with the body, the body temperature will affect the measurement and prevent accurate temperature measurement. Therefore, it is common practice to remove the wearable device from the body and leave it for a reasonable period of time. In other words, the temperature measured by the temperature sensor of a wearable device while it is in close contact with the body may be affected by both the body temperature and the ambient temperature.

[0046] The location information acquisition unit 164 acquires location information. In this embodiment, the location information acquired by the location information acquisition unit 164 is considered to be information relating to the location of the first motion information acquisition device 11, and is considered to be information relating to the location of the subject 51 to which the first motion information acquisition device 11 is attached. In other words, in this embodiment, the location of the location information acquisition unit 164, the location of the first motion information acquisition device 11, and the location of the subject 51 to which the first motion information acquisition device 11 is attached are considered to be the same.

[0047] For example, the location information acquisition unit 164 may be equipped with a GNSS (Global Navigation Satellite System) sensor. In this embodiment, the sensor may acquire location information by positioning using GNSS. As a specific example, the position information acquisition unit 164 includes a GNSS receiving unit inside the case member 110. This GNSS receiving unit receives GNSS signals using a GNSS antenna and acquires position information based on the received GNSS signals. Here, the GNSS signals are transmitted from one or more GNSS satellites. Furthermore, one or more of the following GNSS systems may be used: GPS (Global Positioning System), GLONASS, Galileo, BeiDou, etc. Positioning may also be called, for example, measurement or measurement.

[0048] As another example, the location information acquisition unit 164 may include a receiving unit for a predetermined communication standard such as LTE (Long Term Evolution). As a specific example, in the location information acquisition unit 164, the receiving unit may receive signals wirelessly transmitted from a base station device of the communication standard and acquire location information based on identification information of the base station device that is the communication partner. In other words, the first motion information acquisition device 11 is located within the communication area of ​​the base station device that is the communication partner and acquires location information based on this. Note that such location information may be estimated location information.

[0049] The time acquisition unit 165 acquires the time. In this embodiment, the time acquisition unit 165 acquires the current time. Furthermore, the current time does not necessarily have to be strictly real-time; it may be slightly off from real-time as long as it does not cause any practical problems.

[0050] In this embodiment, the time acquisition unit 165 communicates with a predetermined external network device via the communication unit 122 and acquires the time by receiving time information from the network device. The network device may, for example, be a device for a time signal service that provides time information.

[0051] As another example, the time acquisition unit 165 may be equipped with a GNSS sensor and acquire the time based on the information acquired by the sensor. Here, for example, if the location information acquisition unit 164 is equipped with a GNSS sensor, the time acquisition unit 165 may also use the same sensor. In this case, the location information acquisition unit 164 and the time acquisition unit 165 may, for example, be integrated into a single unit.

[0052] As another example, the time acquisition unit 165 in the first motion information acquisition device 11 may also have the function of a clock for measuring time.

[0053] The environmental information acquisition unit 166 acquires environmental information. In this embodiment, the environmental information acquisition unit 166 communicates with a predetermined external network device via the communication unit 122 and acquires environmental information by receiving it from the network device. In this embodiment, the network device is an external device, the environmental information providing device 21.

[0054] In this embodiment, the environmental information acquisition unit 166 acquires environmental information of the location of the subject 51 at the current time from the environmental information providing device 21. Here, the current time and the location of the subject 51 may be notified to the environmental information providing device 21 by the environmental information acquisition unit 166 via the communication unit 122, for example, or the environmental information providing device 21 may automatically determine them. As another example, the environmental information acquisition unit 166 may acquire environmental information from the environmental information providing device 21 for an area including the location of the subject 51, and then extract the environmental information for the location of the subject 51 from that area. The environmental information for an area including the location of the subject 51 may be observation results for the relevant area.

[0055] Environmental information may include information regarding the temperature at the location of subject 51. Environmental information may include information regarding humidity at the location of subject 51. The environmental information may include information about the weather at the location of the subject 51. The environmental information acquisition unit 166 may estimate the amount of sunshine corresponding to the location of the subject 51 at the current time based on the information about the weather. This sunshine is also an example of environmental information. Any method may be used to estimate sunshine based on the weather.

[0056] Here, the environmental information at the current time may be, for example, the environmental information at the current time itself, or statistical values ​​of environmental information at multiple different times, including the current time, may be used. Such statistical values ​​may be, for example, the average value. Regarding temperature, instead of using information on the current temperature, past temperature data for the same period may be used as is or after correction.

[0057] The mounting information acquisition unit 167 acquires mounting information regarding the mounting position of the case member 110. The mounting position may be represented, for example, by a part of the human body to which the case member 110 is attached. This part may be, for example, the head, neck, shoulders, back, torso, abdomen, waist, legs, knees, feet, arms, elbows, wrists, hands, etc.

[0058] For example, the first motor information acquisition device 11 may be set in advance by storing the wearing information in the first storage unit 124 or the like, and the wearing information acquisition unit 167 may acquire the wearing information by reading it. In this case, the pre-set wearing information may be fixedly set at the time of manufacture or shipment of the first motor information acquisition device 11, or it may be arbitrarily set or changed by the user, such as the subject 51. As a specific example, if the first motor information acquisition device 11 is a watch-type device, the wearing position may be predetermined to be the wrist. As another example, the mounting information acquisition unit 167 may determine the mounting position of the case member 110 based on the measurement result data output from the sensor unit 141. This determination may be, for example, a speculative determination.

[0059] Furthermore, the attachment information acquisition unit 167 may determine whether or not the first motion information acquisition device 11 has been attached to the subject 51 based on the measurement result data output from the sensor unit 141. In this case, the attachment information may include information indicating whether or not the first motion information acquisition device 11 has been attached to the subject 51. In configurations where mounting information is not used, the mounting information acquisition unit 167 does not necessarily need to be provided.

[0060] The model selection unit 168 selects a pre-trained model to use, inputs predetermined data into the selected pre-trained model, and obtains the data output from the pre-trained model. In this embodiment, the model selection unit 168 selects either the first simplified trained model E or the first detailed trained model F as the trained model to be used. In this embodiment, the data output from the first simplified trained model E and the data output from the first detailed trained model F are the body temperature of the subject 51.

[0061] As another example of configuration, if only one usable pre-trained model is available, the model selection unit 168 may be considered to select that pre-trained model, or the model selection unit 168 may be considered not to be provided.

[0062] The body temperature risk determination unit 169 determines the body temperature risk of the subject 51 based on the body temperature of the subject 51 output from the trained model selected by the model selection unit 168. In this embodiment, the body temperature risk determination result is an example of the information to be notified. The notification unit 123 notifies the body temperature risk determination result.

[0063] Here, the result of the body temperature risk assessment may be expressed in any format; for example, it may be binary information indicating whether or not there is a body temperature risk, or it may be multi-valued information representing the body temperature risk on three or more levels. Furthermore, binary information indicating whether or not there is a body temperature risk may be interpreted as binary information indicating, for example, whether the body temperature risk is high or low.

[0064] As multi-valued information that expresses body temperature risk in three or more levels, for example, information that expresses body temperature risk in three or more levels may be used, or information that expresses body temperature risk by converting it to a percentage using a value from 0 to 100 [%] may be used. Levels of three or more may be represented using any letters or numbers, for example, Level A, Level B, Level C, ..., or Level 1, Level 2, Level 3, ..., etc.

[0065] In this embodiment, the body temperature risk is determined and notified based on either the hyperthermia risk (risk of high body temperature) or the hypothermia risk (risk of low body temperature), or both. One example of a risk associated with high body temperature is the risk of heatstroke. For heatstroke risk, general criteria may be used, or other criteria may be used.

[0066] Here are some examples of general criteria for heatstroke. Heatstroke is classified into four severity levels, ranging from 1 to 4 degrees. Symptoms of a first episode include dizziness, lightheadedness, excessive yawning, profuse sweating, and muscle pain. The first response involves first aid and monitoring; if the symptoms do not improve, the person should be taken to a medical facility. The symptoms of the second stage include headache, vomiting, fatigue, and lethargy. The response to the second stage is to take the person to a medical institution. The symptoms of stage 3 include impaired consciousness, seizures, and liver and kidney dysfunction. The treatment for stage 3 is hospitalization. Symptoms of stage 4 include a core body temperature of 40 degrees Celsius or higher and the inability to communicate. The appropriate response to stage 4 is to immediately implement "active cooling" to cool the affected person's body.

[0067] In general, heatstroke occurs when body temperature becomes abnormally high, making it difficult for the body to properly dissipate heat. Body temperature can generally become difficult to regulate and rise due to one or more of the following factors: ambient temperature, sunlight exposure, physical activity level, or humidity. Regarding temperature, for example, in a high-temperature environment, heat dissipation from the body to the outside air decreases, which can lead to an increase in body temperature. Regarding sunlight, for example, strong sunlight can potentially raise body temperature. Regarding the amount of exercise, for example, if you engage in strenuous exercise, your body may not be able to effectively release the heat it generates, potentially causing your body temperature to rise. Regarding humidity, for example, high humidity makes it difficult for sweat to evaporate, making it harder to regulate body temperature and potentially causing body temperature to rise.

[0068] The learning model will be explained with reference to Figures 3 to 5. In this embodiment, for example, a machine learning model is used as the learning model. Machine learning may include deep learning. In this embodiment, a trained model may be referred to as a trained model, and a model being trained may be referred to as a model being trained.

[0069] Figure 3 shows an example of the input and output of the first simplified trained model E according to the first embodiment. The first pre-trained model E receives the first input data a1, which is the motor information of the subject 51, and the second input data a2, which is the internal temperature of the case member 110. In this case, the first pre-trained model E outputs first output data b1, which is the body temperature of the subject 51. This body temperature may be, for example, core body temperature. The exercise information of the subject 51 and the temperature inside the case member 110 are parameters related to the rise in the subject 51's body temperature.

[0070] Here, the first pre-trained model E uses the motion information of the subject 51 acquired by the first motion information acquisition device 11 and the internal temperature of the case member 110 as input data, and information from the network outside the first motion information acquisition device 11 is not included in the input data. Therefore, the first motion information acquisition device 11 can obtain output from the first pre-trained model E even without communication with the external network.

[0071] Figure 4 shows an example of the input and output of the first simplified learning model Ea according to the first embodiment. In this embodiment, for the sake of explanation, the first simplified learning model that is already trained is referred to as the first simplified learning model E, and the first simplified learning model that is currently being trained is referred to as the first simplified learning model Ea.

[0072] During the training of the first simplified learning model, the first simplified learning model Ea receives input data aa1, which is the motor information of the subject 51, and input data aa2, which is the internal temperature of the case member 110. Furthermore, during the training of the first simplified learning model, the first training data c1, which is the measured body temperature of 51 subjects, is input as feedback to the first simplified learning model Ea. This body temperature may be, for example, core body temperature.

[0073] Here, the first simplified learning model is a model constructed using machine learning. When building a model using machine learning, the model is trained. The model's input data is used as training data. Furthermore, the first training data c1 is used in the learning process. The first training data c1 may, for example, be data that was actually measured.

[0074] Furthermore, the first simplified learning model may include, in addition to the subject's 51 motor information and the internal temperature of the case member 110, other information that does not require information from an external network. In other words, the first simplified learning model constructs a pattern as training data that includes at least the subject's 51 motor information and the internal temperature of the case member 110.

[0075] Figure 5 shows an example of the input and output of the first detailed trained model F according to the first embodiment. The first detailed trained model F receives the following inputs: first input data a1, which is the exercise information of the subject 51; second input data a2, which is the internal temperature of the case member 110; and third input data a3, which is environmental information. This environmental information includes, for example, one or more pieces of information such as temperature, humidity, and sunlight. In this case, the first detailed trained model F outputs the first a output data ba1, which is the body temperature of the subject 51. This body temperature may be, for example, core body temperature. The exercise information of subject 51 and the temperature, air temperature, humidity, and sunlight inside the case component 110 are parameters related to the rise in subject 51's body temperature.

[0076] Here, the first detailed trained model F takes as input data the motion information of the subject 51 acquired by the first motion information acquisition device 11, the internal temperature of the case member 110, and environmental information. In this embodiment, the environmental information is based on information from an external network to the first motion information acquisition device 11. Therefore, in order for the first motion information acquisition device 11 to obtain output from the first detailed trained model F, communication with an external network is required.

[0077] In this embodiment, for the sake of explanation, the first detailed learning model that is already trained is referred to as the first detailed learning model F, and the first detailed learning model that is currently being trained is referred to as the first detailed learning model in progress. The input and output during training of the first detailed training model are the same as in the case of the first simplified training model Ea shown in Figure 4, except that data corresponding to the third input data a3 is also input to the first detailed training model.

[0078] Furthermore, the first detailed learning model may include other information in addition to the subject's 51 movement information, the internal temperature of the case member 110, and the environmental information. In other words, the first detailed learning model constructs a pattern as training data that includes at least the subject's 51 movement information, the internal temperature of the case member 110, and the environmental information.

[0079] In this embodiment, the first motion information acquisition device 11 includes a first simplified trained model E and a first detailed trained model F. The model selection unit 168 then selects a trained model to use either the first simplified trained model E or the first detailed trained model F. There are no particular limitations on the method for selecting a pre-trained model; for example, a method may be used to select a pre-trained model according to the available input data. For example, if all the data that should be input to the first detailed pre-trained model F has been acquired, the first detailed pre-trained model F may be selected. If not all the data that should be input to the first detailed pre-trained model F has been acquired, but all the data that should be input to the first simplified pre-trained model E has been acquired, the first simplified pre-trained model E may be selected.

[0080] In this embodiment, the pre-trained model is a pre-trained model that, when at least exercise information and temperature information are input, outputs the body temperature of the subject 51 estimated based on said exercise information and said temperature information. Furthermore, in this embodiment, the detailed trained model is a trained model that, when given exercise information, temperature information, and environmental information, outputs the body temperature of the subject 51 estimated based on said exercise information, said temperature information, and said environmental information.

[0081] Figure 6 shows an example of the processing procedure performed by the first motion information acquisition device 11 according to the first embodiment. In step S1, the first control unit 125 acquires temperature data and temperature-corrected motion data using the data acquisition unit 121.

[0082] In step S2, the first control unit 125 acquires information including motion information and temperature information using the momentum calculation unit 162 and the temperature information acquisition unit 163. For example, the first control unit 125 may acquire information including motion information, temperature information and environmental information using the momentum calculation unit 162, the temperature information acquisition unit 163 and the environmental information acquisition unit 166. Here, exercise information is obtained from exercise data corrected for temperature. Temperature information is obtained from temperature data. Environmental information is obtained from an external network.

[0083] In step S3, the first control unit 125, using the model selection unit 168, selects the pre-trained model to be used from among the first simplified pre-trained model E and the first detailed pre-trained model F.

[0084] In step S4, the first control unit 125 acquires the body temperature output from the trained model used. In step S5, the first control unit 125 determines the body temperature risk based on the body temperature risk determination unit 169. In step S6, the first control unit 125 notifies the body temperature risk via the notification unit 123, either through the first exercise information acquisition device 11 or an external terminal.

[0085] Furthermore, the body temperature risk may be applied to, for example, hyperthermia risk, or hypothermia risk, or to both hyperthermia risk and hypothermia risk. In other words, the trained model will output a judgment result for either hyperthermia risk or hypothermia risk, or both.

[0086] As described above, the first exercise information acquisition device 11 according to this embodiment acquires temperature information based on the internal temperature data of the case member 110, and acquires exercise information of the subject 51 based on exercise data corrected by temperature, and acquires body temperature determined by a trained model using the temperature information and the exercise information as input data. As a result, the first exercise information acquisition device 11 according to this embodiment can determine the body temperature risk of the subject 51. Furthermore, the first exercise information acquisition device 11 according to this embodiment can improve the accuracy of the body temperature determination result by including environmental information in the input data of the learned model, thereby improving the accuracy of the body temperature risk determination result.

[0087] In this embodiment, the first exercise information acquisition device 11 can use temperature data measured by the sensor unit 141 equipped with a temperature sensor C3 to determine body temperature. For example, it is not necessary to provide a separate sensor to measure the body temperature of the subject 51, thus reducing the device cost. Thus, in the first exercise information acquisition device 11 according to this embodiment, the internal temperature data of the first exercise information acquisition device 11, which is measured to acquire the exercise information of the subject 51, can be reused for determining the body temperature risk.

[0088] Figure 7 shows an example of the configuration of the first motion information acquisition device 11A according to a modified example of the first embodiment. Here, the configuration and operation of the first motion information acquisition device 11A differ from the configuration and operation of the first motion information acquisition device 11 shown in Figure 2 in that it has a first A storage unit 124A that stores n learned model units, namely the first-1 learned model unit D1 to the first-n learned model unit Dn, instead of the first storage unit 124 shown in Figure 2, but is similar in other respects. Therefore, in the example shown in Figure 7, for the sake of explanation, components similar to those shown in Figure 2 will be denoted by the same reference numerals and described accordingly.

[0089] The 1-1 trained model units D1 to 1-n trained model units Dn are each trained model units that correspond to different mounting positions. In other words, if the body temperature of the subjects 51 is the same, the temperature detected by the temperature sensor C3 may change depending on the mounting position of the 1A exercise information acquisition device 11A, so the trained model used is changed for each mounting position. Generally speaking, temperatures tend to be higher closer to the human heart.

[0090] Here, the 1st-1 trained model section D1 to the 1st-n trained model section Dn each include a simplified trained model (not shown) and a detailed trained model (not shown). The simplified pre-trained model and the detailed pre-trained model are the same as the first simplified pre-trained model E and the first detailed pre-trained model F shown in Figure 2. In this modified example, the first-1 pre-trained model section D1 to the first-n pre-trained model section Dn correspond to different mounting positions.

[0091] As described above, in the first A motion information acquisition device 11A, the first A storage unit 124A stores the first-1st learned model unit D1 to the first-nth learned model unit Dn as multiple learned model units corresponding to the mounting position. Furthermore, the model selection unit 168 selects a pre-trained model from among several pre-trained model units that corresponds to the wearing information. Furthermore, the model selection unit 168 further selects either a simplified trained model or a detailed trained model from the selected trained model unit.

[0092] Therefore, the first exercise information acquisition device 11A can achieve the same effects as the first exercise information acquisition device 11, for example. Furthermore, by selecting a learned model according to the wearing position, it is possible to improve the accuracy of the body temperature determination result, thereby improving the accuracy of the body temperature risk determination result.

[0093] In this modified example, a different trained model is selected and used for each mounting position. However, as another example, the input data for trained models such as the first simplified trained model E and the first detailed trained model F shown in Figure 2 may include information about the mounting position. This information may be, for example, mounting information.

[0094] A second embodiment will be described. In the second embodiment, we will describe a case in which the second motion information acquisition device 12 shown in Figure 8 is used as the motion information acquisition device 10 shown in Figure 1. The second motion information acquisition device 12 is an example of the motion information acquisition device 10.

[0095] Figure 8 shows an example of the configuration of the second motion information acquisition device 12 according to the second embodiment. Here, the configuration and operation of the second motion information acquisition device 12 differ from the configuration and operation of the first motion information acquisition device 11 shown in Figure 2 in that it has a second storage unit 324 that stores the second learned model unit G instead of the first storage unit 124 shown in Figure 2, and a second control unit 325 that does not have the body temperature risk determination unit 169 shown in Figure 2 instead of the first control unit 125 shown in Figure 2, but is similar in other respects. Therefore, in the example shown in Figure 8, for the sake of explanation, components similar to those shown in Figure 2 are given the same reference numerals, and detailed explanations are omitted.

[0096] The second pre-trained model unit G includes the second simplified pre-trained model H and the second detailed pre-trained model I. In this embodiment, the second simplified trained model H and the second detailed trained model I each output the body temperature risk of the subject 51. Therefore, in this embodiment, the body temperature risk determination unit 169 shown in Figure 2 is unnecessary.

[0097] In the second control unit 325, the model selection unit 168 selects a pre-trained model to be used, inputs predetermined data to the selected pre-trained model, and acquires data output from the pre-trained model. In this embodiment, the model selection unit 168 selects either the second simplified trained model H or the second detailed trained model I as the trained model to be used. In this embodiment, the data output from the second simplified trained model H and the data output from the second detailed trained model I represent the body temperature risk of the subject 51. In this embodiment, the body temperature risk output from the trained models is used in place of the determination result by the body temperature risk determination unit 169 shown in Figure 2.

[0098] Refer to Figures 9 to 11 to explain the learning model. In this embodiment, the output data from the learning model differs from the examples in Figures 3 to 5 in that it represents body temperature risk. A detailed explanation of the similarities to the examples in Figures 3 to 5 will be omitted.

[0099] Figure 9 shows an example of the input and output of the second simplified trained model H according to the second embodiment. The second simplified pre-trained model H receives the first e-input data e1, which is the motor information of the subject 51, and the second e-input data e2, which is the internal temperature of the case member 110. In this case, the second simplified trained model H outputs the second output data f1, which represents the body temperature risk for the subject 51.

[0100] Figure 10 shows an example of the input and output of the second simplified learning model Ha according to the second embodiment. In this embodiment, for the sake of explanation, the second simplified learning model that is already trained is referred to as the second simplified learning model H, and the second simplified learning model that is currently being trained is referred to as the second simplified learning model Ha.

[0101] During the training of the second simplified learning model, the second simplified learning model Ha receives the first eb input data eb1, which is the motor information of the subject 51, and the second eb input data eb2, which is the internal temperature of the case member 110. Furthermore, during the training of the second simplified learning model, the second training data g1, which represents the body temperature risk of 51 subjects measured in real-world data, is input as feedback to the second simplified learning model Ha.

[0102] Here, the second training data set, g1, is used in the learning process. For example, when acquiring actual measurement data for a learning model, a thermometer or similar device may be attached to the subject to collect their body temperature, and information about the subject's physical condition may be collected through interviews with the subject. Then, a body temperature risk may be determined based on the collected body temperature and physical condition of the subject, and this determined body temperature risk may be used as the second training data g1. The subject in question may be, for example, the same person as subject 51, or a different person from subject 51. Furthermore, for example, information on multiple subjects may be collected, and the second training data g1 may be set based on this information.

[0103] Figure 11 shows an example of the input and output of the second detailed trained model I according to the second embodiment. The second detailed trained model I receives the first e input data e1, which is the movement information of the subject 51; the second e input data e2, which is the internal temperature of the case member 110; and the third e input data e3, which is environmental information. This environmental information includes, for example, one or more pieces of information such as temperature, humidity, and sunlight. In this case, the second detailed trained model I outputs output data fa1, which represents the body temperature risk for the subject 51.

[0104] In this embodiment, for the sake of explanation, the second detailed learning model that is already trained is referred to as the second detailed learning model H, and the second detailed learning model that is currently being trained is referred to as the second detailed learning model in progress. The input and output during training of the second detailed training model are similar to those of the second simplified training model Ha shown in Figure 10, except that data corresponding to the third e input data e3 is also input to the second detailed training model.

[0105] In this embodiment, the second motion information acquisition device 12 includes a second simplified trained model H and a second detailed trained model I. The model selection unit 168 then selects a trained model to use either the second simplified trained model H or the second detailed trained model I.

[0106] In this embodiment, the simplified pre-trained model is a pre-trained model that, when at least exercise information and temperature information are input, outputs the estimated body temperature risk of the subject 51 based on the said exercise information and said temperature information. Furthermore, in this embodiment, the detailed trained model is a trained model that, when given exercise information, temperature information, and environmental information, outputs the estimated body temperature risk of the subject 51 based on the said exercise information, temperature information, and environmental information.

[0107] Figure 12 shows an example of the processing procedure performed by the second motion information acquisition device 12 according to the second embodiment. In step S21, the second control unit 325 acquires temperature data and temperature-corrected motion data using the data acquisition unit 121.

[0108] In step S22, the second control unit 325 acquires information including motion information and temperature information using the momentum calculation unit 162 and the temperature information acquisition unit 163. For example, the second control unit 325 may acquire information including motion information, temperature information and environmental information using the momentum calculation unit 162, the temperature information acquisition unit 163 and the environmental information acquisition unit 166. Here, exercise information is obtained from exercise data corrected for temperature. Temperature information is obtained from temperature data. Environmental information is obtained from an external network.

[0109] In step S23, the second control unit 325, using the model selection unit 168, selects the trained model to be used from among the second simplified trained model H and the second detailed trained model I.

[0110] In step S24, the second control unit 325 acquires the body temperature risk output from the trained model used. In step S25, the second control unit 325 notifies the body temperature risk via the notification unit 123, either through the second exercise information acquisition device 12 or an external terminal.

[0111] Furthermore, the body temperature risk may be applied to, for example, hyperthermia risk, or hypothermia risk, or to both hyperthermia risk and hypothermia risk. In other words, the trained model will output a judgment result for either hyperthermia risk or hypothermia risk, or both.

[0112] As described above, the second exercise information acquisition device 12 according to this embodiment acquires temperature information based on the internal temperature data of the case member 110, and acquires exercise information of the subject 51 based on exercise data corrected for temperature, and acquires body temperature risk determined by a trained model using at least the temperature information and the exercise information as input data. Furthermore, the first exercise information acquisition device 11 according to this embodiment can improve the accuracy of the body temperature risk determination result by including environmental information in the input data of the learned model.

[0113] In this embodiment, the second exercise information acquisition device 12 can utilize temperature data measured by the sensor unit 141 equipped with a temperature sensor C3 to determine body temperature. For example, it is not necessary to provide a separate sensor to measure the body temperature of the subject 51, thereby reducing the device cost. Thus, in the second exercise information acquisition device 12 according to this embodiment, the internal temperature data of the second exercise information acquisition device 12, which is measured to acquire the exercise information of the subject 51, can be reused for determining the body temperature risk.

[0114] Figure 13 shows an example of the configuration of the second A motion information acquisition device 12A according to a modified example of the second embodiment. Here, the configuration and operation of the second motion information acquisition device 12A differ from the configuration and operation of the second motion information acquisition device 12 shown in Figure 8 in that it has a second A storage unit 324A that stores m learned model units, namely the second-1 learned model unit G1 to the second-m learned model unit Gm, instead of the second storage unit 324 shown in Figure 8, but is similar in other respects. Therefore, in the example shown in Figure 13, for the sake of explanation, components similar to those shown in Figure 8 will be denoted by the same reference numerals and described accordingly.

[0115] The 2-1 pre-trained model units G1 to 2-m pre-trained model units Gm are pre-trained model units that correspond to different mounting positions. In other words, if the body temperature of the subjects 51 is the same, the temperature detected by the temperature sensor C3 may change depending on the mounting position of the 2A exercise information acquisition device 12A, so the trained model used is changed for each mounting position.

[0116] Here, the 2-1 pre-trained model section G1 to the 2-m pre-trained model section Gm each include a simplified pre-trained model (not shown) and a detailed pre-trained model (not shown). The simplified pre-trained model and the detailed pre-trained model are the same as the second simplified pre-trained model H and the second detailed pre-trained model I shown in Figure 8. In this modified example, the 2-1 pre-trained model section G1 to the 2-m pre-trained model section Gm correspond to different mounting positions.

[0117] As described above, in the second A motion information acquisition device 12A, the second A storage unit 324A stores the second-1 learned model unit G1 to the second-m learned model unit Gm as multiple learned model units corresponding to the mounting position. Furthermore, the model selection unit 168 selects a pre-trained model from among several pre-trained model units that corresponds to the wearing information. Furthermore, the model selection unit 168 further selects either a simplified trained model or a detailed trained model from the selected trained model unit.

[0118] Therefore, the second exercise information acquisition device 12A can achieve the same effects as the second exercise information acquisition device 12, for example, and furthermore, by selecting a learned model according to the wearing position, it is possible to improve the accuracy of the body temperature risk determination result.

[0119] In this modified example, a different trained model is selected and used for each mounting position. However, as another example, the input data for trained models such as the second simplified trained model H and the second detailed trained model I shown in Figure 8 may include information about the mounting position. This information may be, for example, mounting information.

[0120] An information processing system relating to a modified embodiment will be described. Figure 14 shows an example of the configuration of the αth information processing system 1α, which includes the αth motion information acquisition device 10α according to a modified embodiment. The α-information processing system 1α comprises an α-motion information acquisition device 10α, an α-environmental information provision device 21α, an α-target user terminal 41α, and an α-external terminal 42α. Figure 14 also shows subject α, 51α. The αth motion information acquisition device 10α comprises a sensor device 511 and an external control device 512.

[0121] In this modified example, the main difference from the information processing system 1 shown in Figure 1 is that the αth motion information acquisition device 10α consists of two separate sensor devices 511 and an external control device 512. Other aspects are the same, and a detailed explanation is omitted. The αth target person 51α, the αth environmental information providing device 21α, the αth target person terminal 41α, and the αth external terminal 42α shown in Figure 14 are, in general terms, the same as the target person 51, the environmental information providing device 21, the target person terminal 41, and the external terminal 42 shown in Figure 1. The external control device 512 may be any device, such as a smartphone, tablet, or other computer, or it may be a predetermined server device.

[0122] The external control device 512 and the α environmental information providing device 21α, which constitute the α motion information acquisition device 10α, can communicate wirelessly. The external control device 512 and the α subject terminal 41α, which constitute the α motor information acquisition device 10α, can communicate with each other via wired or wireless means. The external control device 512 and the α external terminal 42α, which constitute the α motion information acquisition device 10α, can communicate with each other via wired or wireless means.

[0123] The sensor device 511, which constitutes the αth motion information acquisition device 10α, includes the αth case member 110α. The α-case member 110α is attached to the α-subject 51α by being fitted to a predetermined part of the α-subject 51α. In this modified example, the sensor device 511 has a shape similar to that of a watch, and the αth case member 110α is worn on the wrist of the αth subject 51α. The sensor device 511 may also have the function of a watch.

[0124] In this modified example, the sensor device 511 has the function of communicating wirelessly with the external control device 512 and the function of the data acquisition unit 121, and transmits the data acquired by the said function wirelessly to the external control device 512. In this modified example, the functions of the data acquisition unit 121 are housed in the αth case member 110α. The external control device 512 acquires the body temperature risk based on the data received from the sensor device 511 and notifies the user of the body temperature risk. In this modified example, the external control device 512 obtains the body temperature risk determination result.

[0125] The body temperature risk may be notified, for example, by the display unit or audio output unit of the external control device 512, or it may be transmitted from the external control device 512 to the target terminal 41 or external terminal 42 and notified by the target terminal 41 or external terminal 42. As another example, if the sensor device 511 includes an output unit such as a display unit or an audio output unit, the body temperature risk may be transmitted from the external control device 512 to the sensor device 511 and notified by the output unit of the sensor device 511.

[0126] The case in which this modification applies to the first embodiment will be described. In this case, the sensor device 511 has the same functions as the data acquisition unit 121 of the first motion information acquisition device 11 shown in Figure 2. Furthermore, the external control device 512 has the same functions as the components of the first motion information acquisition device 11 shown in Figure 2, excluding the data acquisition unit 121. Furthermore, the sensor device 511 and the external control device 512 are equipped with a function to communicate wirelessly with each other. This function may be provided, for example, in the communication unit 122 of the external control device 512. Similarly, this modified example may also be applied to the configuration of the first A motion information acquisition device 11A shown in Figure 7 according to the first embodiment.

[0127] The case in which this modified example applies to the second embodiment will be explained. In this case, the sensor device 511 has the same functions as the data acquisition unit 121 of the second motion information acquisition device 12 shown in Figure 8. Furthermore, the external control device 512 has the same functions as the components of the second motion information acquisition device 12 shown in Figure 8, excluding the data acquisition unit 121. Furthermore, the sensor device 511 and the external control device 512 are equipped with a function to communicate wirelessly with each other. This function may be provided, for example, in the communication unit 122 of the external control device 512. Similarly, this modified example may also be applied to the configuration of the second motion information acquisition device 12A shown in Figure 13 according to the second embodiment.

[0128] In this modified example, the motion information acquisition device 10 shown in Figure 1 is shown as being composed of two separate devices, but the way in which the functions provided in each of these two devices are distributed may be arbitrary. Furthermore, for example, the motion information acquisition device 10 may be composed of three or more separate devices.

[0129] Other variations of the embodiment will be described. In the embodiments described above, the motion information acquisition device 10 is shown to store a simplified trained model and a detailed trained model and to appropriately select and use one of these trained models. However, as a modified example, the motion information acquisition device 10 may be configured to store one trained model and always use that trained model. This trained model may be, for example, a simplified trained model, a detailed trained model, or any other trained model. As another example, the motion information acquisition device 10 may be configured to store one learned model for each of the multiple mounting positions, and to always use one learned model once a mounting position is determined.

[0130] For example, in a configuration where the exercise information acquisition device 10 stores and uses one or more simple pre-trained models but does not use detailed pre-trained models, it is not necessarily required to acquire environmental information from a network, and therefore, for example, it does not need to have a function to communicate wirelessly with external devices. In such a configuration, the exercise information acquisition device 10 can, as a standalone device, acquire and notify the results of the body temperature risk assessment of the subject 51.

[0131] An example configuration of the above embodiment is shown below. As an example configuration, the motion information acquisition device comprises a case member, a data acquisition unit, a control unit, and a storage unit. The case component is attached to the subject. The data acquisition unit is housed in a case member and acquires temperature data from within the case member, and then acquires the subject's exercise data corrected using that temperature data. The control unit acquires the subject's exercise information based on the subject's exercise data corrected with temperature data, and acquires temperature information based on the said temperature data. The memory unit stores a trained model that, when at least movement information and temperature information are input, outputs the estimated body temperature of the subject based on said movement information and temperature information. The control unit determines the temperature risk of the subject based on the subject's body temperature output from the trained model. Therefore, since the exercise information acquisition device includes a data acquisition unit that acquires temperature data within the case member and exercise data of the subject corrected with said temperature data, when acquiring the results of the determination of the subject's body temperature risk, it is not necessary to separately provide, for example, a sensor to measure the subject's body temperature, and the device cost can be reduced.

[0132] Here, in the examples of Figures 1 and 2, the first motor information acquisition device 11, which is an example of a motor information acquisition device 10, the subject 51, the case member 110, the data acquisition unit 121, the first storage unit 124, and the first control unit 125 are, respectively, an example of a motor information acquisition device, an example of a subject, an example of a case member, an example of a data acquisition unit, an example of a storage unit, and an example of a control unit. Also, the first simplified trained model E and the first detailed trained model F are, respectively, examples of trained models. Furthermore, in the examples in Figures 1 and 7, the first A motion information acquisition device 11A, the subject 51, the case member 110, the data acquisition unit 121, the first A storage unit 124A, and the first control unit 125, which are examples of the motion information acquisition device 10, are examples of the motion information acquisition device, an example of the subject, an example of the case member, an example of the data acquisition unit, an example of the storage unit, and an example of the control unit, respectively. In addition, the simplified trained model and the detailed trained model in each of the 1-1 trained model units D1 to 1-n trained model units Dn are examples of trained models, respectively. In the example shown in Figure 14, the αth motion information acquisition device 10α, which includes a sensor device 511 and an external control device 512, the αth subject 51α, and the αth case member 110α are examples of a motion information acquisition device, an example of a subject, and an example of a case member, respectively.

[0133] As one example configuration, the motion information acquisition device further comprises a location information acquisition unit, a time acquisition unit, and a communication unit. The location information acquisition unit acquires location information of the subject regarding the subject's location. The time acquisition unit acquires the current time. The communications unit communicates with external devices. The control unit communicates with an external device to the communication unit to obtain environmental information about the target person's location at the current time. The trained model, upon receiving exercise information, temperature information, and environmental information, outputs the estimated body temperature of the subject based on that information. Therefore, by further utilizing environmental information, the accuracy of the body temperature risk assessment results can be improved in the exercise information acquisition device.

[0134] Here, in the examples of Figures 1 and 2, or Figures 1 and 7, the location information acquisition unit 164, the time acquisition unit 165, and the communication unit 122 are examples of the location information acquisition unit, the time acquisition unit, and the communication unit, respectively. Also, the environmental information providing device 21 and the external communication device 31 are examples of external devices, respectively. In the example shown in Figure 14, the α environmental information providing device 21α, the α target user terminal 41α, and the α external terminal 42α are examples of external devices.

[0135] As an example configuration, the motion information acquisition device comprises a case member, a data acquisition unit, a control unit, and a storage unit. The case component is attached to the subject. The data acquisition unit is housed in a case member and acquires temperature data from within the case member, and then acquires the subject's exercise data corrected using that temperature data. The control unit acquires the subject's exercise information based on the subject's exercise data corrected with temperature data, and acquires temperature information based on the said temperature data. The memory unit stores a trained model that, when at least exercise information and temperature information are input, outputs the estimated body temperature risk of the subject based on said exercise information and said temperature information. Therefore, since the exercise information acquisition device includes a data acquisition unit that acquires temperature data within the case member and exercise data of the subject corrected with said temperature data, when acquiring the results of the determination of the subject's body temperature risk, it is not necessary to separately provide, for example, a sensor to measure the subject's body temperature, and the device cost can be reduced.

[0136] Here, in the examples of Figures 1 and 8, the second motion information acquisition device 12 (an example of the motion information acquisition device 10), the subject 51, the case member 110, the data acquisition unit 121, the second storage unit 324, and the second control unit 325 are, respectively, an example of the motion information acquisition device, an example of the subject, an example of the case member, an example of the data acquisition unit, an example of the storage unit, and an example of the control unit. Also, the second simplified trained model H and the second detailed trained model I are, respectively, examples of trained models. Furthermore, in the examples in Figures 1 and 13, the second A motion information acquisition device 12A, the subject 51, the case member 110, the data acquisition unit 121, the second A storage unit 324A, and the second control unit 325, which are examples of motion information acquisition devices 10, are examples of motion information acquisition devices, examples of subject, examples of case members, examples of data acquisition units, examples of storage units, and examples of control units, respectively. In addition, the simplified trained model and the detailed trained model in each of the 2-1 trained model units G1 to 2-m trained model units Gm are examples of trained models, respectively. In the example shown in Figure 14, the αth motion information acquisition device 10α, which includes a sensor device 511 and an external control device 512, the αth subject 51α, and the αth case member 110α are examples of a motion information acquisition device, an example of a subject, and an example of a case member, respectively.

[0137] As one example configuration, the motion information acquisition device further comprises a location information acquisition unit, a time acquisition unit, and a communication unit. The location information acquisition unit acquires location information of the subject regarding the subject's location. The time acquisition unit acquires the current time. The communications unit communicates with external devices. The control unit communicates with an external device to the communication unit to obtain environmental information about the target person's location at the current time. The trained model, upon receiving exercise information, temperature information, and environmental information, outputs the estimated body temperature risk of the subject based on that information. Therefore, by further utilizing environmental information, the accuracy of the body temperature risk assessment results can be improved in the exercise information acquisition device.

[0138] Here, in the examples of Figures 1 and 8, or Figures 1 and 13, the location information acquisition unit 164, the time acquisition unit 165, and the communication unit 122 are examples of the location information acquisition unit, the time acquisition unit, and the communication unit, respectively. Also, the environmental information providing device 21 and the external communication device 31 are examples of external devices, respectively. In the example shown in Figure 14, the α environmental information providing device 21α, the α target user terminal 41α, and the α external terminal 42α are examples of external devices.

[0139] As an example configuration, the motion information acquisition device was configured as follows. Environmental information includes information about the temperature at the subject's location. Therefore, the exercise information acquisition device can obtain the results of the body temperature risk assessment based on ambient temperature.

[0140] As an example configuration, the motion information acquisition device was configured as follows. Environmental information includes information about humidity at the subject's location. Therefore, the exercise information acquisition device can obtain the results of determining body temperature risk according to humidity.

[0141] As an example configuration, the motion information acquisition device was configured as follows. The control unit acquires weather information from an external device and estimates the amount of sunlight corresponding to the subject's location at the current time. The control unit inputs the estimated sunlight as environmental information into the trained model. Therefore, the exercise information acquisition device can obtain the results of the body temperature risk assessment in accordance with sunlight, for example, it can obtain the results of the body temperature risk assessment in accordance with the intensity of sunlight.

[0142] As one example configuration, the motion information acquisition device further includes a wear information acquisition unit. The mounting information acquisition unit acquires mounting information regarding the mounting position of the case member. The memory unit stores multiple pre-trained models corresponding to the device's placement. The control unit selects a pre-trained model from among several pre-trained models that corresponds to the wear information. Therefore, in a motor information acquisition device, the accuracy of the temperature risk determination can be improved by using a pre-trained model that matches the body part of the person to which the case component of the motor information acquisition device is attached.

[0143] Here, in the examples of Figures 1 and 7, the mounting information acquisition unit 167 is an example of a mounting information acquisition unit. Furthermore, regarding the simplified pre-trained model, the multiple simplified pre-trained models included in the 1st-1st pre-trained model unit D1 to the 1st-nth pre-trained model unit Dn, which are multiple pre-trained model units, are an example of multiple pre-trained models. Similarly, regarding the detailed pre-trained model, the multiple detailed pre-trained models included in the 1st-1st pre-trained model unit D1 to the 1st-nth pre-trained model unit Dn, which are multiple pre-trained model units, are an example of multiple pre-trained models. Furthermore, in the examples of Figures 1 and 13, the mounting information acquisition unit 167 is an example of a mounting information acquisition unit. Also, regarding the simplified pre-trained model, the multiple simplified pre-trained models included in the multiple pre-trained model units, namely the 2-1 pre-trained model unit G1 to the 2-m pre-trained model unit Gm, are an example of multiple pre-trained models. Similarly, regarding the detailed pre-trained model, the multiple detailed pre-trained models included in the multiple pre-trained model units, namely the 2-1 pre-trained model unit G1 to the 2-m pre-trained model unit Gm, are an example of multiple pre-trained models.

[0144] As one example configuration, the motion information acquisition device further includes a notification unit. The notification unit will notify you of the results of the temperature risk assessment. Therefore, the exercise information acquisition device can notify the subject of the body temperature risk assessment result.

[0145] Here, in the examples of Figures 1 and 2, Figures 1 and 7, Figures 1 and 8, or Figures 1 and 13, the notification unit 123 is an example of a notification unit.

[0146] As an example configuration, the motion information acquisition device was configured as follows. The control unit's determination of body temperature risk is communicated to the user's terminal via an external communication device. Therefore, the exercise information acquisition device can notify the subject of the body temperature risk assessment result.

[0147] Here, in the examples of Figures 1 and 2, Figures 1 and 7, Figures 1 and 8, or Figures 1 and 13, the external communication device 31 and the target terminal 41 are examples of an external communication device and an example of a target terminal, respectively.

[0148] For example, it is also possible to provide a control method for a motion information acquisition device that includes predetermined processing steps performed by the motion information acquisition device. For example, it is also possible to provide a computer program that executes predetermined processing steps performed by a motion information acquisition device.

[0149] A program for realizing the function of any component in any of the devices described above may be recorded on a computer-readable recording medium, and the program may be loaded into a computer system and executed. Here, "computer system" includes the operating system and hardware such as peripheral devices. "Computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, ROM (Read Only Memory), CD (Compact Disc)-ROMs, and storage devices such as hard disks built into the computer system. "Computer-readable recording medium" also includes volatile memory within a computer system that acts as a server or client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, which retains the program for a certain period of time. Such volatile memory may be RAM. The recording medium may also be a non-temporary recording medium.

[0150] The above program may be transmitted from a computer system that stores this program in a memory device or the like to another computer system via a transmission medium, or by transmission waves within the transmission medium. The "transmission medium" used to transmit the program refers to a medium that has the function of transmitting information, such as a network like the Internet or a communication line like a telephone line. The above program may be intended to implement some of the functions described above. The above program may also be a so-called differential file, capable of implementing the aforementioned functions in combination with programs already recorded in the computer system. A differential file may also be called a differential program.

[0151] The functions of any component in any device described above may be implemented by a processor. Each process in the embodiment may be implemented by a processor that operates based on information such as a program, and a computer-readable recording medium that stores information such as a program. The functions of each part of the processor may be implemented by separate hardware, or the functions of each part may be implemented by integrated hardware. The processor includes hardware, and the hardware may include at least one of a circuit that processes digital signals and a circuit that processes analog signals. The processor may be configured using one or more circuit devices or one or both of one or more circuit elements mounted on a circuit board. ICs may be used as circuit devices, and resistors or capacitors may be used as circuit elements.

[0152] The processor may be a CPU. However, the processor is not limited to a CPU; various types of processors such as a GPU (Graphics Processing Unit) or a DSP (Digital Signal Processor) may be used. The processor may be a hardware circuit using an ASIC (Application Specific Integrated Circuit). The processor may consist of multiple CPUs, or it may consist of hardware circuits using multiple ASICs. The processor may consist of a combination of multiple CPUs and hardware circuits using multiple ASICs. The processor may include one or more amplifier circuits or filter circuits that process analog signals.

[0153] Although embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and includes designs and the like that do not depart from the gist of this disclosure.

[0154] [Note] The following are configuration examples 1 through 14. Furthermore, the lower-level configuration examples may or may not be applied to the higher-level configuration examples. Furthermore, a lower-level configuration example applicable to any of the two or more higher-level configuration examples may be applied to any of those two or more higher-level configuration examples. Moreover, if two or more application examples arise in this manner, a configuration example even lower than the lower-level example may be applied to any of those two or more application examples.

[0155] <Configuration Example 1> A case component to be attached to the subject, A data acquisition unit housed in the case member acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A control unit that acquires exercise information of the subject based on the subject's exercise data corrected with the temperature data, and acquires temperature information based on the temperature data, The system includes a storage unit that stores a trained model that, when at least the exercise information and the temperature information are input, outputs the body temperature of the subject estimated based on the exercise information and the temperature information, The control unit determines the temperature risk of the subject based on the subject's body temperature output from the trained model. Exercise information acquisition device.

[0156] <Configuration Example 2> A location information acquisition unit that acquires location information of the subject regarding the location of the subject, A time acquisition unit that obtains the current time, A communication unit that communicates with external devices, and a equipped, The control unit causes the communication unit to communicate with the external device and obtains environmental information of the subject's location at the current time. The trained model, upon receiving the exercise information, temperature information, and environmental information, outputs the body temperature of the subject estimated based on the exercise information, temperature information, and environmental information. The motion information acquisition device described in <Configuration Example 1>.

[0157] <Configuration Example 3> A case component to be attached to the subject, A data acquisition unit housed in the case member acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A control unit that acquires exercise information of the subject based on the subject's exercise data corrected with the temperature data, and acquires temperature information based on the temperature data, The system includes a storage unit that stores a trained model that, when at least the exercise information and the temperature information are input, outputs the body temperature risk of the subject estimated based on the exercise information and the temperature information. Exercise information acquisition device.

[0158] <Configuration Example 4> A location information acquisition unit that acquires location information of the subject regarding the location of the subject, A time acquisition unit that obtains the current time, A communication unit that communicates with external devices, and a equipped, The control unit causes the communication unit to communicate with the external device and obtains environmental information of the subject's location at the current time. The trained model, upon receiving the exercise information, temperature information, and environmental information, outputs the estimated body temperature risk of the subject based on the exercise information, temperature information, and environmental information. The motion information acquisition device described in <Configuration Example 3>.

[0159] <Configuration Example 5> The aforementioned environmental information includes information regarding the temperature at the location of the subject, A motion information acquisition device as described in <Configuration Example 2> or <Configuration Example 4>.

[0160] <Configuration Example 6> The aforementioned environmental information includes information regarding humidity at the subject's location. A motion information acquisition device as described in any one of <Configuration Example 2>, <Configuration Example 4>, or <Configuration Example 5>.

[0161] <Configuration Example 7> The control unit acquires weather information from the external device and estimates the amount of sunlight corresponding to the subject's location at the current time. The control unit inputs the estimated sunlight as environmental information to the trained model. A motion information acquisition device as described in any one of the following items: <Configuration Example 2>, <Configuration Example 4>, <Configuration Example 5>, or <Configuration Example 6>.

[0162] <Configuration Example 8> The system includes an installation information acquisition unit that acquires installation information regarding the mounting position of the case member, The memory unit stores a plurality of the learned models corresponding to the mounting position, The control unit selects a learned model from among a plurality of learned models that corresponds to the mounting information. A motion information acquisition device as described in any one of <Configuration Example 1> to <Configuration Example 7>.

[0163] <Configuration Example 9> It includes a notification unit that notifies the result of the body temperature risk determination, A motion information acquisition device as described in any one of <Configuration Example 1> to <Configuration Example 8>.

[0164] <Configuration Example 10> The temperature risk determination result determined by the control unit is notified to the subject's terminal used by the subject via an external communication device. A motion information acquisition device as described in any one of <Configuration Example 1> to <Configuration Example 9>.

[0165] <Configuration Example 11> A control method for a motion information acquisition device comprising: a case member attached to a subject; and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, The steps include acquiring the temperature data in the motion information acquisition device, A step of acquiring the exercise data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model that is stored in a memory unit and outputs the body temperature of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, A step of determining the body temperature risk of the subject based on the subject's body temperature output from the trained model, A control method for the motion information acquisition device, comprising the above-mentioned device.

[0166] <Configuration Example 12> A control method for a motion information acquisition device comprising: a case member attached to a subject; and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, The steps include acquiring the temperature data in the motion information acquisition device, A step of acquiring the exercise data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model stored in a memory unit, which outputs the body temperature risk of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, The steps include obtaining the body temperature risk of the subject, which is output from the trained model, A control method for the motion information acquisition device, comprising the above-mentioned device.

[0167] <Configuration Example 13> A program for controlling a computer that constitutes a motion information acquisition device comprising a case member attached to a subject, and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model that is stored in a memory unit and outputs the body temperature of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, A step of determining the body temperature risk of the subject based on the subject's body temperature output from the trained model, A program that executes something.

[0168] <Configuration Example 14> A program for controlling a computer that constitutes a motion information acquisition device comprising a case member attached to a subject, and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model stored in a memory unit, which outputs the body temperature risk of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, The steps include obtaining the body temperature risk of the subject, which is output from the trained model, A program that executes something. [Explanation of symbols]

[0169] 1...Information processing system, 1α...αth information processing system, 10...Motion information acquisition device, 10α...αth motion information acquisition device, 11...1st motion information acquisition device, 11A...1stA motion information acquisition device, 12...2nd motion information acquisition device, 12A...2ndA motion information acquisition device, 21...Environmental information provision device, 21α...αth environmental information provision device, 31...External communication device, 41...Target user terminal, 41α...αth target user terminal, 42...External terminal, 42α...αth external terminal, 51...Target user, 51α...αth target user, 110...Case member, 110α...αth case member 121...Data acquisition unit, 122...Communication unit, 123...Notification unit, 124...First storage unit, 124A...First A storage unit, 125...First control unit, 141...Sensor unit, 151...First sensor unit, 152...Second sensor unit, 161...Velocity calculation unit, 162...Momentum calculation unit, 163...Temperature information acquisition unit, 164...Location information acquisition unit, 165...Time acquisition unit, 166...Environmental information acquisition unit, 167...Wearing information acquisition unit, 168...Model selection unit, 169...Body temperature risk determination unit, 324...Second storage unit, 324A...Second A storage unit, 325...Second Control unit, 511... Sensor device, 512... External control device, C1... Acceleration sensor, C2... Angular velocity sensor, C3... Temperature sensor, D... First trained model section, D1... 1-1 trained model section, D2... 1-2 trained model section, Dn... 1-n trained model section, E... First simplified trained model, Ea... First simplified model being trained, F... First detailed trained model, G... Second trained model section, G1... 2-1 trained model section, G2... 2-2 trained model section, Gm... 2-m trained model section, H... Second simplified Ha…Trained model, I…Second simplified training model, a1…First input data, aa1…First a input data, a2…Second input data, aa2…Second a input data, a3…Third input data, b1…First output data, ba1…First a output data, c1…First training data, e1…First e input data, eb1…First eb input data, e2…Second e input data, eb2…Second eb input data, e3…Third e input data, f1…Second output data, fa1…Second a output data, g1…Second training data

Claims

1. A case component to be attached to the subject, A data acquisition unit housed in the case member acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A control unit that acquires exercise information of the subject based on the subject's exercise data corrected with the temperature data, and acquires temperature information based on the temperature data, The system includes a storage unit that stores a trained model that, when at least the exercise information and the temperature information are input, outputs the body temperature of the subject estimated based on the exercise information and the temperature information, The control unit determines the temperature risk of the subject based on the subject's body temperature output from the trained model. Exercise information acquisition device.

2. A location information acquisition unit that acquires location information of the subject regarding the location of the subject, A time acquisition unit that obtains the current time, A communication unit that communicates with external devices, and a equipped, The control unit causes the communication unit to communicate with the external device and obtains environmental information of the subject's location at the current time. The trained model, upon receiving the exercise information, temperature information, and environmental information, outputs the body temperature of the subject estimated based on the exercise information, temperature information, and environmental information. The motion information acquisition device according to claim 1.

3. A case component to be attached to the subject, A data acquisition unit housed in the case member acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A control unit that acquires exercise information of the subject based on the subject's exercise data corrected with the temperature data, and acquires temperature information based on the temperature data, The system includes a storage unit that stores a trained model that, when at least the exercise information and the temperature information are input, outputs the body temperature risk of the subject estimated based on the exercise information and the temperature information. Exercise information acquisition device.

4. A location information acquisition unit that acquires location information of the subject regarding the location of the subject, A time acquisition unit that obtains the current time, A communication unit that communicates with external devices, and a equipped, The control unit causes the communication unit to communicate with the external device and obtains environmental information of the subject's location at the current time. The trained model, upon receiving the exercise information, temperature information, and environmental information, outputs the estimated body temperature risk of the subject based on the exercise information, temperature information, and environmental information. The motion information acquisition device according to claim 3.

5. The aforementioned environmental information includes information regarding the temperature at the location of the subject, The motion information acquisition device according to claim 2 or claim 4.

6. The aforementioned environmental information includes information regarding humidity at the subject's location. The motion information acquisition device according to claim 5.

7. The control unit acquires weather information from the external device and estimates the amount of sunlight corresponding to the subject's location at the current time. The control unit inputs the estimated sunlight as environmental information to the trained model. The motion information acquisition device according to claim 6.

8. The system includes an installation information acquisition unit that acquires installation information regarding the mounting position of the case member, The memory unit stores a plurality of the learned models corresponding to the mounting position, The control unit selects a learned model from among a plurality of learned models that corresponds to the mounting information. The motion information acquisition device according to claim 7.

9. It includes a notification unit that notifies the result of the body temperature risk determination, The motion information acquisition device according to claim 8.

10. The temperature risk determination result determined by the control unit is notified to the subject's terminal used by the subject via an external communication device. The motion information acquisition device according to claim 8.

11. A control method for a motion information acquisition device comprising: a case member attached to a subject; and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, The steps include acquiring the temperature data in the motion information acquisition device, A step of acquiring the exercise data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model that is stored in a memory unit and outputs the body temperature of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, A step of determining the body temperature risk of the subject based on the subject's body temperature output from the trained model, A control method for the motion information acquisition device, comprising the above-mentioned device.

12. A control method for a motion information acquisition device comprising: a case member attached to a subject; and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, The steps include acquiring the temperature data in the motion information acquisition device, A step of acquiring the exercise data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model stored in a memory unit, which outputs the body temperature risk of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, The steps include obtaining the body temperature risk of the subject, which is output from the trained model, A control method for the motion information acquisition device, comprising the above-mentioned device.

13. A program for controlling a computer that constitutes a motion information acquisition device comprising a case member attached to a subject, and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model that is stored in a memory unit and outputs the body temperature of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, A step of determining the body temperature risk of the subject based on the subject's body temperature output from the trained model, A program that executes something.

14. A program for controlling a computer that constitutes a motion information acquisition device comprising a case member attached to a subject, and a data acquisition unit housed in the case member, which acquires temperature data within the case member and acquires motion data of the subject corrected with the temperature data, A step of acquiring exercise information of the subject based on the subject's exercise data corrected with the temperature data, A step of acquiring temperature information based on the aforementioned temperature data, The steps include inputting the exercise information and the temperature information into a trained model stored in a memory unit, which outputs the body temperature risk of the subject estimated based on the exercise information and the temperature information when at least the exercise information and the temperature information are input, The steps include obtaining the body temperature risk of the subject, which is output from the trained model, A program that executes something.

Images