WO2023058200A1

WO2023058200A1 - Fatigue degree calculation device, fatigue degree calculation method, and storage medium

Info

Publication number: WO2023058200A1
Application number: PCT/JP2021/037200
Authority: WO
Inventors: 驚文盧; 剛範辻川; 祐北出
Original assignee: 日本電気株式会社
Priority date: 2021-10-07
Filing date: 2021-10-07
Publication date: 2023-04-13

Abstract

A fatigue degree calculation device (1X) has primarily a fatigue degree calculation pattern acquisition means (14X) and a fatigue degree calculation means (17X). The fatigue degree calculation pattern acquisition means (14X) acquires a fatigue degree calculation pattern which is a calculation pattern for the degree of fatigue of a measurement subject, determined on the basis of a state of the measurement subject and measurement subject information relating to an environment. The fatigue degree calculation means (17X) calculates the degree of fatigue of the measurement subject on the basis of the fatigue degree calculation pattern.

Description

FATIGUE CALCULATION DEVICE, FATIGUE CALCULATION METHOD, AND STORAGE MEDIUM

The present disclosure relates to the technical field of fatigue level calculation devices, fatigue level calculation methods, and storage media for estimating fatigue.

A device or system for estimating the degree of fatigue of a subject is known. For example, in Patent Document 1, the higher one of the RPE value of the brain fatigue level and the RPE of the physical fatigue level is set as the RPE value of the overall fatigue level of the person to be measured, and the division is defined as the overall fatigue level. A method of determining fatigue is disclosed that classifies and determines the degree of fatigue.

JP 2017-063966 A

There are individual differences in the degree of fatigue depending on the person being measured, and such individual differences cannot be taken into account only with the biometric data generally used in calculating the degree of fatigue. Therefore, in order to accurately calculate the degree of fatigue, it is necessary to calculate the degree of fatigue in consideration of such individual differences.

In view of the problems described above, the main purpose of the present disclosure is to provide a fatigue level calculation device, a fatigue level calculation method, and a storage medium capable of suitably calculating the fatigue level.

One aspect of the fatigue level calculation device is
Fatigue level calculation pattern acquisition means for acquiring a fatigue level calculation pattern, which is a pattern for calculating the fatigue level of the subject determined based on subject information regarding the subject's condition or environment;
Fatigue level calculation means for calculating the fatigue level of the person to be measured based on the fatigue level calculation pattern;
It is a fatigue degree calculation device having

One aspect of the fatigue level calculation method is
the computer
Acquiring a fatigue level calculation pattern that is a pattern for calculating the fatigue level of the subject determined based on subject information regarding the subject's condition or environment,
calculating the fatigue level of the person to be measured based on the fatigue level calculation pattern;
It is a fatigue calculation method. Note that the "computer" includes any electronic device (it may be a processor included in the electronic device), and may be composed of a plurality of electronic devices.

One aspect of the storage medium is
Acquiring a fatigue level calculation pattern that is a pattern for calculating the fatigue level of the subject determined based on subject information regarding the subject's condition or environment,
A storage medium storing a program for causing a computer to execute a process of calculating the degree of fatigue of the person to be measured based on the fatigue degree calculation pattern.

According to the present disclosure, it is possible to accurately calculate the degree of fatigue of the subject.

1 shows a schematic configuration of a fatigue degree calculation system according to a first embodiment; 1 shows the hardware configuration of a fatigue level calculation device; It is an example of a functional block of a fatigue degree calculation device. It is a table showing a physical fatigue level calculation model, a mental fatigue level calculation model, and a general fatigue level calculation model linked to each fatigue level calculation pattern. 4 is an example of a flowchart executed by the fatigue level calculation device in the first embodiment; It is an example of a functional block of a processor according to a first modification. 1 shows a schematic configuration of a fatigue degree calculation system according to a second embodiment; FIG. 11 is a block diagram of a fatigue level calculation device according to a third embodiment; It is an example of the flowchart which a fatigue degree calculation apparatus in 3rd Embodiment performs.

Hereinafter, embodiments of a fatigue level calculation device, a fatigue level calculation method, and a storage medium will be described with reference to the drawings.

<First embodiment>
(1) System Configuration FIG. 1 shows a schematic configuration of a fatigue degree calculation system 100 according to the first embodiment. The fatigue level calculation system 100 mainly includes a fatigue level calculation device 1 , an input device 2 , an output device 3 , a storage device 4 and a sensor 5 .

The fatigue degree calculation device 1 performs processing related to calculation of the subject's fatigue degree. In this embodiment, as an example, fatigue levels are classified into mental fatigue levels and physical fatigue levels. Then, after calculating the degree of mental fatigue and the degree of physical fatigue, the fatigue degree calculation device 1 calculates the overall degree of fatigue, which is the degree of fatigue in which these are integrated, based on the degree of mental fatigue and the degree of physical fatigue. The fatigue level calculation device 1 performs data communication with the input device 2, the output device 3, and the sensor 5 via a communication network or direct wireless or wired communication. Then, based on the input signal "S1" supplied from the input device 2, the sensor signal "S3" supplied from the sensor 5, and the information stored in the storage device 4, the fatigue degree calculation device 1 perform fatigue level calculation processing. In addition, the fatigue level calculation device 1 generates an output signal “S2” based on the fatigue calculation result, and supplies the generated output signal S2 to the output device 3 .

The input device 2 is an interface that accepts manual input (external input) of information about each subject. The user who inputs information using the input device 2 may be the subject himself or herself, or may be a person who manages or supervises the activity of the subject. The input device 2 may be, for example, various user input interfaces such as a touch panel, buttons, keyboard, mouse, and voice input device. The input device 2 supplies the generated input signal S<b>1 to the fatigue level calculation device 1 . The output device 3 displays or outputs predetermined information based on the output signal S2 supplied from the fatigue level calculation device 1 . The output device 3 is, for example, a display, a projector, a speaker, or the like.

The sensor 5 measures the subject's biological signal and the like, and supplies the measured biological signal and the like to the fatigue level calculation device 1 as a sensor signal S3. In this case, the sensor signal S3 is any biological data (including vital information) such as heartbeat, brain wave, perspiration, hormone secretion, cerebral blood flow, blood pressure, body temperature, myoelectricity, electrocardiogram, respiration rate, etc. ). Moreover, the sensor 5 may be a device that analyzes the blood sampled from the person to be measured and outputs a sensor signal S3 indicating the analysis result. Further, the sensor 5 may be a device that performs physical measurements such as jumping for measuring the degree of physical fatigue. As such, sensor 5 may be any instrument or device for obtaining objective measurements. Hereinafter, an objective measured value is an arbitrary measured value (including the above-mentioned biological data, etc.) obtained by a measuring device without relying on human judgment or evaluation.

The storage device 4 is a memory that stores various information necessary for calculating various degrees of fatigue. The storage device 4 may be an external storage device such as a hard disk connected to or built into the fatigue level calculation device 1, or may be a storage medium such as a flash memory. Further, the storage device 4 may be a server device that performs data communication with the fatigue level calculation device 1 . Also, the storage device 4 may be composed of a plurality of devices.

The storage device 4 functionally has a subject information storage unit 41 and a fatigue level calculation model storage unit 42 .

The subject information storage unit 41 stores subject information. Subject information is information about the subject's condition or environment, and is information that affects the subject's physical or mental aspects. The measured person information is used to determine the fatigue level calculation pattern of the measured person. A first example of subject information is information (also referred to as "season information") about the season in which the subject is a sports player and/or the schedule of important games. call). A second example of subject information is information about the subject's health condition (also referred to as "subject's health information"). The health information of the person to be measured may be information related to a medical history, and if the person to be measured is an athlete, the current condition of the person to be measured (for example, "condition immediately after injury", "under treatment", " It may also be information on the state of injury classified as "after healing or not injured" or the like, or information on the amount of exercise. A third example of subject information is history information (also referred to as “exercise history information”) relating to exercise menus or training loads performed by the subject when the subject is an athlete. The amount of load may be, for example, a value obtained by converting the exercise amount of the person to be measured into a predetermined index such as calories, or may be a value represented by a physical quantity such as moving distance or acceleration.

It should be noted that the subject information is not limited to the examples described above, and may be arbitrary information regarding the subject's condition or environment that affects the subject's physical or mental aspects. Further, the subject information stored in the subject information storage unit 41 may be updated periodically according to the status of the subject. The subject information stored in the subject information storage unit 41 may be updated by the fatigue level calculation device 1 or by a device other than the fatigue level calculation device 1 .

The fatigue level calculation model storage unit 42 stores information related to the fatigue level calculation model, which is a model for calculating the fatigue level of the subject. As will be described later, the fatigue level calculation model is learned in advance for each type of fatigue level to be calculated and for each fatigue level calculation pattern determined by the fatigue level calculation device 1 . The parameters obtained by learning are stored in the fatigue level calculation model storage unit 42 . For example, when each fatigue level calculation model is a linear model, the fatigue level calculation model storage unit 42 stores parameter (weight) information of each linear model. The fatigue level calculation model is not limited to the linear model, and may be a regression model (statistical model) or a machine learning model other than the linear model. In these cases, the fatigue level calculation model storage unit 42 stores information on parameters necessary for constructing each fatigue level calculation model. For example, when each fatigue level calculation model is a model based on a neural network such as a convolutional neural network, the fatigue level calculation model storage unit 42 stores the layer structure, the neuron structure of each layer, the number and size of filters in each layer, and each filter information of various parameters such as the weight of each element of .

The configuration of the fatigue level calculation system 100 shown in FIG. 1 is an example, and various changes may be made to the configuration. For example, the input device 2 and the output device 3 may be integrally configured. In this case, the input device 2 and the output device 3 may be configured as a tablet terminal integrated with or separate from the fatigue level calculation device 1 . Moreover, the input device 2 and the sensor 5 may be configured integrally. Further, the fatigue level calculation device 1 may be configured by a plurality of devices. In this case, the plurality of devices constituting the degree-of-fatigue calculation device 1 exchange information necessary for executing pre-assigned processing among the plurality of devices.

(2) Hardware Configuration of Fatigue Degree Calculating Device FIG. 2 shows the hardware configuration of the fatigue degree calculating device 1 . The fatigue level calculation device 1 includes a processor 11, a memory 12, and an interface 13 as hardware. Processor 11 , memory 12 and interface 13 are connected via data bus 19 .

The processor 11 functions as a controller (arithmetic device) that controls the entire fatigue level calculation device 1 by executing a program stored in the memory 12 . The processor 11 is, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a TPU (Tensor Processing Unit). Processor 11 may be composed of a plurality of processors. Processor 11 is an example of a computer.

The memory 12 is composed of various volatile and nonvolatile memories such as RAM (Random Access Memory), ROM (Read Only Memory), and flash memory. The memory 12 also stores a program for executing the process executed by the fatigue level calculation device 1 . Note that part of the information stored in the memory 12 may be stored in one or more external storage devices that can communicate with the fatigue level calculation device 1, or may be stored in a storage medium detachable from the fatigue level calculation device 1. may be stored.

The interface 13 is an interface for electrically connecting the fatigue level calculation device 1 and other devices. These interfaces may be wireless interfaces such as network adapters for wirelessly transmitting and receiving data to and from other devices, or hardware interfaces for connecting to other devices via cables or the like.

Note that the hardware configuration of the fatigue level calculation device 1 is not limited to the configuration shown in FIG. For example, the fatigue level calculation device 1 may include at least one of the input device 2 and the output device 3 . Further, the fatigue level calculation device 1 may be connected to or built in a sound output device such as a speaker.

(3) Functional Blocks FIG. 3 is an example of functional blocks of the fatigue level calculation device 1 . The processor 11 of the fatigue level calculation device 1 functionally includes a fatigue level calculation pattern determination unit 14, a mental fatigue level calculation unit 15, a physical fatigue level calculation unit 16, a general fatigue level calculation unit 17, and an output control unit. a portion 18; In FIG. 3, the blocks that exchange data are connected by solid lines, but the combinations of blocks that exchange data are not limited to those shown in FIG. The same applies to other functional block diagrams to be described later.

The fatigue level calculation pattern determination unit 14 determines the fatigue level calculation pattern "β", which is identification information linked to the fatigue level calculation model to be used, based on the subject information stored in the subject information storage unit 41. do. The details of the determination method of the fatigue level calculation pattern β by the fatigue level calculation pattern determination unit 14 will be described later. The fatigue level calculation pattern determination unit 14 supplies the determined fatigue level calculation pattern β to the mental fatigue level calculation unit 15, the physical fatigue level calculation unit 16, and the overall fatigue level calculation unit 17, respectively.

The mental fatigue level calculation unit 15 compares the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14 with the subject's objective measurement value (eg, biological data such as heartbeat and electroencephalogram) represented by the sensor signal S3. Based on this, the degree of mental fatigue of the subject is calculated. In this case, the mental fatigue level calculation unit 15 calculates the mental fatigue level calculation model registered in the fatigue level calculation model storage unit 42 based on the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14 degree calculation model”), select the mental fatigue degree calculation model to be used. Then, the mental fatigue level calculation unit 15 acquires the subject's mental fatigue level as a score by inputting the subject's objective measurement value or its characteristic quantity into the selected mental fatigue level calculation model. In this case, the mental fatigue level calculation model is learned in advance so as to output the mental fatigue level of the subject when an objective measurement value or its feature value is input, and the learned parameter is the fatigue level calculation model It is stored in the storage unit 42 . The mental fatigue level calculation unit 15 supplies the calculated mental fatigue level to the overall fatigue level calculation unit 17 .

Note that the mental fatigue level calculation unit 15 uses the subjective measured value indicated by the input signal S1 (questionnaire results for measuring the mental fatigue level, etc.) instead of the subject's objective measured value indicated by the sensor signal S3. Based on this, the subject's degree of mental fatigue may be calculated. In this case, the mental fatigue level calculation model used by the mental fatigue level calculation unit 15 is set in advance so as to output the subject's mental fatigue level when, for example, the subjective measurement value indicated by the input signal S1 is input. It is learned, and the learned parameters are stored in the fatigue level calculation model storage unit 42 . In still another example, the mental fatigue level calculation unit 15 calculates the subject stored in the subject information storage unit 41 instead of or in addition to the objective measurement value of the subject represented by the sensor signal S3. The subject's degree of mental fatigue may be calculated based on the information (for example, information on the amount of practice). In this case, the mental fatigue level calculation model used by the mental fatigue level calculation unit 15 is pre-learned so as to output the mental fatigue level of the subject when the subject information is input, and the learned parameter is It is stored in the fatigue level calculation model storage unit 42 .

The physical fatigue level calculation unit 16 calculates the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14, and the subject's objective measurement value represented by the sensor signal S3 (for example, heart rate, jump measurement result, etc.). Based on, the degree of physical fatigue of the subject is calculated. In this case, the physical fatigue level calculation unit 16 uses the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14 to calculate the physical fatigue level calculation model ("physical fatigue The physical fatigue degree calculation model to be used is selected from among the physical fatigue degree calculation models. Then, the physical fatigue level calculation unit 16 acquires the physical fatigue level of the person being measured as a score by inputting the measured person's objective measurement value or its feature value into the selected physical fatigue level calculation model. In this case, the physical fatigue level calculation model is pre-learned so as to output the physical fatigue level of the person to be measured when an objective measurement value or its feature value is input, and the learned parameters are used in the fatigue level calculation model. It is stored in the storage unit 42 . The physical fatigue level calculation unit 16 supplies the calculated physical fatigue level to the overall fatigue level calculation unit 17 .

Note that the physical fatigue level calculation unit 16 uses the subjective measured value indicated by the input signal S1 (questionnaire results for measuring the physical fatigue level, etc.) instead of the subject's objective measured value indicated by the sensor signal S3. Based on this, the degree of physical fatigue of the subject may be calculated. In this case, the physical fatigue level calculation model used by the physical fatigue level calculation unit 16 is set in advance so as to output the physical fatigue level of the subject when, for example, the subjective measurement value indicated by the input signal S1 is input. It is learned, and the learned parameters are stored in the fatigue level calculation model storage unit 42 . In still another example, the physical fatigue level calculation unit 16 calculates the subject stored in the subject information storage unit 41 instead of or in addition to the objective measurement value of the subject represented by the sensor signal S3. The degree of physical fatigue of the person to be measured may be calculated based on information (for example, information on the amount of exercise). In this case, the physical fatigue level calculation model used by the physical fatigue level calculation unit 16 is pre-learned so as to output the physical fatigue level of the subject when the subject information is input, and the learned parameter is It is stored in the fatigue level calculation model storage unit 42 .

Also, the objective measurement value used by the mental fatigue level calculation unit 15 and the objective measurement value used by the physical fatigue level calculation unit 16 may be different. In this case, the mental fatigue level calculation unit 15 calculates the mental fatigue level using a specific type of objective measurement value suitable for calculating the mental fatigue level, and the physical fatigue level calculation unit 16 calculates the physical fatigue level Physical fatigue is calculated using a specific type of objective measurement suitable for

The overall fatigue level calculation unit 17 calculates the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14, the mental fatigue level calculated by the mental fatigue level calculation unit 15, and the physical fatigue calculated by the physical fatigue level calculation unit 16. The total fatigue level of the person to be measured is calculated based on the degree of fatigue. In this case, the general fatigue level calculation unit 17 calculates a general fatigue level calculation model registered in the fatigue level calculation model storage unit 42 based on the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14 (“total fatigue level Select the general fatigue degree calculation model to be used from the list. Then, the overall fatigue level calculation unit 17 acquires the overall fatigue level of the person to be measured by inputting the mental fatigue level and the physical fatigue level into the selected overall fatigue level calculation model. In this case, the general fatigue level calculation model is a model trained in advance so as to output the measurement subject's general fatigue level when the mental fatigue level and the physical fatigue level are input. The overall fatigue level calculator 17 supplies the calculated overall fatigue level to the output controller 18 .

The output control unit 18 displays the information on the overall fatigue level calculated by the overall fatigue level calculation unit 17 on the display unit, or outputs the information as sound using the sound output unit. In this case, the output control section 18 may, for example, determine the fatigue level of the subject and notify the determination level. In this case, the output control unit 18 compares the overall fatigue level of the person being measured with a threshold value stored in advance in the storage device 4 or the memory 12, so that when the person is in a state of high fatigue requiring attention or coping, It determines whether or not there is, and outputs the determination result. Note that a plurality of threshold values may be provided in order to classify the fatigue state in stages. In addition to the general fatigue level, the output control unit 18 may also output information regarding the mental fatigue level and the physical fatigue level.

Note that each component of the fatigue level calculation pattern determination unit 14, the mental fatigue level calculation unit 15, the physical fatigue level calculation unit 16, the overall fatigue level calculation unit 17, and the output control unit 18 described with reference to FIG. can be realized by executing the program. Further, each component may be realized by recording necessary programs in an arbitrary nonvolatile storage medium and installing them as necessary. Note that at least part of each of these components may be realized by any combination of hardware, firmware, and software, without being limited to being implemented by program software. Also, at least part of each of these components may be implemented using a user-programmable integrated circuit, such as an FPGA (Field-Programmable Gate Array) or a microcontroller. In this case, this integrated circuit may be used to implement a program composed of the above components. Also, at least part of each component may be configured by an ASSP (Application Specific Standard Produce), an ASIC (Application Specific Integrated Circuit), or a quantum processor (quantum computer control chip). Thus, each component may be realized by various hardware. The above also applies to other embodiments described later. Furthermore, each of these components may be realized by cooperation of a plurality of computers using, for example, cloud computing technology. The above also applies to other embodiments described later.

(4) Selection of Fatigue Level Calculation Model FIG. 4 is a table showing a physical fatigue level calculation model, a mental fatigue level calculation model, and a general fatigue level calculation model linked to each fatigue level calculation pattern β. Hereinafter, "n" (n is an integer equal to or greater than 2) represents the total number of fatigue level calculation patterns β. For convenience of explanation, each fatigue level calculation pattern β is assumed to be a serial number from 1 to n.

As shown in FIG. 4, each fatigue level calculation pattern β is associated with a physical fatigue level calculation model, a mental fatigue level calculation model, and a general fatigue level calculation model. Here, the models "P1" to "Pn" are physical fatigue level calculation models, the models "M1" to "Mn" are mental fatigue level calculation models, and the models "T1" to "Tn" are general This is a fatigue calculation model. Then, each fatigue level calculation model is learned for each corresponding fatigue level calculation pattern β.

For example, the model P1 is learned using the subject's objective measured value when the fatigue level calculation pattern β is "β=1" and the correct physical fatigue level (for example, a score based on a questionnaire). . Similarly, the model M1 is learned using the subject's objective measured value when the fatigue level calculation pattern β is "β=1" and the correct mental fatigue level. In addition, the model T1 is learned using the subject's physical fatigue level and mental fatigue level when the fatigue level calculation pattern β is "β=1", and the correct total fatigue level. Each fatigue level calculation model linked to a fatigue level calculation pattern β other than "β=1" is similarly learned. The parameters and the like obtained by these learnings are stored in the fatigue degree calculation model storage unit 42 . Note that the physical fatigue level calculation models P1 to Pn do not all need to be different, and at least some of them may be the same model. The same applies to the mental fatigue degree calculation models M1 to Mn.

Next, the method of determining the fatigue degree calculation pattern β based on the subject information will be explained.

In the first example, if the subject information is season information, the fatigue level calculation pattern determination unit 14 determines whether the subject is in season at the time of measurement based on the season information and the measurement date and time. , the fatigue degree calculation pattern β is determined based on the determination result. In this case, the total pattern number n is 2, and the fatigue level calculation pattern β is, for example, "1" during the season and "2" during the off-season. By further subdividing the period into "just before the season," "during the season," "just after the off-season," and "other periods," the total number of patterns n can be 3 or more (4 in this example). The fatigue degree calculation pattern β may be designed so that

In the second example, when the subject information is subject health information, the fatigue level calculation pattern determination unit 14 calculates the degree of injury of the subject at the time of measurement based on the subject health information and the measurement date and time. It is determined whether the state is "immediately after injury", "under treatment", or "after recovery from injury or no injury", and fatigue degree calculation pattern β is calculated based on the determination result. decide. In this case, the total number of patterns n is three. The total pattern number n may be set to 2 by judging whether or not the subject is injured at the time of measurement. You may make it become.

In the third example, when the subject information is practice history information, the fatigue level calculation pattern determination unit 14 performs the exercise menu or exercise load within a predetermined time (predetermined number of days) at the time of measurement. A fatigue level calculation pattern β is determined. In this case, for example, correspondence information indicating the correspondence relationship between each fatigue level calculation pattern β and the type (and the number of executions) of the corresponding exercise menu and/or the amount of exercise load is stored in the storage device 4 or the memory 12. there is Then, the fatigue level calculation pattern determining unit 14 determines the fatigue level calculation pattern β from the exercise history information by referring to the correspondence information. In this case, the total number of patterns n may be any number equal to or greater than 2.

It should be noted that the fatigue level calculation pattern determination unit 14 may determine the fatigue level calculation pattern β based on a plurality of pieces of information among season information, subject health information, and practice history information. In this case, for example, the fatigue level calculation pattern determining unit 14 determines the fatigue level calculation pattern β based on the subject's condition and/or the environment at the time of measurement represented by these pieces of information. In this case, for example, correspondence information indicating the correspondence relationship between each fatigue level calculation pattern β and the corresponding subject's condition and/or environment is stored in the storage device 4 or the memory 12, and the fatigue level calculation pattern determination unit 14 determines the corresponding fatigue level calculation pattern β by referring to the correspondence information.

As described above, the fatigue level calculation pattern determination unit 14 determines the fatigue level calculation pattern β based on the subject information, which is information that affects the subject's physical or mental aspects. As a result, the fatigue level calculation pattern determination unit 14 can cause the mental fatigue level calculation unit 15, the physical fatigue level calculation unit 16, and the general fatigue level calculation unit 17 to use an appropriate fatigue level calculation model.

(5) Comprehensive Fatigue Computation Example Next, a specific example of computation of the comprehensive fatigue level by the comprehensive fatigue level computation unit 17 will be described.

Assuming that the overall fatigue level calculated by the overall fatigue level calculation unit 17 is "Y", the mental fatigue level is "X1", the physical fatigue level is "X2", and the function representing the overall fatigue level calculation model is "G", the following formula holds.
Y=G(X1, X2, β)
Here, as an example, the function G shall be a multiple regression model. In this case, assuming that the fatigue level calculation pattern β is i (i=1 to n), the overall fatigue level Y _i is expressed by the following equation (1).
Y _i =w1 _i X1 _i +w2 _i X2 _i +w0 _i (1)
“w0 _i ”, “w1 _i ”, and “w2 _i ” are parameters to be obtained by learning, and represent parameters when the fatigue level calculation pattern β is “β=i”. For example, assume that n=2, "β=1" corresponds to the on-season, and "β=2" corresponds to the off-season. In this case, a plurality of sets of the mental fatigue level X1, the physical fatigue level X2, and the overall fatigue level Y measured within a certain period when the season is on are used as learning data sets, and "w0 ₁ ", "w1 ₁ ", " w2 ₁ ” is learned. In addition, a plurality of sets of mental fatigue X1, physical fatigue X2, and general fatigue Y measured in a certain period during the off-season are used as learning data sets, and are set to “w0 ₂ ”, “w1 ₂ ”, “w2 ₂ ” is learned. These parameters are stored in the fatigue level calculation model storage unit 42 . In addition, for example, in the collection of the learning data set, for example, the mental fatigue level X1 is a fatigue score obtained by a POMS (Profile of Mood States) questionnaire, and the physical fatigue level X2 is measured by, for example, a jump test. It is a score based on the maximum speed, and the overall fatigue level Y is a score based on the analysis results of the subject's saliva, for example.

Then, when calculating the overall fatigue level Y using the formula (1), the overall fatigue level calculation unit 17, based on the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14, each of the formula (1) Set parameters. Then, the general fatigue level calculation unit 17 sets the mental fatigue level calculated by the mental fatigue level calculation part 15 as X1, the physical fatigue level calculated by the physical fatigue level calculation part 16 as X2, and sets each parameter by the formula (1 ), the overall fatigue level Y is calculated.

Note that the overall fatigue level calculation unit 17 may calculate the overall fatigue level based on a plurality of scores representing the mental fatigue level and a plurality of scores representing the physical fatigue level. Here, the plurality of mental fatigue level scores and the plurality of physical fatigue level scores may be scores calculated by the mental fatigue level calculation unit 15 and the physical fatigue level calculation unit 16 within a predetermined period from the time of measurement. , a score calculated by a plurality of mental fatigue degree methods and a plurality of physical fatigue degree calculation methods.

In this case, if the index of the set of multiple mental fatigue levels and physical fatigue levels to be used is "j" (j = 1, ... m), the total fatigue level Y _i corresponding to "β = i" is as follows: It is represented by Formula (2).
Y _i =Σ _j=1,...m (w1 _ij X1 _ij +w2 _ij X2 _ij )+w0 _i (2)
Parameters corresponding to “w0 _i ”, “w1 _ij ”, and “w2 _ij ” are obtained in advance by learning and stored in the fatigue level calculation model storage unit 42 . According to the formula (2), the overall fatigue level calculation unit 17 can accurately calculate the overall fatigue level Y based on a plurality of sets of mental fatigue levels and physical fatigue levels.

(6) Processing Flow FIG. 5 is an example of a flow chart executed by the fatigue level calculation device 1 in the first embodiment. The fatigue level calculation device 1 repeatedly executes the process of the flowchart shown in FIG.

First, the fatigue level calculation device 1 acquires measured values (objective measured values or subjective measured values) and measured person information about the subject (step S11). In this case, the fatigue level calculation device 1 receives the input signal S1 or the sensor signal S3 via the interface 13 to obtain the measured values used for calculating the mental fatigue level and the physical fatigue level. In addition, the fatigue level calculation device 1 extracts subject information corresponding to the subject from the subject information storage unit 41 .

Next, the fatigue level calculation pattern determination unit 14 of the fatigue level calculation device 1 determines the fatigue level calculation pattern β based on the subject information (step S12). Then, the fatigue level calculation device 1 calculates the mental fatigue level and the physical fatigue level (step S13). In this case, the mental fatigue level calculation unit 15 calculates the mental fatigue level based on the mental fatigue level calculation model linked to the fatigue level calculation pattern β determined in step S12 and the measurement value of the subject acquired in step S11. , and the physical fatigue level calculation unit 16 calculates physical fatigue based on the physical fatigue level calculation model linked to the fatigue level calculation pattern β determined in step S12 and the measurement value of the subject acquired in step S11. Calculate degrees.

Next, the fatigue level calculation device 1 calculates the overall fatigue level (step S14). In this case, the overall fatigue level calculation unit 17 calculates the overall fatigue level based on the overall fatigue level calculation model based on the fatigue level calculation pattern β determined in step S12 and the mental fatigue level and physical fatigue level calculated in step S13. Calculate degrees. Then, the output control unit 18 outputs information about the calculated fatigue level (step S15). In this case, the output control unit 18 notifies the subject or the subject's manager of the subject's fatigue state by, for example, displaying or sound-outputting the calculation result of the overall fatigue level.

(7) Modification Next, a modification suitable for the first embodiment will be described. The following modifications may be applied in combination.

(First modification)
Instead of calculating the overall fatigue level based on the mental fatigue level and the physical fatigue level, the overall fatigue level calculation unit 17 may calculate the overall fatigue level based on the measured value of the subject.

FIG. 6 is an example of functional blocks of the processor 11 according to the first modified example. In the example of FIG. 6, the general fatigue level calculation unit 17 acquires the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14 and the input signal S1 or the sensor signal S3. Then, the general fatigue degree calculation unit 17 selects a general fatigue degree calculation model based on the fatigue degree calculation pattern β, and applies the measurement value of the subject indicated by the input signal S1 or the sensor signal S3 to the selected general fatigue degree calculation model. By inputting, the overall fatigue level is calculated. In this case, the general fatigue level calculation model is a model trained in advance so as to output the general fatigue level of the subject when the subject's measurement value or its feature quantity is input.

In this way, the fatigue level calculation device 1 may calculate the overall fatigue level without calculating the physical fatigue level and the mental fatigue level. Further, the fatigue level calculation device 1 may calculate the overall fatigue level using either the physical fatigue level or the mental fatigue level. In this case, the general fatigue level calculation unit 17 calculates the overall fatigue level calculation model linked to the fatigue level calculation pattern β determined by the fatigue level calculation pattern determination unit 14 and the mental fatigue level calculation unit 15 or the physical fatigue level calculation unit 16 Based on the measured fatigue level (and measured value of the subject), the total fatigue level is calculated. In this way, the fatigue level calculation device 1 calculates at least one of the physical fatigue level and the mental fatigue level, and calculates the overall fatigue level based on at least one of the physical fatigue level and the mental fatigue level and the fatigue level calculation pattern β. can be calculated.

(Second modification)
Fatigue is not limited to categories of physical and mental fatigue.

Alternatively, for example, fatigue may be classified into central fatigue and peripheral fatigue. In this case, central fatigue indicates fatigue felt by the brain due to mental activity, and peripheral fatigue indicates fatigue in the periphery other than the central. In this case, the fatigue level calculation device 1 calculates the central fatigue level and the peripheral fatigue level by the same process as the mental fatigue level and the physical fatigue level calculation process, and calculates the central fatigue level and peripheral fatigue level. , and the overall fatigue level calculation model linked to the fatigue level calculation pattern β, the overall fatigue level that integrates central fatigue and peripheral fatigue is calculated. In this case, instead of the mental fatigue level calculation model and the physical fatigue level calculation model, the fatigue level calculation model storage unit 42 stores a central fatigue level calculation model and a peripheral fatigue level calculation model linked to each fatigue level calculation pattern β. Calculation model parameters are stored.

In another example, fatigue may be categorized by its origin. In this case, for example
Fatigue due to pure exercise (1st degree of fatigue)
Mental fatigue due to stress in human relationships (second level of fatigue)
Fatigue caused by the environment such as heat and cold (third degree of fatigue)
In this case, the fatigue level calculation device 1 calculates the overall fatigue level that integrates the three fatigue levels described above based on these three fatigue levels and the overall fatigue level calculation model linked to the fatigue level calculation pattern β. . In addition, the fatigue level calculation device 1 also calculates these three fatigue levels by the same processing as the mental fatigue level and physical fatigue level calculation processes. In this case, instead of the mental fatigue level calculation model and the physical fatigue level calculation model, the fatigue level calculation model storage unit 42 stores the parameters of the three fatigue level calculation models linked to each fatigue level calculation pattern β. It is

As described above, the fatigue level calculation device 1 may calculate the overall fatigue level based on fatigue levels based on various classifications. The degree of mental fatigue, the degree of physical fatigue, the degree of central fatigue, the degree of peripheral fatigue, and the first to third fatigue levels are examples of "classified fatigue levels." Further, the mental fatigue level calculation unit 15 and the physical fatigue level calculation unit 16 are examples of the "classified fatigue level calculation means".

<Second embodiment>
FIG. 7 shows a schematic configuration of a fatigue level calculation system 100A in the second embodiment. A fatigue degree calculation system 100A according to the second embodiment is a server-client model system, and a fatigue degree calculation device 1A functioning as a server device performs the processing of the fatigue degree calculation device 1 in the first embodiment. Henceforth, about the same component as 1st Embodiment, the same code|symbol is attached suitably, and the description is abbreviate|omitted.

As shown in FIG. 7, the fatigue level calculation system 100A mainly includes a fatigue level calculation device 1A that functions as a server, a storage device 4 that stores data necessary for fatigue level calculation processing, and a terminal device that functions as a client. 8 and a management device 9 for managing personal information of a plurality of persons including the subject. The fatigue level calculation device 1A and the terminal device 8 perform data communication via the network 7. FIG.

The terminal device 8 is a terminal having an input function, a display function, and a communication function, and functions as the input device 2 and the output device 3 shown in FIG. The terminal device 8 may be, for example, a personal computer, a tablet terminal, a PDA (Personal Digital Assistant), or the like. The terminal device 8 receives an objective measured value of the subject output by the sensor 5 (that is, information corresponding to the sensor signal S3 in FIG. 1) or a subjective measured value based on user input (that is, the input signal S1 in FIG. ), etc., to the fatigue level calculation device 1A.

The fatigue degree calculation device 1A has the same hardware configuration as the fatigue degree calculation device 1 shown in FIG. 2, and the processor 11 of the fatigue degree calculation device 1A has the functional blocks shown in FIG. Then, the fatigue level calculation device 1A receives information obtained from the input device 2 and the sensor 5 by the fatigue level calculation device 1 shown in FIG. Further, the fatigue level calculation device 1A transmits an output signal indicating information about the fatigue level of the person to be measured to the terminal device 8 via the network 7 based on a request from the terminal device 8 . In addition, when the storage device 4 does not store the subject information corresponding to the subject, the fatigue level calculation apparatus 1A receives information about the subject such as past history from the management device 9 via the network 7. Information is received, and the fatigue level calculation pattern β is determined based on the received subject information.

As described above, the fatigue level calculation device 1A according to the second embodiment can suitably present information about the fatigue level to the user of the terminal device 8.

<Third Embodiment>
FIG. 8 is a block diagram of the fatigue level calculation device 1X according to the third embodiment. The fatigue level calculation device 1X mainly includes fatigue level calculation pattern acquisition means 14X and fatigue level calculation means 17X. Note that the fatigue level calculation device 1X may be configured by a plurality of devices.

The fatigue level calculation pattern acquisition means 14X acquires a fatigue level calculation pattern, which is a pattern for calculating the fatigue level of the subject determined based on the subject information regarding the subject's condition or environment. In this case, the fatigue level calculation pattern acquisition means 14X may determine the fatigue level calculation pattern based on the subject information, and the fatigue level calculation pattern determined in advance based on the subject information and linked to the subject. , a storage device, or the like. The fatigue level calculation pattern acquisition unit 14X can be, for example, the fatigue level calculation pattern determination unit 14 in the first embodiment (including modifications, the same applies hereinafter) or the second embodiment.

The fatigue level calculation means 17X calculates the fatigue level of the subject based on the fatigue level calculation pattern. The fatigue level in this case may be a physical fatigue level, a mental fatigue level, a general fatigue level, or any other fatigue level. The fatigue degree calculation means 17X can be, for example, the mental fatigue degree calculation unit 15, the physical fatigue degree calculation unit 16, or the overall fatigue degree calculation unit 17 in the first embodiment or the second embodiment.

FIG. 9 is an example of a flowchart executed by the fatigue level calculation device 1X in the third embodiment. First, the fatigue level calculation pattern acquisition means 14X acquires a fatigue level calculation pattern, which is a pattern for calculating the fatigue level of the subject determined based on subject information regarding the subject's condition or environment (step S21). . The fatigue level calculation means 17X calculates the fatigue level of the subject based on the fatigue level calculation pattern (step S22).

The fatigue level calculation device 1X according to the third embodiment can accurately calculate the fatigue level of the subject.

Note that in each of the above-described embodiments, the program can be stored using various types of non-transitory computer readable media and supplied to a processor or the like that is a computer. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic storage media (e.g., floppy disks, magnetic tapes, hard disk drives), magneto-optical storage media (e.g., magneto-optical discs), CD-ROMs (Read Only Memory), CD-Rs, CD-R/W, semiconductor memory (eg mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)). The program may also be delivered to the computer on various types of transitory computer readable medium. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can deliver the program to the computer via wired channels, such as wires and optical fibers, or wireless channels.

Although the present invention has been described with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. That is, the present invention naturally includes various variations and modifications that a person skilled in the art can make according to the entire disclosure including the scope of claims and technical ideas. In addition, the disclosures of the cited patent documents and the like are incorporated herein by reference.

1, 1A, 1X Fatigue calculation device 2 Input device 3 Output device 4 Storage device 5 Sensor 8 Terminal device 100, 100A Fatigue calculation system

Claims

Fatigue level calculation pattern acquisition means for acquiring a fatigue level calculation pattern, which is a pattern for calculating the fatigue level of the subject determined based on subject information regarding the subject's condition or environment;
Fatigue level calculation means for calculating the fatigue level of the person to be measured based on the fatigue level calculation pattern;
A fatigue degree calculation device having
The fatigue level calculation device according to claim 1, wherein the fatigue level calculation means selects a fatigue level calculation model linked to the fatigue level calculation pattern, and calculates the fatigue level based on the selected fatigue level calculation model.
The fatigue level calculation means is
A classified fatigue level calculation means for calculating a classified fatigue level, which is the classified fatigue level of the subject, based on the subject's objective measurement value or subjective measurement value;
Comprehensive fatigue level calculation means for calculating a comprehensive fatigue level, which is the overall fatigue level of the subject, based on the classified fatigue level and the fatigue level calculation pattern;
The fatigue level calculation device according to claim 1 or 2, comprising:
The classified fatigue level calculation means calculates the classified fatigue level based on the objective measurement value or the subjective measurement value and the classification fatigue level calculation model linked to the fatigue level calculation pattern,
4. The fatigue level calculation according to claim 3, wherein the overall fatigue level calculation means calculates the overall fatigue level based on the classified fatigue level and the overall fatigue level calculation model linked to the fatigue level calculation pattern. Device.
The classified fatigue level calculation means calculates at least one of a mental fatigue level that is the mental fatigue level of the person to be measured and a physical fatigue level that is the physical fatigue level of the person to be measured, based on the classified fatigue level. calculated as
5. The fatigue level calculation according to claim 3, wherein the overall fatigue level calculation means calculates the overall fatigue level based on at least one of the mental fatigue level or the physical fatigue level and the fatigue level calculation pattern. Device.
The fatigue level calculation pattern acquisition means obtains the above The fatigue level calculation device according to any one of claims 1 to 5, which determines a fatigue level calculation pattern.
The fatigue degree calculation device according to any one of claims 1 to 6, further comprising output control means for displaying or sound-outputting information on the degree of fatigue.
the computer
Acquiring a fatigue level calculation pattern that is a pattern for calculating the fatigue level of the subject determined based on subject information regarding the subject's condition or environment,
calculating the fatigue level of the person to be measured based on the fatigue level calculation pattern;
Fatigue calculation method.
Acquiring a fatigue level calculation pattern that is a pattern for calculating the fatigue level of the subject determined based on subject information regarding the subject's condition or environment,
A storage medium storing a program for causing a computer to execute a process of calculating the degree of fatigue of the subject based on the fatigue degree calculation pattern.