JP6791361B2 - Information processing equipment, methods and programs - Google Patents

Description

The present invention relates to an information processing device, a method and a program.

With the declining birthrate and aging population, the working-age population is declining and the labor shortage is advancing, and the need to maintain and improve intellectual productivity, which is difficult to replace with robots and artificial intelligence (AI), is being called for. However, it is known that due to drowsiness (low arousal state) and stress (high arousal state), the intellectual ability of an individual cannot be fully exerted, and intellectual productivity decreases.

In various workplaces such as companies and government offices, it is necessary to estimate the arousal level accompanied by the decrease in intellectual productivity in order to control the environment so as to prevent the decrease in intellectual productivity.

Various methods for estimating drowsiness (low arousal state) and stress (high arousal state) from biological information (for example, blinking, heartbeat, brain waves, etc.) have been proposed. For example, a method has been proposed in which drowsiness calculated by evaluating facial expressions by a plurality of people is taken as the correct answer and estimated. Further, a method of estimating the stress state by applying stress step by step by the Stroop test is also known.

Patent Document 1 discloses a work arousal level estimation device that enables selection of an appropriate model according to the state of an estimation target person, thereby enabling highly accurate estimation in consideration of the individual state. In this device, the feature amount indicating the heart rate variability during the work of the user whose pre-data is to be measured and the information regarding the information processing ability during the work of the plurality of users are associated with each other at the same time in advance. It has a pre-database to store data. The feature amount indicating the heart rate variability during work of the user to be estimated is calculated, and the feature amount indicating the calculated heart rate variability is used as the estimation target based on the calculated feature amount and the prior data stored in the prior database. Estimate the information processing ability value of the user. Preliminary data A regression model is created using the feature quantity indicating the heart rate variability during work of the user to be measured as an explanatory variable and the work performance of the user at the same time as the objective variable, and is calculated in the process of creating the regression model. The regression coefficient is stored in the prior database in association with the feature amount indicating the heart rate variability as the explanatory variable. Then, the ability estimation means reads the regression coefficient corresponding to the feature amount indicating the calculated heart rate variability from the prior database, and the estimation target is obtained from the read regression coefficient and the calculated feature amount of the heart rate variability. Calculate the estimated value of the information processing ability value of the user.

Japanese Unexamined Patent Publication No. 2016-137138

An analysis of related technologies is given below.

With the above-mentioned related techniques, it is difficult to estimate the arousal level accompanied by a decrease in intellectual ability with a desired accuracy. The reason is that it lacks the means to provide a correspondence between intellectual ability and alertness.

The present invention has been devised in view of the above problems, and an object of the present invention is to provide a device, a method, and a program capable of estimating an arousal level due to, for example, a decrease in intellectual ability.

According to one embodiment of the present invention, the first method of generating a learning model by using the biological information during the intellectual ability test in a plurality of different awakening states of the user to be measured and the intellectual ability test result. An information processing device including the above means and a second means for estimating the arousal degree using the learning model with respect to the biological information acquired from the user to be estimated is provided.

According to another embodiment of the present invention, it is a method of estimating the arousal degree based on the biological information by a computer, and the biological information during the test of the intellectual ability of the user to be measured in a plurality of different arousal states and the above. Provided is an arousal level estimation method that generates an arousal level estimation model based on the results of an intellectual ability test and estimates the arousal level using the arousal level estimation model for biological information acquired from a user to be estimated. Will be done.

According to another embodiment of the present invention, an alertness estimation model is based on a computer based on biological information during a test of intellectual ability of a user to be measured in a plurality of different arousal states and the result of the intellectual ability test. Is provided, and a program for executing the first process of generating the arousal level and the second process of estimating the arousal level using the arousal level estimation model for the biological information acquired from the user to be estimated. ..

According to still another embodiment of the present invention, a computer-readable recording medium (for example, RAM (Random Access Memory), ROM (Read Only Memory), or EEPROM (Electrically Erasable and Programmable ROM)) that stores the program of the above embodiment. ) And other semiconductor storage, HDD (Hard Disk Drive), CD (Compact Disc), DVD (Digital Versatile Disc) and other non-transitory computer readable recording media (non-transitory computer readable recording medium) are provided. ..

According to the present invention, it is possible to estimate the arousal level due to, for example, a decrease in intellectual ability.

It is a figure explaining the structure of the 1st Embodiment of this invention. It is a figure explaining the example 1st Embodiment of this invention. It is a figure which illustrates the structural example of the 1st Embodiment of this invention. It is a figure which illustrates the structural example of the 1st Embodiment of this invention. It is a flow chart explaining the operation of the 1st Embodiment of this invention. It is a figure explaining the structure of the 2nd Embodiment of this invention. It is a figure explaining the structure of the 3rd Embodiment of this invention.

An exemplary embodiment of the present invention will be described.

<Embodiment 1>
FIG. 1 is a diagram for explaining the configuration of an exemplary first embodiment of the present invention. Referring to FIG. 1, the information processing apparatus 10 according to the first exemplary embodiment generates an arousal level estimation model as a configuration for estimating an arousal level accompanied by at least a decrease in intellectual ability based on biological information. The means (part) 11 and the arousal level estimation means (part) 12 are provided. The information processing device 10 may be referred to as, for example, an "alertness estimation device" by using a part of its function. In addition, in FIG. 1 and the like, the notation of the alertness estimation model generation means (part) 11 may be such that the "means" of the alertness estimation model generation means 11 may be configured as a unit, that is, an alertness estimation model generation unit. Represents. Similarly, the alertness estimation means (part) 12 indicates that the alertness estimation means 12 may be configured as an alertness estimation unit.

The arousal level estimation model generation means (part) 11 estimates the arousal level based on the biological information during the intellectual ability test in a plurality of different arousal states of the user to be measured and the test result of the intellectual ability. The model 131 is generated and stored in the storage device 13.

The arousal level estimation means (unit) 12 estimates the arousal level with respect to the biological information acquired from the user to be estimated by using the arousal level estimation model 131 stored in the storage device 13. If the storage device 13 can pass the alertness estimation model 131 generated by the alertness estimation model generation means (part) 11 to the alertness estimation means (part) 12, the alertness estimation model generation means (part) 11 or the arousal degree estimation means (part) 12 may be provided in the configuration. The arousal level estimation model generation means (part) 11 and the arousal level estimation means (part) 12 may be realized as separate node devices connected via, for example, a communication network. In this case, the information processing device 10 may be referred to as an information processing system (or "alertness estimation system" or the like).

FIG. 2 is a diagram illustrating an exemplary first embodiment of the present invention, schematically showing a biological information sensor worn by a user and a measurement environment.

With reference to FIG. 2, in the alertness estimation model generation phase, the electroencephalograph 20-1 may be attached to the user 1 to be measured. That is, by measuring the electroencephalogram of the user 1 with the electroencephalograph 20-1, the arousal state of the user 1 is monitored, and a plurality of different awakening states of the user 1 (for example, a low arousal state, a high arousal state, an intermediate state, etc.) ) May be determined. For example, in a low arousal state, it is known that brain waves represent the degree of arousal, such as the continuity of α waves in the back of the head is not recognized, the frequency becomes slower, and the amplitude decreases. In addition, FIG. 2 exemplifies an electroencephalograph 20-1 having a configuration in which an electroencephalogram is picked up by simply wearing a sensor band on the head of the user 1. For example, 19 electroencephalograms are taken according to the International 10/20 Law. It may be a cap electrode for electroencephalogram measurement in which the electrode of is arranged. The electroencephalograph 20-1 may be configured to convert the detected electroencephalogram into a digital signal and transmit it to the information processing device 10 by wireless communication such as Bluetooth (registered trademark). Alternatively, the measurement result may be transmitted to the information processing device 10 by wired communication such as USB (Universal Serial Bus), RS232C, or an optical cable. In addition, another biological information sensor may be used instead of the electroencephalograph 20-1 to discriminate a plurality of different arousal states of the user 1 to be measured.

Although not particularly limited, the heart rate sensor 20-2 is exemplified by, for example, a wristwatch type, but may be an arm-wrap type. The wristwatch-type heart rate sensor 20-2 converts the sensed heart rate data into digital data and transmits it to the information processing device 10 by wireless communication such as Bluetooth (registered trademark).

The camera 20-3 on the front of the display of the personal computer 30 is used to capture the face image of the user 1 and analyze the image data to detect blinks and the like. Alternatively, a glasses-type sensor 20-4 capable of detecting the angle of sight, the speed of blinking, and the like may be used. The image data captured by the camera 20-3 may be transmitted from the personal computer 30 to the information processing device 10 by wire or wirelessly such as USB or Ethernet (registered trademark). The glasses-type sensor 20-4 transmits the sensed blink data and the like to the information processing device 10 by wireless communication such as Bluetooth (registered trademark). The camera 20-3 may be used not only for detecting blinks but also for monitoring the posture and body movement of the user 1.

Alternatively, the microwave biological information sensor 20-5 may be arranged at a position away from the user 1 to sense the heartbeat and respiration of the user 1 in a non-contact manner. Alternatively, a sheet-type biometric information sensor 20-6 that is arranged on a chair and senses the heartbeat, respiration, and body movement of the user 1 sitting on the chair may be provided. The sensors 20-5 and 20-6 convert the sensed heartbeat data into digital data and transmit it to the information processing device 10 by wired or wireless communication. Alternatively, the pulse signal may be sensed by using the ear clip type photoelectric pulse wave sensor 20-7 and transmitted to the information processing apparatus 10 by wireless communication such as Bluetooth (registered trademark).

In FIG. 2, the configuration may include any one of the sensors 20-2, 20-5, 20-6, 20-7, the camera 20-3 functioning as a blink sensor, and the sensor 20-4. ..

In the arousal level estimation model generation phase, the information processing apparatus 10 acquires the brain wave of the user 1 to be measured working on the personal computer 30 by using, for example, an electroencephalograph 20-1, and determines the arousal state of the user 1 to be measured. May be done. Further, the awakening state may be determined from the facial expression of the user 1. Further, the awakening state may be determined by the subjectivity of the user 1. When it is detected that the awake state of the user 1 to be measured is, for example, a low arousal state, the user 1 to be measured undergoes an intellectual ability test. At that time, the biometric information of the user 1 to be measured during the execution of the intellectual ability test is acquired by, for example, a biometric information sensor (at least one of 20-2 to 20-7 in FIG. 2). Here, as described above, the determination of a plurality of different arousal states of the user 1 to be measured is performed by body movement sensed by, for example, sensors 20-2 to 20-7 instead of the electroencephalograph 20-1. , Posture, heartbeat, respiration data, and other sensing results.

In the arousal level estimation phase, the user 1 to be estimated acquires biological information, for example, while actually working. For this reason, the electroencephalograph 20-1 that imposes a heavy burden on the user 1 to be estimated is not used as the biometric information sensor, and the wristwatch-type heart rate sensor 20-2 and the sensor 20-4 that can work in a natural posture are not used. At least one such as ~ 20-7 is used. The estimation target user 1 performs the actual work with the electroencephalograph 20-1 of FIG. 2 removed. The user 1 to be measured and the user 1 to be estimated may be the same person or different people.

Note that FIG. 2 shows an example in which the information processing device 10 is arranged as a device different from the personal computer 30 for the sake of simplicity of explanation, but the information processing device 10 is mounted on the personal computer 30. May be good. Alternatively, wireless communication with the biometric information sensor by Bluetooth (registered trademark) or the like is performed by the personal computer 30, and analysis of biometric information received by the personal computer 30 is performed by a server (not shown) to which the personal computer 30 is connected. May be good.

FIG. 3 is a diagram illustrating a configuration example of the alertness estimation model generation means (part) 11 of FIG. The arousal level estimation model generation means (unit) 11 includes an awakening state monitor unit 111, an intellectual ability test execution control unit 112, a biological information acquisition unit 113, a normalization unit 114, a feature amount extraction unit 115, and an estimation model learning unit 116. I have. The biometric information sensors 20A and 20B include biometric information detection units 201A and 201B, and communication control units 202A and 202B, respectively.

The communication control units 202A and 202B are provided with a wireless communication or a wired communication interface as described above, and transmit the biometric information sensed by the biometric information detection units 201A and 201B to the alertness estimation model generation means (unit) 11. The communication control units 202A and 202B have, for example, a wireless antenna (not shown) as an interface for wireless communication. The biological information sensor 20A may be one or more of the electroencephalograph 20-1 shown in FIG. 2 or the other sensors 20-2 to 20-7. The biological information sensor 20B may be one or more of the sensors 20-2 to 20-7 in FIG. The biological information sensor 20A and the biological information sensor 20B may be the same, and may be any of the sensors 20-2 to 20-7 in FIG.

The communication control unit 110 of the arousal degree estimation model generation means (unit) 11 communicates with the biometric information sensors 20A and 20B wirelessly or by wire, and for example, an instruction to start / stop sensing to the biometric information sensors 20A and 20B and sensing data. It receives the transmission of a command instructing transmission and the sensing data (biological information) transmitted from the biometric information sensors 20A and 20B. The communication control unit 110 has an interface for wireless communication and / or wired communication. The communication control unit 110 has, for example, a wireless antenna (not shown) as an interface for wireless communication.

The awakening state monitor unit 111 acquires biological information from the biological information sensor 20A attached to the measurement target user 1 (FIG. 2) at the time of generating the arousal degree estimation model, and based on the biological information, determines the awakening state of the measurement target user 1. Monitor.

When the awakening state monitor unit 111 determines that the awakening state of the user 1 (FIG. 2) has changed to a low awakening state, the intellectual ability test execution control unit 112 receives an instruction from the awakening state monitor unit 111. Have the measurement target user 1 execute the intellectual ability test. The intellectual ability test execution control unit 112 may instruct the personal computer 30 of FIG. 2 to execute the intellectual ability test, for example.

For example, the user 1 to be measured stops the work on the personal computer 30 (FIG. 2) and performs an intellectual ability test. The intellectual ability test execution control unit 112 may automatically open an intellectual ability test screen (window) on the screen of the display of the personal computer 30 to perform the intellectual ability test online. Alternatively, the user 1 to be measured may operate the personal computer 30 to start the application program for the intellectual ability test.

The user 1 to be measured inputs an answer to the problem displayed on the screen of the personal computer 30 from an input means such as a keyboard and a mouse. With the start of a series of intellectual ability tests (for example, sentence comprehension ability, numerical processing ability (calculation ability), logical reasoning ability, etc.) by the intellectual ability test execution control unit 112, the intellectual ability test execution control unit 112 Based on the instruction of, the biometric information acquisition unit 113 acquires biometric information (for example, heartbeat data from a heart rate monitor) in which the user 1 (FIG. 2) to be measured is executing the intellectual ability test. The intellectual ability test execution control unit 112 notifies the measurement target user 1 of the execution of the intellectual ability test via the personal computer 30, and the measurement target user 1 is subjected to a paper test (written test) prepared in advance. The intellectual ability test may be performed, and the scoring result (time required for answering) may be notified to the intellectual ability test execution control unit 112 via the personal computer 30.

For example, the normalization unit 114 sets the intellectual ability test result (score, time required for answer) of the user 1 to be measured in the low arousal state, the high awakening state (stress state), and the state in between as the low awakening state. It may be normalized by a representative point (for example, the highest score, the shortest time required for answering, etc.) in a state other than the high arousal state. Alternatively, the average of some percentage of the highest score of the user 1's intellectual ability test result (score) to be measured, and the shortest time required to answer the user 1's intellectual ability test result (time required for answering). May be normalized by averaging some percentage of response time.

For example, if the maximum score of the intellectual ability test of the user A to be measured is 70 points and 49 points in the low arousal state, normalization with the highest score results in 49/70 = 0.7 in the low arousal state. .. If the highest score of the intellectual ability test of another user B to be measured is 80 points and 48 points in the low arousal state, when normalized with the highest score, the low arousal state is 48/80 = 0.6. Become. The scores of the low arousal intellectual ability test of user A and user B to be measured are about the same as 49 points and 48 points, respectively, but by normalization, they are 0.7 (70%) and 0, respectively. It is 6.6 (60%), and the degree of depression of user B is larger than that of user A. In this way, by normalizing the distribution of scores that differs for each user to be measured by the normalization unit 114, for example, it is possible to standardize the determination of the degree of depression in a low arousal state.

The feature amount extraction unit 115 extracts the feature amount from the biological information (for example, heart rate data) acquired by the biological information acquisition unit 113. For example, the timing of the amplitude peak of the heartbeat signal is detected based on the heartbeat data from the heartbeat sensor (20-2, 20-6, 20-7, etc. in FIG. 2), the interval of each timing of the amplitude peak is detected, and the heartbeat interval is detected. Various methods are used, such as converting the data into the frequency domain and calculating the spectral density for fluctuations in the heartbeat interval. Alternatively, the degree of eye opening, the average duration of eye closure, distribution, PERCLOS (Percent of the time eyelids are closed), the number of blinks, and the like may be used as feature quantities for blinking. In the case of a microwave non-contact respiration sensor (20-5 in FIG. 2) or the like, the respiration cycle or the like may be converted into a frequency domain to acquire the feature amount, or the feature amount may be extracted from the respiration amplitude or the like. In the feature amount extraction unit 115, the biometric information acquisition unit 113 is such that the user 1 to be measured is executing the intellectual ability test (the intellectual ability test is executed within a predetermined time limit such as 5 minutes or 10 minutes, for example. The feature amount (representative value) is the value obtained by statistically processing the time-series data of the feature amount of the biometric information acquired from the biometric information sensor in order to measure the time until all the questions are answered. ) May be used.

The estimation model learning unit 116 generates the alertness estimation model 131. More specifically, the estimation model learning unit 116 learns the alertness estimation model 131 based on the normalized value of the intellectual ability test result and the feature amount of the biological information, and stores it in the storage device 13. Although not particularly limited, as the arousal degree estimation model 131, the feature amount of the biological information (biological information during the execution of the intellectual ability test) in each arousal state is used as an explanatory variable, and the normalized value of the intellectual ability test result is intended. Regression analysis may be performed using variables (explained variables). For example, the alertness estimation model 131 may be obtained by deriving a coefficient (parameter) that minimizes the residual by first-order or polynomial approximation of the objective variable with the explanatory variable. The alertness estimation model 131 is not limited to the linear regression model, and a non-linear regression model may be used.

Further, the estimation model learning unit 116 may individually generate an alertness estimation model 131 in each of the low arousal state, the high arousal state, and the state in between.

Further, the estimation model learning unit 116 may generate the alertness estimation model 131 by weighting the intellectual ability test results according to the work content (occupation type, job title, etc.) of the user 1. For example, in duties such as accounting department and tax accounting affairs, the intellectual ability test result (normalized value) of calculation ability is weighted by a larger value than the result of other tests (normalized value) such as sentence comprehension ability. You may do.
Score = W1 x (normalized value of sentence comprehension ability) + W2 x (normalized value of calculation ability) + W3 x (normalized value of logical reasoning ability),
W1 + W2 + W3 = 1, 0 ≤ W1, W2, W3 ≤ 1

On the other hand, in duties such as contracts, public relations, and patent work, the intellectual ability test result (normalized value) of sentence comprehension ability may be weighted with a larger value than the result of other tests (normalized value). ..

FIG. 4 is a diagram illustrating a configuration example of the alertness estimation means (part) 12 of FIG. Referring to FIG. 4, the alertness estimation means (unit) 12 includes a communication control unit 120, a biological information acquisition unit 121, a feature amount extraction unit 122, an estimation unit 123, and an estimation result output unit 124. .. The communication control unit 120 communicates wirelessly or by wire with the biometric information sensor, instructs the start of sensing of biometric information, transmission of sensing data, and the like, and receives the sensing data.

The biological information acquisition unit 121 receives biological information from the communication control unit 120 from the biological information sensor 20B of the user to be estimated.

The biological information sensor 20B, the biological information acquired by the biological information acquisition unit 121, and the feature amount extracted by the feature amount extraction unit 122 are the biological information acquisition of the biological information sensor 20B in FIG. 3 and the arousal degree estimation model generation means (part) 11. The biological information acquired by the unit 113 and the feature amount extracted by the feature amount extraction unit 115 are the same. For example, in the arousal degree estimation model generation means (part) 11 of FIG. 3, the biometric information acquisition unit 113 acquires the biometric information for 5 minutes of the measurement target user 1 who is executing the intellectual ability test, and the feature amount extraction unit. When the 115 extracts the feature amount from the biological information, the feature amount extraction unit 122 extracts the feature amount of the biological information acquired by the biological information sensor 20B from the user 1 to be estimated for 5 minutes by the biological information acquisition unit 121. .. The biological information acquisition unit 121 and the feature amount extraction unit 122 in FIG. 4 may be the same as the biological information acquisition unit 113 and the feature amount extraction unit 115 in FIG.

The estimation unit 123 receives the feature amount extracted by the feature amount extraction unit 122 as an input, and estimates the arousal degree using the arousal degree estimation model 131 (model parameter) stored in the storage device 13.

The estimation unit 123 estimates the normalized value of the intellectual ability test result from the feature amount input from the feature amount extraction unit 122 by using the arousal degree estimation model 131, and estimates the arousal degree corresponding to the normalized value. You may try to do it.

The estimation result output unit 124 outputs the estimation result of the arousal level to a display device or the like.

FIG. 5 is a flow chart illustrating the operation of the first embodiment of the present invention. With reference to FIG. 5 (A), the arousal degree estimation model generation means (part) 11 is used by the user 1 (FIG. 2) to be measured for a plurality of arousal states i = 1 to N (N is an integer of 2 or more). , The biological information during the execution of the intellectual ability test is acquired, the feature amount is extracted, and the feature amount is stored in the storage unit corresponding to the awakening state i (S1).

The intellectual ability test execution control unit 112 of the arousal level estimation model generation means (unit) 11 collects the test results of the intellectual ability test and stores them corresponding to the arousal state i (S2).

As a result of executing steps S1 and S2 for the awakening states i = 1 to N, the normalization unit 114 of the arousal degree estimation model generation means (part) 11 has acquired the knowledge in a state other than the low arousal state and the low awakening state, for example. Intellectual ability test in each awake state of the same user based on the score of the test result of the target ability test (for example, the highest score or the representative value (statistical value such as the first quartile from the highest score and the median)) The test result of is divided and normalized (S3).

The estimation model learning unit 116 of the arousalness estimation model generation means (unit) 11 includes the feature amount extracted by the feature amount extraction unit 115, the normalized value of the test result of the intellectual ability test from the normalization unit 114, and the normalized value. Based on the above, the alertness estimation model 131 is learned and stored in the storage device 13 (S4).

With reference to FIG. 5B, the arousal level estimation means (part) 12 acquires the biological information of the user to be estimated and extracts the feature amount (S11).

The estimation unit 123 of the arousal level estimation means (unit) 12 receives the feature amount and estimates the arousal level based on the arousal level estimation model 131 stored in the storage device 13 (S12). The estimation result output unit 124 of the arousal level estimation means (unit) 12 outputs the arousal level estimation result to a display device or the like (S13).

<Embodiment 2>
Next, as an exemplary second embodiment of the present invention, an example of a usage pattern of the alertness estimation result will be presented. In the second embodiment, the basic configuration for obtaining the alertness estimation result is the same as that of the above-described embodiment described with reference to FIG. 1 and the like.

In the second embodiment, for example, in the workplace of a government office, a company, various offices, etc., the arousal degree estimation value obtained by the information processing device 10 of FIG. 1 is fed back to the employee, and the employee himself manages the time. Provide information to support health care.

FIG. 6 is a diagram illustrating an example of the configuration of the second embodiment. In FIG. 6, the biological information sensor 20, the alertness estimation means (part) 12, the alertness estimation model 131, and the storage device 13 are, for example, the biological information sensor 20B, the alertness estimation means (part) 12, and the alertness estimation in FIG. It can be made to correspond to the model 131. In FIG. 6, the alertness estimation model generation means (part) 11 of FIG. 1 is omitted. In FIG. 6, it is assumed that the alertness estimation model 131 is generated by the alertness estimation model generation means (part) 11 described in the first embodiment.

When the management information providing means (department) 31 receives the arousal level estimation value from the arousal level estimation means (department) 12, for example, the current arousal level of the employee is displayed on the employee's personal computer (for example, 30 in FIG. 2). You may also present a screen to display. Although not particularly limited, for example, when it is determined that the employee is in a low arousal state, the management information providing means (department) 31 pays attention on the screen of the employee's personal computer (for example, 30 in FIG. 2). Present information (for example, recommend a simple refreshing exercise that can be done on the spot, or be careful to have enough sleep at night), or be careful with sound, voice, etc. as long as it does not disturb the neighborhood. You may try to arouse.

Further, the management information providing means (department) 31 stores the estimated value of the arousal degree of the employee in the storage device 32 in association with, for example, the estimated time information (or time zone information), the employee identification information (ID), and the like. The employee database 321 may be recorded and used for employee management and business management (scheduling management, business efficiency management, etc.) at a workplace or a remote workplace, for example. Further, the management information providing means (department) 31 may notify the administrator's terminal (not shown) or the like. As described above, according to the second embodiment, it is possible to use the estimated value of the alertness of the employee for employee management in the workplace or a remote workplace. The management information providing means (part) 31 may be mounted as a single device, or may be mounted on a server connected to the information processing device 10 of FIG. 1 via a communication network. Alternatively, the management information providing means (part) 31 may be incorporated into the information processing device 10 of FIG. 1 as an integrated device configuration.

<Embodiment 3>
FIG. 7 is a diagram illustrating an example in which the information processing apparatus 10 described with reference to FIG. 1 and the like is realized by a computer program as an exemplary third embodiment. Referring to FIG. 7, the computer device 300 constituting the information processing device 10 includes a processor (CPU (Central Processing Unit), data processing device) 301, a semiconductor memory (for example, RAM (Random Access Memory), ROM (Read Only Memory)). , Or a storage device 302 including at least one of EEPROM (Electrically Erasable and Programmable ROM), HDD (Hard Disk Drive), CD (Compact Disc), DVD (Digital Versatile Disc), etc., a display device 303, and the like. A communication interface 304 is provided. The function of the information processing device 10 may be realized by executing the alertness estimation program stored in the storage device 302 on the processor 301. The storage device 302 may be the same storage device as the storage device 13 that stores the alertness estimation model. Further, the storage device 302 may be used as a storage device for storing the execution result of the intellectual ability test, its normalized value, the biological information, and the feature amount extracted from the biological information. The communication interface 304 is wirelessly or wiredly connected to any of the biometric information sensors (sensors 20-1, 20-2, 20-4 to 20-7, camera 20-3 in FIG. 2) together with the processor 301, and is a living body. A communication control device (FIGS. 3 and 4) for acquiring information may be configured. The arousal level estimation program of the computer device 300 may be installed in the personal computer 30 of FIG. 2 so that the personal computer 30 functions as the information processing device 10.

The disclosure of Patent Document 1 described above shall be incorporated into this document by citation. Within the framework of the entire disclosure (including the scope of claims) of the present invention, it is possible to change or adjust the embodiments or examples based on the basic technical idea thereof. Further, various combinations or selections of various disclosure elements (including each element of each claim, each element of each embodiment, each element of each drawing, etc.) are possible within the scope of the claims of the present invention. .. That is, it goes without saying that the present invention includes all disclosure including claims, and various modifications and modifications that can be made by those skilled in the art in accordance with the technical idea.

In the above embodiment, the features of the method are added, for example, as follows.
(Appendix 1)
A first means for generating an alertness estimation model using biological information during an intellectual ability test in a plurality of different arousal states of a user to be measured and the test result of the intellectual ability.
A second means for estimating the arousal level using the arousal level estimation model with respect to the biological information acquired from the user to be estimated, and
An information processing device characterized by being equipped with.

(Appendix 2)
The first means is
A feature amount extraction unit that extracts a feature amount from the biological information during the test,
A normalization unit that normalizes the test results of the intellectual ability of the user to be measured, and
An estimation model generation unit that generates an alertness estimation model based on a value obtained by normalizing the feature quantity and the test result of the intellectual ability.
The information processing apparatus according to Appendix 1, wherein the information processing apparatus is provided with.

(Appendix 3)
The normalization unit normalizes the test results of the intellectual ability in a plurality of different awake states by using the test results of the intellectual ability of the user when the arousal state is in a predetermined state. , The information processing apparatus according to Appendix 2.

(Appendix 4)
The information processing apparatus according to Appendix 2 or 3, wherein the estimation model generation unit separately models the decrease in intellectual ability due to the first awake state and the decrease in intellectual ability due to the second awake state.

(Appendix 5)
The information processing apparatus according to any one of Supplementary note 1 to 4, wherein the first means measures at least one of sentence comprehension ability, numerical processing ability, and logical reasoning ability as a test of the intellectual ability. ..

(Appendix 6)
The information processing apparatus according to any one of Appendix 1 to 4, wherein the first means weights the test result of the intellectual ability according to the attribute of the user to be measured.

(Appendix 7)
Based on the estimation result of the arousal degree, the user is connected to a management information providing means for providing predetermined management information, or the management information providing means is provided in the device. The information processing apparatus according to any one of 1 to 6.

(Appendix 8)
A method of estimating alertness based on biological information using a computer.
An arousal degree estimation model is generated using the biological information during the intellectual ability test in a plurality of arousal states of the user to be measured and the test result of the intellectual ability.
A method for estimating an arousal level, which estimates the arousal level using the arousal level estimation model for biological information acquired from a user to be estimated.

(Appendix 9)
In generating the alertness estimation model,
Feature quantities were extracted from the biological information during the test.
Normalize the test results of the intellectual ability of the user to be measured,
The arousal level estimation method according to Appendix 8, wherein the arousal level estimation model is generated based on a value obtained by normalizing the feature amount and the test result of the intellectual ability.

(Appendix 10)
In normalizing the test results of the intellectual ability, the intellectual ability in a plurality of different awakening states is used by using the test result of the intellectual ability of the user when the alertness state is in a predetermined state. The arousal level estimation method according to Appendix 9, which normalizes the test results of.

(Appendix 11)
Described in any of Appendix 8 to 10, which separately models the decrease in intellectual ability due to the first arousal state and the decrease in intellectual ability due to the second arousal state in generating the alertness estimation model. Arousal level estimation method.

(Appendix 12)
The arousal level estimation method according to any one of Appendix 8 to 11, which measures at least one of sentence comprehension ability, numerical processing ability, and logical reasoning ability as a test of the intellectual ability.

(Appendix 13)
The arousal level estimation method according to any one of Appendix 8 to 12, which weights the test result of the intellectual ability according to the attribute of the user to be measured.

(Appendix 14)
The arousal level estimation method according to any one of Supplementary note 8 to 13, wherein predetermined management information is provided regarding the user to be estimated based on the arousal level estimation result.

(Appendix 15)
On the computer
The first process of generating an alertness estimation model using the biological information during the intellectual ability test in a plurality of different arousal states of the user to be measured and the test result of the intellectual ability, and
The second process of estimating the arousal level using the arousal level estimation model for the biological information acquired from the user to be estimated, and
A program that executes.

(Appendix 16)
The first process is
The feature amount extraction process for extracting the feature amount from the biological information during the test, and
A normalization process that normalizes the test results of the intellectual ability of the user to be measured, and
A model generation process that generates an alertness estimation model based on the normalized values of the features and the test results of the intellectual ability, and
The program according to Appendix 15 for executing the above.

(Appendix 17)
The normalization process normalizes the test results of the intellectual ability in a plurality of different awakening states by using the test results of the intellectual ability of the user when the arousal state is in a predetermined state. , The program according to Appendix 16.

(Appendix 18)
The program according to Appendix 16 or 17, wherein the model generation process separately models the decrease in intellectual ability due to the first arousal state and the decrease in intellectual ability due to the second awake state.

(Appendix 19)
The program according to any one of Appendix 15 to 18, wherein the first process measures at least one of calculation ability, reading ability, and memory ability as a test of the intellectual ability.

(Appendix 20)
The program according to any one of Appendix 15 to 19, wherein the first process weights the test result of the intellectual ability according to the attribute of the user to be measured.

(Appendix 21)
The program according to any one of Supplementary note 15 to 20, which causes the computer to execute a process of providing predetermined management information regarding the user to be estimated based on the estimation result of the arousal degree.

1 User 10 Information processing device 11 Alertness estimation model generation means (part)
12 Alertness estimation means (part)
13 Storage device 20, 20A, 20B Biometric information sensor 20-1 Brain wave meter 20-2 Heart rate sensor 20-3 Camera 20-4 Glass-type sensor 20-5 Microwave biometric information sensor 20-6 Sheet-type biometric information sensor 20 -7 Ear clip type photoelectric pulse wave sensor 30 Personal computer 31 Management information providing means (part)
32 Storage device 321 Employee database 110, 120 Communication control unit 111 Awakening state monitor unit 112 Intellectual ability test execution control unit 113 Biometric information acquisition unit 114 Normalization unit 115, 122 Feature extraction unit 116 Estimated model learning unit 121 Biological information Acquisition unit 123 Estimating unit 124 Estimating result output unit 131 Arousal degree estimation model 20A, 20B Biometric information sensor 201A, 201B Biometric information detection unit 202A, 202B Communication control unit 300 Computer device 301 Processor 302 Storage device 303 Display device 304 Interface

Claims (14)

A first means for generating an alertness estimation model based on biological information during a test of intellectual ability of a user to be measured in a plurality of different arousal states and the test result of the intellectual ability.
A second means for estimating the arousal level corresponding to the test result of the intellectual ability by using the arousalness estimation model with respect to the biological information acquired from the user to be estimated.
With
The first means is an information processing device that weights a plurality of types of test results of the intellectual ability according to the attributes of the user to be measured . The first means is
A feature amount extraction unit that extracts a feature amount from the biological information during the test,
A normalization unit that normalizes the test results of the intellectual ability of the user to be measured, and
An estimation model generation unit that generates an alertness estimation model based on a value obtained by normalizing the feature quantity and the test result of the intellectual ability.
Equipped with a,
The estimation model generation unit has a value obtained by weighting a normalized value of the test results of the plurality of types of the intellectual ability of the user to be measured according to the attribute of the user to be measured, and the feature amount. The information processing apparatus according to claim 1 , wherein the arousal degree estimation model is generated based on the above . The normalization unit uses the test results of the intellectual ability of the user to be measured when the arousal state is in a predetermined state, and uses the test results of the intellectual ability in a plurality of different awake states. The information processing apparatus according to claim 2, wherein the information processing apparatus is normalized. The estimation model generation unit is characterized in that it generates an alertness estimation model that separately models the decrease in intellectual ability due to the first arousal state and the decrease in intellectual ability due to the second awake state. The information processing apparatus according to claim 2 or 3. The first means is characterized in that, as the test of the intellectual ability, at least two of the three types of intellectual ability tests of sentence comprehension ability, numerical processing ability, and logical reasoning ability are measured. The information processing apparatus according to any one of claims 1 to 4. A claim characterized in that it is connected to a management information providing means that provides predetermined management information about the user to be estimated based on the estimation result of the arousal level, or the management information providing means is provided in the device. Item 2. The information processing apparatus according to any one of Items 1 to 5 . A method of estimating alertness based on biological information using a computer.
An alertness estimation model is generated based on the biological information during the intellectual ability test in a plurality of different arousal states of the user to be measured and the test result of the intellectual ability.
With respect to the biological information acquired from the user to be estimated, the alertness corresponding to the test result of the intellectual ability is estimated by using the alertness estimation model.
A method for estimating arousalness, which comprises weighting a plurality of types of test results of the intellectual ability according to the attributes of the user to be measured in generating the arousalness estimation model . In generating the alertness estimation model,
Feature quantities were extracted from the biological information during the test.
The test results of the plurality of types of the intellectual ability of the user to be measured are normalized.
The arousal level estimation model based on a value obtained by weighting the feature amount and the normalized value of the test results of the plurality of types of the intellectual ability of the user to be measured according to the attribute of the user to be measured. The arousal degree estimation method according to claim 7 , wherein the method is generated. In normalizing the test results of the intellectual ability, the test results of the intellectual ability of the user to be measured when the arousal state is in a predetermined state are used to describe the above in a plurality of different arousal states. The arousal level estimation method according to claim 8 , wherein the test result of intellectual ability is normalized. In generating the alertness estimation model, a claim to generate an alertness estimation model that separately models the decrease in intellectual ability due to the first arousal state and the decrease in intellectual ability due to the second arousal state. Item 8. The arousal level estimation method according to any one of Items 7 to 9 . Claims 7 to 10 , wherein at least two of the three types of intellectual ability tests, that is, sentence comprehension ability, numerical processing ability, and logical reasoning ability , are measured as the intellectual ability test . The arousal degree estimation method according to any one of the items. The arousal level estimation method according to any one of claims 7 to 11 , wherein a predetermined management information regarding the user to be estimated is provided based on the arousal level estimation result. On the computer
The first process of generating an alertness estimation model based on the biological information during the intellectual ability test in a plurality of different arousal states of the user to be measured and the test result of the intellectual ability, and
A second process of estimating the arousal level corresponding to the test result of the intellectual ability by using the arousalness estimation model for the biological information acquired from the user to be estimated, and
In the first process, in generating the alertness estimation model, a plurality of types of test results of the intellectual ability are weighted according to the attributes of the user to be measured. ,program. The first process is
The feature amount extraction process for extracting the feature amount from the biological information during the test, and
A normalization process that normalizes the test results of the intellectual ability of the user to be measured, and
And the feature quantity, the plurality of kinds of values of the test results were normalized the mental capacity of a user of the measurement object, based on the value obtained by weighting in accordance with the user attributes of the measurement target, the wakefulness estimation model Model generation process to generate
13. The program according to claim 13 .

Images