JP2020171734A - Drowsiness calculation device - Google Patents

Abstract

To provide a drowsiness calculation device that is able to highly accurately calculate drowsiness taking account of the present activity as well as the past activity of the subject.SOLUTION: In a smart phone 1, an I/F18 acquires a heart rate of a subject, measured by a heart beat sensor 19, and a measurement time, and a condition determination unit 11 determines an active state of the subject and transmits it to a server 2. Then, in the server 2, according to the active state transmitted from the smart phone 1, a correction unit 24 acquires a drowsiness reference heart rate from a drowsiness reference heart rate table 21 in which drowsiness reference heart rates of the subject are stored for each active state. Then, the drowsiness reference heart rate acquired by the correction unit 24 is corrected based on a fatigue degree, sleep time, and diet. Next, the corrected drowsiness reference heart rate is transmitted to the smart phone 1, and a drowsiness degree calculation unit 16 of the smart phone 1 calculates a drowsiness degree of the subject on the basis of the corrected drowsiness reference heart rate and the heart rate acquired by the I/F 18.SELECTED DRAWING: Figure 6

Description

The present invention relates to a drowsiness calculation device for calculating drowsiness of a subject.

For example, in order to detect the dozing driving of an automobile, it has been proposed to detect the dozing state from the heart rate of the driver (see, for example, Patent Documents 1 and 2).

In Patent Document 1, the average value of the RRI (RR Interval) values of the heartbeat detected by the heart rate sensor during awakening and a predetermined multiple of the integrated value of the RRI value exceeding the average value are set as threshold values, and the RRI value exceeding the average value is integrated. It is described that if the threshold value is exceeded, it is determined that the patient is dozing.

Patent Document 2 obtains heartbeat interval data in which RRI is time-series based on the heartbeat waveform of a resting subject measured by a sensor. Next, the heartbeat interval data is frequency-analyzed to obtain the frequency analysis result of the heartbeat fluctuation including the power spectral density (PSD) and the total power (TP) of the autonomic nerves with respect to the frequency at a certain time. Next, the frequency analysis result was set as the initial state, and the origin of the drowsiness position and the origin of the awakening position were set based on the estimated drowsiness position and the estimated awakening position included in the initial state. Determine the drowsiness scale. Then, it is described that the drowsiness of the subject is determined based on the drowsiness scale.

Japanese Patent No. 3252586 Japanese Unexamined Patent Publication No. 2014-12042

In the case of the method described in Patent Document 1, the data at the time of initial awakening is used as a reference. However, the initial state differs from person to person, and the average value of RRI values and the like may not be set appropriately depending on the arousal level in the initial state. Therefore, there is a problem that it is not possible to cope with the difference in the initial state depending on the person.

The method described in Patent Document 2 has the following problems. The correspondence between heart rate information and drowsiness scale changes due to various factors. Even based on the resting state, there are daily changes and time zone changes. For example, it is known that the time when drowsiness becomes strong is from 3:00 to 4:00 in the early morning and from 3:00 to 4:00 in the daytime. Therefore, it is difficult to accurately estimate drowsiness only from heartbeat information. In addition, driving is a kind of stress-bearing condition, and the baseline of heart rate differs depending on the road condition (urban area or highway). Furthermore, since the state at the beginning of measurement is not constant, it was not possible to respond to changes such as when sleepy from the beginning and when not sleepy at the beginning.

Further, in order to determine drowsiness, it is necessary to set some reference heart rate or the like as in Patent Documents 1 and 2. However, the heart rate not only varies from person to person, but also fluctuates depending on the time of day and the state of activity. In addition, drowsiness can also be caused by past behaviors (activities) such as sleep status (whether you slept well the day before), diet status (whether you ate a meal, etc.) or fatigue status (whether you are tired). It depends.

Since the methods described in Patent Documents 1 and 2 do not consider the activity of the subject at all, accurate detection of drowsiness may not be possible depending on the activity of the subject.

Therefore, in view of the above-mentioned problems, the present invention provides, for example, a drowsiness calculation device capable of calculating drowsiness with high accuracy in consideration of the current activity and the past activity of the subject. Make it an issue.

In order to solve the above problems, the invention according to claim 1 has a biological information acquisition unit that acquires biological information regarding the heartbeat of the subject, and a fatigue degree that acquires fatigue degree information regarding the fatigue degree of the subject. The drowsiness calculation device is characterized by comprising an information acquisition unit and a drowsiness degree calculation unit that calculates information on the current drowsiness of the subject based on the biological information and the fatigue degree information.

It is a schematic block diagram of the drowsiness calculation apparatus which concerns on 1st Example of this invention. It is a schematic block diagram of the smartphone shown in FIG. It is a schematic block diagram of the server shown in FIG. It is a table which showed the discrimination example of the activity state in the state discrimination part shown in FIG. It is a table which showed the example of the parameter table shown in FIG. It is explanatory drawing of the display example of the drowsiness display part shown in FIG. It is a table which showed the example of the drowsiness reference heart rate table shown in FIG. This is another configuration example for calculating and setting the drowsiness reference heart rate table. It is explanatory drawing about the interpolation of the drowsiness reference heart rate table. It is a table of correction values corresponding to the fatigue level. This is an example of a screen in which the subject inputs the degree of fatigue. This is an example of a screen in which the subject inputs the sleep state. It is a table of correction values corresponding to the elapsed time after a meal. It is a flowchart which determines after a meal from the position information. It is a table of correction values corresponding to fatigue level and sleep level. It is a flowchart of the operation of the drowsiness calculation device shown in FIG. It is a flowchart of the operation which corrects the drowsiness reference heart rate shown in FIG. It is a table of correction values corresponding to the destination of the drowsiness calculation device according to the second embodiment of the present invention. It is a table of correction values corresponding to the distance to the destination. It is a table of correction values corresponding to the road shape. It is explanatory drawing of the display example before subjective evaluation of the drowsiness display part of the drowsiness calculation apparatus which concerns on 3rd Example of this invention. It is explanatory drawing of the display example after subjective evaluation of the drowsiness display part of the drowsiness calculation apparatus which concerns on 3rd Example of this invention.

Hereinafter, the drowsiness calculation device according to the embodiment of the present invention will be described. In the drowsiness calculation device according to the embodiment of the present invention, the biometric information acquisition unit acquires biometric information regarding the heartbeat of the subject, and the activity state acquisition unit acquires the current active state, which is the current active state of the subject. Then, the activity history acquisition department acquires information on the past activity status of the subject. Next, the drowsiness reference heart rate of the subject is stored for each activity state according to the activity state acquired by the activity state acquisition section of the drowsiness reference heart rate acquisition section. To get. Next, the drowsiness reference heart rate acquired by the drowsiness reference heart rate acquisition unit in the correction unit is corrected based on the information on the past activity state acquired by the activity history acquisition unit. Then, the information on the drowsiness of the subject is calculated based on the drowsiness reference heart rate corrected by the correction unit by the drowsiness degree calculation unit and the biological information acquired by the biological information acquisition unit. By doing so, the drowsiness reference heart rate can be corrected based on the past activity state of the subject, so that the drowsiness can be calculated with high accuracy by considering not only the current activity but also the past activity. can do.

In addition, the activity history acquisition unit may acquire at least one of the past sleep information, the past meal information, and the fatigue information associated with the past activity of the subject. By doing so, the drowsiness reference heart rate can be corrected in consideration of the past sleep information, the past meal information, and the fatigue information associated with the past activity of the subject. Therefore, it is possible to calculate the drowsiness level in consideration of these factors.

In addition, the activity history acquisition unit may acquire the past stay history at a specific point of the examiner. By doing so, the past activity can be estimated based on a specific point such as a restaurant or a hot spring where the subject has stayed in the past, and the drowsiness reference heart rate can be corrected.

In addition, an activity prediction unit that predicts the activity of the subject is further provided, and the correction unit further corrects the drowsiness reference heart rate acquired by the drowsiness reference heart rate acquisition unit based on the activity predicted by the activity prediction unit. May be good. By doing so, it is possible to correct the drowsiness reference heart rate in consideration of future schedules such as going to play in the future in addition to past activities.

Further, a destination information acquisition unit for acquiring information on the destination of the subject may be further provided, and the activity prediction unit may predict the activity of the subject based on the information on the destination. By doing so, it is possible to predict future plans such as whether the destination itself is a home or a trip.

In addition, the current location information acquisition unit that acquires information about the subject's current location is further provided, and the correction unit is a drowsiness standard heart rate acquisition unit when the current activity status acquired by the activity status acquisition unit is driving a vehicle. The acquired drowsiness reference heart rate may be corrected based on the information regarding the current location acquired by the current location information acquisition unit. By doing so, when the subject is driving the vehicle, the drowsiness reference heart rate can be corrected according to the conditions such as the road currently being driven.

In addition, the biometric information acquisition unit acquires the measurement time of the acquired biometric information, and the drowsiness reference heart rate acquisition unit stores the drowsiness reference heart rate of the subject for each time and activity state. The drowsiness reference heart rate may be acquired from the unit according to the measurement time and the activity state. By doing so, the drowsiness reference heart rate can be selected in consideration of the time as well as the active state. Therefore, drowsiness can be calculated more accurately.

In addition, the drowsiness degree calculation unit may calculate information on the drowsiness of the subject based on the drowsiness prediction parameters set in advance for each activity state. By doing so, it is possible to weight a plurality of elements included in the biological information regarding the heartbeat according to the activity state.

Further, it includes a display unit for displaying information on drowsiness to the subject, and an input unit for inputting the evaluation of the subject for the information on drowsiness displayed on the display unit. Then, the drowsiness degree calculation unit may update the drowsiness reference heart rate stored in the drowsiness reference heart rate storage unit based on the evaluation input by the input unit, and calculate information on drowsiness. .. By doing so, the subject can subjectively evaluate the information on drowsiness calculated by the drowsiness degree calculation unit. Then, the drowsiness degree calculation unit can calculate the information on drowsiness again by feeding back the subjective evaluation result. Therefore, the information on drowsiness can be calculated more accurately according to the individual sense of the subject.

Further, in the information processing apparatus according to the embodiment of the present invention, the activity state acquisition unit acquires the activity state of the subject, and the activity history acquisition unit acquires information on the past activity state of the subject. Then, the drowsiness reference heart rate selected from the drowsiness reference heart rate storage unit in which the drowsiness reference heart rate of the subject is stored for each activity state according to the activity state acquired by the activity state acquisition unit in the correction unit is activated. Make corrections based on the information about the past activity status acquired by the history acquisition unit. By doing so, the drowsiness reference heart rate can be corrected based on the past activity state of the subject.

Further, in the drowsiness calculation device according to another embodiment of the present invention, the biometric information acquisition unit acquires biometric information regarding the heartbeat of the subject, and the activity state acquisition unit is the current activity state of the subject. Get the state. Next, the activity prediction unit predicts the activity status of the subject. Next, the drowsiness reference heart rate acquisition unit acquires the drowsiness reference heart rate from the drowsiness reference heart rate storage unit in which the drowsiness reference heart rate of the subject is stored for each activity state according to the current activity state. Next, the drowsiness reference heart rate acquired by the drowsiness reference heart rate acquisition unit in the correction unit is corrected based on the activity state predicted by the activity prediction unit. Then, the information on the drowsiness of the subject is calculated based on the drowsiness reference heart rate corrected by the correction unit by the drowsiness degree calculation unit and the biological information acquired by the biological information acquisition unit. By doing so, the drowsiness reference heart rate can be corrected in consideration of the subject's future schedule, so that the drowsiness can be calculated with high accuracy in consideration of not only the current activity but also the future activity. can do.

Further, in the drowsiness calculation method according to the embodiment of the present invention, the biometric information acquisition process acquires biometric information regarding the heartbeat of the subject, and the active state acquisition step is the current active state of the subject. Is acquired, and the activity history acquisition process acquires information on the past activity status of the subject. Next, the drowsiness reference heart rate acquisition step acquires the drowsiness reference heart rate from the drowsiness reference heart rate storage unit in which the drowsiness reference heart rate of the subject is stored for each activity state according to the current activity state. Next, the correction step corrects the drowsiness reference heart rate acquired in the drowsiness reference heart rate acquisition step based on the information on the past activity state acquired in the activity history acquisition step. Then, the drowsiness reference heart rate corrected by the drowsiness calculation step in the correction step and the information on the drowsiness of the subject are calculated based on the biological information acquired in the biological information acquisition step. By doing so, the drowsiness reference heart rate can be corrected based on the past activity state of the subject, so that the drowsiness can be calculated with high accuracy by considering not only the current activity but also the past activity. can do.

Further, a drowsiness calculation program may be used in which the above-mentioned drowsiness calculation method is executed by a computer. By doing so, the drowsiness reference heart rate can be corrected based on the subject's past activity state using a computer, so that high accuracy is taken into consideration not only the current activity but also the past activity. It is possible to calculate drowsiness.

Further, the above-mentioned drowsiness calculation program may be stored in a computer-readable recording medium. By doing so, the program can be distributed as a single unit in addition to being incorporated in the device, and version upgrades and the like can be easily performed.

The drowsiness calculation device according to the first embodiment of the present invention will be described with reference to FIGS. 1 to 13. As shown in FIG. 1, the drowsiness calculation device 50 according to this embodiment includes a smartphone 1 and a server 2 as an information processing device. Further, the server 2 is configured to be able to communicate with the stationary measuring instrument 3. The stationary measuring device 3 is installed indoors, for example, and can measure the heart rate and blood glucose level of the subject. When these measurements are taken, the measurement result is displayed to the subject and the server 2 is used. Send to. The server 2 also accumulates the measurement results of the stationary measuring instrument 3.

As shown in FIG. 2, the smartphone 1 includes a state determination unit 11 as an activity state acquisition unit, a GPS receiver 12, a G sensor 13, a parameter table 14, a communication unit 15, and a drowsiness calculation unit 16. The drowsiness display unit 17 as a display unit and the I / F 18 as a biological information acquisition unit are provided. The heart rate sensor 19 is connected to the smartphone 1.

The configuration of the smartphone 1 shown in FIG. 2 may be configured as, for example, an application program (application). Further, the smartphone 1 may be configured to include the heart rate sensor 19.

In this embodiment, the smartphone 1 will be described, but it goes without saying that the smartphone 1 is not the only one, and it may be a mobile phone, a tablet-type terminal, or the like, or a wristwatch-type terminal or the like. Alternatively, it may be an in-vehicle device such as a car navigation system.

As the heart rate sensor 19, a well-known sensor can be used as long as it is a sensor capable of acquiring at least a heart rate as biological information regarding the heart rate. For example, various forms such as a wristwatch type can be used. Further, the heart rate sensor 19 is not limited to one type, and a plurality of types may be used properly according to the activity state described later.

In the smartphone 1 having the above-described configuration, a calculation device such as a CPU (Central Processing Unit) functions in the state determination unit 11 and the drowsiness calculation unit 16. In addition, a storage medium such as a flash memory functions in the parameter table 14. Further, the drowsiness display unit 17 functions as a display device such as a liquid crystal display. The I / F 18 functions as a communication control unit or the like that communicates with the heart rate sensor 19 or the like. Further, as the GPS receiver 12 and the G sensor 13, those built in the smartphone 1 can be used.

The state determination unit 11 is resting, driving, working, sleeping, etc. based on the current location information and acceleration information (current location and acceleration of the subject) of the smartphone 1 input from the GPS receiver 12 and the G sensor 13. The current activity state (current activity state) of the subject is determined. That is, the state determination unit 11 acquires the current activity state of the subject.

As is well known, the GPS receiver 12 receives radio waves transmitted from a plurality of GPS (Global Positioning System) satellites, obtains current location information (latitude, longitude), and outputs the information to the state determination unit 11.

The G sensor 13 is a so-called acceleration sensor. For example, if it is a 3-axis acceleration sensor, it can measure acceleration in three directions of the XYZ axes. The G sensor 13 outputs the measured acceleration to the state determination unit 11.

FIG. 4 shows an example of determining the active state in the state determination unit 11. FIG. 4 is an example of a table for determining the activity state. In the table of FIG. 4, the content of the state sta1 indicates the resting state, the content of the state sta2 indicates the driving state, the content of the state sta3 indicates the working state, and the content of the state sta4 indicates the active state of sleeping. Of course, the activity status may include items other than those shown in the figure, such as exercise and hard labor.

In the table of FIG. 4, when the position information is the living room, the acceleration information is small, the speed is small, and the device is a wristwatch, the state sta1 (rest) is determined. Here, the speed may be calculated from, for example, a change in the current location information. The device indicates the type of the heart rate sensor 19 and the location where the heart rate sensor 19 is installed, and may be acquired from the heart rate sensor 19 or may be set separately by the subject or the like.

Further, when the current location information is the vehicle, the acceleration information is medium, the speed is high, and the device is the driver's seat, the state sta2 (during driving) is determined. When the current location information is an office, the acceleration information is large, the speed is medium, and the device is a chair, it is determined to be in the state sta3 (working). When the current location information is a bed, the acceleration information is small, the speed is low, and the device is a bed, the state sta4 (sleep) is determined. In particular, acceleration information and speed are examples, and specific numerical values and the like can be arbitrarily changed in the settings.

In the table of FIG. 4, the determination is made based on the current location information, the acceleration information, the speed information, and the device information, but the determination may be made by only one item or only two or three items. Further, it may be discriminated by the heart rate measured by the heart rate sensor 19. For example, if the change in heart rate is small, it can be roughly determined as resting or sleeping, and if the heart rate is low but fluctuating, it can be roughly determined as driving or working.

The parameter table 14 includes a table in which drowsiness prediction parameters, which will be described later, are set for each active state. Then, based on the determination result of the state determination unit 11, the drowsiness prediction parameter corresponding to the activity state is output to the drowsiness degree calculation unit 16. An example of the table is shown in FIG.

As shown in FIG. 5, two types of drowsiness prediction parameters, a and b, are set. In the example of FIG. 5, in the case of the state sta1 (rest), the drowsiness prediction parameter a is 0.2, the drowsiness prediction parameter b is 0.2, and in the state sta2 (during driving), the drowsiness prediction parameter a is 0.5. , The drowsiness prediction parameter b is set to 0. Further, in the case of state sta3 (working), the drowsiness prediction parameter a is 0.1 and the drowsiness prediction parameter b is 0.2, and in the case of state sta4 (sleep), the drowsiness prediction parameter a is 0.2 and the drowsiness prediction parameter b is 0.2. As is clear from the table of FIG. 5, the drowsiness prediction parameters a and b are set to values in the range of 0 to 1.

The communication unit 15 communicates with the server 2. The communication unit 15 transmits to the server 2 the heart rate (may include heart rate fluctuation) measured by the heart rate sensor 19, the measurement time, and the activity state determined by the state determination unit 11. The communication unit 15 receives the corrected drowsiness reference heart rate transmitted from the server 2. The corrected drowsiness reference heart rate is a drowsiness reference heart rate corrected later, and the drowsiness reference heart rate will be described later.

The drowsiness calculation unit 16 is drowsiness based on the heart rate measured by the heart rate sensor 19, the drowsiness prediction parameter output from the parameter table 14, and the corrected drowsiness reference heart rate received by the communication unit 15 from the server 2. Calculate the degree (information about drowsiness).

The degree of drowsiness is the difference between the current heart rate and the drowsiness reference heart rate when the current heart rate is lower than the drowsiness reference heart rate, and is according to the rate at which the current heart rate falls below the drowsiness reference heart rate. It is calculated to increase drowsiness.

Here, the premise for calculating the drowsiness level will be described. In order to estimate the balance of the autonomic nerves from heart rate variability, from the time series data on heart rate variability, the high frequency fluctuation component (HF component) corresponding to the respiratory variability and the low frequency corresponding to the Mayer wave which is the blood pressure variability. A component (LF component) is extracted and the sizes of both are compared. The HF component, which reflects respiratory variability, appears in heart rate variability only when the parasympathetic nerves are tense (activated). On the other hand, the LF component also appears in heart rate variability when the sympathetic nerve is tense and when the parasympathetic nerve is tense.

For the HF component, the square root is generally used for the total value of the intensities of the HF component region (from 0.15 Hz to 0.40 Hz) of the power spectrum. The HF component (HFS) varies greatly among individuals, and is normalized for each individual and converted to a value from 1 to 5.
HFS = β × √ (HF) ・ ・ ・ (1)

Here, the value of β is determined so that the average value of HFS is 2. If the HFS value is less than 1, it is set to 1, and if it is larger than 5, it is set to 5. As a result, HFS is a value from 1 to 5.

In the drowsiness calculation unit 16, the drowsiness prediction parameters are a and b, the RR interval obtained from the current heart rate HR is RR, the reference RR interval obtained from the reference heart rate HR_ref is RR_ref, and the heart rate fluctuation is HF. Then, the drowsiness degree D is calculated by the following equation (2).
D = a × (RR-RR_ref) + b × HFS ... (1)

Here, since the heart rate HR is the number of heartbeats per minute, the RR interval is calculated from the heart rate HR by the following equation (3).
RR = 60000 / HR (milliseconds) ... (3)

Similarly, RR_ref is calculated by the following equation (4).
RR_ref = 60000 / HR_ref (milliseconds) ... (4)

In this embodiment, the HFS is obtained from the heart rate by the drowsiness calculation unit 16, but it may be obtained from the heart rate sensor 19. In that case, the biological information acquired by the I / F18 is a high-frequency component of the heart rate and the heart rate fluctuation.

Here, setting the drowsiness prediction parameters a and b, respectively, will be described. For example, drowsiness during driving is likely to occur during monotonous driving (highway, etc.), and functional deterioration accompanied by drowsiness occurs. In terms of physiological function, such functional deterioration appears while the heart rate, blood pressure, etc. are calmed down, and abnormalities of eye movements and brain waves are agitated. Subjective symptoms and tiredness are greatly increased mainly by drowsiness and drowsiness, and tiredness of limbs, and a decrease in concentration is also strongly felt. Behavioral Ability There is a large increase in reaction time, increased variability, reduced accuracy, and even dangerous conditions due to eye closure and drowsiness.

The drowsiness state is classified as follows according to the function of the autonomic nerve.
<1. If you are not drowsy>
It is a state in which the sympathetic nerve is enhanced and the parasympathetic nerve is suppressed. The heart rate HR is large, and the high-frequency component HF of heart rate fluctuation is small.
<2. If there are signs of drowsiness>
Due to monotonous driving and fatigue, there is little psychological awareness of drowsiness, but the signs appear physiologically. The heart rate drops as sympathetic activity changes from hyperactive to suppressed.
<3. If you feel drowsy>
The sympathetic nerve remains suppressed, but the parasympathetic nerve activity changes to an hyperactive state, so that the heart rate HR decreases and the high-frequency component HF of the heart rate fluctuation increases.
<4. Conflict against drowsiness>
Tension occurs to feel dangerous and to resist drowsiness. The sympathetic nerve activity is intermittently increased and the high-frequency component HF of the heartbeat fluctuation is decreased when the person is sick.
<5. A state that cannot withstand drowsiness>
The tension disappears and the person begins to fall asleep. Heart rate HR decreases because sympathetic nerve activity is suppressed.

According to the above classification, in normal drowsiness driving, the state changes from 1 state (when there is no drowsiness) to 2 states (when there are signs of drowsiness), and further reaches 4 states (conflict state against drowsiness). There are many. On the other hand, in the resting state, the state changes from 1 to 2, changes to 3 (when drowsiness occurs), and when sleeping, it reaches 5 (drowsiness cannot be resisted).

Therefore, in the equation (2), as shown in FIG. 4, the drowsiness prediction parameter b of the heartbeat fluctuation is set to 0 during driving for calculation. That is, in the driving state, the drowsiness prediction parameter a of the heart rate change is increased, and the drowsiness prediction parameter b of the heart rate fluctuation is decreased. On the other hand, in the resting state, the drowsiness prediction parameter a, which is an element of heart rate change, is reduced, and the drowsiness prediction parameter b, which is a heart rate fluctuation, is increased.

That is, the drowsiness prediction parameters a and b are coefficients for weighting each of the RR interval and the heartbeat fluctuation. As described above, since the RR interval and the heart rate fluctuation have different contributions to drowsiness depending on the active state, the accuracy of drowsiness is improved by weighting each of them.

Then, the drowsiness degree calculated by the equation (2) is in the range of numerical values of 1 to 5. The degree of drowsiness is 1 for less drowsiness and 5 for greater drowsiness. Further, since the drowsiness degree D is the difference between the current heart rate and the drowsiness reference heart rate when the current heart rate is lower than the drowsiness reference heart rate, the drowsiness degree in the case of RR <RR_ref (HR> HR_ref). Is 1.

That is, since the drowsiness prediction parameter changes depending on the activity state, the drowsiness degree calculation unit 16 calculates the drowsiness degree based on the heart rate (biological information), the activity state, and the drowsiness reference heart rate.

The drowsiness degree display unit 17 displays the drowsiness degree calculated by the drowsiness degree calculation unit 16. The drowsiness level may be displayed only by the numerical value at that time, or may be displayed by a bar graph, a line graph, or the like so that the change in time series can be understood.

A display example of the drowsiness level display unit 17 is shown in FIG. FIG. 6A is a table showing the heart rate for each time, the drowsiness reference heart rate, and the calculated drowsiness level. FIG. 6B is a bar graph of FIG. 6A. That is, when the heart rate is measured as shown in FIG. 6A, it is displayed to the subject as shown in FIG. 6B.

The I / F 18 is an interface (I / F) to which the heart rate sensor 19 is connected. The I / F 18 is an interface corresponding to a wired connection when the heart rate sensor 19 is a wired connection, and an interface corresponding to a wireless connection when the heart rate sensor 19 is a wireless connection. That is, the I / F18 acquires biological information (heart rate, measurement time, etc.) regarding the subject's heart rate measured by the subject.

As shown in FIG. 3, the server 2 stores the drowsiness reference heart rate table 21 as the drowsiness reference heart rate storage unit, the terminal communication unit 22, the external communication unit 23, the correction unit 24, and individual history data. It includes a unit 25 and.

As is well known, the server 2 is installed in a business office or the like, and can communicate with a plurality of terminals such as smartphones 1 via a network such as the Internet. Further, as described above, the server 2 can also communicate with the stationary measuring instrument 3. In the server 2 having the above-described configuration, a storage medium such as a hard disk functions as the drowsiness reference heart rate table 21 and the personal history data storage unit 25. Further, in the terminal communication unit 22 and the external communication unit 23, a substrate for network control, a semiconductor circuit, and the like function. Further, in the correction unit 24, an arithmetic unit such as a CPU functions.

The drowsiness reference heart rate table 21 includes a table in which the drowsiness reference heart rate of the subject is stored for each time and activity state. Then, based on the determination result of the state determination unit 11 received from the smartphone 1, the drowsiness reference heart rate corresponding to the active state is output to the correction unit 24. An example of the table is shown in FIG.

Here, the drowsiness reference heart rate is the heart rate at the time of drowsiness occurrence. That is, the heart rate below this heart rate is the heart rate at which a person feels drowsy. As a method of calculating the drowsiness reference heart rate, for example, the minimum heart rate and the standard deviation of the heart rate in a certain active state such as driving are obtained, and the standard deviation is added to the minimum heart rate.

In the case of the example of FIG. 7, the drowsiness reference heart rate is set for each state sta1 to sta3 at 1-hour intervals of times t1 to t4. Times t1 to t4 indicate times such as 0:00 pm and 1:00 pm.

The drowsiness reference heart rate is calculated based on the standard deviation or the like calculated based on the information such as the heart rate acquired from the heart rate sensor 19. For example, when calculating the reference heart rate at midnight, obtain the heart rate for a predetermined period near midnight, obtain the minimum heart rate and standard deviation as described above, and add the standard deviation to the minimum heart rate. It can be calculated with. Then, the activity state at that time is acquired from the state determination unit 11 of the smartphone 1 and set in the table as the drowsiness reference heart rate at midnight of the activity state.

Further, the drowsiness reference heart rate may be calculated and set by the smartphone 1 shown in FIG. 1, or information such as the heart rate may be transmitted to the server 2 and calculated by the server 2. It may be calculated and set separately with the configuration as shown above, and transferred to the drowsiness reference heart rate table 21 of the server 2. The initial calibration unit 31 calculates the drowsiness reference heart rate by the method described above.

In addition, since a person performs various activities in a day, it is difficult to fill in all the times and activity states of the drowsiness reference heart rate table 21 even if the heart rate is measured for 24 hours (FIG. 9 (a)). ). Therefore, the data may be interpolated so that the blank portion becomes smooth based on the data before and after the blank portion (FIG. 9 (b)).

In addition, the portion filled by interpolation in the initial state may be updated (added) to the calculated value when the drowsiness reference heart rate is calculated by the subsequent measurement. Further, other interpolated values may be updated based on the update (addition). By doing so, the accuracy of the drowsiness reference heart rate can be improved. That is, the drowsiness reference heart rate table 21 adds or updates the drowsiness reference heart rate based on the measurement time of the heart rate and the activity state of the subject detected by the state determination unit 11 (activity state acquisition unit). It also functions as a number setting unit.

The terminal communication unit 22 receives the heart rate (including heart rate fluctuation), the measurement time, and the activity state determined by the state determination unit 11 from the smartphone 1. The received heart rate, measurement time, and activity state are used by the correction unit 24 and are stored in the personal history data storage unit 25. Further, the terminal communication unit 22 transmits the corrected drowsiness reference heart rate corrected by the correction unit 24 to the smartphone 1. That is, the terminal communication unit 22 functions as an activity state acquisition unit in the server 2.

The external communication unit 23 acquires information on the heart rate and blood glucose level from the stationary measuring device 3 (including the measurement time). The acquired heart rate and blood glucose division methods are stored and stored in the personal history data storage unit 25.

The correction unit 24 reads and acquires the drowsiness reference heart rate from the drowsiness reference heart rate table 21 based on the current time and the activity state determined by the state determination unit 11. Then, the read drowsiness reference heart rate is acquired from the heart rate, activity state, blood glucose level, etc. stored in the personal history data storage unit 25, and the drowsiness reference heart rate is obtained based on the information. To correct. The current time may be referred to from the clock function built in the server 2, or may be acquired from an external NTP (Network Time Protocol) server or the like. That is, the correction unit 24 also functions as a drowsiness reference heart rate acquisition unit and a date / time acquisition unit.

Here, a method for the correction unit 24 to acquire (calculate) information on past activities will be described. Information on past activities that correct the drowsiness reference heart rate in this embodiment includes fatigue, sleep time, and dietary status (whether after meals or not).

First, the degree of fatigue will be described. Fatigue indicates the degree of current fatigue due to past activities (fatigue information associated with past activities). Since it is easy to get sleepy depending on the degree of fatigue, the accuracy of calculating the degree of drowsiness can be improved by correcting the reference heart rate for drowsiness according to the degree of fatigue. The degree of fatigue can be calculated from the high-frequency component HF of the heartbeat fluctuation and the low-frequency component LF of the heartbeat fluctuation described above. The low frequency component LF can be obtained by frequency analysis of the RR interval in the same manner as the high frequency component HF. Since the RR interval is the reciprocal of the heart rate as shown in the equation (3), it can be calculated from the heart rate stored in the personal history data storage unit 25. The degree of fatigue is calculated by the following equation (5).
Fatigue HRV = LF / HF ... (5)

Then, assuming that the average value of the fatigue degree HRV is av,
If HRV> av, I'm not tired at all,
When av ≧ HRV> 0.75 × av, I am a little tired,
If 0.75 x av ≥ HRV> 0.5 x av, you are tired.
If 0.5 x av ≥ HRV> 0.25 x av, you are quite tired,
If 0.25 x av ≥ HRV, you are very tired,
Can be classified into 5 stages.

Then, according to the above classification, "not tired at all" is level 0, "slightly tired" is level 1, "tired" is level 2, "quite tired" is level 3, and "very tired". As shown in FIG. 10, the drowsiness reference heart rate is corrected according to the fatigue level. In the case of the example of FIG. 10, when the fatigue level is 4, 10 is added to the read drowsiness reference heart rate. This added value becomes the corrected drowsiness reference heart rate. The added correction value is an example, and can be changed as appropriate by setting.

The degree of fatigue can also be calculated from the results of an activity meter (activity sensor) (not shown). The activity meter detects a change in acceleration due to body movement at a frequency of 2 to 3 Hz at 0.01 G or higher. It is known that the average amount of activity during awakening is about 200 times / minute as measured by such an activity meter. Therefore, the current amount of activity is classified as follows.
When the amount of activity> 400, I am not tired at all,
If 400 ≥ activity> 350, you are a little tired,
If 350 ≥ activity> 250, you are tired,
If 250 ≥ activity> 200, you are quite tired,
If 200 ≥ activity, you are very tired.

When classified in this way, the drowsiness reference heart rate can be corrected using FIG. Therefore, the degree of fatigue can also be calculated by a method in which the measurement result of the activity meter is periodically transmitted to the server 2 and stored in the personal history data storage unit 25.

Alternatively, the screen as shown in FIG. 11 may be displayed on the smartphone 1 so that the subject can select it.

Next, the sleep time will be described. Sleep time indicates whether or not you slept well the night before. That is, it shows past sleep information. If you cannot sleep well, you tend to get sleepy after that. Therefore, you can improve the accuracy of calculating the drowsiness level by correcting the drowsiness reference heart rate according to the sleep time. Since the heart rate decreases during sleep, the sleep time can be estimated from the heart rate stored in the personal history data storage unit 25. Then, the sleep time is classified as follows.
If sleep time> 8 hours, I slept well,
When 8 hours ≥ sleep time> 6 hours, I slept normally,
When 6 hours ≥ sleep time> 2 hours, I couldn't sleep much,
When 2 hours ≥ sleep time> 0 hours, I couldn't sleep,
When 0 hours = sleep time, I could not sleep at all.

Then, according to the above classification, "I slept well" was level 0, "I slept normally" was level 1, "I couldn't sleep much" was level 2, and "I couldn't sleep" was level 3. , "I couldn't sleep at all" is set to level 4, and the drowsiness reference heart rate is corrected according to the sleep level as in FIG. Of course, the correction value may be a value different from the example of FIG.

Further, regarding sleep, the screen as shown in FIG. 12 may be displayed on the smartphone 1 so that the subject can select it.

Next, the meal situation will be described. The meal status indicates whether or not the person has recently eaten (fullness, etc.). That is, it shows past meal information. It is possible to determine whether or not a person has eaten by detecting an increase in blood glucose level. Since the blood glucose level is accumulated in the personal history data storage unit 25, it is determined from the data.

Then, the correction value is added as shown in FIG. 13 according to the elapsed time from the meal. For example, if it is within 1 hour after eating, 3 is added to the read drowsiness reference heart rate. The correction value is an example and can be changed as appropriate by setting.

In addition, the meal situation may be determined from the position information of the subject. For example, if you stay near a specific point (within a certain range) such as a restaurant for a certain period of time or more, and if your heart rate rises, it is determined that you are eating. The position information of the subject can be determined by acquiring the information of the GPS receiver 12 of the smartphone 1. That is, in this case, the individual history data storage unit 25 also stores the past position information (stay history) of the subject.

The flow chart of the meal determination will be described with reference to FIG. The flowchart of FIG. 14 may be performed by the correction unit of the server 2, but may be performed by the smartphone 1 and only the result is transmitted. When the server 2 executes it, it provides map information, point information, etc., or acquires it from the outside. When executing on smartphone 1, it is necessary that a map application and a navigation application (navigation application) are installed.

First, in step S11 of FIG. 14, the current location is acquired. Next, in step S12, it is determined whether or not there is a facility to eat within a certain range, and if there is (yes), the staying time is acquired in step S13. On the other hand, if there is no facility to eat within a certain range (NO), the process returns to step S11 (determines that the person has not eaten).

Next, in step S14, it is determined whether or not the person has stayed for a certain period of time or more, and if he / she has stayed for a certain period of time or more (YES), the heart rate is acquired in step S15. Then, in step S16, it is determined whether or not the heart rate has increased, and if it has increased (YES), it is determined that the person has eaten. On the other hand, if the person does not stay for a certain period of time or more in step S14 (NO) or the heart rate does not increase in step S16 (NO), the process returns to step S11 (determines that he / she is not eating). That is, the past stay history is that the person stayed at the eating facility (specific point) for a certain period of time or longer.

In addition, corrections may be made based on information on a plurality of past activities. For example, a value as shown in FIG. 15 may be added and corrected depending on both the state of fatigue and the state of sleep time. In the case of FIG. 15, when the fatigue level is 4 and the sleep level is 4, 10 is added.

In addition, dietary conditions may also be combined. For example, in FIG. 15, the correction value of the fatigue degree and the sleep situation may be obtained, then the correction value of the dietary situation may be obtained, and both correction values may be added.

The personal history data storage unit 25 contains historical data such as heart rate, measurement time, activity status, etc. received by the terminal communication unit 22, and heart rate, blood glucose level, measurement time, etc. transmitted from the stationary measuring device 3. It is stored for each individual. The server 2 may create or update the drowsiness reference heart rate table 21 based on the history data stored in the personal history data storage unit 25.

FIG. 16 shows a flowchart of the operation of the drowsiness calculation device 50 having the above-described configuration. First, in step S21, the communication unit 15 transmits the user ID and password assigned to each user from the smartphone 1 to the server 2. The server 2 authenticates the user with the user ID and password transmitted from the smartphone 1 in step S31.

Next, the communication unit 15 transmits the activity state determined by the state determination unit 11 from the smartphone 1 to the server 2. The server 2 receives the activity state transmitted from the smartphone 1 in step S32. That is, this step functions as an activity state acquisition process.

Next, the server 2 acquires (reads) the history data (heart rate, blood glucose level, etc.) stored in the individual history data storage unit 25 in step S33. Then, in step S34, the correction unit 24 reads the drowsiness reference heart rate from the activity state and the current time from the drowsiness reference heart rate table 21, corrects the read drowsiness reference heart rate based on the above-mentioned fatigue level, and corrects it. It is transmitted to the smartphone 1 as a drowsiness reference heart rate. That is, step S34 functions as a drowsiness reference heart rate acquisition step, an activity history acquisition step, and a correction step.

Next, the smartphone 1 receives the corrected drowsiness reference heart rate from the server 2 in step S23. Subsequently, in step S24, the drowsiness degree calculation unit 16 calculates the drowsiness degree and displays it on the drowsiness degree display unit 17. That is, step S24 functions as a drowsiness calculation step. Then, in step S25, the history data (heart rate, measurement time, etc.) is transmitted to the server 2. That is, this step functions as a biological information acquisition step. The history data may be transmitted when the activity state is transmitted in step S22.

Next, in step S35, the server 2 stores the received history data in the personal history data storage unit 25.

FIG. 17 shows a flowchart of the operation of step S34 (correcting and transmitting the drowsiness reference heart rate) of FIG. First, in step S41, the degree of fatigue and the sleep time are calculated, and in step S42, the correction value is calculated from the degree of fatigue and the sleep time based on the table shown in FIG.

Next, in step S43, it is determined whether or not it is after a meal from the blood glucose level and the position information as described above. If it is after a meal, the correction value based on the table shown in FIG. 13 is further added to the correction value calculated in step S43 (+ α), and the drowsiness reference heart rate corrected by the correction value calculated in step S44 in step S45. The number is calculated as the corrected drowsiness reference heart rate and transmitted. On the other hand, if it is not after meals, the drowsiness reference heart rate corrected by the correction value calculated in step S42 in step S45 is calculated as the corrected drowsiness reference heart rate and transmitted.

In the flowchart of FIG. 17, the drowsiness reference heart rate was corrected each time, but for the fatigue level and sleep time, the correction values were determined in the morning of the day, and the drowsiness reference heart rate table was generated based on the correction values. You may try to do it. Then, the drowsiness reference heart rate may be read out from the generated drowsiness reference heart rate table based on the activity state and the current time. For meals, the values in the generated drowsiness reference heart rate table may be corrected.

According to this embodiment, in the smartphone 1, the I / F 18 acquires the heart rate and the measurement time of the subject measured by the heart rate sensor 19, and the state determination unit 11 determines the activity state of the subject. Send to server 2. Next, in the server 2, the drowsiness reference heart rate from the drowsiness reference heart rate table 21 in which the drowsiness reference heart rate of the subject is stored for each activity state according to the activity state transmitted from the smartphone 1 by the correction unit 24 To get. Next, the drowsiness reference heart rate acquired by the correction unit 24 is corrected based on the degree of fatigue, sleep time, and meal status calculated from the history data read from the personal history data storage unit 25. Then, the corrected drowsiness reference heart rate (corrected drowsiness reference heart rate) is transmitted to the smartphone 1, and the test is performed based on the corrected drowsiness reference heart rate and the heart rate acquired by the I / F 18 by the drowsiness degree calculation unit 16 of the smartphone 1. Calculate the drowsiness of a person. By doing so, the drowsiness reference heart rate can be corrected based on the past activity state of the subject, so that the drowsiness can be calculated with high accuracy by considering not only the current activity but also the past activity. can do.

In addition, the correction unit 24 has acquired information on the degree of fatigue, sleep time, and meal status as information on the past activity status of the subject. By doing so, the drowsiness reference heart rate can be corrected in consideration of the subject's fatigue level, sleep time, and dietary status information. Therefore, it is possible to calculate the drowsiness level in consideration of these factors.

Further, the server 2 adds or updates the drowsiness reference heart rate stored in the drowsiness reference heart rate table 21 based on the time when the heart rate is measured and the activity state of the subject determined by the state determination unit 11. There is. By doing so, it is possible to update or add the change in the drowsiness reference heart rate for each time of the active state due to the daily life of the subject at any time.

In addition, the drowsiness calculation unit 16 calculates the drowsiness of the subject based on the drowsiness prediction parameters set in advance for each active state. By doing so, the heart rate and the heart rate fluctuation can be weighted according to the activity state.

Further, since the drowsiness display unit 17 is provided, the subject can specifically perceive his / her drowsiness, and can take measures such as resting and exercising based on the displayed drowsiness. it can.

It should be noted that the degree of fatigue of the subject, the sleeping time, and the dietary status information are not limited to be acquired, and only one of them may be acquired.

In addition, although it has been explained that the position information is used when determining whether or not it is after a meal, it is not limited to the determination after a meal. For example, after staying in a relaxation facility such as a hot spring, the tension is relaxed and it is easy to get sleepy. Therefore, if the patient stays in the relaxation facility for a certain period of time or longer, the drowsiness reference heart rate may be corrected. Whether or not the person stayed at the relaxation facility can be determined in the same manner as the flowchart of FIG. That is, the past stay history is that the person stayed at the relaxation facility (specific point) for a certain period of time or longer.

Further, in the above-described embodiment, the drowsiness prediction parameter and the drowsiness reference heart rate were selected based on the activity state and the measurement time, but even if the drowsiness prediction parameter and the drowsiness reference heart rate are selected based only on the activity state. Good. However, it is preferable to consider the measurement time because an appropriate drowsiness prediction parameter and drowsiness reference heart rate can be selected.

Further, in addition to the drowsiness degree display unit 17, the drowsiness degree may be notified by voice. Alternatively, voice notification may be given when the degree of drowsiness is above a certain level.

Further, the server 2 may include both or one of the parameter table 14 and the drowsiness degree calculation unit 16, and the smartphone 1 may include both or one of the drowsiness reference heart rate table 21 and the correction unit 24. Further, the smartphone 1 may be provided with the configuration without using the server 2.

Next, the drowsiness calculation device according to the second embodiment of this embodiment will be described with reference to FIGS. 18 to 20. The same parts as those in the first embodiment described above are designated by the same reference numerals, and the description thereof will be omitted.

In the first embodiment, the drowsiness reference heart rate was corrected based on the information on the past activity, but in the present embodiment, the future activity is predicted and the correction is performed accordingly. The configuration is the same as the configuration shown in FIGS. 1 to 3. That is, the correction unit 24 functions as an activity prediction unit. In this embodiment, the smartphone 1 will be described, but as is clear from the following description, a car navigation system may be used.

For example, when a subject drives a vehicle such as a car and returns to his / her home, it is predicted that there will be more relatively calm and relaxing activities such as resting and sleeping in the future, and the tension will be relaxed and he / she will easily become sleepy. On the other hand, when going to a resort on a trip, etc., it is predicted that there will be more relatively active activities such as shopping and walking in the future, and it is thought that the mood is often uplifted and it is difficult to get sleepy.

Therefore, when the destination is set in the navigation application or the like of the smartphone 1, the information is transmitted to the server 2. Then, based on the destination, correction is performed by further adding a correction value as shown in FIG. 18, for example, to the corrected drowsiness reference heart rate corrected in the first embodiment. In addition, the information of "home" or "resort" may be transmitted from the smartphone 1 instead of the information of the destination. That is, the terminal communication unit 22 functions as a destination information acquisition unit that acquires information about the destination to which the subject is heading, and the correction unit 24 predicts the activity of the subject based on the information about the destination. There is.

Also, even when heading to a resort, you will not feel drowsy at the time of departure, but you may get sleepy at the intermediate point. Therefore, in addition to the correction shown in FIG. 18, as shown in FIG. 19, the destination is from the intermediate point. It may be corrected according to the distance of. As for the distance in FIG. 19, 0% is the starting point and 100% is the destination. Further, not limited to the distance, the time required from the departure point to the destination may be corrected according to the ratio of the time required from the intermediate point to the destination. In that case, even if the distance in FIG. 19 is changed to the required time, the same correction can be made.

According to this embodiment, the correction unit 24 predicts the activity of the subject, and corrects the drowsiness reference heart rate read from the drowsiness reference heart rate table 21 based on the predicted activity. By doing so, it is possible to correct the drowsiness reference heart rate in consideration of future schedules such as going to play in the future in addition to past activities.

Further, the server 2 acquires information on the destination to which the subject is heading from the smartphone 1 by the terminal communication unit 22, and the correction unit 24 predicts the activity of the subject based on the information on the destination. .. By doing so, it is possible to predict future plans such as whether the destination itself is a home or a trip.

In the above description, corrections have been made in addition to the past activity status described in the first embodiment, but only future predictions described in the present embodiment may be corrected.

Also, when driving a vehicle, if the road you are currently driving is monotonous, you will easily get sleepy, and if it is a complicated road, you will concentrate on it, so it will be clear, so in addition to corrections based on past and future predictions, As shown in FIG. 20, the correction may be made based on the shape of the road currently traveling.

That is, the terminal communication unit 22 acquires information on the current location where the subject is located. Next, when the current activity state of the subject acquired by the terminal communication unit 22 is driving a vehicle, the correction unit 24 obtains the drowsiness reference heart rate acquired according to the activity state as information on the current location. Correct based on. It should be noted that the fact that the vehicle is being driven can be determined by the state determination unit 11 as described above.

Further, the route to be guided by the navigation application or the like may be changed based on the drowsiness degree calculated by the smartphone 1. That is, a guide unit (navigation application) that searches for a route to a preset destination and provides guidance is further provided, and the guide unit is a route to the destination based on the drowsiness degree calculated by the drowsiness degree calculation unit 16. You may search for.

Next, the drowsiness calculation device according to the third embodiment of this embodiment will be described with reference to FIGS. 21 and 22. The same parts as those of the first and second embodiments described above are designated by the same reference numerals, and the description thereof will be omitted.

The basic configuration of this embodiment is the same as that of the first embodiment (FIGS. 1 to 3). The drowsiness level shown in the first embodiment is calculated based on the heart rate and the like measured by the heart rate sensor 19, but the calculated value and the subject's sensation may deviate from each other. Therefore, in this embodiment, the subject subjectively evaluates the drowsiness level displayed on the drowsiness level display unit 17, and corrects (updates) the drowsiness reference heart rate based on the evaluation.

A specific example will be described with reference to FIGS. 21 and 22. 21 and 22 are display examples of the drowsiness degree display unit 17, and show a change in heart rate, a drowsiness reference heart rate graph 171 and a drowsiness degree graph 172, and a drowsiness degree level. For this drowsiness level, the evaluation of the subject can be input by touching the displayed numerical value. That is, in the examples of FIGS. 17 and 18, the drowsiness display unit 17 is a touch panel.

In the case of FIG. 21, the drowsiness reference heart rate is 74. The current drowsiness level is 4 from the calculation result of the drowsiness level calculation unit 16. At this time, the subject subjectively evaluates the current degree of drowsiness.

As a result of the subjective evaluation, when the subject evaluates that the drowsiness level is 2, the subject selects and operates the drowsiness level 2 of the input unit 9 as shown in FIG. Then, the drowsiness reference heart rate correction unit 10 corrects the drowsiness reference heart rate according to the subjective evaluation. In the case of FIG. 21, it is corrected to 72. Then, the drowsiness degree is recalculated based on the corrected drowsiness reference heart rate, and the drowsiness degree graph 6b is also corrected (FIG. 22).

Next, the correction of the drowsiness reference heart rate in the drowsiness reference heart rate correction unit 10 will be described. When the equation (2) described in the first embodiment is modified, the following equation (6) is obtained.
RR_ref = RR- (Db × HFS) / a ... (6)

Therefore, the modified RR_ref can be calculated by substituting the subjective evaluation value into D in Eq. (6). Then, the drowsiness degree is recalculated by the equation (2) based on the modified RR_ref. Since RR_ref and the drowsiness reference heart rate HR_ref have the relationship shown in the equation (4) described in the first embodiment, the drowsiness reference heart rate HR_ref can be easily calculated by modifying the equation (4). can do.

The modified drowsiness reference heart rate HR_ref is used to display the change in heart rate and the drowsiness reference heart rate graph 6a, and is also transmitted to the server 2 to display the drowsiness reference at the corresponding activity state and time of the drowsiness reference heart rate table 21. Heart rate corrections are also made. Further, not only the drowsiness reference heart rate but also various correction values may be modified. Since the correction values described in the first and second embodiments may also have individual differences, it is advisable to feed back the results of the subjective evaluation.

According to this embodiment, a touch panel is provided for inputting a subjective evaluation of the subject for the drowsiness level presented on the drowsiness level display unit 17. Then, the drowsiness degree calculation unit 16 corrects the drowsiness reference heart rate based on the subjective evaluation input by the touch panel, and calculates the drowsiness degree again based on the corrected drowsiness reference heart rate. By doing so, the subject can subjectively evaluate the drowsiness degree calculated by the drowsiness degree calculation unit 16. Then, the drowsiness degree calculation unit 16 can calculate the drowsiness degree again by feeding back the subjective evaluation result. Therefore, it is possible to more accurately calculate information on drowsiness tailored to the individual subject.

The present invention is not limited to the above examples. That is, those skilled in the art can carry out various modifications according to conventionally known knowledge within a range that does not deviate from the gist of the present invention. Of course, such a modification is included in the category of the present invention as long as it still has the configuration of the drowsiness calculation device of the present invention.

1 Smartphone 2 Server (information processing device)
3 Stationary measuring instrument 11 Status determination unit (activity status acquisition unit)
12 GPS receiver (current location information acquisition department)
13 G sensor 14 Parameter table 15 Communication unit 16 Drowsiness calculation unit 17 Drowsiness display unit (display unit, destination information acquisition unit, input unit)
18 I / F (Biological Information Acquisition Department)
19 Heart rate sensor 21 Drowsiness standard heart rate table (drowsiness standard heart rate storage unit)
22 Terminal communication department (biological information acquisition department, activity status acquisition department, current location information acquisition department, destination information acquisition department)
23 External communication unit 24 Correction unit (sleepiness standard heart rate acquisition unit, activity history acquisition unit, activity prediction unit)
25 Individual history data storage unit 50 Drowsiness calculation device S25 History data reception (biological information acquisition process)
S22 Activity status acquisition (activity status acquisition process)
S23 History data acquisition (activity history acquisition process)
S24 Correct and transmit the reference heart rate (drowsiness reference heart rate acquisition process, correction process)
S14 Drowsiness calculation (sleepiness calculation process)

Claims (1)

A biometric information acquisition unit that acquires biometric information regarding the subject's heartbeat,
A fatigue level information acquisition unit that acquires fatigue level information regarding the fatigue level of the subject, and
A drowsiness calculation unit that calculates information on the current drowsiness of the subject based on the biological information and the fatigue degree information.
A drowsiness calculation device characterized by comprising.

Images