JP5862407B2 - Biological information processing apparatus and biological information processing method - Google Patents

Description

  The present case relates to a biological information processing apparatus and a biological information processing method.

  Even if a driver who drives a vehicle (for example, an automobile) does not have an accident, he or she may encounter a dangerous situation such as “near” or “hit”. Such a dangerous state is called “near-miss”. Conventionally, it has been proposed to reduce accidents by collecting points where “missing hats” occur and providing information on “missing hats” to vehicles traveling through these “missing hats” (for example, Patent Document 1). reference).

JP 2003-123185 A

  Such “missing hats” occur, for example, when passing through a chronic danger position due to the road environment, such as darkness, poor visibility, and frequent parking on the road, or just before an accident occurs. To do. As a method of extracting the “missing hat” during driving, for example, there is a method of acquiring the heart rate from the driving driver and extracting the case where the heart rate has greatly changed from the average value as the “missing hat”.

  In this case, a near-accident near-accident incident is relatively easy to detect because a large biological reaction that doubles the heart rate occurs. However, regarding the near-miss when passing through a chronic danger position, the change in heart rate is about 10% higher than the average value, so detection is difficult due to the influence of other noise factors. There is a fear.

  Elements that cause noise include the state of the driver's body (such as fatigue). For this reason, if the driver gets tired due to long-term driving, etc., the heart rate decreases, the sensitivity to stimulation decreases, and the biological reaction becomes dull. .

  Therefore, the present case has been made in view of the above problems, and a biological information processing apparatus and a biological body capable of executing processing using biological information of the driver while suppressing the influence of the physical state of the driver An object is to provide an information processing method.

  The biometric information processing device described in the present specification includes a biometric information acquisition unit that acquires biometric information of a driver who drives a vehicle in association with position information, and the driver's biometric information obtained from a time change of the biometric information. A calculation unit that calculates a correction value for correcting the influence of fatigue on the biological information, a correction unit that corrects the biological information based on the correction value, and a process using the corrected biological information are executed. And a processing unit.

  Further, the biological information processing apparatus described in the present specification includes a biological information acquisition unit that acquires biological information of a driver who drives a vehicle in association with position information, a detection unit that detects sleepiness of the driver, A processing unit that executes processing using biological information other than the biological information corresponding to the timing at which the driver's sleepiness is detected by the detection unit.

  Further, the biological information processing method described in the present specification includes the biological information acquisition step of acquiring the biological information of the driver who drives the vehicle in association with the position information, and the driving obtained from the time change of the biological information. A calculation step for calculating a correction value for correcting the influence on the biological information due to the fatigue of the person, a correction step for correcting the biological information based on the correction value, and a process using the corrected biological information And a biological information processing method executed by a computer.

  Further, the biological information processing method described in the present specification includes a biological information acquisition step of acquiring biological information of a driver who drives a vehicle in association with position information, a detection step of detecting sleepiness of the driver, A biological information processing method in which a computer executes a processing step of executing processing using biological information other than biological information corresponding to timing at which the driver's sleepiness is detected.

  The biometric information processing device and the biometric information processing method described in the present specification have an effect that it is possible to execute processing using the driver's biometric information while suppressing the influence of the driver's physical state.

It is a figure showing roughly the composition of the hazard map creation system concerning one embodiment. It is a block diagram of a heart rate variability recording device and a hazard map creation device. It is a figure which shows the hardware constitutions of a hazard map production apparatus. FIG. 4A is a diagram showing the heart rate information DB, and FIG. 4B is a diagram showing the heart rate variability DB. FIG. 5A is a diagram illustrating the heart rate variability during travel of the driver A, FIG. 5B is a diagram illustrating the heart rate variability during travel of the driver B, and FIG. It is a figure which shows the heartbeat fluctuation average at the time of driving | running | working of B. It is a model figure of the heart rate change by the time passage of a long driving. It is a flowchart which shows the flow of a calculation process of a correction parameter. FIG. 8A is a diagram illustrating an example of data read when calculating the correction parameter, and FIG. 8B is a table illustrating an example of actual measurement values. It is a flowchart which shows the process of a heart rate variability statistical process part. FIGS. 10A and 10B are diagrams showing examples of simulations when the average heart rate is reduced from 70 to 50 due to fatigue due to running. FIG. 11A and FIG. 11B are diagrams showing examples of simulations when the average heart rate decreases from 70 to 50 due to fatigue due to running and sleepiness occurs in part of running. It is a flowchart which shows the process of the heart rate variability statistical process part concerning a modification.

  Hereinafter, a hazard map creation system according to an embodiment will be described in detail with reference to FIGS. FIG. 1 schematically shows a configuration of a hazard map creation system 100 according to an embodiment. This hazard map creating system 100 is based on, for example, the heartbeat of the driver who drives the vehicle, a chronic danger position (missing hat) caused by the road environment such as darkness, poor visibility, and frequent parking on the road. This is a system that identifies and outputs a point.

  The hazard map creation system 100 includes a heart rate variability recording apparatus 10 mounted on a vehicle (in the present embodiment, an automobile) and a hazard map creation apparatus 30 as a biological information processing apparatus. The heart rate variability recording apparatus 10 and the hazard map creating apparatus 30 are connected to a network 80 such as the Internet or a LAN (Local Area Network).

  FIG. 2 shows a block diagram of the heart rate variability recording device 10 and the hazard map creation device 30. As shown in FIG. 2, the heart rate variability recording device 10 includes a heart rate measuring device 12, a position measuring device 14, a time measuring device 16, a recording unit 18, a communication unit 20, and a heart rate information DB 22.

  The heart rate measuring device 12 is a device that measures the driver's heart rate, for example, by being installed on the steering wheel of the vehicle or attached to the driver's ear and contacting (or approaching) the driver. As the heartbeat measuring device 12, a pulse sensor using infrared rays can be used. The position measuring device 14 includes a GPS (Global Positioning System) module, an acceleration sensor, and the like, and measures the position of the vehicle (an absolute position represented by latitude and longitude, a distance from the starting point of the route, etc.). In addition, when the car navigation system is previously mounted on the vehicle, the position measurement function of the car navigation system may be used as the position measurement device 14. The time measuring device 16 has a time measuring function and transmits the current date and time to the recording unit 18.

  The recording unit 18 has a CPU and the like, and stores it in the heartbeat information DB 22 in a state in which the measurement results in the heartbeat measurement device 12, the position measurement device 14, and the time measurement device 16 are associated with each other. The communication unit 20 transmits the heart rate data stored in the heart rate information DB 22 to the hazard map creation device 30 at predetermined time intervals (for example, every other day).

  The heartbeat information DB 22 has, for example, a data structure as shown in FIG. That is, the heart rate information DB 22 has fields of “time”, “route”, “distance”, and “heart rate”. In the “time” field, the time when the heart rate is measured by the heart rate measuring device 12 (measured by the time measuring device 16) is input. In the “route” field, the name of the route on which the vehicle is traveling, which is derived from the position measured by the position measurement device 14 when the heart rate is measured, is input. In the “distance” field, the distance from the starting point of the route, which is derived from the position measured by the position measuring device 14 when the heart rate is measured, is input. In the “heart rate” field, the heart rate measured by the heart rate measuring device 12 is input.

  The hazard map creation device 30 includes a server and has a hardware configuration as shown in FIG. Specifically, as shown in FIG. 3, the hazard map creation device 30 includes a CPU 90, a ROM 92, a RAM 94, a storage unit (HDD (Hard Disk Drive)) 96, a network interface 97, and a portable storage medium drive 99. The components of the hazard map creation device 30 are connected to a bus 98. In the hazard map creation device 30, the CPU 90 executes a program stored in the ROM 92 or the HDD 96 or a program read from the portable storage medium 91 by the portable storage medium drive 99, whereby the functions of the respective units in FIG. Realized.

  That is, in the hazard map creation device 30, when the CPU 90 executes the program, the communication unit 32 as the biological information acquisition unit, the heart rate variability statistical processing unit 34, the correction parameter calculation unit 38 as the calculation unit, and the near-miss point specifying unit 36. Function as. FIG. 2 also shows a heart rate variability DB 40 stored in the HDD 96 or the like.

  The communication unit 32 receives heart rate data from the communication unit 20 of the heart rate variability recording apparatus 10 and stores it in the heart rate variability DB 40. Here, the heart rate variability DB 40 has a data structure as shown in FIG. That is, the heart rate variability DB 40 has fields of “driver”, “time”, “route”, “distance”, and “heart rate”. In the “driver” field, a driver who is driving the vehicle (assumed to be registered in advance) is input. For the other fields, data similar to the heartbeat information DB 22 in FIG. 4A is input.

  The heart rate variability statistical processing unit 34 extracts necessary data from the heart rate variability DB 40 based on the conditions input by the user of the hazard map creation device 30 and corrects or totals the extracted data. Output to the near-miss point identifying unit 36.

  The correction parameter calculation unit 38 calculates correction parameters used in the heart rate variability statistical processing unit 34. Details of the correction parameters will be described later.

  The near-miss point identifying unit 36 identifies and outputs a position (a near-miss point) where the driver feels dangerous based on the data output from the heart rate variability statistical processing unit 34.

  Next, the process of the hazard map creating apparatus 30 in the present embodiment will be described in detail with reference to FIGS. 5 to 11 and appropriately referring to other drawings.

  Here, the identification principle of the near-miss point in the present embodiment will be described. When a driver passes a chronic danger position (near-missing point) such as a curve with poor visibility or a difficult-to-drive road, the heart rate of the driver increases by about 10% and is difficult to detect. Therefore, in the present embodiment, for example, as shown in FIGS. 5A and 5B, the heart rate variability corresponding to the travel distance from a certain starting point is plural times for each of a plurality of drivers (drivers A and B). Obtained, and as shown in FIG. 5C, the average heart rate variability during driving of each driver is calculated. In this case, in each driver, a point where the heart rate variability average is increasing (a point where the heart rate variability (rate) increases by a predetermined value or more) can be identified as a near-miss point.

  However, when the driver continues driving for a long time, the driver gets tired, so that the biological function is generally lowered and the reaction becomes dull. Even if the average heart rate variability during driving as shown in FIG. 5 (c) is calculated in this state, since the heart rate variability when the driver is tired is small, it has an influence on the identification of a chronic danger position (near-miss point). May occur.

  In addition to fatigue, other influences on identifying near-miss points include a decrease in perception due to sleepiness. A certain amount of sleepiness will cause a decrease in the biological response as well as fatigue, but if the driver receives intense sleepiness, the driver will be less conscious or in a state of dredging. End up.

  Therefore, in this embodiment, in order to suppress the influence of fatigue due to long-time driving, a correction parameter is calculated and used to identify the near-miss point, and the heart rate data when drowsiness is occurring is used as near-miss It will not be used to identify a point.

  FIG. 6 is a model diagram showing a change in heart rate over time of long-time driving for explaining the calculation principle of the correction parameter. As shown in FIG. 6, when the driver accumulates fatigue over time, the average heart rate of the driver (shown by a broken line) generally decreases and the heart rate fluctuation amount (shown by a solid line). ) Decreases. Therefore, in the present embodiment, the heart rate change during driving by the driver is applied to this model, and the rate of change of the average heart rate b and the instantaneous rate are compared by comparing the time range a0 with less fatigue with the time range a1 with progress of fatigue. The relationship of the rate of change of heart rate fluctuation d is used as a correction parameter.

Specifically, in the model of FIG. 6, it is assumed that the average heart rate fluctuates from b0 to b1 and the instantaneous heart rate fluctuation fluctuates from d0 to d1 due to the transition from the range a0 to a1. In this case, the model of FIG. 6 is a linear proportional model represented by the following equation (1), where p is a proportional constant.
(D1-d0) = p × (b1-b0) (1)

  The proportionality constant p represents the change in sensitivity of the heart rate to the accumulation of fatigue (fatigue progression) and is considered to have individual differences. For this reason, for each driver, a range in which the driving conditions are set from actual driving data (location where the near-miss state is difficult to occur during driving) a0 and a1 are sampled, and a representative value (or an average value obtained by sampling a plurality of values) b0. , B1, d0, d1 may be used to determine the proportionality constant p. Note that the first-order proportional model in FIG. 6 has only one parameter to be obtained, so that there is an advantage that parameter identification is easy.

  Hereinafter, the flow of the correction parameter calculation process will be specifically described with reference to FIG. The process in FIG. 7 is a process executed by the correction parameter calculation unit 38 in FIG.

  In the process of FIG. 7, first, in step S <b> 10, the correction parameter calculation unit 38 reads out the target data of the driver whose correction parameter is to be calculated from the heart rate variability DB 40. In this case, for example, actual data as shown in FIG.

  Next, in step S12, the correction parameter calculation unit 38 detects a stable travel region. As the stable travel region, for example, a point (region) that has not been determined as a near-miss point from other driver data in the processing so far can be detected. In the data of FIG. 8A, it is assumed that the range a0 (range of 10 to 15 minutes) and the range a1 (range of 70 to 75 minutes) are detected as the stable travel region.

  Next, in step S14, the correction parameter calculation unit 38 calculates a combination of heart rate versus instantaneous heart rate fluctuation. Here, as shown in FIG. 8B, the value in the “average” column is calculated as the heart rate, and the value in the “unbiased variance” column is calculated as the instantaneous heart rate fluctuation. Unbiased variance indicates the degree of fluctuation in instantaneous heart rate.

Next, in step S16, the correction parameter calculation unit 38 calculates a correction parameter. In this case, the correction parameter p is calculated based on the above equation (1). Since the unbiased variance indicates the fluctuation rate of the instantaneous heart rate as described above, it is necessary to obtain the reduction rate of the unbiased variance as the left side of the above equation (1).
(29.262465-28.211638) /29.262465×100=p× (101.6933−94.51807)
p ≒ 3.59 / 7.18 ≒ 4/7

  In the present embodiment, the heart rate variability statistical processing unit 34 uses the correction parameter p obtained through the processing of FIG. 7 to obtain data (heart rate variability statistics) necessary for identifying the near-miss point according to the flowchart shown in FIG. Value). Hereinafter, the processing of the heart rate variability statistical processing unit 34 will be described in detail with reference to FIG.

  In the process of FIG. 9, first, in step S <b> 20, the heart rate variability statistical processing unit 34 waits until a search condition is set by the user of the hazard map creation device 30. Note that the user inputs a route, range, and time zone for which a hazard map is to be created as a search condition.

  When the search condition is input by the user, the heart rate variability statistical processing unit 34 proceeds to step S22 and creates a database search condition. In this case, the heart rate variability statistical processing unit 34 calculates a route range set as a search condition, divides the route range at a predetermined interval (for example, 100 m interval), Estimate the time of passage.

  Next, in step S24, the heart rate variability statistical processing unit 34 searches the heart rate variability DB 40 based on the created database search condition, and acquires data that meets the search condition. In this case, it is assumed that a plurality of drivers acquire data for a plurality of times when driving in the same range.

  Next, in step S26, the heart rate variability statistical processing unit 34 performs fatigue correction using the correction parameter p.

  FIG. 10 shows an example of a simulation when the average heart rate is reduced from 70 to 50 due to fatigue due to running. In FIG. 10 (a), it is assumed that sections 10 to 20 (range a0) and 80 to 90 (range a1) of the running time are near-miss points and the heart rate variability increases by 5%. In FIG. 10 (b), the heart rate measurement values in five runs shown in FIG. 10 (a) are superimposed. When the correction due to fatigue is not performed, the heart rate fluctuation rate decreases due to fatigue. Therefore, as shown in FIG. 10B, the increase in heart rate reaches 5% in the section of the range a1 (running time 80 to 90). It turns out that it cannot be judged. On the other hand, when correction by fatigue is performed using the correction parameter p, it is possible to determine that the increase in heart rate has reached 5% in the section of the range a1 (running time 80 to 90). . In the correction using the correction parameter p, for example, if p is 4/7, the average heart rate is decreased by 20, so that the heart rate in the range a1 is 20 × 1 / p = 28 (%). Correction is performed so that the fluctuation width of the heartbeat increases (the heart rate variability increases).

  Returning to FIG. 9, in the next step S28, the heart rate variability statistical processing unit 34 determines whether or not the driver is drowsy in the data retrieved in step S24. For the determination of drowsiness, for example, a method based on autonomic nervous system analysis based on heart rate measurement can be employed.

  If the determination in step S28 is affirmative, the process proceeds to step S30, and the heart rate variability statistical processing unit 34 excludes data while sleepiness is occurring. Thereafter, the process proceeds to step S32. On the other hand, if the determination in step S28 is negative, the process proceeds directly to step S32 without passing through step S30.

  Here, FIG. 11 (a) and FIG. 11 (b) show examples of simulations when the average heart rate decreases from 70 to 50 due to fatigue due to running and sleepiness occurs in part of running. ing. In FIG. 11 (a), it is assumed that the sections of the travel time range of 10-20 (a0) and 80-90 range (a1) are near-miss points, and the heart rate variability increases by 5%. In FIG. 11 (b), it is assumed that no increase in heart rate has occurred due to the occurrence of sleepiness only once during five runs. In this case, when the exclusion process (drowsiness correction) based on the drowsiness detection is not performed, since the overlapping is performed without excluding the run in which the heart rate does not increase, the increase in the heart rate is caused as shown by the broken line in FIG. It can be seen that it cannot be determined that the rate has reached 5%. On the other hand, when sleepiness correction (data exclusion) is performed, it is possible to determine that the increase in heart rate has reached 5% in the sections of the ranges a0 and a1.

  Returning to FIG. 9, when the process proceeds to step S <b> 32, the heart rate variability statistical processing unit 34 aggregates the heart rate variability statistical values using the data corrected by fatigue and sleepiness, and outputs the statistics to the near-miss point specifying unit 36.

  The near-miss point specifying unit 36 specifies and outputs a near-miss point using the heart rate variability statistical value output by the heart rate variability statistical processing unit 34.

  As can be seen from the above description, the heart rate variability statistical processing unit 34 of the present embodiment corrects the heart rate data based on the correction parameters, the detection unit that detects the driver's sleepiness, and the correction. A function is realized as a processing unit that executes processing using later biological information and processing using data other than heart rate data corresponding to the timing when sleepiness is detected.

  As described above in detail, according to the present embodiment, the communication unit 32 acquires the heart rate data (associated with the travel position) of the driver who drives the vehicle, and the correction parameter calculation unit 38. Calculates a correction parameter for correcting the influence of the driver's fatigue on the heart rate data, which is obtained from the time change of the heart rate and instantaneous heart rate fluctuation, and the heart rate fluctuation statistical processing unit 34 sets the correction parameter as the correction parameter. Based on this, the heart rate data is corrected, and the heart rate variability statistical values are totaled and output using the corrected data. Thus, in the present embodiment, even if the instantaneous heart rate variability is reduced due to driver fatigue, the heart rate variability statistical value is output using the data after correcting the decrease. It is possible to calculate the near-miss point based on the value with high accuracy. For example, when performing long-distance driving, the return may be less fatigued due to fatigue and the increase in heart rate may be smaller than going home. It is possible to suppress an erroneous determination that “it is easier to feel danger (that is, dangerous)”. In addition, this embodiment is particularly effective when a specialized driver that accumulates fatigue due to long-time driving is targeted for evaluation.

  Further, according to the present embodiment, the heart rate variability statistical processing unit 34 detects the occurrence of the driver's sleepiness, excludes heart rate data at the timing when the sleepiness is detected, and totals the heart rate variability statistics. Output. This eliminates the influence of the driver's sleepiness (decreased perception due to sleepiness, reduced consciousness, and driving state), and the heart rate variability statistical values can be totaled and output. Therefore, also from this point, it is possible to calculate the near-miss point based on the heartbeat variability statistical value with high accuracy.

  In the embodiment described above, in order to add correction due to fatigue and drowsiness, the heart rate variability statistical values are tabulated using the heart rate data after fatigue and drowsiness correction, and output to the near miss point specifying unit 36. explained. However, the present invention is not limited to this. For example, fatigue and sleepiness evaluation values together with heart rate data may be output to the near-miss point specifying unit 36. In this case, as shown in FIG. 12, steps S26 to S30 in FIG. 9 are omitted as the processing of the heart rate variability statistical processing unit 34. In this way, if the processing as shown in FIG. 12 is performed, the amount of data and processing handled by the near miss point specifying unit 36 will be larger than the processing in FIG. 9, but the fatigue and sleepiness evaluation scales are adjusted when identifying the near miss point. There is an advantage that you can.

  In addition, although the said embodiment demonstrated the case where the hazard map production apparatus 30 had the near miss spot specific | specification part 36, it is not restricted to this. That is, the hazard map creation device 30 may not have the near-miss point specifying unit 36 and may simply output the heartbeat variability statistical value. In this case, the process of identifying the near-miss point from the heart rate variability statistical value output from the hazard map creation device 30 may be performed by a person, or may be performed by another device.

  In the above-described embodiment, the case where the method based on autonomic nervous system analysis based on heart rate measurement is used as the drowsiness detection method has been described. However, the present invention is not limited to this. For example, a method based on detection of closed eyes can be used. In this case, there is a facial expression evaluation standard by NEDO (New Energy and Industrial Technology Development Organization) as an evaluation standard of sleepiness intensity, and sleepiness corresponding to sleepiness level 5 (very sleepy) is detected in this standard. In such a place, it can be determined that near-miss detection is impossible, and it can be excluded from the target of aggregation of heart rate variability statistics.

  In the above embodiment, fatigue is quantitatively evaluated based on a decrease in average heart rate. However, correction may be performed using an amount indicating other fatigue. For example, as a fatigue parameter that can be evaluated from a heartbeat signal, an increase in the LF (low frequency) / HF (high frequency) component ratio of the heartbeat fluctuation frequency is known. Therefore, instead of decreasing the average heart rate, an increase rate of the heart rate fluctuation LF / HF component ratio may be used.

  In the above-described embodiment, the case where the vehicle on which the heart rate variability recording apparatus 10 is mounted is an automobile. However, the present invention is not limited to this. Other vehicles (for example, motorcycles, trains, airplanes, etc.) may be adopted as the vehicles.

  In the above-described embodiment, the case has been described in which information related to the heartbeat is acquired as biological information, and processing (totalization, output, etc.) using the information is performed. However, the present invention is not limited to this. For example, as biological information, other biological information such as body movement and respiration may be acquired and processing using the information may be performed.

  The above processing functions can be realized by a computer. In that case, a program describing the processing contents of the functions that the processing apparatus should have is provided. By executing the program on a computer, the above processing functions are realized on the computer. The program describing the processing contents can be recorded on a computer-readable recording medium.

  When the program is distributed, for example, it is sold in the form of a portable recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. It is also possible to store the program in a storage device of a server computer and transfer the program from the server computer to another computer via a network.

  The computer that executes the program stores, for example, the program recorded on the portable recording medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes processing according to the program. The computer can also read the program directly from the portable recording medium and execute processing according to the program. Further, each time the program is transferred from the server computer, the computer can sequentially execute processing according to the received program.

  The above-described embodiment is an example of a preferred embodiment of the present invention. However, the present invention is not limited to this, and various modifications can be made without departing from the scope of the present invention.

In addition, the following additional notes are disclosed regarding the above description.
(Supplementary Note 1) A biometric information acquisition unit that acquires biometric information of a driver who drives a vehicle in association with position information;
A calculation unit that calculates a correction value for correcting an influence on the biological information due to fatigue of the driver, which is obtained from a time change of the biological information;
A correction unit that corrects the biological information based on the correction value;
A biological information processing apparatus comprising: a processing unit that executes processing using the corrected biological information.
(Additional remark 2) It further has a detection part which detects the driver's sleepiness,
The biological information according to claim 1, wherein the processing unit performs the processing by excluding the driver's biological information corresponding to the timing at which the driver's sleepiness is detected by the detection unit. Processing equipment.
(Supplementary Note 3) The biological information processing apparatus according to Supplementary Note 1 or 2, wherein the correction value is a value determined based on a change in average heart rate during a predetermined time during driving and instantaneous heart rate fluctuation. .
(Supplementary Note 4) A biometric information acquisition unit that acquires biometric information of a driver who drives a vehicle in association with position information;
A detection unit for detecting sleepiness of the driver;
A biological information processing apparatus comprising: a processing unit that executes processing using biological information other than biological information corresponding to the timing at which the driver's sleepiness is detected by the detection unit.
(Additional remark 5) The said process part performs the process which specifies the position where the driver | operator felt danger, The biological information processing apparatus in any one of Additional remark 1-4 characterized by the above-mentioned.
(Additional remark 6) The biometric information acquisition process which matches and acquires the biometric information of the driver who drives a vehicle with position information,
A calculation step for calculating a correction value for correcting an influence on the biological information due to fatigue of the driver, which is obtained from a time change of the biological information;
A correction step of correcting the biological information based on the correction value;
A biological information processing method, wherein a computer executes a processing step of executing processing using the corrected biological information.
(Additional remark 7) The said computer further performs the detection process which detects the driver | operator's sleepiness,
The biological information according to appendix 5, wherein the processing step excludes the driver's biological information corresponding to the timing at which the driver's sleepiness was detected by the detection step, and executes the processing. Processing method.
(Supplementary note 8) The biological information processing method according to supplementary note 6 or 7, wherein the correction value is a value determined based on a change in average heart rate during a predetermined time during driving and a fluctuation in instantaneous heart rate. .
(Supplementary Note 9) A biometric information acquisition step of acquiring biometric information of a driver who drives a vehicle in association with position information;
A detection step of detecting sleepiness of the driver;
A biological information processing method, wherein a computer executes a processing step of executing processing using biological information other than biological information corresponding to timing at which the driver's sleepiness is detected.
(Supplementary note 10) The biological information processing method according to any one of supplementary notes 6 to 9, wherein the processing step executes a process of identifying a position where the driver feels danger.

30 Hazard map creation device (biological information processing device)
32 Communication unit (biological information acquisition unit)
38 Correction parameter calculation unit (calculation unit)
34 Heart rate variability statistical processing unit (correction unit, processing unit, detection unit)
36 Near-miss point identification part (processing part)

Claims (5)

A biometric information acquisition unit that acquires biometric information of a driver who drives the vehicle in association with position information;
A calculation unit that calculates a correction value for correcting an influence on the biological information due to fatigue of the driver, which is obtained from a time change of the biological information;
A correction unit that corrects the biological information based on the correction value;
A biological information processing apparatus comprising: a processing unit that executes processing using the corrected biological information. A detection unit for detecting the driver's sleepiness;
2. The living body according to claim 1, wherein the processing unit performs the processing by excluding the driver's biological information corresponding to a timing at which the driver's sleepiness is detected by the detection unit. Information processing device.   The biological information processing apparatus according to claim 1, wherein the correction value is a value determined based on a change in average heart rate during a predetermined time during driving and instantaneous heart rate fluctuation. Wherein the processing unit, the biological information processing apparatus according to any one of claims 1-3, characterized in that executes processing for specifying the driver feels dangerous position. A biometric information acquisition step of acquiring biometric information of a driver who drives the vehicle in association with position information;
A calculation step for calculating a correction value for correcting an influence on the biological information due to fatigue of the driver, which is obtained from a time change of the biological information;
A correction step of correcting the biological information based on the correction value;
A biological information processing method, wherein a computer executes a processing step of executing processing using the corrected biological information.

Images