JP2021196625A - Driving support method, driving support system, and driving support server - Google Patents

Abstract

To predict the risk of a traffic accident from biological data of a driver and travel state data.SOLUTION: A computer performs: generating an accident risk definition model for estimating a probability of danger occurrence as an accident risk by allowing first on-vehicle sensor data collected in the past and danger occurrence data where information of danger occurrence is pre-set from the first on-vehicle sensor data to be defined as inputs: inputting second on-vehicle sensor data collected in the past to the accident risk definition model; estimating a probability of danger occurrence to generate accident risk estimation data; generating an accident risk prediction model for predicting an accident risk after a predetermined time by allowing first biological index data corresponding to the second on-vehicle sensor data and the accident risk estimation data to be defined as inputs; acquiring biological data of a driver during driving a vehicle to calculate second biological index data from the biological data; inputting the second biological index data to the accident risk prediction model; and then predicting an accident risk after a predetermined time.SELECTED DRAWING: Figure 2

Description

The present invention relates to an operation support method, an operation support system, and an operation support server that predict the risk of a traffic accident and support the operation of transportation means.

In recent years, the occurrence of traffic accidents due to the health condition and fatigue of drivers has become a social problem in distribution trucks and long-distance buses. In order to prevent traffic accidents, biosensors that monitor the state of the driver while driving and technologies that measure the driving state of the vehicle such as inter-vehicle distance and speed in real time are being applied.

Patent Document 1 is known as a technique for supporting the driving operation of a vehicle. In Patent Document 1, in addition to the causal relationship between the driving situation data and the driving operation data, the table including the causal relationship with the driving operation and the physiological state data unrelated to the driving situation is updated and includes the margin. Discloses a technology that predicts driving operations related to sudden braking and provides efficient and accurate driving support.

Japanese Unexamined Patent Publication No. 2009-245147

However, in the above-mentioned conventional technique, although it is possible to predict the driving operation of sudden braking based on the driver's physiological state data, the driving operation data, and the driving situation data, it is possible to predict the driving operation focusing on a specific driving operation. There was a problem that it was difficult to predict events that do not occur frequently, such as traffic accidents.

Therefore, the present invention has been made in view of the above problems, and provides a driving support method, an operation support system, and an operation support server that can predict the risk of a traffic accident from the driver's biometric data and the driving state data. The purpose is to do.

The present invention is an operation support method in which a computer having a processor and a memory supports the operation of the vehicle, and the first in-vehicle sensor data indicating the running state of the vehicle collected in the past and the first in-vehicle sensor data. The first step to generate an accident risk definition model that estimates the probability that a danger will occur by machine learning by inputting the danger occurrence data preset with the information that the danger has occurred from, and the running of the vehicle collected in the past. The second step of inputting the second in-vehicle sensor data indicating the state into the accident risk definition model, estimating the probability of occurrence of danger, and generating the accident risk estimation data, and the second in-vehicle sensor data. By inputting the first biometric index data calculated in advance from the driver's biometric data at the time of collection and the accident risk estimation data, an accident risk prediction model for predicting the accident risk after a predetermined time is generated by machine learning. The third step, the fourth step of acquiring the biometric data of the driver who is driving the vehicle, and calculating the second biometric index data indicating the state of the driver from the biometric data, and the accident risk. A fifth step of inputting the second biometric data into the prediction model to predict the accident risk after the predetermined time is included.

Therefore, according to the present invention, it is possible to predict the risk of occurrence after a predetermined time for an event such as a traffic accident from the driver's biometric data and the driving state data.

Details of at least one practice of the subject matter disclosed herein are set forth in the accompanying drawings and in the description below. Other features, aspects, and effects of the disclosed subject matter are manifested in the following disclosures, drawings, and claims.

It is a block diagram which shows Example 1 of this invention and shows an example of the structure of the operation support system. It is a figure which shows the Example 1 of this invention, and shows the outline of the processing performed in the operation support system. It is a flowchart which shows Example 1 of this invention and shows an example of the generation process of the accident risk prediction model performed by the operation support server. It is a flowchart which shows Example 1 of this invention and shows an example of the generation process of the biometric index data performed by the operation support server. It is a flowchart which shows Example 1 of this invention and shows an example of the prediction processing performed by the operation support server. It is a flowchart which shows Example 1 of this invention and shows an example of the alert generation processing performed in the operation support server. It is a flowchart which shows Example 1 of this invention and shows an example of the calculation process of a biometric index performed by an operation support server. It is a graph which shows Example 1 of this invention and shows an example of heart rate data. It is a graph which shows Example 1 of this invention and shows an example of heart rate variability. FIG. 1 is a graph showing Example 1 of the present invention and showing an example of the spectral power density of heart rate variability. It is a graph which shows Example 1 of this invention and shows an example of an autonomic nerve NNXX. It is a figure which shows Example 1 of this invention and shows an example of the biometric index data. It is a figure which shows Example 1 of this invention and shows an example of business data. It is a figure which shows Example 1 of this invention and shows an example of environmental data. It is a figure which shows Example 1 of this invention and shows an example of an in-vehicle sensor data. It is a figure which shows Example 1 of this invention and shows an example of danger occurrence data. It is a figure which shows Example 1 of this invention and shows an example of accident risk estimation data. It is a figure which shows Example 1 of this invention and shows an example of alert definition data. It is a figure which shows Example 1 of this invention and shows an example of accident risk prediction data. It is a figure which shows Example 1 of this invention and shows an example of the prediction result display screen. It is a figure which shows Example 1 of this invention and shows an example of the prediction result notification screen. FIG. 2 is a block diagram showing a second embodiment of the present invention and showing an example of a configuration of an operation support system.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

FIG. 1 is a block diagram showing a first embodiment of the present invention and showing an example of a configuration of an operation support system.

The operation support system of this embodiment includes an operation support server 1 that supports the operation of one or more vehicles 7 via the network 13. The vehicle 7 collects an in-vehicle sensor 8 for detecting a driving state, a biosensor 12 for detecting the biometric data of the driver, a driver ID reading device 11 for identifying the driver, and the detected sensor data and the driver ID. The operation data collection device 10 that is transmitted to the operation support server 1 and the operation support server 1 receive notifications according to the driver's traffic accident risk (hereinafter referred to as accident risk), and notify the driver of the prediction result. Includes device 9.

Although the illustrated example shows an example in which the operation data collection device 10 and the prediction result notification device 9 are independent devices, it can be configured by one mobile terminal. In this case, it functions as an operation data collection unit and a prediction result notification unit.

The in-vehicle sensor 8 includes a GNSS (Global Navigation Satellite System) 81 that detects the position information of the vehicle 7, an acceleration sensor 82 that detects the behavior and speed of the vehicle 7, and a camera 83 that detects the driving environment as an image. Can be done.

The in-vehicle sensor 8 is not limited to the above, and a distance measuring sensor for detecting an object and a distance around the vehicle 7, a steering angle sensor for detecting a driving operation, and the like can be used. Further, the acceleration sensor 82 is preferably a 3-axis acceleration sensor.

The biological sensor 12 includes a heart rate sensor 121 that detects heart rate data and an acceleration sensor 122 that detects the movement of the driver. The biological sensor 12 is not limited to the above, and a sensor that detects the amount of sweating, body temperature, blinking, eye movement, brain wave, or the like can be adopted. The biosensor 12 includes a wearable device that can be worn by the driver, a sensing device attached to the inside of the vehicle 7 such as a steering wheel, a seat, and a seat belt, and an image that captures the facial expression and behavior of the driver and analyzes the image. A recognition system or the like can be used.

The driver ID reading device 11 reads a card in which the driver's identifier is recorded. The driving data collecting device 10 collects data from the vehicle-mounted sensor 8 and the biological sensor 12 at a predetermined cycle, and transmits the data to the operation support server 1 via the network 13.

The operation support server 1 is a computer including a processor 2, a memory 3, a storage device 4, an input / output device 5, and a communication device 6. The memory 3 includes a biometric index calculation unit 31, an accident risk definition generation unit 32, an accident risk prediction model generation unit 33, a prediction model selection unit 34, an accident risk prediction unit 35, an accident risk notification unit 36, and data. Each functional unit of the collection unit 37 is loaded as a program. Each program is executed by processor 2. The details of each functional unit will be described later.

The processor 2 operates as a functional unit that provides a predetermined function by executing a process according to a program of each functional unit. For example, the processor 2 functions as a biometric index calculation unit 31 by executing a biometric index calculation program. The same applies to other programs. Further, the processor 2 also operates as a functional unit that provides each function of a plurality of processes executed by each program. A computer and a computer system are devices and systems including these functional parts.

The storage device 4 stores the data used by each of the above functional units. The storage device 4 includes in-vehicle sensor data 40, biosensor data 41, business data 42, accident risk prediction model 43, accident risk prediction data 44, danger occurrence data 45, biometric index data 46, and environmental data. 47, the accident risk definition model 48, the alert definition data 49, and the accident risk estimation data 50 are stored. Details of each data will be described later.

The input / output device 5 includes an input device such as a mouse, a keyboard, or a touch panel, and an output device such as a display. The communication device 6 communicates with the vehicle 7 via the network 13.

<Overview of operation support system>
FIG. 2 is a diagram showing an outline of processing performed by the operation support system. First, the accident risk definition generation unit 32 inputs preset danger occurrence data 45 and in-vehicle sensor data 40-m1 collected in the past, and estimates the probability of danger as an accident risk definition model. Generate 48 (S1). The accident risk definition model 48 estimates the probability that a danger will occur by inputting the vehicle-mounted sensor data 40-m2 indicating the running state of the vehicle 7.

The danger occurrence data 45 is data in which the manager or the like determines an incident or an event linked to an incident from the time-series in-vehicle sensor data 40-m1 indicating the running state of the vehicle 7, and sets the occurrence date and time and the importance of the incident. be.

For example, when the in-vehicle sensor data 40-m1 is the sensor data of the acceleration sensor 82, an incident such as a sudden braking or a sharp turn or a running state leading to the incident is detected, and the administrator or the like sets the importance of the occurrence of danger. Hazard occurrence data 45 is generated.

In addition, the importance shows an example in which the risk increases as the value increases. In addition, the driving state that leads to an incident indicates a state in which the driver feels afraid (or a surprise). In the following description, an incident or a running condition leading to an incident is regarded as a danger occurrence.

In the generation of the danger occurrence data 45, the operation support server 1 detects a running state in which the front-rear acceleration exceeds a predetermined threshold value and a running state (danger occurrence) in which the yaw rate exceeds a predetermined threshold value, and the detected danger. The administrator or the like may set the importance of the event that has occurred.

The time series of the vehicle-mounted sensor data 40-m1 shown in FIG. 2 and the time series of the danger occurrence data 45 are the same time series.

The accident risk definition generation unit 32 inputs the in-vehicle sensor data 40-m1 and the danger occurrence data 45, and generates a machine learning model for estimating the accident risk from the running state as the accident risk definition model 48.

As a machine learning model, a well-known or known method such as a neural network or logistic regression may be adopted, and thus is not described in detail in this embodiment. The accident risk is the probability (percentage) of causing an incident (or the occurrence of a danger). Further, in this embodiment, an event leading to a traffic accident is regarded as an incident.

Next, the accident risk definition generation unit 32 inputs into the generated accident risk definition model 48 the vehicle-mounted sensor data 40-m2, which is a time series different from the vehicle-mounted sensor data 40-m1 and has been collected in the past. The accident risk estimation data 50 is generated by outputting the probability that the accident risk will occur (S2).

The accident risk estimation data 50 is data in which the probability that an incident will occur (or the probability that an accident will occur) with respect to the vehicle-mounted sensor data 40-m2 is generated as the same time series as the vehicle-mounted sensor data 40-m2.

Next, the biometric index calculation unit 31 calculates the driver's biometric index data 46-m from the past biosensor data 41 (driver's biometric data) corresponding to the acquisition of the in-vehicle sensor data 40-m2. do. The biometric index data 46-m includes, for example, an autonomic nerve index based on a power spectral density (described later) calculated from the driver's heartbeat data and an NN interval (interval between R waves and R waves) calculated from time domain analysis. Etc. (described later) can be used.

The in-vehicle sensor data 40-m1, 40-m2 and the biometric index data 46-m collected in the past may be stored in a predetermined area of the storage device 4.

Next, the accident risk prediction model generation unit 33 inputs the accident risk estimation data 50 and the biometric index data 46-m, and outputs the accident risk (probability) after a predetermined time from the biometric index data 46 of the moving vehicle 7. A model of machine learning to be performed is generated as an accident risk prediction model 43 (S3).

The accident risk prediction model 43 may generate a plurality of models according to the type of in-vehicle sensor data 40 to be used and the environment for prediction, and the prediction model selection unit 34 may select the model to be used. good.

Further, the accident risk prediction model 43 may generate a plurality of types according to the difference in the driving characteristics of the vehicle 7, the driving history of the driver, the biometric data before operation, and the like. For example, as for the difference in driving characteristics of the vehicle 7, it is desirable to generate different models for vehicles having different steering wheel operations when turning or reversing, such as a truck and a trailer. Further, as the driving history of the driver, it is preferable to generate a model based on the difference in the accuracy of the driving operation, the risk sensitivity, the number of years of driving, the driving experience vehicle (large size, special, etc.), the driving route history, and the like. In addition, as the driver's pre-operation biometric data, it is preferable to generate a model based on differences in body temperature, blood pressure, blood oxygen concentration, sleep time on the previous day, and the like.

Next, the operation support server 1 predicts the accident risk of the vehicle 7 actually running by using the generated accident risk prediction model 43 (S4). In the operation support server 1, when a plurality of accident risk prediction models 43 exist, the prediction model selection unit 34 selects the accident risk prediction model 43 according to the in-vehicle sensor data 40 to be used, the environmental data 47 of the vehicle 7, and the like.

The accident risk prediction unit 35 inputs the heartbeat data of the biometric sensor 12 received by the data collection unit 37 via the vehicle 7 into the biometric index calculation unit 31 to calculate the biometric index data 46. Then, the accident risk prediction unit 35 inputs the calculated biometric index data 46 into the accident risk prediction model 43 to predict the future accident risk from the present to a predetermined time Δt. Further, when the accident risk prediction model 43 outputs interpretation data (described later) indicating the driver's condition, the accident risk prediction unit 35 can add the interpretation data to the prediction value of the accident risk.

Then, when the accident risk after the predetermined time Δt is equal to or higher than the predetermined threshold Th, the accident risk notification unit 36 generates an alert or a message according to the accident risk value, interpretation data, driving condition, or environmental data. An alert or a message is transmitted to the vehicle 7 in which the risk of an accident is predicted to increase (S5).

When the vehicle 7 receives the alert from the operation support server 1, the prediction result notification device 9 outputs the alert and transmits the alert or the message to the driver. Further, when the accident risk notification unit 36 is predicted to increase the accident risk after a predetermined time Δt, the accident risk notification unit 36 informs the manager of the operation support server 1 the position information of the corresponding vehicle 7 and the accident risk of the driver. An image including the amount of work and the like can be generated and displayed on the display of the input / output device 5.

The operation support server 1 predicts that the accident risk will be equal to or higher than the threshold Th after a predetermined time Δt, and notifies the display of the prediction result notification device 9 and the input / output device 5 of the corresponding vehicle 7, thereby causing the accident risk. It will be possible to alert drivers and managers with alerts and messages before they increase. As a result, the operation support server 1 can reduce the actual accident risk (51) and promote the safe operation of each vehicle 7.

It is desirable to set the predetermined time Δt for predicting the future accident risk to a value such as 30 minutes or 1 hour, and recommend the driver to take a break or present advice before the time when the accident risk increases. Can be done.

<Data>
Next, each data used in the operation support system will be described.

FIG. 8 is a diagram showing an example of biometric index data 46. The biometric index data 46 is a table that stores data calculated by the biometric index calculation unit 31 for each predetermined period from the heartbeat data of the biometric sensor data 41.

The biometric data 46 includes the user ID 460, the date and time 461, the autonomic nerve total power 462, the autonomic nerve LF / HF463, the autonomic nerve NN50 465, and the average RRI464 in one record. The driver's identifier is stored in the user ID 460. The date and time when the biosensor data 41 (heart rate data) is acquired is stored in the date and time 461.

As will be described later, the autonomic nerve total power 462 has a total value of a low frequency (LF: Low Frequency) component and a high frequency (HF: High Frequency) component of the power spectrum density of the R wave interval (RRI) of the heart rate data. , Stored as a value indicating the balance of the autonomic nerves (sympathetic nerve and parasympathetic nerve).

The autonomic nerve LF / HF463 stores the ratio of the low frequency (LF) component and the high frequency (HF) component of the power spectral density. The low frequency component indicates the activity index of the sympathetic nerve, and the high frequency component indicates the activity index of the parasympathetic nerve. The average RRI464 stores the average value of the R wave interval (RRI) within a preset period.

As will be described later, the autonomic nerve NN50 465 stores the total number of differential values for which the differential value is 50 msec or more for the differential series ΔRRI (t) of the heart rate variability time series data RRI as a value indicating the magnitude of parasympathetic nerve activity. Will be done.

The illustrated example shows an example of calculating the autonomic nerve total power 462, the autonomic nerve LF / HF463, and the autonomic nerve NN50 465 at 1-minute intervals, but the present invention is not limited to this, and the biometric index is not limited to this. The data 46 may be calculated.

FIG. 9 is a diagram showing an example of business data 42. The business data 42 is a table that stores information for managing the vehicle 7 driven by the driver and business, and is set by a person in charge or a manager of the operation support system.

The business data 42 includes a user ID 420, a business start date and time 421, a business end date and time 422, a vehicle ID 423 that stores an identifier of the vehicle 7, and a business type 424 in one record. The business content of the driver is stored in the business type 424.

FIG. 10 is a diagram showing an example of environmental data 47. The environmental data 47 is a table for storing information based on the vehicle-mounted sensor data 40 of the vehicle 7. The environmental data 47 stores the vehicle ID 470 that stores the identifier of the vehicle 7, the date and time 471 that generated the environmental data 47, the traffic congestion condition 472 of the road on which the vehicle 7 travels, the weather 473, and the temperature 474.

The traffic jam situation 472 may be determined from the image of the camera 83 of the vehicle 7, or may be acquired from the traffic information service on the network 13 based on the position information calculated by the GNSS 81.

FIG. 11 is a diagram showing an example of the vehicle-mounted sensor data 40. The vehicle-mounted sensor data 40 is a table that stores information collected by the data collecting unit 37 from the vehicle-mounted sensor 8 of the vehicle 7 at a predetermined cycle.

The vehicle-mounted sensor data 40 includes a vehicle ID 400 that stores an identifier of the vehicle 7, a date and time 401 that acquires data from the vehicle-mounted sensor 8, a position 402 that stores position information detected by the GNSS 81, a speed 403 of the vehicle 7, and acceleration. The acceleration 404 detected by the sensor 82 is included in one record.

FIG. 12 is a diagram showing an example of danger occurrence data 45. As shown in FIG. 2, the danger occurrence data 45 is a table generated based on the in-vehicle sensor data 40-m1.

The danger occurrence data 45 includes the vehicle ID 450 that stores the identifier of the vehicle 7, the date and time 451 of the danger occurrence, the danger type 452 that stores the type of danger that has occurred, and the importance level 453 of the danger that has occurred in one record. .. Values determined by the administrator or the like are stored in the danger type 452 and the importance level 453.

In the danger occurrence data 45, the administrator or the like determines an incident or a state that causes an incident from the running state of the vehicle 7 indicated by the in-vehicle sensor data 40-m1, and sets the danger type 452 and the importance level 453.

FIG. 13 is a diagram showing an example of accident risk estimation data 50. The accident risk estimation data 50 is a table in which the accident risk definition generation unit 32 inputs the in-vehicle sensor data 40-m2 into the accident risk definition model 48 to estimate the accident risk.

The accident risk estimation data 50 includes a user ID 500 that stores a driver's identifier, a vehicle ID 501 that stores an identifier of a vehicle 7, a date and time 502 when an accident risk occurs, and an accident risk that stores the probability of reaching an incident (percentage). 503 is included in one record.

The accident risk 503 is a result of giving the speed, acceleration, and position information of the vehicle 7 to the accident risk definition model 48 to estimate the probability that an incident will occur. In the illustrated example, an example of calculating the accident risk 503 at 1-minute intervals is shown, but the present invention is not limited to this.

FIG. 14 is a diagram showing an example of alert definition data 49. The alert definition data 49 is a table in which alerts or messages notified by the accident risk notification unit 36 are set in advance.

The alert definition data 49 includes an alert ID 490, an accident risk condition 491, a time condition 492, a traffic jam condition 493, a weather condition 494, a priority order 495, and a comment 496 in one record.

The alert ID 490 stores an identifier for identifying the alert. The accident risk condition 491 stores an accident risk condition for selecting an alert for the record. For example, in the record of alert ID 490 = "1", a condition to be selected when the value of the accident risk is 70% or less is set.

In the time condition 492, a time zone for selecting an alert for the record is set. In the traffic jam condition 493, a traffic jam situation (presence / absence) for selecting an alert for the record is set. In the weather condition 494, the weather for selecting the alert of the record is set.

In the priority order 495, when a plurality of records satisfying the accident risk condition 491 are extracted, the priority of the record to be selected is set in advance. The comment 496 stores the content of the alert (or message) to be notified.

FIG. 15 is a diagram showing an example of accident risk prediction data 44. The accident risk prediction data 44 is a table for storing the accident risk prediction result calculated by the accident risk prediction model 43 in which the biosensor data 41 of the driver of the moving vehicle 7 is input.

The accident risk prediction data 44 includes the user ID 440, the vehicle ID 441, the date and time 442 when the vehicle-mounted sensor data 40 is acquired, the predicted date and time 443, and the accident risk 444 in one record.

The predicted date and time 443 stores the date and time after the predetermined time Δt. The accident risk 444 stores a predicted value (percentage) of the accident risk after a predetermined time Δt.

<Details of processing>
Next, the processing performed by the operation support system will be described.

FIG. 3 is a flowchart showing an example of the generation process of the accident risk prediction model 43 performed by the operation support server 1. This process is performed before the vehicle-mounted sensor 8 and the biological sensor 12 are received from the vehicle 7, and the accident risk prediction model 43 is generated.

The accident risk definition generation unit 32 generates an accident risk definition model 48 by machine learning by inputting the danger occurrence data 45 generated in advance and the in-vehicle sensor data 40 (40-m1 in FIG. 2) collected in the past (S11). ).

Then, the accident risk definition generation unit 32 inputs the in-vehicle sensor data 40 (40-m2 in FIG. 2) collected in the past into the generated accident risk definition model 48, and generates the accident risk estimation data 50 (S12). ).

Next, the accident risk prediction model generation unit 33 acquires the biometric index data 46-m corresponding to the in-vehicle sensor data 40 (40-m2 in FIG. 2) collected in the past, and obtains the accident risk estimation data 50 and the biometric index. An accident risk prediction model 43 is generated from the data 46-m by machine learning (S13).

The accident risk prediction model generation unit 33 acquires the driver's information from the business data 42 and the driving environment of the vehicle 7 from the environmental data 47 when performing machine learning, and the accident risk prediction model 43 of the accident risk prediction model 43. Perform generation.

By the above processing, after the accident risk definition model 48 is created and the accident risk estimation data 50 is generated, the accident risk prediction model 43 is generated from the biometric index data 46 and the accident risk estimation data 50 collected in the past.

FIG. 4 is a flowchart showing an example of the generation process of the biometric index data 46 performed by the operation support server 1. This process is executed every time data is received from the vehicle 7. The data collection unit 37 of the operation support server 1 receives the data of the vehicle-mounted sensor 8 and the biosensor 12 from the driving data collection device 10 of the vehicle 7 (S21).

The data collection unit 37 stores the heart rate data detected by the heart rate sensor 121 and the acceleration sensor 122, and the acceleration data in the biosensor data 41 (S22). The data of the vehicle-mounted sensor 8 is stored in the vehicle-mounted sensor data 40 by the data collection unit 37.

Next, the biometric index calculation unit 31 reads the biosensor data 41 and calculates the biometric index as described later (S23). The biometric index calculation unit 31 stores the calculated biometric index in the biometric index data 46 (S24).

FIG. 7A is a flowchart showing an example of the calculation process of the biometric index performed by the biometric index calculation unit 31. This process is executed in step S23 of FIG.

The biometric index calculation unit 31 acquires heart rate data from the biosensor data 41 (S51). The acquired heart rate data is data within a predetermined period from the latest heart rate data. Next, the biometric index calculation unit 31 calculates RRI (RR Interval) from the intervals of R waves included in the heart rate data (S52).

FIG. 7B is a diagram showing an example of heart rate data detected by the biological sensor 12. The biometric index calculation unit 31 detects the time interval between the peak of the R wave and the peak of the next R wave in the figure as RRI, calculates a predetermined number (or a predetermined period) of RRI as heart rate variability time series data, and further RRI. Is calculated as the average RRI464.

Next, the biometric index calculation unit 31 calculates the fluctuation from the calculated heart rate variability time series data. FIG. 7C is a graph showing an example of fluctuation (heart rate variability) of heart rate data calculated by the biometric index calculation unit 31. The RRI of heart rate data is not constant and fluctuates depending on the activity of autonomic nerves and the like.

The biometric index calculation unit 31 performs frequency spectrum analysis from time-series heart rate variability data (S53), and then calculates power spectral density (PSD: Power Spectral density) (S54). A well-known method may be applied to calculate the power spectral density.

Next, the biometric index calculation unit 31 calculates the intensity LF of the low frequency component and the intensity HF of the high frequency component of the power spectral density. FIG. 7D is a graph showing an example of the frequency domain of the power spectral density of heart rate variability.

As shown in FIG. 7D, the biometric index calculation unit 31 has an intensity (integral value) LF in the low frequency component region (0.05 Hz to 0.15 Hz) of the power spectrum and a high frequency component region (0.15 Hz to 0. The total value (LF + HF) of the intensity (integral value) HF (up to 40 Hz) is calculated as the autonomic nerve total power 462.

Further, the biometric index calculation unit 31 calculates the ratio (LF / HF) of the intensity LF of the low frequency component and the intensity HF of the high frequency component of the power spectrum as the autonomic nerve LF / HF463.

By the above processing, time-series heart rate variability data is calculated from the heart rate data of the biological sensor data 41, and the intensities (LF, HF) of the low frequency component and the high frequency component are calculated to obtain the autonomic nerve total power 462 and the autonomic nerve. LF / HF463 is obtained.

Here, the high-frequency component appears in the heart rate variability when the parasympathetic nerve is activated (tension), and the low-frequency component activates the parasympathetic nerve (tension) even when the sympathetic nerve is activated (tension). It also appears in heart rate variability when you are nervous.

It is known that when the sympathetic nerve is activated, it is in a stressed state, and when the parasympathetic nerve is activated, it is in a relaxed state. It is possible to determine whether a person is in a stressed state or a relaxed state.

After that, the biometric index calculation unit 31 calculates a time domain index obtained from the time domain analysis of the heart rate variability time series data RRI (S55). FIG. 7E is a graph showing an example of calculating the autonomic nerve NNXX, which is one of the time domain indexes, from the difference series ΔRRI (t) of the heart rate variability time series data RRI.

As shown in FIG. 7E, the biometric index calculation unit 31 calculates ΔRRI (t), which is a difference series obtained by taking the difference between adjacent RRIs for the heart rate variability time series data RRI, and from ΔRRI (t), ΔRRI (t). The autonomic nerve NNXX, which is the total number of difference values in which the difference values constituting the above are XX msec or more, is calculated. Typically, as shown in FIG. 7E, when XX = 50, the total number of difference values in which the difference values constituting ΔRRI (t) are 50 msec or more (= difference values existing in the grid shaded range). The autonomic nerve NN50 465 which is the total number of) is calculated.

Here, since the autonomic nerve NN50 465 is known to be an index showing the magnitude of parasympathetic nerve activity, which is similar to the intensity HF of the high frequency component, the magnitude of the relaxed state of the driver is determined from the autonomic nerve NN50 465. Can be determined.

Note that NNXX is not limited to the above definition. For example, instead of the total number of difference values in which the difference values constituting ΔRRI (t) are 50 msec or more, the total number of difference values in which the absolute value of the difference values constituting ΔRRI (t) is 50 msec or more (= grid network). The absNN50, which is the total number of difference values existing in the multiplication range and the shaded shaded range), may be calculated, or the autonomic nerve NN50 465 is divided by the total number of difference values included in ΔRRI (t) and normalized. You may calculate pNN50 which is a value (= the total number of difference values existing in the grid shaded range ÷ the total number of difference values existing in the dotted shaded range). Further, instead of the condition that the difference value constituting ΔRRI (t) is 50 msec or more, the autonomic nerve NN50 465 may be calculated based on the condition that the difference value constituting ΔRRI (t) exceeds 50 msec. .. Further, instead of XX = 50, NNXX may be calculated with XX = 40, 60, 100 and the like.

Then, the biometric index calculation unit 31 stores the calculated autonomic nerve total power 462, the autonomic nerve LF / HF463, the autonomic nerve NN50 465, and the average RRI464 in the biometric index data 46 (S56 and S24 in FIG. 4).

Therefore, the accident risk prediction model 43 obtains interpretation data regarding the driver's condition from a biometric index based on intensity LF and HF such as autonomic nerve LF / HF463 and a biometric index based on time domain analysis such as autonomic nerve NN50 465. Can be output. The interpretation data may include the stress state and the relaxed state of the driver.

FIG. 5 is a flowchart showing an example of the prediction process performed by the operation support server 1. This process is executed at a predetermined timing, such as after the biometric index data 46 is updated. The accident risk prediction unit 35 acquires the biometric index data 46 from the latest data to a predetermined period (S31).

Next, the prediction model selection unit 34 identifies the user ID 420 to be analyzed and the vehicle ID 423 from the business data 42, and selects the accident risk prediction model 43 to be used using the environmental data 47 (S32). The user ID 420 to be analyzed can be, for example, the user ID 460 of the unprocessed biometric index data 46.

Further, when a plurality of accident risk prediction models 43 exist, the prediction model selection unit 34 selects a model to be used based on the weather 473 of the environmental data 47, the date and time 471, the traffic jam situation 472, and the like.

Next, the accident risk prediction unit 35 inputs the biometric index data 46 of the user ID to be analyzed into the selected accident risk prediction model 43, and calculates the accident risk (S33). The calculated accident risk is stored in the accident risk 444 of the accident risk prediction data 44.

Although FIG. 15 shows an example of storing the accident risk 444, when the accident risk prediction model 43 outputs interpretation data (stress state or relaxed state) regarding the driver's state from the autonomic nerve LF / HF463 or the like. Can store the interpretation data in the biometric data 46.

Further, although the example in which the biometric index data 46 is input to the accident risk prediction model 43 is shown above, the present invention is not limited to this, and the environmental data 47 and the in-vehicle sensor data 40 are added to the input of the accident risk prediction model 43. You may. For example, when the accident risk prediction model 43 outputs interpretation data, the prediction accuracy can be improved by inputting the traffic jam situation or the like into the accident risk prediction model 43.

By the above processing, the accident risk (and interpretation data) after the predetermined time Δt is predicted by the accident risk prediction model 43 at a predetermined timing such as after the biometric index data 46 is updated.

FIG. 6 is a flowchart showing an example of the alert generation process performed by the operation support server. This process is executed after the prediction process of FIG. 5 is completed.

The accident risk notification unit 36 acquires the alert definition data 49 (S41). The accident risk notification unit 36 searches for a driver whose value of the accident risk 444 after a predetermined time Δt is equal to or higher than a preset threshold Th (reference value in the figure) with reference to the accident risk prediction data 44 (S42).

If there is a driver whose accident risk 444 value is the threshold value Th or more after a predetermined time Δt, the accident risk notification unit 36 proceeds to step S44 and proceeds to step S44 from the identifier of the driver whose threshold value Th or more is the vehicle ID 423 of the business data 42. Is acquired and the alert is transmitted (S44).

Then, the accident risk notification unit 36 acquires the environmental data 47 with the vehicle ID 470 of the vehicle 7, and from the alert definition data 49, the conditions of the environmental data 47 (time condition 492, traffic jam condition 493, weather condition 494) and the accident risk. The alert ID 490 that satisfies the condition 491 is selected, and the accident risk alert (not shown) specified by the alert ID 490 and the comment 496 of the selected record are output (S45).

The accident risk notification unit 36 acquires the position 402 of the vehicle 7 from the in-vehicle sensor data 40, adds the position information of the vehicle 7, and generates an alert.

By the above processing, an alert is transmitted to the driver's vehicle 7 whose accident risk is predicted to be equal to or higher than the threshold value Th after a predetermined time Δt. In the vehicle 7 that has received the alert, the prediction result notification device 9 notifies the driver of the alert. Further, in the operation support server 1, the accident risk notification unit 36 displays the vehicle 7 to which the alert is transmitted on the display of the input / output device 5.

Note that the alert definition data 49 in FIG. 14 shows an example in which the comment and the alert ID 490 are determined based on the accident risk condition 491, the environmental condition, and the priority order 495, but the present invention is not limited to this. For example, when the accident risk prediction model 43 outputs interpretation data regarding the driver's condition, a condition for determining the alert ID may be set based on the interpretation data.

As an example, when the accident risk 444 is the same, when the interpretation data is in a stressed state or a relaxed state, the alert ID 490 when the accident risk is high in the stressed state and the alert when the accident risk is high in the relaxed state. Set ID 490 as a different alert. Thereby, by adding the interpretation data to the value of the accident risk 444, it is possible to realize a highly accurate prediction.

FIG. 16A is a diagram showing an example of a prediction result display screen 600 output by the accident risk notification unit 36 to the display of the input / output device 5. On the prediction result display screen 600 output by the accident risk notification unit 36, the icon 602 of the vehicle 7 to be managed is displayed on the map, and the alert icon 601 is added to the icon 602 that issued the alert.

Further, in the vicinity of the alert icon 601 the driving status 603 of the driver whose accident risk has increased is displayed, and the amount of work of the driver and the number of breaks can be notified to the manager or the like.

In addition, the manager can list and confirm the accident risks of a plurality of drivers on a map, and can select a driver with a high accident risk and give an instruction remotely.

In the illustrated example, the position of the vehicle 7 and the situation of the driver are displayed on the map, but the present invention is not limited to this, and the notification may be performed by text information such as a list. good.

Further, the accident risk notification unit 36 manages the driver whose accident risk is predicted to increase by displaying the interpretation data in the driving status 603 when the interpretation data can be obtained from the autonomic nerve LF / HF463 or the like. It becomes possible for a person or the like to grasp the stress state and the relaxed state of the driver.

FIG. 16B is a diagram showing an example of a prediction result display screen 650 output by the prediction result notification device 9. The prediction result notification device 9 has a display (not shown) and displays a prediction result display screen 650 when an alert is received from the operation support server 1.

The prediction result display screen 650 includes an area 651 for displaying an accident risk alert and an area 652 for displaying a comment. The driver can recognize the accident risk by visually recognizing the prediction result display screen 650 of the prediction result notification device 9.

As described above, in the operation support system of this embodiment, the biometric index data 46 calculated by the operation support server 1 from the heartbeat data of the biosensor 12 is input to the accident risk prediction model 43, and the accident risk after a predetermined time Δt Predict 444. This makes it possible to predict in advance a state in which a traffic accident is likely to occur according to the state of the autonomic nerves of the driver of the vehicle 7 and give feedback to the driver such as recommending a break. ..

In the first embodiment, the present invention is applied to the operation support system for managing the vehicle 7, but the present invention is not limited thereto. For example, instead of the vehicle 7, it can be applied to a moving body that requires a driver or a driver, such as a railroad vehicle, a ship, or an aircraft.

Further, in the first embodiment, an example in which the accident risk definition model 48 is generated from the in-vehicle sensor data 40-m1 collected in the past and the danger occurrence data 45 is shown, but the present invention is not limited thereto. For example, from the new in-vehicle sensor data 40 for which work has been completed, a location determined by the driver to be dangerous is specified, new danger occurrence data 45 is generated, added as learning data, and the accident risk definition model 48 is re-established. You may learn. In this case, the accident risk prediction model 43 will also be generated again.

FIG. 17 is a block diagram showing the second embodiment and showing an example of the configuration of the operation support system. In this embodiment, the biometric index calculation unit 31, the accident risk prediction unit 35, and the biometric index data 46 are arranged in the driving data collection device 10 of the vehicle 7, and the accident selected by the prediction model selection unit 34 of the operation support server 1. Predict accident risk with risk prediction model 43A.

The biometric index data is calculated and the accident risk is predicted by the driving data collecting device 10 of the vehicle 7, and the accident risk is transmitted to the operation support server 1. In the operation support server 1, when the accident risk notification unit 36 has an accident risk of the threshold value Th or more after a predetermined time Δt, the accident risk notification unit 36 outputs an alert to the corresponding vehicle 7 as in the first embodiment.

In this embodiment, it is possible to reduce the load on the operation support server 1 and increase the number of vehicles 7 managed by the operation support server 1 by calculating the biometric index and predicting the accident risk on the vehicle 7 side. It becomes.

<Conclusion>
As described above, the operation support method of the above embodiment can be configured as follows.

(1) A computer having a processor (2) and a memory (3) is an operation support method for supporting the operation of the vehicle (7), and the first method showing the running state of the vehicle collected by the computer in the past. Danger occurs by machine learning by inputting in-vehicle sensor data (40-m1) and danger occurrence data (45) in which information on which danger has occurred is preset from the first in-vehicle sensor data (40-m1). The first step of generating an accident risk definition model (48) that estimates the probability of this as an accident risk, and the second in-vehicle sensor data (40-) indicating the running state of the vehicle (7) collected in the past by the computer. The second step of inputting m2) into the accident risk definition model (48) to estimate the probability of occurrence of danger and generating the accident risk estimation data (50), and the second vehicle-mounted computer. After a predetermined time, the first biometric index data (46-m) calculated in advance from the driver's biometric data when the sensor data (40-m2) is collected and the accident risk estimation data (50) are input. The third step of generating an accident risk prediction model (43) for predicting the accident risk of the above, and the computer acquires the biometric data of the driver who is driving the vehicle (7), and the biometric data. In the fourth step of calculating the second biometric index data (46) indicating the state of the driver, the computer applies the second biometric index data (46) to the accident risk prediction model (43). An operation support method comprising the fifth step of inputting and predicting the accident risk (44) after the predetermined time Δt.

With the above configuration, the operation support server 1 can predict the accident risk after a predetermined time Δt from the biometric data of the driver who is driving the vehicle 7.

(2) In the operation support method according to (1) above, when the computer generates an alert (600) when the predicted value of the accident risk after the predetermined time Δt is equal to or higher than the preset threshold value Th. An operation support method characterized by further including a sixth step of outputting.

With the above configuration, the operation support server 1 predicts that the accident risk will reach the threshold value Th or more after a predetermined time Δt, and notifies the display of the prediction result notification device 9 and the input / output device 5 of the corresponding vehicle 7. This makes it possible to alert drivers and managers with alerts and messages before the risk of an accident increases. As a result, the operation support server 1 can promote the safe operation of each vehicle 7.

(3) In the operation support method according to the above (1), the fourth step is a step of acquiring the driver's heartbeat data as the biological data and a heartbeat by calculating RRI from the heartbeat data. From the step of generating the fluctuation time series data, the step of performing the frequency spectrum analysis of the heart rate fluctuation time series data, and the intensity LF of the low frequency component of the power spectrum density and the intensity HF of the high frequency component from the result of the frequency spectrum analysis. An operation support method including a step of calculating the sum as the total power of the autonomic nerve and calculating it as biometric index data (462).

With the above configuration, time-series heart rate variability data is calculated from the heart rate data of the biological sensor data 41, and the intensities (LF, HF) of the low frequency component and the high frequency component are calculated to obtain the autonomic nerve total power 462 and the autonomic nerve. LF / HF463 is obtained.

(4) In the operation support method according to (3) above, in the fifth step, the intensity (LF) of the low frequency component and the high frequency component of the power spectral density are described in the accident risk prediction model (43). An operation support method comprising inputting an intensity (HF) and outputting interpretation data indicating the driver's condition by the accident risk prediction model (43).

According to the above configuration, it is known that when the sympathetic nerve is activated, it is in a stress state, and when the parasympathetic nerve is activated, it is in a relaxed state. From the HF, it can be determined whether the driver is in a stressed state or a relaxed state.

(5) In the operation support method according to (2) above, in the sixth step, the position information (position 402) of the vehicle (7) is acquired, and the position information of the vehicle (7) (7). An operation support method comprising outputting a screen (prediction result display screen 600) for displaying 402) and information (603) indicating the state of the driver.

With the above configuration, the manager can list and confirm the accident risks of a plurality of drivers on a map, and can select a driver with a high accident risk and give an instruction remotely.

(16) In the operation support method according to (1) above, the fourth step is a step of acquiring the driver's heartbeat data as the biological data and a heartbeat by calculating RRI from the heartbeat data. A step of generating variable time-series data, a step of calculating the difference value of adjacent RRIs for the heart rate variability time-series data to generate a difference series ΔRRI (t), and the difference value from the difference series ΔRRI (t). An operation support method comprising a step of calculating the total number of difference values having a predetermined value of XX msec or more as autonomic nerve NNXX and using it as biometric index data (462).

With the above configuration, the time-series heart rate variability data is calculated from the heart rate data of the biosensor data 41, the difference series ΔRRI (t) is calculated from the heart rate variability data, and the difference value becomes a predetermined value XXmsec or more. By calculating the total number of autonomic nerves NNXX, biometric index data 46 can be obtained as an index showing the magnitude of parasympathetic nerve activity.

The present invention is not limited to the above-described embodiment, and includes various modifications. For example, the above-described embodiment is described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the configurations described. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, for a part of the configuration of each embodiment, any of addition, deletion, or replacement of other configurations can be applied alone or in combination.

Further, each of the above configurations, functions, processing units, processing means and the like may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations and functions may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be placed in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

In addition, the control lines and information lines indicate those that are considered necessary for explanation, and do not necessarily indicate all the control lines and information lines in the product. In practice, it can be considered that almost all configurations are interconnected.

1 Operation support server 2 Processor 3 Memory 4 Storage device 7 Vehicle 8 In-vehicle sensor 12 Biosensor 31 Biometric index calculation unit 32 Accident risk definition generation unit 33 Accident risk prediction model generation unit 34 Prediction model selection unit 35 Accident risk prediction unit 36 Accident risk Notification unit 40 In-vehicle sensor data 41 Biosensor data 42 Business data 43 Accident risk prediction model 44 Accident risk prediction data 45 Hazard occurrence data 46 Bioindex data 47 Environmental data 48 Accident risk definition model 50 Accident risk estimation data

Claims (18)

A computer with a processor and memory is an operation support method that supports the operation of a vehicle.
Danger occurs by machine learning by inputting the first in-vehicle sensor data showing the running state of the vehicle collected in the past and the danger occurrence data in which the information on which the danger has occurred is preset from the first in-vehicle sensor data. The first step in generating an accident risk definition model that estimates the probability of
The second step of inputting the second in-vehicle sensor data indicating the running state of the vehicle collected in the past into the accident risk definition model, estimating the probability of occurrence of danger, and generating the accident risk estimation data, and
An accident that predicts the accident risk after a predetermined time by inputting the first biometric index data calculated in advance from the biometric data of the driver when the second in-vehicle sensor data is collected and the accident risk estimation data. The third step of generating a risk prediction model by machine learning,
The fourth step of acquiring the biometric data of the driver who is driving the vehicle and calculating the second biometric index data indicating the state of the driver from the biometric data.
A fifth step of inputting the second biometric index data into the accident risk prediction model to predict the accident risk after a predetermined time, and
Operation support method characterized by including. The operation support method according to claim 1.
An operation support method further comprising a sixth step of generating and outputting an alert when the predicted value of the accident risk after a predetermined time is equal to or higher than a preset threshold value. The operation support method according to claim 1.
The fourth step is
The step of acquiring the driver's heartbeat data as the biometric data,
A step of calculating RRI from the heart rate data to generate heart rate variability time series data,
The step of performing frequency spectrum analysis of the heart rate variability time series data,
From the result of the frequency spectrum analysis, the step of calculating the sum of the intensity of the low frequency component of the power spectral density and the intensity of the high frequency component as the total power of the autonomic nerve and using it as the biometric index data.
Operation support method characterized by including. The operation support method according to claim 3.
The fifth step is
An operation support method characterized in that the intensity of a low frequency component and the intensity of a high frequency component of the power spectral density are input to the accident risk prediction model, and the accident risk prediction model outputs interpretation data indicating the driver's condition. .. The operation support method according to claim 2.
The sixth step is
An operation support method comprising acquiring the position information of the vehicle and outputting a screen displaying the position information of the vehicle and the information indicating the state of the driver. A server with a processor and memory,
It is an operation support system that supports the operation of the vehicle including an in-vehicle sensor that detects a driving state and a vehicle having a biosensor that detects a driver's biometric data.
The server
Danger occurs by machine learning by inputting the first in-vehicle sensor data showing the running state of the vehicle collected in the past and the danger occurrence data in which the information on which the danger has occurred is preset from the first in-vehicle sensor data. An accident risk definition model that estimates the probability of occurrence as an accident risk is generated, and the second in-vehicle sensor data indicating the running state of the vehicle collected in the past is input to the accident risk definition model to estimate the probability that a danger will occur. And the accident risk definition generation unit that generates accident risk estimation data,
An accident that predicts the accident risk after a predetermined time by inputting the first biometric index data calculated in advance from the biometric data of the driver when the second in-vehicle sensor data is collected and the accident risk estimation data. Accident risk prediction model generation unit that generates risk prediction model by machine learning,
A biometric index calculation unit that acquires biometric data of the driver who is driving from the biosensor of the vehicle and calculates a second biometric index data indicating the state of the driver from the biometric data.
An accident risk prediction unit that inputs the second biometric index data into the accident risk prediction model to predict the accident risk after a predetermined time, and the accident risk prediction unit.
An operation support system characterized by having. The operation support system according to claim 6.
An operation support system further comprising an accident risk notification unit that generates and outputs an alert when the predicted value of the accident risk after a predetermined time is equal to or higher than a preset threshold value. The operation support system according to claim 6.
The biometric index calculation unit
The driver's heartbeat data is acquired as the biometric data, RRI is calculated from the heartbeat data to generate heartbeat fluctuation time series data, frequency spectrum analysis of the heartbeat fluctuation time series data is performed, and the frequency spectrum analysis is performed. An operation support system characterized by calculating the sum of the intensity of the low frequency component of the power spectrum density and the intensity of the high frequency component as the total autonomic nerve power from the results and using it as biometric index data. The operation support system according to claim 8.
The accident risk prediction department
An operation support system characterized in that the intensity of the low frequency component and the intensity of the high frequency component of the power spectral density are input to the accident risk prediction model, and the accident risk prediction model outputs interpretation data indicating the driver's condition. .. The operation support system according to claim 7.
The accident risk notification unit
An operation support system characterized by acquiring position information from an in-vehicle sensor of the vehicle and outputting a screen displaying the position information of the vehicle and information indicating the state of the driver. It is an operation support server that has a processor and memory and supports the operation of vehicles.
Danger occurs by machine learning by inputting the first in-vehicle sensor data showing the running state of the vehicle collected in the past and the danger occurrence data in which the information on which the danger has occurred is preset from the first in-vehicle sensor data. An accident risk definition model that estimates the probability of occurrence as an accident risk is generated, and the second in-vehicle sensor data indicating the running state of the vehicle collected in the past is input to the accident risk definition model to estimate the probability that a danger will occur. And the accident risk definition model generator that generates accident risk estimation data,
Accident risk that predicts the accident risk after a predetermined time by inputting the first biometric index data calculated in advance from the biometric data of the driver when the second in-vehicle sensor data is collected and the accident risk estimation data. Accident risk prediction model generation unit that generates prediction model by machine learning,
A biometric index calculation unit that acquires biometric data of the driver who is driving the vehicle and calculates a second biometric index data indicating the state of the driver from the biometric data.
An accident risk prediction unit that inputs the second biometric index data into the accident risk prediction model to predict the accident risk after a predetermined time, and the accident risk prediction unit.
An operation support server characterized by having. The operation support server according to claim 11.
An operation support server further comprising an accident risk notification unit that generates and outputs an alert when the predicted value of the accident risk after a predetermined time is equal to or higher than a preset threshold value. The operation support server according to claim 11.
The biometric index calculation unit
The driver's heartbeat data is acquired as the biometric data, RRI is calculated from the heartbeat data to generate heartbeat fluctuation time series data, frequency spectrum analysis of the heartbeat fluctuation time series data is performed, and the frequency spectrum analysis is performed. An operation support server characterized by calculating the sum of the intensity of the low frequency component of the power spectrum density and the intensity of the high frequency component as the total autonomic nerve power from the result and using it as biometric index data. The operation support server according to claim 13.
The accident risk prediction department
An operation support server characterized in that the intensity of the low frequency component and the intensity of the high frequency component of the power spectral density are input to the accident risk prediction model, and the accident risk prediction model outputs interpretation data indicating the driver's condition. .. The operation support server according to claim 12.
The accident risk notification unit
An operation support server characterized by acquiring position information from an in-vehicle sensor of the vehicle and outputting a screen displaying the position information of the vehicle and information indicating the state of the driver. The operation support method according to claim 1.
The fourth step is
The step of acquiring the driver's heartbeat data as the biometric data,
A step of calculating RRI from the heart rate data to generate heart rate variability time series data,
A step of calculating a difference value of adjacent RRIs for the heart rate variability time series data and generating a difference series ΔRRI (t).
A step of calculating the total number of difference values whose difference value becomes a predetermined value XXmsec or more from the difference series ΔRRI (t) as an autonomic nerve NNXX and using it as biometric index data.
Operation support method characterized by including. The operation support system according to claim 6.
The biometric index calculation unit
The driver's heart rate data is acquired as the biometric data, RRI is calculated from the heart rate data to generate heart rate variability time series data, and the difference value of adjacent RRIs is calculated for the heart rate variability time series data to make a difference. An operation characterized in that a sequence ΔRRI (t) is generated, and the total number of difference values whose difference value becomes a predetermined value XXmsec or more from the difference sequence ΔRRI (t) is calculated as autonomic nerve NNXX and used as biometric index data. Support system. The operation support server according to claim 11.
The biometric index calculation unit
The driver's heart rate data is acquired as the biometric data, RRI is calculated from the heart rate data to generate heart rate variability time series data, and the difference value of adjacent RRIs is calculated for the heart rate variability time series data to make a difference. An operation characterized in that a series ΔRRI (t) is generated, and the total number of difference values whose difference value becomes a predetermined value XXmsec or more is calculated as autonomic nerve NNXX from the difference series ΔRRI (t) and used as biometric index data. Support server.

Images