JP2020194206A - Learning method, driving support method, learning program, driving support program, learning device, driving support system, and learning system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain a standard of cognitive load capable of determining the possibility of dangerous driving. SOLUTION: The learning method determines that the learning unit is dangerous driving in a driving diagnosis based on driving data in which information on vehicle running is recorded in time series from time series data of cognitive load obtained from a driver's physiological index. A plurality of data between the time set and the time before a predetermined time are extracted, and the relationship between the cognitive load and dangerous driving is learned using the extracted data, and the definition unit learns. Based on the above relationship, the criteria for dangerous driving are defined for the cognitive load, and the learning unit does not use the data in which the cognitive load included in the data is all equal to or less than the threshold value among the plurality of the data. [Selection diagram] FIG. 7

Description

The present invention relates to a learning method, a driving support method, a learning program, a driving support program, a learning device, a driving support system, and a learning system.

A device has been proposed that controls the provision of information to a driver according to the cognitive load of the driver while driving a vehicle (see, for example, Patent Document 1).

JP-A-2010-33549

It is known that a high cognitive load increases the probability that a driver will have an accident. However, in the prior art, the standard of cognitive load that causes dangerous driving or condition that leads to an accident has not been examined.

In one aspect, the present invention aims to obtain a cognitive load criterion that can determine the possibility of dangerous driving.

In one aspect, the learning method is defined as dangerous driving in a driving diagnosis based on driving data in which the learning unit records information on the running of the vehicle in time series from the time series data of the cognitive load obtained from the driver's physiological index. A plurality of data between the determined time and the time before a predetermined time are extracted, and the relationship between the cognitive load and dangerous driving is learned using the extracted data, and the definition unit determines. From the learned relationship, the standard of dangerous driving is defined for the cognitive load, and the learning unit does not use the data in which the cognitive load included in the data is all equal to or less than the threshold value in the learning. The method.

It is possible to obtain a standard of cognitive load that can judge the possibility of dangerous driving.

FIG. 1 is a block diagram showing a configuration of a driving support system according to a first embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of the information processing device. FIG. 3A is a diagram showing an example of the configuration of the cognitive load data DB, and FIG. 3B is a diagram showing an example of the cognitive load data. FIG. 4A is a diagram showing an example of the configuration of the operation data DB, FIG. 4B is a diagram showing an example of the diagnostic data, and FIG. 4C is a diagram showing the configuration of the diagnostic data DB. It is a figure which shows an example. FIG. 5 is a diagram showing an example of the hardware configuration of the operation support server. FIG. 6 is a diagram showing an example of the configuration of the teacher data DB. FIG. 7 is a flowchart showing an example of the learning process. 8 (A) and 8 (B) are diagrams (No. 1) for explaining the learning process of FIG. 7. FIG. 9 is a diagram (No. 2) for explaining the learning process of FIG. 7. FIG. 10 (A) is a diagram showing an example of the configuration of the learning data DB, and FIG. 10 (B) is a diagram showing an example of the configuration of the reference data DB included in the driving support server, FIG. 10 (C). Is a diagram showing an example of the configuration of a reference data DB included in the information processing apparatus. FIG. 11 is a flowchart showing an example of dangerous driving prediction processing. FIG. 12 is a block diagram showing a configuration of the driving support system according to the second embodiment. FIG. 13 is a block diagram showing a configuration of the driving support system according to the third embodiment. FIG. 14 is a block diagram showing another example of the configuration of the driving support system according to the third embodiment. FIG. 15 is a flowchart showing an example of the prediction accuracy determination process.

Hereinafter, the driving support system according to the first embodiment will be described in detail with reference to FIGS. 1 to 11. The driving support system is a system that supports the driver's driving by predicting dangerous driving based on the driver's cognitive load.

FIG. 1 schematically shows the configuration of the driving support system 100 according to the first embodiment. As shown in FIG. 1, the driving support system 100 includes a driving support device 10 and a driving support server 20. In the first embodiment, the driving support device 10 is an example of the first information processing device, and the driving support server 20 is an example of the second information processing device. Further, in the first embodiment, the driving support server 20 is an example of the learning device. The driving support system 100 is an example of a learning system.

The driving support device 10 is mounted on a vehicle (not shown) and includes a notification device 11, a physiological index measuring device 12, a driving information acquisition device 13, a driver information acquisition device 14, and an information processing device 30.

Examples of the notification device 11 include, but are not limited to, a display and a speaker. The display and the speaker may be the display and the speaker provided in the vehicle in advance, respectively.

The physiological index measuring device 12 is a device that measures the physiological index of a driver who drives a vehicle. Examples of physiological indicators include, but are not limited to, heart rate, eye movements, pupil diameter, cerebral blood flow, sweating, and facial skin temperature. The cognitive load of the driver can be obtained from the physiological index. When the driver's cognitive load is high, heart rate increases, saccade-type invasion increases in eye movements, pupil diameter increases, cerebral blood flow increases, sweating increases, and facial skin temperature increases. .. When the physiological index is heart rate, the physiological index measuring device 12 is a heart rate monitor, and when the physiological index is eye movement or pupil diameter, the physiological index measuring device 12 is a camera. Further, for example, when the physiological index is cerebral blood flow, the physiological index measuring device 12 is an optical topography device, and the amount of sweating, the physiological index measuring device 12 is a sweat meter, and the facial skin temperature. The physiological index measuring device 12 is a thermography. The physiological index measuring device 12 measures at least one physiological index and transmits the measurement result to the information processing device 30.

The traveling information acquisition device 13 is a device that acquires information related to the traveling of the vehicle. Examples of information on vehicle running include engine speed, vehicle speed, acceleration, angular velocity, steering angle, accelerator pedal operation amount, brake pedal operation amount, and images around the vehicle, but are limited to this. It is not something that can be done. When the information about the running of the vehicle is the engine speed, the running information acquisition device 13 is a tachometer, a vehicle speed sensor when it is a vehicle speed, an acceleration sensor when it is an acceleration, and a gyro sensor when it is an angular velocity. When it is the steering angle of the steering wheel, it is a handle angle sensor. Further, when the information regarding the traveling of the vehicle is the operation amount of the accelerator pedal, the travel information acquisition device 13 is the accelerator pedal sensor, when the information regarding the operation of the brake pedal is the brake pedal sensor, and when it is an image of the surroundings of the vehicle. It is a drive recorder. The travel information acquisition device 13 acquires at least one piece of information regarding the travel of the vehicle and transmits it to the information processing device 30.

The driver information acquisition device 14 is a device that acquires driver identification information, and is, for example, a card reader. For example, when the driver holds the license over the driver information acquisition device 14, the driver information acquisition device 14 acquires the license number as the driver's identification information from the IC chip embedded in the driver's license. The driver information acquisition device 14 transmits the acquired driver identification information to the information processing device 30.

The information processing device 30 executes various processes described later based on the information acquired from the physiological index measuring device 12, the traveling information acquisition device 13, and the driver information acquisition device 14. The information processing device 30 is connected to the driving support server 20 via a network NW such as the Internet.

The information processing device 30 has a hardware configuration as shown in FIG. Specifically, as shown in FIG. 2, the information processing apparatus 30 includes a Central Processing Unit (CPU) 311 and a Read Only Memory (ROM) 312, a Random Access Memory (RAM) 313, and a storage device (Hard Disk Drive: HDD). ) 314, a network interface 315, a portable storage medium drive 317 that can read the data stored in the portable storage medium 316, and the like. Each component of the information processing device 30 is connected to the bus 320. The CPU 311 causes the information processing apparatus 30 to function as each part of FIG. 1 by executing a program stored in the ROM 312 or the HDD 314 or a program read from the portable storage medium 316 by the portable storage medium drive 317.

Specifically, as shown in FIG. 1, when the CPU 311 executes a program, the information processing device 30 includes an acquisition unit 31, a diagnosis unit 32, a communication unit 33, and a first determination unit, a notification unit, and a first unit. 2 It functions as a control unit 34 as a determination unit.

The acquisition unit 31 acquires the physiological index of the driver from the physiological index measuring device 12, and associates the time series data of the cognitive load (hereinafter referred to as cognitive load data) obtained by the physiological index with the identification information of the driver. It is stored in the cognitive load data DB351. The cognitive load data may be, for example, the physiological index itself measured by the physiological index measuring device 12, or the result obtained by performing a predetermined process on the physiological index (for example, a moving average of the physiological index). There may be. Further, the acquisition unit 31 outputs the physiological index acquired from the physiological index measuring device 12 to the control unit 34.

As shown in FIG. 3A, the cognitive load data DB 351 includes fields such as a driver ID, cognitive load data, and a transmitted flag. In the driver ID field, the driver identification information (for example, the license number) acquired by the driver information acquisition device 14 is stored. In the field of cognitive load data, time series data of cognitive load acquired during one trip is stored as shown in FIG. 3 (B). In this embodiment, one trip is defined as one on-period of the ignition switch.

The transmitted flag is a flag indicating whether or not the cognitive load data has been transmitted to the driving support server 20, and is checked when the cognitive load data has been transmitted to the driving support server 20. In this way, the cognitive load data DB 351 stores the cognitive load data for each driver. The cognitive load data DB 351 may include, for example, a field for storing the acquisition start time and the acquisition end time of the cognitive load data.

Further, the acquisition unit 31 stores the driving data in which the driving information acquisition device 13 has acquired the driving information of the vehicle in time series in the driving data DB 352.

As shown in FIG. 4A, the operation data DB 352 includes fields such as a driver ID, operation data, and a diagnosed flag. In the driver ID field, the driver identification information (for example, the license number) acquired by the driver information acquisition device 14 is stored. The driving data acquired during one trip is stored in the driving data field. The diagnosed flag is a flag indicating whether or not the driving diagnosis described later is performed based on the driving data, and is checked when the driving diagnosis is performed based on the driving data. In this way, the operation data DB 352 stores the operation data for each driver. The operation data DB 352 may include, for example, a field for storing the acquisition start time and the acquisition end time of the operation data.

Returning to FIG. 1, when the trip is completed, the diagnosis unit 32 diagnoses the driver's operation based on the operation data stored in the operation data DB 352, and records the operation diagnosis result in the diagnosis data DB 353. When the operation diagnosis is completed, the diagnosis unit 32 checks the diagnosed flag of the operation data for which the operation diagnosis has been performed in the operation data DB 352. In this embodiment, the diagnosis unit 32 diagnoses the dangerous driving degree, which indicates the degree of dangerous driving, based on the driving data. For example, when the rate of time change of the vehicle speed exceeds a predetermined threshold value (that is, when sudden acceleration or sudden deceleration occurs), the diagnosis unit 32 diagnoses that the degree of dangerous driving is high. Further, for example, the diagnostic unit 32 determines that the degree of dangerous driving is high when the rate of time change of the steering angle of the steering wheel exceeds a predetermined threshold value (that is, when the driver suddenly turns the steering wheel). The diagnosis unit 32 may diagnose the degree of dangerous driving based on a plurality of information (for example, acceleration and an image recorded by a drive recorder). As a result, in this embodiment, time-series data of the degree of dangerous driving as shown in FIG. 4B is acquired as diagnostic data.

As shown in FIG. 4C, the diagnostic data DB 353 includes fields such as a driver ID, diagnostic data, and a transmitted flag. In the driver ID field, the driver ID included in the driving data used for the driving diagnosis is stored. In the field of diagnostic data, the time series data of the dangerous driving degree shown in FIG. 4B is stored. The transmitted flag is a flag indicating whether or not the diagnostic data has been transmitted to the driving support server 20, and is checked when the diagnostic data is transmitted to the driving support server 20. In this way, the diagnostic data DB 353 stores diagnostic data for each driver.

Returning to FIG. 1, when the trip is completed, the communication unit 33 transmits the cognitive load data stored in the cognitive load data DB 351 and the diagnostic data stored in the diagnostic data DB 353 to the driving support server 20 together with the vehicle information 355. To do. When the transmission is completed, the communication unit 33 checks the transmitted flags of the cognitive load data and the diagnostic data transmitted to the driving support server 20.

The vehicle information 355 is stored in the HDD 314 or the like and is information indicating the type of the vehicle. The information indicating the type of vehicle may be, for example, the vehicle name, year, or model or a combination thereof, or may be a vehicle type such as an ordinary passenger car or a small passenger car, a minivan, a sedan, a compact vehicle, or an SUV (Sport Utility Vehicle). ) May be the type of vehicle body type. In this embodiment, the vehicle information 355 will be described on the assumption that it is a type of vehicle body type.

Further, at the start of the trip, the communication unit 33 transmits a reference data transmission request including vehicle information 355 and driver identification information to the driving support server 20, and the transmitted vehicle information 355 and the driver from the driving support server 20. Acquire (receive) dangerous driving criteria for cognitive load defined for combination with identification information. The communication unit 33 stores the acquired reference in the reference data DB 354.

The control unit 34 is driven by the driver using the driver's cognitive load obtained from the physiological index input from the acquisition unit 31 and the dangerous driving standard for the cognitive load defined by the driving support server 20 described later. Judge the possibility of dangerous driving. More specifically, the possibility of dangerous driving is judged based on whether the cognitive load of the driver meets the defined dangerous driving criteria. When the control unit 34 determines that there is a possibility of dangerous driving, the control unit 34 controls the notification device 11 to notify the driver that there is a possibility of dangerous driving. The control unit 34 may acquire the physiological index directly from the physiological index measuring device 12. The details of the process executed by the control unit 34 will be described later.

The driving support server 20 is, for example, a cloud server, and defines a dangerous driving standard for the cognitive load based on the cognitive load data and the diagnostic data received from the information processing device 30.

The operation support server 20 has a hardware configuration as shown in FIG. Specifically, as shown in FIG. 5, the operation support server 20 is for a portable storage medium that can read the data stored in the CPU 211, the ROM 212, the RAM 213, the HDD 214, the network interface 215, and the portable storage medium 216. It is equipped with a drive 217 and the like. Each component of the driving support server 20 is connected to the bus 220. The CPU 211 causes the operation support server 20 to function as each part of FIG. 1 by executing a program stored in the ROM 212 or the HDD 214, or a program read from the portable storage medium 216 by the portable storage medium drive 217.

Specifically, as shown in FIG. 1, when the CPU 211 executes a program, the driving support server 20 functions as a communication unit 21 and a learning unit 22 as a learning unit and a definition unit.

The communication unit 21 receives cognitive load data and diagnostic data from the information processing device 30 together with vehicle information 355, and stores the received cognitive load data and diagnostic data pair as teacher data in the teacher data DB 251. Since the communication unit 33 of the information processing device 30 transmits the cognitive load data and the diagnostic data when the trip is completed, one teacher data can be obtained for each trip.

As shown in FIG. 6, the teacher data DB 251 includes fields such as vehicle type, driver ID, cognitive load data, diagnostic data, and learned flag. In the vehicle type field, the vehicle type included in the vehicle information 355 received from the information processing device 30 is stored. In the driver ID field, the driver ID information included in the received cognitive load data or diagnostic data is stored. The received cognitive load data and diagnostic data are stored in the fields of the cognitive load data and the diagnostic data, respectively. The learned flag is a flag indicating whether or not the learning of the relationship between the cognitive load and dangerous driving using the cognitive load data and the diagnostic data is completed, and is checked when the learning is completed.

In addition, the communication unit 21 transmits the dangerous driving standard for the cognitive load defined by the learning unit 22 to the information processing device 30.

The learning unit 22 learns the relationship between the cognitive load and dangerous driving based on the teacher data. In addition, the learning unit 22 defines the criteria for dangerous driving for cognitive load based on the learned relationships.

(Learning process)
Next, the learning process executed by the learning unit 22 of the driving support server 20 will be described with reference to the flowchart of FIG. The process of FIG. 7 may be executed each time the cognitive load data and the diagnostic data are received from the information processing device 30, or may be executed when a predetermined number of teacher data for a combination of a certain vehicle type and the driver ID are accumulated. You may. In this embodiment, the driving support server 20 will be described as executing the process of FIG. 7 when receiving the cognitive load data and the diagnostic data from the information processing device 30.

In the process of FIG. 7, first, the learning unit 22 reads the teacher data stored in the teacher data DB 251 (step S11). More specifically, the teacher for the same combination as the combination of the driver ID included in the cognitive load data and the diagnostic data and the vehicle type included in the vehicle information 355 received together with the cognitive load data and the diagnostic data from the teacher data DB 251 Of the data, read the data for which the learned flag is not checked.

The teacher data is, for example, cognitive load data (shown in the lower row) and diagnostic data (shown in the upper row) collected during one trip as shown in FIG. 8 (A).

Next, the learning unit 22 obtains data between the time determined to be dangerous driving and the time before a predetermined time (T) from the cognitive load data in relation to the cognitive load and dangerous driving. Is extracted as learning data for learning (step S13). When the degree of dangerous driving in the diagnostic data exceeds a predetermined threshold value, the learning unit 22 determines that the driving is dangerous. For example, as shown in FIG. 8B, when the dangerous driving degree exceeds the threshold value at the times t11 and t21, the times t11 and t21 become the times when the dangerous driving is determined.

Then, as shown in FIG. 8 (B), the learning unit 22 sets the data between the time t11 and the time (t11-T) and the time t21 and the time (t21-T) from the cognitive load data. And extract the data between. The learning unit 22 may extract data in a predetermined time (T) range before the time determined to be dangerous driving. For example, the learning unit 22 may extract data between a time (t11-α) (α <T) and a time (t11-α-T) before the time t11. In other words, the learning data may or may not include data on the cognitive load at the time determined to be dangerous driving.

Returning to FIG. 7, the learning unit 22 then excludes the data whose cognitive load is equal to or less than the threshold value among the extracted data (step S15). The threshold is set based on the driver's normal cognitive load measured in advance. For example, in the example of FIG. 9, since all the cognitive loads included in the data between the time (t11-T) and the time t11 are equal to or less than the threshold value Vth, the data between the time (t11-T) and the time t11. Is excluded from the training data.

Next, the learning unit 22 stores the remaining data in the learning data DB 253 as learning data for learning the relationship between the cognitive load and dangerous driving (step S17). As a result, the data after the time determined to be dangerous driving (for example, in FIG. 9, the data from the time t11 to the time (t21-T), the data after the time t21) is the relationship between the cognitive load and the dangerous driving. Is not stored as training data for learning. Therefore, the data when the cognitive load increases due to dangerous driving is not used as learning data. Further, the learning unit 22 does not store the data between the time determined to be dangerous driving and the time predetermined time before the time, in which the cognitive load is equal to or less than the threshold value, as learning data. Therefore, the data when dangerous driving occurs due to an external factor (for example, interruption of another vehicle) is excluded from the learning data. As a result, only the data when dangerous driving occurs due to the cognitive load can be used as the learning data.

As shown in FIG. 10A, the learning data DB 253 includes fields such as vehicle type, driver ID, and learning data. The vehicle type and driver ID associated with the teacher data read in step S11 are stored in the vehicle type and driver ID fields, respectively. In the field of learning data, among the cognitive load data, there is data between the time determined to be dangerous driving and the time before a predetermined time (T) from the time, and the cognitive load is not equal to or less than the threshold value. It is stored.

Returning to FIG. 7, the learning unit 22 checks the learned flag of the teacher data for which the learning data has been acquired in the teacher data DB 251 (step S18). The learning unit 22 may delete the teacher data from which the learning data has been acquired. In this case, the learned flag is unnecessary.

Next, the learning unit 22 defines the criteria for dangerous driving with respect to the cognitive load based on the learning data stored in the learning data DB 253 (step S19). Specifically, the learning unit 22 reads the learning data for the combination of the vehicle type and the driver ID from the learning data DB 253, and based on the learning data, regarding the cognitive load for the combination of the vehicle type and the driver ID. Define criteria for dangerous driving. For example, the learning unit 22 defines a pattern of time change of cognitive load between a time determined to be dangerous driving and a time predetermined time before the time as a standard for dangerous driving based on the learning data. The learning unit 22 may define the standard deviation of the cognitive load between the time determined to be dangerous driving and the time predetermined time before the time as the standard deviation of dangerous driving.

The learning unit 22 registers the defined reference in the reference data DB 252 (step S21), and ends the learning process.

As shown in FIG. 10B, the reference data DB 252 includes fields for vehicle type, driver ID, and reference data. In the vehicle type and driver ID fields, the vehicle type and the driver ID used for selecting the learning data in step S19 are stored, respectively. The reference data field stores the criteria for dangerous driving defined in step S19.

As described above, when the trip is completed, the communication unit 33 of the information processing device 30 transmits the cognitive load data and the diagnostic data to the driving support server 20, so that when the number of trips increases (the number of driving increases), the teacher data Will increase. Therefore, the learning accuracy (validity of the standard for dangerous driving) is improved by performing the process of FIG. 7 each time the cognitive load data and the diagnostic data are received.

When the communication unit 21 receives, for example, a reference data transmission request including the vehicle information 355 and the driver identification information from the information processing device 30, the communication unit 21 has the reference data DB 252 defined for the combination of the vehicle information 355 and the driver identification information. The reference data of the above is transmitted to the information processing apparatus 30. As a result, as shown in FIG. 10C, the reference data DB 354 of the information processing device 30 stores the reference data for each driver who drives the vehicle on which the information processing device 30 is mounted.

(Dangerous driving prediction)
Next, a process of predicting dangerous driving of the driver executed by the information processing device 30 included in the driving support device 10 mounted on the vehicle will be described. FIG. 11 is a flowchart showing dangerous driving prediction processing. When the trip is started, the process of FIG. 11 is executed until the trip ends.

In FIG. 11, the control unit 34 of the information processing device 30 acquires the cognitive load of the driver from the physiological index of the driver input from the acquisition unit 31 (step S31).

Next, the control unit 34 acquires the reference data associated with the driver who is currently driving the vehicle from the reference data stored in the reference data DB 354 (step S32).

Next, the control unit 34 determines the possibility of dangerous driving based on the cognitive load data and the dangerous driving standard included in the reference data acquired in step S32 (step S33). The control unit 34 is dangerous when, for example, the similarity between the time change of the cognitive load in the predetermined time (T) range and the time change pattern of the cognitive load defined as the standard of dangerous driving is equal to or more than the threshold value. Judge that there is a possibility of driving.

The control unit 34 returns to step S31 when there is no possibility of dangerous driving (step S35 / NO), but when there is a possibility of dangerous driving (step S35 / YES), there is a possibility of dangerous driving by the notification device 11. Is notified to the driver (step S37). For example, the control unit 34 notifies the driver of the possibility of dangerous driving by a buzzer sound. The control unit 34 may output a voice message such as "There is a possibility of dangerous driving" from the notification device 11. In addition, the control unit 34 may display an image or the like indicating the possibility of dangerous driving on the display of the navigation device.

As described in detail above, according to the first embodiment, the driving support system 100 records the driving data of the vehicle in time series from the time series data of the cognitive load obtained from the physiological index of the driver. Multiple data between the time determined to be dangerous driving in the driving diagnosis based on the above and the time before a predetermined time are extracted, and the relationship between the cognitive load and dangerous driving is learned using the extracted data. The learning unit 22 is provided to define the criteria for dangerous driving for cognitive load based on the learned relationships. The learning unit 22 does not store in the learning data DB 253 the data in which the cognitive load included in the data is all equal to or less than the threshold value among the extracted plurality of data. That is, the learning unit 22 does not use the data after the time determined to be dangerous driving for learning, and does not use the data in which the cognitive load included in the data is all below the threshold value for learning among the extracted plurality of data. .. As a result, it is possible to exclude from learning when the cognitive load increases due to dangerous driving or when dangerous driving occurs due to external factors (for example, interruption of another vehicle). It is possible to obtain a highly accurate standard that can be judged.

Further, in the first embodiment, the cognitive load time series data (cognitive load data) and the driving data are acquired for each combination of the driver and the vehicle type (see, for example, FIG. 6), and the learning unit 22 , Define the criteria for dangerous driving for each combination of driver and vehicle type. As a result, it is possible to obtain a more accurate standard that reflects the influence of the type of vehicle on driving and individual differences.

Further, in the first embodiment, the driving support system 100 determines the possibility of dangerous driving based on the cognitive load of the driver obtained from the physiological index input from the physiological index measuring device 12 and the standard of dangerous driving. The control unit 34 is provided to perform notification based on the determination result. Since the possibility of dangerous driving can be judged using a highly accurate standard for cognitive load, the possibility of dangerous driving can be judged with high accuracy. More specifically, the accuracy of the timing of alerting dangerous driving is improved as compared with the case of alerting dangerous driving based on whether or not the physiological index exceeds the threshold value. In addition, by notifying the driver of the possibility of dangerous driving, it is possible to support the safe driving of the driver.

Further, in the first embodiment, since the driving support server 20 includes the learning unit 22, it is easy to revise the learning algorithm as appropriate, and highly accurate learning is possible.

Further, in the first embodiment, the driving support system 100 includes a diagnostic unit 32 that performs a driving diagnosis based on the driving data. As a result, the amount of data transmitted to the operation support server 20 can be reduced as compared with the case where the operation data is transmitted. It should be noted that the driving data may be transmitted to the driving support server 20 instead of the driving data.

In the process of FIG. 11 of the first embodiment, the control unit 34 determines the volume of the buzzer, the sound pattern, and the sound according to the high possibility of dangerous driving (for example, depending on the degree of similarity). The content of the message (mode of notification) may be changed. For example, if the possibility of dangerous driving is low, the possibility of dangerous driving may be notified by a voice message, and if the possibility of dangerous driving is high, the possibility of dangerous driving may be notified by a buzzer or the like. ..

Further, in the first embodiment, the cognitive load data and the driving data are acquired for each combination of the driver and the vehicle type (see, for example, FIG. 6), but may be acquired for each driver. , May be acquired for each type of vehicle. In this case, the criteria for dangerous driving are defined for each driver or each type of vehicle.

In the first embodiment, the communication unit 33 of the information processing device 30 transmits the diagnostic data to the driving support server 20, but the present invention is not limited to this. For example, the communication unit 33 may transmit the time determined as dangerous driving in the diagnostic data (the time when the dangerous driving degree exceeds the threshold value) to the driving support server 20.

In the first embodiment, the diagnostic data is transmitted to the driving support server 20, and the learning unit 22 of the driving support server 20 defines the standard for dangerous driving. However, the information processing device 30 defines the standard for dangerous driving. You may.

FIG. 12 is a block diagram showing a configuration of the driving support system 100A according to the second embodiment. As shown in FIG. 12, the information processing device 30A according to the second embodiment includes a learning unit 35. In the second embodiment, the information processing device 30A is an example of the learning device. The information processing device 30A is an example of the first information processing device.

The learning unit 35 performs the same learning process as in FIG. 7. Specifically, the learning unit 35 extracts learning data using the cognitive load data stored in the cognitive load data DB 351 and the diagnostic data stored in the diagnostic data DB 353 as teacher data, and stores them in the learning data DB 356. To do. Then, the learning unit 35 defines the criteria for dangerous driving with respect to the cognitive load based on the learning data stored in the learning data DB 356.

Since other configurations are the same as those in the first embodiment, detailed description thereof will be omitted. In the second embodiment, since it is not necessary to transmit the cognitive load data and the diagnostic data to the driving support server 20, the communication unit 33 can be omitted.

The driving support device 10 provided in the driving support system may be realized by an electronic device such as a smartphone. FIG. 13 is a block diagram showing a configuration of the driving support system 100B according to the third embodiment. The driving support system 100B according to the third embodiment includes an electronic device 50 (driving support device 10). The electronic device 50 is, for example, a smartphone, and includes a notification device 11, a physiological index measuring device 12, a traveling information acquisition device 13, and an information processing device 30A.

The notification device 11 is, for example, a speaker included in the electronic device 50. The physiological index measuring device 12 is, for example, a camera included in the electronic device 50. By attaching the electronic device 50 to the windshield, dashboard, or the like of the vehicle so that the driver's eyeball can be photographed, the pupil diameter and / or the eyeball movement Can function as a physiological index measuring device 12 for measuring.

The traveling information acquisition device 13 is, for example, an acceleration sensor and a gyro sensor built in the electronic device 50.

Since other configurations are the same as those in the second embodiment, detailed description thereof will be omitted.

In the third embodiment, as in the driving support system 100C shown in FIG. 14, the communication unit 33 of the information processing device 30 of the electronic device 50A transmits the cognitive load data and the diagnostic data to the driving support server 20. It may be configured as. At this time, the communication unit 33 transmits, for example, the telephone number of the smartphone as the identification information of the driver. Further, the communication unit 33 transmits the vehicle type information input by the user in the application installed on the smartphone as the vehicle information 355.

By using the electronic devices 50 and 50A owned by an individual such as a smartphone, the driver information acquisition device 14 can be omitted.

In the first to third embodiments, the control unit 34 may perform the dangerous driving prediction process described with reference to FIG. 11 after the dangerous driving prediction accuracy reaches a predetermined accuracy. FIG. 15 is a flowchart showing an example of the prediction accuracy determination process. The process of FIG. 15 is executed when the running of the vehicle is completed.

First, the control unit 34 specifies a time (predicted dangerous driving time) at which it is determined that there is a possibility of dangerous driving when the current reference data is used in the cognitive load data acquired in this trip. (Step S51). Further, the control unit 34 specifies a time (dangerous driving time) determined to be dangerous driving in the diagnostic data of this trip (step S53). The processing order of steps S51 and S53 may be reversed or may be performed in parallel.

Next, the control unit 34 determines the validity of the reference data (step S55). For example, the control unit 34 determines the validity of the reference data, for example, based on the concordance rate between the dangerous driving predicted time and the dangerous driving time. In the control unit 34, the coincidence rate between the time when it is determined that there is a possibility of dangerous driving when the current reference data is used and the time when it is determined that there is dangerous driving in the diagnostic data is a predetermined threshold value (for example, 70). %) Or more, it is judged that the standard data is appropriate. If the reference data is not valid (step S55 / NO), the process of FIG. 15 ends. When the reference data is valid (step S55 / YES), the control unit 34 permits the start of the dangerous driving prediction process (step S57), and ends the process of FIG. For example, the control unit 34 may turn on the flag that allows the start of the dangerous driving prediction process, and if the flag is ON at the next driving, the dangerous driving prediction process of FIG. 11 may be executed. This makes it possible to prevent the driver from being erroneously notified of the possibility of dangerous driving when the prediction accuracy of dangerous driving is low (when learning is insufficient) using the current standard of dangerous driving.

The above processing function can be realized by a computer. In that case, a program that describes the processing content of the function that the processing device should have is provided. By executing the program on a computer, the above processing function is realized on the computer. The program describing the processing content can be recorded on a computer-readable recording medium (however, the carrier wave is excluded).

When a program is distributed, it is sold in the form of a portable storage 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 the storage device of the server computer and transfer the program from the server computer to another computer via the network.

The computer that executes the program stores, for example, the program recorded on the portable storage 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 the processing according to the program. The computer can also read the program directly from the portable storage medium and execute the process according to the program. In addition, the computer can sequentially execute processing according to the received program each time the program is transferred from the server computer.

The embodiments described above are examples of preferred embodiments of the present invention. However, the present invention is not limited to this, and various modifications can be made without departing from the gist of the present invention.

10 Driving support device 20 Driving support server 22 Learning unit 32 Diagnosis unit 34 Control unit 35 Learning unit 100, 100A, 100B, 100C Driving support system

Claims (15)

From the time when the learning department judged dangerous driving in the driving diagnosis based on the driving data that recorded the information about the driving of the vehicle in time series from the time series data of the cognitive load obtained from the driver's physiological index, and from that time A plurality of data between the time before a predetermined time are extracted, and the relationship between the cognitive load and dangerous driving is learned by using the extracted data.
The definition department defines the criteria for dangerous driving for cognitive load from the above-mentioned relationships learned.
The learning unit does not use the data in which the cognitive load included in the data is all equal to or less than the threshold value among the plurality of data for learning.
Learning method. The time-series data of the cognitive load and the driving data are acquired for each driver, each type of the vehicle, or each combination of the driver and the type of the vehicle.
The definition unit defines the standard for each driver, each type of vehicle, or each combination of the driver and the type of vehicle.
The learning method according to claim 1. The physiological index includes at least one of heart rate, eye movement, pupil diameter, cerebral blood flow, sweating state, and facial skin temperature.
The learning method according to claim 1 or 2. The vehicle travel information includes at least one of engine speed, vehicle speed, acceleration, angular velocity, steering angle, accelerator pedal operation, brake pedal operation, and images around the vehicle.
The learning method according to any one of claims 1 to 3. The first determination unit acquires a cognitive load from the physiological index measured by the physiological index measuring device, and the acquired cognitive load and the reference defined by the learning method according to any one of claims 1 to 4. Judging the possibility of dangerous driving based on
The notification unit makes a notification based on the judgment result.
Driving support method. The notification unit changes the mode of notification depending on whether the possibility of dangerous driving is high or low.
The driving support method according to claim 5. The result of the second determination unit determining the possibility of dangerous driving using the reference with respect to the time-series data of the cognitive load acquired during one trip, and the operation data acquired during the one trip. The validity of the above criteria is judged based on the comparison with the result of the driving diagnosis based on.
The driving support method according to claim 5 or 6. When the notification unit determines that the standard is appropriate, the notification unit starts the notification based on the determination result.
The driving support method according to claim 7. The diagnosis unit performs a driving diagnosis based on the driving data.
The driving support method according to any one of claims 5 to 8. On the computer
From the time-series data of cognitive load obtained from the driver's physiological index, the time when it was judged to be dangerous driving in the driving diagnosis based on the driving data that recorded the information about the driving of the vehicle in time series, and the predetermined time before the time. A process of extracting a plurality of data between times and learning the relationship between cognitive load and dangerous driving using the extracted data.
From the above-mentioned learned relationship, the process of defining the criteria for dangerous driving for cognitive load, and
To run,
In the learning process, among the plurality of data, data in which the cognitive load included in the data is all equal to or less than the threshold value is not used for learning.
Learning program. On the computer
A cognitive load is acquired from the physiological index measured by the physiological index measuring device, and the possibility of dangerous driving is determined based on the acquired cognitive load and the criteria defined by the learning program according to claim 10. Processing and
Processing to notify based on the judgment result and
Driving support program to execute. From the time-series data of cognitive load obtained from the driver's physiological index, the time when it was judged to be dangerous driving in the driving diagnosis based on the driving data that recorded the information about the driving of the vehicle in time series, and the time before the predetermined time A learning unit that extracts a plurality of data between times and learns the relationship between cognitive load and dangerous driving using the extracted data.
From the above-mentioned learned relationship, the definition part that defines the criteria for dangerous driving for cognitive load,
With
The learning unit does not use the data in which the cognitive load included in the data is all equal to or less than the threshold value among the plurality of data for learning.
Learning device. A cognitive load is acquired from the physiological index measured by the physiological index measuring device, and the possibility of dangerous driving is determined based on the acquired cognitive load and the criterion defined by the learning device according to claim 12. The first judgment unit to do
A notification unit that provides notification based on the judgment result,
Driving support system equipped with. The first information processing device mounted on the vehicle and
A second information processing device capable of communicating with the first information processing device is provided.
The first information processing device includes a communication unit that transmits time-series data of cognitive load and a result of a driving diagnosis based on the driving data to the second information processing device.
The second information processing device includes the learning device according to claim 12.
Learning system. Equipped with a first information processing device mounted on the vehicle
The first information processing device includes the learning device according to claim 12.
Learning system.

Images