WO2020225956A1 - Système de prédiction des risques de conduite dangereuse - Google Patents

Système de prédiction des risques de conduite dangereuse Download PDF

Info

Publication number
WO2020225956A1
WO2020225956A1 PCT/JP2020/006268 JP2020006268W WO2020225956A1 WO 2020225956 A1 WO2020225956 A1 WO 2020225956A1 JP 2020006268 W JP2020006268 W JP 2020006268W WO 2020225956 A1 WO2020225956 A1 WO 2020225956A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
model
driving
risk
prediction
Prior art date
Application number
PCT/JP2020/006268
Other languages
English (en)
Japanese (ja)
Inventor
田中　毅
俊輔 三幣
栗山　裕之
大知 尾白
佐藤　公則
Original Assignee
株式会社日立物流
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社日立物流 filed Critical 株式会社日立物流
Publication of WO2020225956A1 publication Critical patent/WO2020225956A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems

Definitions

  • This disclosure relates to the prediction of driving danger risk.
  • Patent Document 1 states, "The safe driving support device 100 receives life log data from the life log sensor 300 of the mobile phone terminal 200, receives driving behavior data from the telematics device 400 of the mobile body 400M, and has an accident from the insurance server 500. It accepts data, uses life log data, driving behavior data, and accident data to identify the degree of danger when a living body drives a vehicle, and provides caution information for accident avoidance to the mobile phone terminal 200 and telematics device 400. Provide. ”(Eg summary).
  • Patent Document 1 issues an alert based on a remarkable abnormal value of life log data that is seen when an accident occurs, and it was not possible to predict daily small fluctuations in accident risk. Further, Patent Document 1 is based on general accident data, and cannot reflect differences between individuals and characteristics of each individual. Therefore, a technology that can appropriately predict the risk of danger in driving for each individual is desired.
  • the system of one aspect of the present disclosure includes one or more processors that operate according to a program stored in the one or more storage devices.
  • the one or more processors are prediction models that predict the number of dangerous driving operations based on biometric data, acquire a prediction model corresponding to the past biometric data of an individual, and use the acquired prediction model to obtain a prediction model. Based on the biometric data measured prior to the driving of the individual vehicle, the risk risk prediction level in the driving of the individual vehicle is determined.
  • An example of a system configuration including an operation management assistance system is shown.
  • An example of the hardware configuration of the operation management assistance system is shown.
  • a configuration example of the biological data DB is shown.
  • a configuration example of the subjective evaluation data DB is included.
  • a configuration example of the dangerous driving operation data DB is shown.
  • An example of the configuration of the association data is shown.
  • the flowchart which the biological data collecting device acquires the heart rate variability parameter is shown.
  • An example of heart rate variability is shown.
  • the time change of the peak interval RR is shown.
  • An example of the frequency spectrum of the time change of the peak interval RR is shown.
  • a flowchart of a processing example by the subjective evaluation data collection device is shown.
  • An image example of two VAS is shown.
  • FIG. 1 It is a figure for demonstrating the generation of the association data, the generation of the trained prediction model, and the prediction of the risk risk level by the trained prediction model.
  • a flowchart of a processing example of the operation management assist system and related data are shown.
  • An example of a flowchart for selecting a biological model by a biological model selection program is shown.
  • An image example of the report presented by the prediction result presentation program is shown.
  • An image example of the report presented by the prediction result presentation program is shown.
  • the operation management assistance system can assist the operation management of vehicles in the land transportation industry such as trucks, buses, and taxis.
  • the prediction of the danger risk in driving of the present disclosure is not limited to the operation management of a plurality of vehicles, and can be applied to the prediction of the danger risk before driving of one or a plurality of drivers.
  • FIG. 1 shows an example of a system configuration including an operation management assistance system.
  • the operation management assistance system 2 the operation data collection device 15, the prediction result display terminal 31, the biological data collection device 32, and the subjective evaluation data collection device 33 can each communicate via the network.
  • the driving data collecting device 15 is mounted on the vehicle 1, acquires measurement data (vehicle-mounted sensor data or driving data) of the sensor device mounted on the vehicle 1, and transmits the measurement data (vehicle-mounted sensor data or driving data) to the operation management assist system 2.
  • the sensor device mounted on the vehicle 1 includes a position sensor (GNSS) 11 by a GNSS (Global Navigation Satellite System), an inter-vehicle distance sensor 12, a speedometer 13, and an acceleration sensor 14.
  • GNSS position sensor
  • the driving data collecting device 15 may be installed outside the vehicle 1 and receive data from the vehicle-mounted sensor device via the network.
  • the prediction result display terminal 31 displays the prediction result of the danger risk during operation by the operation management assistance system 2. Details of the danger risk prediction method and the display image of the prediction result will be described later.
  • the biometric data collecting device 32 acquires the driver's measurement data from the biometric measuring instrument and transmits it to the operation management assist system 2.
  • the biometric instruments used include a heart rate monitor 34, a thermometer 35 and a sphygmomanometer 36.
  • the driver or manager uses a biometric instrument to measure the biometric data of the driver, for example, before and after a day's driving.
  • the subjective evaluation data collecting device 33 acquires the subjective evaluation of the driver and transmits it to the operation management assist system 2. For example, when measuring the biological data of the driver, the driver inputs a subjective evaluation of his / her physical condition to the subjective evaluation data collecting device 33. The details of inputting the subjective evaluation will be described later.
  • the operation management assistance system 2 holds a plurality of programs to be processed and data processed by the plurality of programs.
  • the program executed by the operation management assist system 2 includes a danger determination program 221, a biological model selection program 222, a prediction model training program 223, and a prediction result presentation program 224.
  • the danger determination program 221 analyzes the in-vehicle sensor data transmitted from the operation data collection device 15 to detect a dangerous driving operation.
  • the biological model selection program 222 selects a biological model suitable for the driver. Details of the biological model will be described later.
  • the predictive model training program 223 trains the predictive model contained in the selected biological model to generate the trained predictive model 253. As will be described later, the trained prediction model 253 predicts the driver's driving risk risk level.
  • the Prediction Results Presentation Program 224 presents information about the predicted driver risk level.
  • the data held by the operation management assistance system 2 includes the history data 24, the biological model DB 251 and the association data 252, the trained prediction model 253, and the pre-driving data 26.
  • Historical data 24 includes past data history for one or more vehicles and one or more drivers, and in the examples described below, includes past data history for multiple vehicles and multiple drivers. .. Specifically, the history data 24 includes a biological data database (DB) 241, a subjective evaluation data DB 242, a dangerous driving operation data DB 243, and an in-vehicle sensor data DB 244.
  • DB biological data database
  • the biological data DB 241 stores the biological data received from the biological data collecting device 32.
  • the biological data DB 241 stores the measured biological data history of a plurality of drivers. In the examples described below, values that can change before and after driving, such as heart rate variability and body temperature, are measured.
  • the subjective evaluation data DB 242 stores the subjective evaluation data received from the subjective evaluation data collecting device 33.
  • the subjective evaluation data shows the subjective evaluation of the driver's physical condition.
  • the subjective evaluation data DB 242 stores the subjective evaluation data history of a plurality of drivers. As will be described later, the individual data in the biometric data DB 241 and the subjective evaluation data DB 242 are referred to for selecting a prediction model of driving risk.
  • the vehicle-mounted sensor data DB 244 stores the vehicle-mounted sensor data (driving data) received from the driving data collecting device 15.
  • the vehicle-mounted sensor data DB 244 stores the history of vehicle-mounted sensor data of a plurality of drivers.
  • the dangerous driving operation data DB 243 stores a history of dangerous driving operations in driving (dangerous driving operation data history).
  • the danger determination program 221 detects dangerous driving operations in each driving unit (for example, one driver's daily driving) from the data stored in the in-vehicle sensor data DB 244, and transmits the information to the dangerous driving operation data DB 243. Store.
  • the danger determination program 221 detects various dangerous driving operations from the in-vehicle sensor data. For example, sudden braking and sudden start can be detected from the data of the acceleration sensor 14, and the inter-vehicle distance can be acquired from the data of the inter-vehicle distance sensor 12.
  • the legal speed is known from the position sensor 11 and map information (not shown), and the vehicle speed is known by the speedometer 13.
  • the biological model DB 251 stores a plurality of biological models.
  • the biological model includes an explanatory model, semantic interpretation data, and a risk risk prediction model, as described below. These details will be described later.
  • the association data 252 is generated from the history data 24 by the biological model selection program 222.
  • the association data 252 is the data of a specific driver extracted from the history data 24.
  • the trained prediction model 253 is a prediction model included in the biological model selected for a particular driver and trained by the association data 252 of that particular driver.
  • the trained prediction model 253 is a prediction model corresponding to the past biometric data of an individual.
  • the pre-driving data 26 is data about the driver acquired before driving by the driver (individual), and is biometric data 261 measured before the driving of the driver's vehicle and the driving of the driver's vehicle. Includes previously evaluated subjective evaluation data 262.
  • the subjective evaluation data 262 shows the subjective evaluation of the physical condition before the driving by the driver. As will be described later, the subjective evaluation data 262 is referred to for preparing the explanatory text in the pre-driving report.
  • the biological data 261 is input to the trained prediction model 253 that predicts the number of dangerous driving operations in the driving.
  • the biometric data 261 includes, for example, biometric data measured before driving on the driving day, biometric data measured before and after driving on the immediately preceding driving day, differences in biometric data measured before and after driving on the immediately preceding driving day, and past. It includes the inclination of the regression equation representing the transition of each biometric data before and after the operation for a predetermined period, or a combination of a part or all of them.
  • the data contained in the pre-operation data 26 may differ between the trained prediction models 253.
  • the input of the trained prediction model 253 may include subjective evaluation data.
  • FIG. 2 shows an example of the hardware configuration of the operation management assistance system 2.
  • the operation management assistance system 2 can have a general computer configuration.
  • the operation management auxiliary system 2 includes a processor 401, a memory (main storage device) 402, an auxiliary storage device 403, an output device 404, an input device 405, and a communication interface (I / F) 407.
  • the above components are connected to each other by a bus.
  • the memory 402, the auxiliary storage device 403, or a combination thereof is a storage device and stores the program and data shown in FIG.
  • the memory 402 is composed of, for example, a semiconductor memory, and is mainly used for holding a program or data being executed.
  • the processor 401 executes various processes according to the program stored in the memory 402. When the processor 401 operates according to the program, various functional units are realized.
  • the auxiliary storage device 403 is composed of a large-capacity storage device such as a hard disk drive or a solid state drive, and is used for holding programs and data for a long period of time.
  • the processor 401 can be composed of a single processing unit or a plurality of processing units, and can include a single or a plurality of arithmetic units, or a plurality of processing cores.
  • Processor 401 manipulates signals based on one or more central processing units, microprocessors, microprocessors, microcontrollers, digital signal processors, state machines, logic circuits, graphics processing units, chip-on systems, and / or control instructions. It can be implemented as any device.
  • the program and data stored in the auxiliary storage device 403 are loaded into the memory 402 at startup or when necessary, and the processor 401 executes the program to execute various processes of the operation management auxiliary system 2. Therefore, the processing executed by the operation management assist system 2 in the following is the processing by the processor 401 or the program.
  • the input device 405 is a hardware device for the user to input instructions, information, etc. to the operation management assist system 2.
  • the output device 404 is a hardware device that presents various images for input / output, and is, for example, a display device or a printing device.
  • the communication I / F 407 is an interface for connecting to a network.
  • the input device 405 and the output device 404 may be omitted, and the user may access the operation management assist system 2 from the terminal via the network.
  • the function of the operation management assistance system 2 can be implemented in a computer system consisting of one or more computers including one or more processors and one or more storage devices including a non-transient storage medium. Multiple computers communicate over a network. For example, a part of a plurality of functions of the operation management assist system 2 may be implemented in one computer, and a part of the other may be implemented in another computer.
  • the operation data collection device 15, the prediction result display terminal 31, the biological data collection device 32, and the subjective evaluation data collection device 33 can each have a computer configuration similar to the operation management assistance system 2.
  • the functions of a plurality of devices in the above device may be implemented in one device.
  • the operation management assist system 2, the prediction result display terminal 31, the biological data collection device 32, and the subjective evaluation data collection device 33 are one. It may be integrated into the device.
  • each element of the software may be stored in any area in the storage device.
  • the processor 401 functions as a specific functional unit by operating according to a specific program.
  • the processor 401 functions as a danger determination unit, a biological model selection unit, a prediction model training unit, and a prediction result display unit according to the above program.
  • FIG. 3 shows a configuration example of the biological data DB 241.
  • the data stored in the biological data DB 241 includes data measured before the operation on the day of operation.
  • the biological data DB 241 includes a user ID column, a date and time column, an autonomic nerve total power column, an autonomic nerve LF / HF column, and a body temperature column.
  • the user ID column indicates a user ID that identifies each driver who is a user.
  • the date and time column indicates the measurement date and time of biological data.
  • the autonomic nerve Total Power column indicates Total Power (TP), which is one of the electrocardiographic fluctuation parameters.
  • Total Power is the total power of the power spectrum of a specific frequency band of electrocardiographic fluctuation, and is related to fatigue.
  • the autonomic nerve LF / HF indicates the ratio of the power of the low frequency band (LF) and the high frequency band (HF) in the specific frequency band, which is one of the electrocardiographic fluctuation parameters.
  • LF / HF represents the overall balance of sympathetic and parasympathetic nerves.
  • the body temperature column shows the measured value of the driver's body temperature.
  • FIG. 4 includes a configuration example of the subjective evaluation data DB 242.
  • the data stored in the subjective evaluation data DB 242 includes the subjective evaluation data before driving on the day of driving.
  • the subjective evaluation data DB 242 includes a user ID column, a date and time column, and a VAS1 column to a VAS5 column.
  • the user ID column indicates a user ID that identifies each driver who is a user, and the date and time column indicates the date and time when the subjective evaluation was performed.
  • the VAS1 column to the VAS5 column indicate different VAS (Visual Analog Scale) values, respectively.
  • the VAS value represents, for example, a self-assessment of fatigue and sleep.
  • the VAS is an example of a self-evaluation method, and a method different from the VAS may be used.
  • FIG. 5 shows a configuration example of the dangerous driving operation data DB 243.
  • the dangerous driving operation data DB 243 stores the determination result of the danger determination program 221.
  • the dangerous driving operation data DB 243 includes a user ID column, a date column, a start time column, an end time column, a dangerous driving operation 1 column to a dangerous driving operation 4 column.
  • the user ID column indicates a user ID that identifies each driver who is a user
  • the date column indicates the date of a specific driving period for which a dangerous driving operation is detected.
  • the start time column and end time column indicate the start time and end time of the operation period.
  • the dangerous driving operation column 1 to the dangerous driving operation column 4 indicate the number of predetermined dangerous driving operations, respectively.
  • the dangerous driving operation 1 to the dangerous driving operation 4 indicate different dangerous driving operations.
  • FIG. 6 shows a configuration example of the association data 252.
  • the association data 252 is data of the same user (driver) extracted from the biological data DB 241 and the subjective evaluation data DB 242 and the dangerous driving operation data DB 243.
  • Each record of the association data 252 indicates information extracted from the above three DBs 241, 242 and 243 for one operating period.
  • This configuration example includes a user ID column, a date column, a pre-driving autonomic nerve Total Power column on the previous day, a pre-driving autonomic nerve Total Power column on the previous day, a post-driving autonomic nerve Total Power column on the previous day, a differential autonomic nerve Total Power column before and after the previous day driving, and the current day.
  • VAS1 before driving to VAS5 before driving on the same day VAS1 after driving on the same day to VAS5 after driving on the same day, and dangerous driving operation 1 to 4 columns. Some columns are omitted in FIG.
  • the association data 252 is used to select a predictive model suitable for a specific user from a plurality of risk risk predictive models, and to train the selected predictive model.
  • dangerous driving operations are detected in daily driving, and the number of dangerous driving operations indicates the dangerous risk level of driving. Therefore, by using the history of dangerous driving operations for each individual, it is possible to generate a trained prediction model suitable for each individual.
  • FIG. 7 shows a flowchart in which the biological data collecting device 32 acquires a heart rate variability parameter.
  • the biometric data collecting device 32 measures the biometric data of the driver by the biometric instrument and transmits it to the operation management assist system 2.
  • the biological data collecting device 32 measures the electrocardiogram (heartbeat) with the heart rate monitor 34 (S101).
  • FIG. 8 shows an example of heart rate variability, where the horizontal axis represents time and the vertical axis represents potential. "RR" indicates the interval between peaks of a particular type.
  • the biological data collecting device 32 detects the interval RR between peaks of a specific type in the measurement result of the heart rate monitor 34 (S102).
  • FIG. 9 shows the time variation of the interval RR.
  • the biological data acquisition device 32 analyzes the frequency spectrum of the time change of the interval RR (S103).
  • FIG. 10 shows an example of the frequency spectrum of the time change of the interval RR.
  • FIG. 10 shows the spectral power density of the interval RR.
  • the biological data collecting device 32 extracts the power of the low frequency band LF and the power of the high frequency band HF in the frequency spectrum, and calculates a predetermined heart rate variability parameter (S104).
  • Predetermined heart rate variability parameters include Total Power and the power ratio of LF to HF (LF / HF). In this example, Total Power is the sum of LF and HF.
  • the biological data collecting device 32 transmits the calculated information about the heart rate variability to the operation management assisting system 2 and records it in the biological data DB 241 (S105).
  • FIG. 11 shows a flowchart of a processing example by the subjective evaluation data collecting device 33.
  • the subjective evaluation data collecting device 33 receives the input of VAS1 from the driver (S121) and calculates the input value of VAS1 (S122). Similarly, the subjective evaluation data collecting device 33 receives the inputs of VAS2 to VAS4 from the driver and calculates the VAS4 input value from the VAS2 input value (not shown). Further, the subjective evaluation data collecting device 33 receives the input of VAS5 from the driver (S123) and calculates the input value of VAS5 (S124). The subjective evaluation data collecting device 33 transmits the VAS5 input value from the VAS1 input value to the operation management assist system 2 and records it in the subjective evaluation data DB 242.
  • FIG. 12 shows two VAS image examples 501 and 502.
  • VAS501 is a VAS for inputting a feeling of fatigue
  • VAS502 is a VAS for inputting information about sleep last night.
  • the driver inputs a self-evaluation of fatigue by moving the black dot 512 on the line 511 to determine the position.
  • the subjective evaluation data collecting device calculates the VAS input value from the position of the input black dot 512.
  • the left end of line 521 in VAS502 corresponds to a state in which he could not sleep at all, and the right end corresponds to a state in which he slept well.
  • the driver inputs a self-assessment of sleep by moving the black dot 522 on line 521 to determine the position.
  • the subjective evaluation data collecting device calculates the VAS input value from the position of the input black dot 522.
  • FIG. 13 is a diagram for explaining the generation of the association data 252, the generation of the trained prediction model 253, and the prediction of the number of dangerous operations by the trained prediction model 253.
  • the upper part of FIG. 13 shows the generation of the association data 252, and the lower part shows the training of the prediction model using the association data 252 and the prediction of the number of dangerous operations by the trained prediction model 253.
  • FIG. 13 shows the biological data and dangerous driving operation data included in the association data 252 as examples, and the subjective evaluation data is omitted.
  • the association data 252 includes a biometric data history of a specific individual from day K to day N.
  • the heart marks in the morning and evening of each day indicate the measurement of biometric data, and the ⁇ below the vehicle indicates the detected dangerous driving operation.
  • the trained prediction model 253 predicts the number of dangerous driving in the driving of the day from the biological data before the previous day's driving, the biological data after the previous day's driving, the biological data difference before and after the previous day's driving, and the biological data before the current day's driving. To do.
  • the number of dangerous driving is one of the indexes showing the dangerous risk level.
  • the association data 252 associates the biometric data before the previous day's driving, the biometric data after the previous day's driving, the biological data difference before and after the previous day's driving, and the biometric data before the current day's driving with respect to the driving of each specific individual from the K + 1 day to the Nth day. Is stored.
  • the association data 252 further stores dangerous driving operation data indicating the number of dangerous driving operations in each operation from the K + 1 day to the N day in association with the biometric data for the driving of each day.
  • the biometric data 531A is the biometric data before driving on the K day day and the biometric data before driving on the K + 1 day.
  • the biometric data 531B is the biometric data after the driving on the K day day and the biometric data after the driving on the K + 1 day.
  • the biometric data difference 532 is a biometric data difference before and after the driving on the K day day, and is a biometric data difference before and after the driving on the K + 1 day.
  • the biometric data 541A is the biometric data before driving on the day of K + 1 and the biometric data before driving on the day before K + 2.
  • the number of danger determinations (dangerous driving operation data) 543 on the K + 1 day is associated with the biological data 531A, the biological data 531B, the biological data difference 532, and the biological data 541A.
  • the biometric data and dangerous driving operation data stored in the association data 252 are used as training data for the prediction model.
  • the prediction model is trained by a machine learning method using the association data 252 (S143), and a trained prediction model 253 is generated.
  • the training updates the parameters of the prediction model based on the error between the output of the prediction model and the correct answer.
  • the trained prediction model 253 predicts the number of dangerous driving operations (number of dangerous driving operations) 563 per unit time in the driving of the day.
  • the output of the trained predictive model 253 is the total number of all dangerous driving operations per unit time in one driving period (eg, one day).
  • the trained prediction model 253 may predict the number of times per unit time for each dangerous driving operation type.
  • the trained prediction model 253 is based on the previous day's pre-driving biometric data 551A, the previous day's post-driving biometric data 551B, the previous day's pre- and post-driving biometric data difference 552, and the same-day pre-driving biometric data 561A. Predict 563.
  • the biometric data before and after driving on the previous day shows changes in biometric data due to driving, and more appropriate prediction becomes possible. Further, the biometric data before driving on the day is the biometric data immediately before driving, and more appropriate prediction becomes possible. As described above, the input data does not have to be common between the prediction models.
  • FIG. 14 shows a flowchart of a processing example of the operation management assist system 2 and data related thereto.
  • the biological model selection program 222 reads out the association data 252 of the target user (driver) from the history data 24 (S141).
  • the biological model selection program 222 selects an appropriate biological model 280 from a plurality of biological models in the biological model DB 251 based on the association data 252 (S142). Details of the selection method of the biological model 280 will be described later.
  • the biological model 280 includes the explanatory model 281, the predictive model 282, and the semantic interpretation data 283 that are associated in advance.
  • the predictive model training program 223 trains the predictive model 282 using the association data 252 as training data (S143).
  • the parameters of the prediction model 282 are updated to generate the trained prediction model 253.
  • the trained prediction model 253 calculates a predicted value of the number of dangerous driving operations in driving by the target user based on the pre-driving data 26 of the target user (S144).
  • the predicted value is, for example, the number of times or the total number of dangerous driving operations for each type.
  • the input to the trained prediction model 253 may include biometric data 261 before driving (on the day or before) and may also include subjective evaluation data 262.
  • the prediction result presentation program 224 uses the semantic interpretation data 283 of the biological model 280 to generate a semantic interpretation sentence (explanation), and determines the danger risk prediction level based on the number of dangerous driving predictions.
  • the prediction result presentation program 224 presents the semantic interpretation sentence and the risk / risk prediction level to the target user and / or the administrator (S145).
  • the prediction result presentation program 224 generates display data 27 and displays it on the output device 404.
  • the display data 27 includes a risk risk prediction level 271 and a semantic interpretation sentence (explanation).
  • the prediction result presentation program 224 predicts the danger risk based on, for example, the history of the past number of dangerous driving operations of the target user and / or the comparison result (for example, deviation value) with the statistical value of the number of dangerous driving operations of other drivers. Determine level 271.
  • FIG. 15 shows an example of a flowchart of selection of a biological model (S142) by the biological model selection program 222.
  • the biological model selection program 222 tests the association data 252 for each of the plurality of explanatory models (statistical models) in the biological model DB 251 (S161), and selects an explanatory model that matches the association data 252 (S162). ..
  • the explanatory model shows the relationship between subjective evaluation data and biometric data.
  • the relationship between a plurality of explanatory variables of subjective evaluation data and one objective variable in biometric data can be identified by multiple regression analysis.
  • the explanatory model shows, for example, an equation obtained by multiple regression analysis.
  • the biological model selection program 222 may select, for example, the explanatory model having the smallest multiple correlation coefficient between the explanatory model and the association data 252 or within a predetermined range.
  • the explanatory model may show the relational expression between each of the plurality of objective variables of the biological data and the objective variables in one or more subjective evaluation data.
  • the biological model selection program 222 may select an explanatory model based on a predetermined statistical value of a multiple correlation coefficient between the explanatory model and the association data 252 for a plurality of relational expressions.
  • the explanatory model shows the relationship between one or more VAS and one or more types of biometric data.
  • An explanatory model as a more specific example shows the correlation coefficient between one VAS (for example, a feeling of fatigue) and the autonomic nerve Total Power.
  • the biological model selection program 222 selects an explanatory model of the number of correlations having the closest correlation coefficient calculated from the association data 252 or within the range of measures.
  • FIG. 15 shows the explanatory model A281A and the explanatory model B281B as examples.
  • the explanatory model A281A and the explanatory model B281B each show a correlation coefficient with the autonomic nerve Total Power.
  • the explanatory model A281A is selected as the explanatory model that best matches the association data 252.
  • the biological model selection program 222 selects the biological model associated with the biological model including the selected explanatory model from the biological model DB 251 (S163).
  • a biological model 280A including the explanatory model A281A is selected.
  • the biological model 280A includes the prediction model A282A and the semantic interpretation data A283A in addition to the explanatory model A281A.
  • the biological model 280B including the prediction model B282B and the semantic interpretation data B283B is not selected.
  • the relationship between subjective evaluation and biometric data can vary from individual to individual.
  • the correlation coefficient between the autonomic nerve Total Power of a certain user and VAS1 may be a negative value
  • the correlation coefficient between the autonomic nerve Total Power of another user and VAS1 may be a positive value.
  • the biological model selection program 222 may select the prediction model without using the explanatory model (the explanatory model is omitted).
  • the biological model selection program 222 may select a classification model that best matches the historical data of the target user.
  • training of the prediction model may be omitted.
  • the classification model that best matches the historical data of the target user and the prediction model that omits training are prediction models that correspond to the past biometric data of the individual.
  • the trained prediction model obtained by training the prediction model 282 trained using the prediction model 282 pre-associated with the explanatory model 281 and the association data 252 is a prediction based on the prediction model associated with the explanatory model. It is a model.
  • FIG. 16 and 17 show image examples of the report presented by the prediction result presentation program 224, respectively.
  • FIG. 16 shows the report 600 for the target user (driver) A
  • FIG. 17 shows the report 620 for the target user (driver) B.
  • Report 600 shown in FIG. 16 includes measurement results 601 of biological data.
  • the measurement result 601 shows the biological data measured after the previous day's operation and the biological data measured before the current day's operation.
  • Report 600 also contains information on predicting danger risks in driving on the day. Specifically, Report 600 shows the risk risk prediction level 603 and the semantic interpretation (explanatory text) 605 related to the risk risk.
  • the semantic interpretation sentence 605 further includes a semantic interpretation sentence 607 for biometric data and a semantic interpretation sentence 609 for the risk risk prediction level 603.
  • the danger risk prediction level By presenting the danger risk prediction level, it is possible to alert the target user A, or to urge the operation manager to take measures such as changing the business content of the target user A. Further, by presenting the semantic interpretation sentence 607 of the biological data, it is possible to enhance the understanding of the physical condition of the target user A. Furthermore, by presenting the semantic interpretation sentence 609 about the danger risk prediction level, the degree of understanding of the danger risk prediction level can be enhanced. Note that some of the information presented by Report 600 may be omitted.
  • Report 620 shown in FIG. 17 includes measurement results 621 of biometric data.
  • the measurement result 621 shows the biological data measured after the previous day's operation and the biological data measured before the current day's operation.
  • Report 620 also contains information on predicting danger risks in driving on the day. Specifically, Report 620 provides a risk risk prediction level of 623 and a semantic interpretation (explanatory text) 625 related to risk.
  • the semantic interpretation sentence 625 includes a semantic interpretation sentence 627 for biometric data. Since the risk risk prediction level is low, the semantic interpretation of the risk risk prediction level is omitted.
  • the report 620 can exert the same effect as the report 600 for the target user B. In addition, some of the information presented by Report 620 may be omitted.
  • the prediction result presentation program 224 determines the danger risk prediction level based on the number of dangerous driving operations predicted by the trained prediction model 253. If the trained prediction model 253 indicates the number of times for each dangerous driving operation type, the prediction result presentation program 224 may give a predetermined weight to each dangerous driving operation type.
  • the prediction result presentation program 224 determines the expression of the measurement result from the numerical values of the biological data based on a predetermined standard. The criteria may be determined for each target user based on historical data.
  • the prediction result presentation program 224 refers to the semantic interpretation data 283 in the selected biological model 280 and generates a semantic interpretation sentence.
  • Semantic interpretation data 283 indicates sentences associated with each of the different levels of biometric data and further indicates sentences associated with each of the different risk risk prediction levels.
  • the semantic interpretation data 283 associates the semantic interpretation sentence 607 with the fact that the numerical value representing the autonomic nerve after driving on the previous day is "slightly high”. Further, the semantic interpretation data 283 associates the semantic interpretation sentence 609 with the risk risk prediction level of "a little higher risk”. Similarly, in the example of report 620 of FIG. 17, the semantic interpretation data 283 in the selected biological model 280 associates the semantic interpretation sentence 627 with the "high" number representing the autonomic nerves before driving today.
  • the semantic interpretation data 283 is selected based on the subjective evaluation data and the biological data of the target user together with the explanatory model 281 and the prediction model 282. Therefore, it is possible to present an appropriate semantic interpretation sentence for the measurement result of the biological data of the target user and the risk risk prediction level.
  • the semantic interpretation data 283 is associated with the explanatory model 281 and the prediction model 282. Even if the explanatory model 281 is omitted, the semantic interpretation data 283 is associated with the prediction model 282.
  • the prediction result presentation program 224 refers to the semantic interpretation data 283 associated with the selected prediction model 282 to generate a semantic interpretation statement.
  • the present invention is not limited to the above-described embodiment, and includes various modifications.
  • the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the described configurations.
  • 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.
  • each of the above configurations, functions, processing units, etc. may be realized by hardware, for example, by designing a part or all of them with an integrated circuit. Further, each of the above configurations, functions, and the like 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 or an SD card.
  • SSD Solid State Drive
  • control lines and information lines indicate what is considered necessary for explanation, and not all control lines and information lines are necessarily shown on the product. In practice, it can be considered that almost all configurations are interconnected.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

La présente invention concerne un système comprenant un ou plusieurs dispositifs de mémoire, et un ou plusieurs processeurs qui fonctionnent conformément à un programme stocké sur un ou plusieurs dispositifs de mémoire. Le ou les processeurs acquièrent un modèle de prédiction qui correspond aux données biométriques passées de l'individu, et qui est un modèle de prédiction qui prédit le nombre d'opérations de conduite dangereuses sur la base de données biométriques. Le ou les processeurs utilisent le modèle de prédiction acquis pour déterminer le niveau prédit de risque de conduite dangereuse sur la base de données biométriques mesurées avant que le véhicule ne soit conduit par l'individu.
PCT/JP2020/006268 2019-05-09 2020-02-18 Système de prédiction des risques de conduite dangereuse WO2020225956A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019088870A JP7334057B2 (ja) 2019-05-09 2019-05-09 運転の危険リスクを予測するシステム
JP2019-088870 2019-05-09

Publications (1)

Publication Number Publication Date
WO2020225956A1 true WO2020225956A1 (fr) 2020-11-12

Family

ID=73044730

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/006268 WO2020225956A1 (fr) 2019-05-09 2020-02-18 Système de prédiction des risques de conduite dangereuse

Country Status (2)

Country Link
JP (1) JP7334057B2 (fr)
WO (1) WO2020225956A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022259881A1 (fr) * 2021-06-08 2022-12-15 株式会社日立物流 Système d'aide à la gestion opérationnelle, et procédé d'aide à la gestion opérationnelle

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016018314A (ja) * 2014-07-07 2016-02-01 エヌ・ティ・ティ・コミュニケーションズ株式会社 運転者危機管理装置、運転者危機管理方法、および運転者危機管理プログラム
JP2018147021A (ja) * 2017-03-01 2018-09-20 富士通株式会社 危険状態予測装置、危険状態予測方法、及び危険状態予測プログラム、並びに危険状態予測用データ取得装置、危険状態予測用データ取得方法、及び危険状態予測用データ取得プログラム
JP2018180983A (ja) * 2017-04-14 2018-11-15 ソニー株式会社 情報処理装置、情報処理方法、及び、プログラム

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5828111B2 (ja) 2011-07-28 2015-12-02 パナソニックＩｐマネジメント株式会社 心理状態評価装置、心理状態評価システムおよびプログラム
NZ630770A (en) 2013-10-09 2016-03-31 Resmed Sensor Technologies Ltd Fatigue monitoring and management system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016018314A (ja) * 2014-07-07 2016-02-01 エヌ・ティ・ティ・コミュニケーションズ株式会社 運転者危機管理装置、運転者危機管理方法、および運転者危機管理プログラム
JP2018147021A (ja) * 2017-03-01 2018-09-20 富士通株式会社 危険状態予測装置、危険状態予測方法、及び危険状態予測プログラム、並びに危険状態予測用データ取得装置、危険状態予測用データ取得方法、及び危険状態予測用データ取得プログラム
JP2018180983A (ja) * 2017-04-14 2018-11-15 ソニー株式会社 情報処理装置、情報処理方法、及び、プログラム

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022259881A1 (fr) * 2021-06-08 2022-12-15 株式会社日立物流 Système d'aide à la gestion opérationnelle, et procédé d'aide à la gestion opérationnelle

Also Published As

Publication number Publication date
JP7334057B2 (ja) 2023-08-28
JP2020184248A (ja) 2020-11-12

Similar Documents

Publication Publication Date Title
US11821741B2 (en) Stress map and vehicle navigation route
US9676395B2 (en) Incapacitated driving detection and prevention
Ba et al. Crash prediction with behavioral and physiological features for advanced vehicle collision avoidance system
US8738523B1 (en) Systems and methods to identify and profile a vehicle operator
Gold et al. Taking over control from highly automated vehicles
US20230013561A1 (en) Systems and methods for reducing carbon emissions by recommending one or more alternative forms of transportation
Yu et al. Measurement and prediction of driver trust in automated vehicle technologies: An application of hand position transition probability matrix
Scherer et al. How the driver wants to be driven-modelling driving styles in highly automated driving
US20230211780A1 (en) Operation support method, operation support system, and operation support server
CN104887253A (zh) 驾驶员疲劳检测
Wang et al. Modeling and recognition of driving fatigue state based on RR intervals of ECG data
JP7437241B2 (ja) 運行支援方法、運行支援システム及び運行支援サーバ
Ma et al. Dynamic Bayesian network approach to evaluate vehicle driving risk based on on-road experiment driving data
WO2020225956A1 (fr) Système de prédiction des risques de conduite dangereuse
JP2016091056A (ja) ドライバ状態診断装置
CN110816542A (zh) 提供驾驶员帮助的方法
Zhang et al. On the importance of working memory in the driving safety field: a systematic review
Strle et al. Physiological Signals as Predictors of Cognitive Load Induced by the Type of Automotive Head-Up Display
Madison et al. The design and integration of a comprehensive measurement system to assess trust in automated driving
CN104054059B (zh) 信息处理装置和信息处理方法
Murphey et al. Personalized driver workload estimation in real-world driving
WO2022259881A1 (fr) Système d'aide à la gestion opérationnelle, et procédé d'aide à la gestion opérationnelle
Swain et al. Left turns by older drivers with vision impairment: A naturalistic driving study
Lee et al. Predicting Driver's mental workload using physiological signals: A functional data analysis approach
Chen et al. Exploring the associations of demographics and scale measures with cognitive driving behavior among older drivers in China

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20802327

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20802327

Country of ref document: EP

Kind code of ref document: A1