CN114973450A - Driving evaluation device and driving evaluation method - Google Patents

Abstract

The present invention provides a driving evaluation device and a driving evaluation method, so that a user can quickly determine the driving that requires guidance. The driving evaluation device performs a driving evaluation including a determination of an instruction subject whether or not the event time series determined from the vehicle driving situation data is suitable for the instruction subject based on the determination data, and outputs the driving evaluation information indicating the result of the driving evaluation. Event time series for judgment. The vehicle driving condition data is data representing a plurality of events related to the vehicle and the respective occurrence times of the plurality of events.

Description

Driving evaluation device and driving evaluation method

technical field

The present invention generally relates to an apparatus and method for performing a driving evaluation of a driver.

Background technique

In a transportation company that transports vehicles (typically, automobiles) such as trucks, buses, and taxis, an operation manager is generally selected for each business office, and the operation manager instructs each driver on safe driving. For the purpose of improving the efficiency of safe driving education, a service is proposed that evaluates the driving of each driver based on data acquired by a driving recorder and the like, and provides the evaluation results to the operation manager.

As a driving evaluation device for an automobile, there is a technique described in Japanese Patent Application Laid-Open No. 2010-072573 (Patent Document 1). In this publication, it is stated: "The quality of the driving operation of the driver is evaluated, and when the evaluation means makes a good evaluation, the display means performs a good evaluation at the location of the driving scene of the evaluation target on the map. The display of the meaning of the evaluation, when the evaluation means makes a bad evaluation, the display of the meaning of the bad evaluation is made at the location of the driving scene of the evaluation object on the map" and "for example, when the driver is driving on a straight road, the When the emergency braking action is performed, a sudden deceleration (0.3G in the forward direction) is detected by the accelerator opening sensor 42, the brake depression sensor 43, the front, rear, left, right, and vertical sensors 44, etc.".

When the operation manager confirms the evaluation result of the driver by using the technique of Patent Document 1, all the drives evaluated as poor are collectively provided. For example, all driving operations in the case where a gravitational force greater than 0.3 G is applied in the forward direction is provided as a sharply decelerated driving. In a case where there are "driver's distraction", "inadequate vehicle time", and "sudden break-in" as major causes of emergency braking, the operation manager preferably treats the driver as "driver's distraction" or The emergency braking due to "insufficient vehicle time" is used as a guidance object (for example, the guidance priority is increased compared to the emergency braking due to "sudden entry"). However, in the technique described in Patent Document 1, all emergency braking is not displayed in a mixed manner, so the operation manager cannot determine which emergency braking is to be guided (for example, which emergency braking instruction priority high).

Such a problem also exists for other types of operators in which the driving of the vehicle occurs in the business and the evaluation of the driving of the driver is performed.

Patent Document 1: Japanese Patent Laid-Open No. 2010-072573

SUMMARY OF THE INVENTION

In order to solve the above-mentioned problems, one of the representative driving evaluation apparatuses of the present invention performs a driving evaluation including a determination of a guidance object based on a comparison of the driving conditions of the vehicle based on the determination data, and outputs driving evaluation information indicating the result of the driving evaluation. It is determined whether the event time series determined by the data is suitable for the event time series of the guidance object. The vehicle driving condition data is data representing a plurality of events related to the vehicle and the respective occurrence times of the plurality of events.

According to the present invention, a user (eg, a manager) can quickly identify a driving requiring guidance (eg, a driving with a high priority). Problems, structures, and effects other than those described above will be clarified by the description of the following embodiments.

Description of drawings

FIG. 1 is a diagram showing a configuration example of the entire system including the driving evaluation device according to the first embodiment of the present invention.

FIG. 2 is a diagram showing an example of a hardware configuration of the drive recorder.

FIG. 3 is a diagram showing an example of a hardware configuration of the driving evaluation device.

FIG. 4 is a diagram showing an example of a hardware configuration of an operation management terminal.

FIG. 5 is a diagram showing an example of the functional configuration of the driving evaluation device.

FIG. 6 is a diagram showing an example of a table indicating acceleration and position in the vehicle driving condition table.

FIG. 7 is a diagram showing an example of a table showing video and audio in the vehicle driving condition table.

FIG. 8 is a flowchart showing an example of driving evaluation processing.

FIG. 9 is a diagram showing an example of a travel event table.

FIG. 10 is a diagram showing an example of a peripheral event table.

FIG. 11 is a diagram showing an example of an action event table.

FIG. 12 is a diagram showing an example of a time-series event table.

FIG. 13 is a diagram showing an example of the determination table in the first embodiment.

FIG. 14 is a diagram showing an example of a driving evaluation screen.

FIG. 15 is a diagram showing an example of a judgment table according to the second embodiment.

Description of reference numerals

105...driving evaluation device, 510...vehicle driving condition table, 504...determination table, 520...driving evaluation unit, 506...evaluation output unit.

Detailed ways

In the following description, the "interface device" may be one or more communication interface devices. The one or more communication interface devices may be more than one communication interface device of the same type, or may be two or more communication interface devices of different types.

In addition, in the following description, "memory" refers to one or more storage devices, and typically, it may be a main storage device. At least one storage device in the memory may be a volatile storage device or a non-volatile storage device.

In addition, in the following description, a "persistent storage device" may be one or more persistent storage devices as an example of one or more storage devices. The persistent storage device can typically be a non-volatile storage device (such as an auxiliary storage device), and specifically, can be, for example, an HDD (Hard Disk Drive, hard disk drive), SSD (Solid State Drive, solid-state drive), NVME (Non- Volatile Memory Express, non-volatile memory host controller interface specification) drive or SCM (Storage Class Memory, storage class memory).

In addition, in the following description, the "storage device" may be at least a permanent storage device among a memory and a permanent storage device.

In addition, in the following description, a "processor" may be more than one processor device. Typically, the at least one processor device may be a microprocessor device such as a CPU (Central Processing Unit, central processing unit), but may also be another type of processor device such as a GPU (Graphics Processing Unit, graphics processor). At least one processor device may be single-core or multi-core. At least one processor device may also be a processor core. The at least one processor device may also be a circuit that uses a hardware description language that performs part or all of the processing as a collection of gate arrays (for example, an FPGA (Field-Programmable Gate Array, Field Programmable Gate Array), a CPLD (Complex Programmable Logic Device) , complex programmable logic device) or ASIC (Application Specific Integrated Circuit, application-specific integrated circuit)) such a generalized processor device.

In addition, in the following description, the function may be described by the expression of "yyy part", but the function may be realized by executing one or more computer programs by a processor, or may be realized by one or more hardware circuits (for example, FPGA or ASIC). ), or a combination of them. When the function is realized by the processor executing the program, the function may be at least a part of the processor because the determined processing is performed while using the storage device and/or the interface device as appropriate. The processing described with the function as the subject may be performed by a processor or a device having the processor. Programs can be installed from program sources. The program source may be, for example, a program distribution computer or a computer-readable recording medium (eg, a non-transitory recording medium). The description of each function is an example, and a plurality of functions may be aggregated into one function, or one function may be divided into a plurality of functions.

In addition, in the following description, the data (information) that is output with respect to the input may be described by the expression "xxx table", but the data (information) may be a table of any structure, or may be generated in a relative manner. Learning models represented by neural networks, genetic algorithms, and random forests based on input and output. Therefore, "xxx table" can be called "xxx data" ("xxx information"). In addition, in the following description, one table may be divided into two or more tables, and all or a part of two or more tables may be one table.

In addition, in the following description, when describing without distinguishing the same elements, the common reference numerals among the reference numerals may be used. mark.

Hereinafter, an Example is demonstrated using drawing.

[Example 1]

In the present embodiment, an operation manager (an example of a user) conducts safe driving instructions for a driver in a business office.

FIG. 1 is a diagram showing a configuration example of the entire system including the driving evaluation device according to the first embodiment of the present invention.

The driving evaluation system 100 is a system for evaluating the driving of the driver of the vehicle 101 (for example, the drivers of the vehicles 101A and 101B). The driving evaluation system 100 includes: a driving recorder 102 mounted on the vehicle 101 ; a driving evaluation device 105 which evaluates driving based on data acquired by the driving recorder 102 ; Provision of driving evaluation results. The operation manager 106 determines the driving to be guided based on the operation evaluation result displayed on the operation management terminal 107 . The driving evaluation device 105 according to the first embodiment is a server device. The driving evaluation device may be a computer system (one or more computers) such as a server device, or a logic device (eg, a device as a virtual computer, container, or cloud computing service) implemented on a computer system (eg, a cloud platform) . In addition, the "display of information" of the driving evaluation device may be that information is displayed on a display device included in the driving evaluation device, or the driving evaluation device may transmit information for display to an external information processing terminal (in the latter case). down, the information is displayed by the information processing terminal).

The vehicle 101 is assumed to be an automobile such as a truck, a bus, or a taxi, but is not particularly limited. Also, the number of vehicles is not limited to two.

The dash cam 102 is connected to the Internet 108 (one example of a communication network) via wireless communication. The driving evaluation device 105 and the operation management terminal 107 are also connected to the Internet 108 . The driving recorder 102 and the operation management terminal 107 can communicate with each other with the driving evaluation device 105 via the Internet 108 . The Internet 108 may also be a private network. The operation management terminal 107 may be an example of a user terminal that is an information processing terminal of a user, for example, a client device using the driving evaluation device 105 as a server device, or may be a personal computer (for example, a laptop or tablet personal computer) or smartphone.

FIG. 2 is a diagram showing an example of the hardware configuration of the drive recorder 102 .

The driving recorder 102 includes a front camera 201, an acceleration sensor 202, a GPS receiver 203, an in-vehicle microphone 204, an in-vehicle camera 205, a ROM 207 (eg, a flash ROM), a RAM 208, a communication interface 209, and a CPU 206 connected to them. Elements 201 to 205 may each be an example of a sensor. That is, the dash cam 102 may include one or more sensors. At least one sensor may be installed in a place other than the dash cam 102 .

The front camera 201 is installed in the vehicle 101 (for example, in the upper center of the windshield), captures an image in front of the vehicle 101 , and outputs image information indicating the captured image to the CPU 206 . The acceleration sensor 202 detects accelerations in the three-axis directions of the vehicle 101 , and outputs acceleration information indicating the detected accelerations to the CPU 206 . The GPS receiver 203 outputs, to the CPU 206 , the position information indicating the position of the vehicle 101 detected based on the signals received from the GPS satellites. The in-vehicle microphone 204 records the sound inside the vehicle 101 and outputs the recorded sound information to the CPU 206 . The in-vehicle camera 205 is installed in the vehicle 101 (eg, in the upper center of the windshield), captures a video of the driver's seat inside the vehicle 101 , and outputs video information representing the captured video to the CPU 206 .

In addition, the CPU 206 reads out a program stored in at least one of the ROM 207 and the RAM 208 , operates based on the read program, and controls the function of the drive recorder 102 . The ROM 207 stores a boot program executed by the CPU 206 when the drive recorder 102 is activated, a program depending on the hardware of the drive recorder 102 , various data, and the like. The communication interface 304 transmits the data generated by the CPU 206 to the driving evaluation device 105 via the Internet 108 .

FIG. 3 is a diagram showing an example of the hardware configuration of the driving evaluation device 105 .

The driving evaluation device 105 includes a ROM 302 , a RAM 303 , a communication interface 304 , an HDD 305 , and a CPU 301 connected to these. ROM 302 and RAM 303 are examples of memories. HDD 305 is an example of a permanent storage device. The communication interface 304 is an example of an interface device. The CPU 301 is an example of a processor.

The CPU 301 reads a program stored in at least one of the ROM 302 and the RAM 303 , operates based on the read program, and controls the function of the driving evaluation device 105 . The ROM 302 stores a boot program executed by the CPU 301 when the drive evaluation device 105 is activated, a program depending on the hardware of the drive evaluation device 105 , various data, and the like. The RAM 303 stores programs executed by the CPU 301 , data used by the CPU 301 , and the like. In addition, each function of the driving evaluation device 105 is constructed by executing a predetermined program read by the CPU 301 . In addition, the communication interface 304 receives data from the drive recorder 102 or the operation management terminal 107 via the Internet 108 and transmits it to the CPU 301 , and transmits the data generated by the CPU 301 to the drive recorder 102 or the operation management terminal 107 via the Internet 108 . Data from the bicycle recorder 102 can be stored in the HDD 305 .

FIG. 4 is a diagram showing an example of the hardware configuration of the operation management terminal 107 .

The operation management terminal 107 includes a ROM 402 , a RAM 403 , a communication interface 404 , an input device 405 , a display device 406 , and a CPU 401 connected to these.

The CPU 401 reads out a program stored in at least one of the ROM 402 and the RAM 403 , operates based on the read program, and controls the function of the operation management terminal 107 . The ROM 402 stores a boot program executed by the CPU 401 when the operation management terminal 107 starts up, programs depending on the hardware of the operation management terminal 107 , and the like. The RAM 403 stores programs executed by the CPU 401 , data used by the CPU 401 , and the like. In addition, each function of the operation management terminal 107 is constructed by executing a predetermined program read by the CPU 401 . In addition, the communication interface 404 receives data from the driving evaluation device 105 via the Internet 108 and transmits it to the CPU 401 , and transmits the data generated by the CPU 401 to the driving evaluation device 105 via the Internet 108 .

FIG. 5 is a diagram showing an example of the functional configuration of the driving evaluation device 105 .

In the driving evaluation device 105 , the CPU 401 executes a program to realize the functions of the driving evaluation unit 520 and the evaluation output unit 506 . The driving evaluation unit 520 includes a reception unit 501 , an event detection unit 502 , a sequence detection unit 503 , and an instruction target determination unit 505 . In addition, the event detection unit 502 includes a driving event detection unit 507 , a surrounding event detection unit 508 , and an action event detection unit 509 .

The receiving unit 501 receives information such as the image information of the front of the vehicle, the acceleration information of the vehicle, the position information of the vehicle, the sound information inside the vehicle, and the image information of the driver's seat of the vehicle acquired by the driving recorder 102, and converts the received information ( The ID of the vehicle 101 on which the drive recorder 102 is mounted) is stored in the vehicle driving condition table 510 .

The vehicle driving condition table 510 is a table in which information received by the receiving unit 501 from the drive recorder 102 is stored. The vehicle driving condition table 510 is stored in a storage device (eg, HDD 305 ) inside (or outside) the drive evaluation device 105 . In this embodiment, the vehicle driving condition table 510 exists for each vehicle 101 .

The event detection unit 502 detects an event related to the vehicle 101 based on the vehicle driving condition table 510 , and transmits the detected event and the occurrence time of the event to the sequence detection unit 503 .

The sequence detection unit 503 detects the sequence of events based on the respective occurrence times of the plurality of events detected by the event detection unit 502 , and transmits the occurrence time of each event and the detected sequence of events to the instruction target determination unit 505 .

The determination table 504 is a table showing the order of occurrence of events and the priority of instruction to be instructed for safe driving education. The determination table 504 is stored in a storage device (eg, HDD 305 ) inside (or outside) the driving evaluation device 105 .

The guidance object determination unit 505 checks the event occurrence order and event occurrence time from the order detection section 503 with the event occurrence order and guidance priority shown in the judgment table 504, and determines the event occurrence order and guidance priority to be the guidance object and transmits the determined event occurrence order and its instruction priority to the evaluation output unit 506 .

The evaluation output unit 506 transmits, to the operation management terminal 107 , the driving evaluation information indicating the driving evaluation result including the event occurrence time and the instruction priority from the instruction target determination unit 505 . The driving evaluation result indicated by the driving evaluation information transmitted to the operation management terminal 107 is displayed on the display device 406 of the operation management terminal 107 .

In Embodiment 1, information such as images and acceleration is acquired by the dash cam 102 and sent to the driving evaluation device 105 , but at least part of the information may be sent to the driver from a device other than the dash cam 102 (for example, the sensor itself) Evaluation device 105 .

In addition, in the present embodiment, the “event” related to the vehicle 101 is defined as being capable of being detected based on information acquired by a plurality of sensors included in the vehicle 101 and being directly or indirectly caused by driving by the driver. event.

In addition, in the present embodiment, the vehicle driving condition table 510 indirectly represents the event, but may directly represent the event. "Indirectly representing an event" means that an event (eg, emergency braking, distraction) can be detected through analysis of the vehicle driving conditions table 510 . "Directly representing an event" means that the vehicle driving condition table 510 has a value representing the event itself (eg, "emergency braking", "distraction").

The driving event detection unit 507 detects a driving event (an event related to the driving of the vehicle 101 ) and its generation time based on the vehicle driving situation table 510 . As the driving event, for example, any one of sudden braking, temporary stop, sudden turning, left-right turning, and reverse movement of the vehicle can be employed. In addition, a "driving event" may also be referred to as an "operation event" as an event generated by a driving operation (for example, operation of a steering wheel, an accelerator, a brake, etc.) that affects the driving of the vehicle.

The surrounding event detection unit 508 detects surrounding events (events related to the surrounding of the vehicle 101 ) and their generation times based on the vehicle driving condition table 510 . As the surrounding event, for example, any one of the inter-vehicle distance between the host vehicle and the preceding vehicle, the inter-vehicle time, and the change in TTC (Time-To-Collision, time-to-collision) can be used.

The action event detection unit 509 detects an action event (an event related to the action of the driver of the vehicle 101 ) and its generation time based on the vehicle driving situation table 510 . As the action event, for example, any one of driver's distraction and left-right confirmation can be employed. In addition, among the actions of the driver, the driving operation affects the driving event, and actions other than the driving operation may affect the action event.

Next, processing executed by the driving evaluation system 100 illustrated in FIG. 1 will be described.

The drive recorder 102 illustrated in FIG. 2 is supplied with power while the ignition switch of the vehicle 101 is turned on, and its function is always performed. When the ignition switch is turned on, the CPU 206 analyzes the image information of the front of the vehicle 101 received from the front camera 201 , the acceleration information of the vehicle 101 received from the acceleration sensor 202 , and the information of the vehicle 101 received from the GPS receiver 203 as necessary. The position information, the sound information inside the vehicle 101 received from the in-vehicle microphone 204, and the video information of the driver's seat of the vehicle 101 received from the in-vehicle camera 205 are analyzed by AD conversion for digital electric signals, etc., and are combined with each information. The generation times of are stored in the ROM 207 in association with each other. The CPU 206 also transmits the vehicle driving condition table (a table storing information from sensors such as the front camera 201 ) stored in the ROM 207 to the driving evaluation device 105 via the communication interface 209 at a timing when wireless communication is possible.

The processing of the driving evaluation device 105 is roughly classified into data storage processing and driving evaluation processing.

First, data storage processing executed in the driving evaluation device 105 will be described. The driving evaluation device 105 is always supplied with power, and waits for the reception of data from the cycle recorder 102 . The data storage process is a process executed at the timing when the vehicle driving condition table is received from the drive recorder 102 . When receiving the vehicle driving condition table from the dash cam 102 , the receiving unit 501 receives the image information in front of the vehicle, the acceleration information of the vehicle, the position information of the vehicle, the sound information inside the vehicle, and the driver's seat of the vehicle acquired by the dash cam 102 . The vehicle driving condition table composed of the video information and the generation time of each information is stored as the vehicle driving condition table 510 together with the information for identifying the vehicle 101 on which the driving recorder is mounted. The vehicle driving condition table 510 may be a table composed of the tables shown in FIGS. 6 and 7 .

FIG. 6 is a diagram showing an example of a table indicating acceleration and position in the vehicle driving situation table 510 . The table illustrated in FIG. 6 has records for each time, and each record has a vehicle field 601 , an occurrence time field 602 , a front-rear direction acceleration field 603 , a left-right direction acceleration field 604 , an up-down direction acceleration field 605 , a latitude field 606 , and a longitude field 607 . The vehicle field 601 is a field in which the ID (for example, a character string identifying the vehicle 101 ) of the vehicle 101 mounted with the tachograph 102 that transmits the vehicle driving condition table is described. The occurrence time field 602 is a field in which the time is described. The front-rear direction acceleration field 603 is a field in which acceleration data in the front-rear direction of the vehicle acquired by the acceleration sensor 202 of the drive recorder 102 at that time is described. The left-right direction acceleration field 604 is a field which describes the acceleration data of the vehicle's left-right direction acquired by the acceleration sensor 202 of the drive recorder 102 at this time. The vertical acceleration field 605 is a field in which acceleration data in the vertical direction of the vehicle acquired by the acceleration sensor 202 of the drive recorder 102 at the time is described.

FIG. 7 is a diagram showing an example of a table representing video and audio in the vehicle driving status table 510 . The table illustrated in FIG. 7 has records for each time period, and each record has a vehicle field 701 , a shooting start time field 702 , a shooting end time field 703 , a front video file name field 704 , and an in-vehicle video and audio file name field 705 . The vehicle field 701 is a field for describing the ID of the vehicle 101 on which the drive recorder 102 that transmitted the vehicle driving condition table is mounted. The shooting start time field 702 is a field for describing the time at which the front camera 201 , the in-vehicle microphone 204 , and the in-vehicle camera 205 in the dash cam 102 started shooting (the start time of the time period). The shooting end time field 703 is a field describing the time at which the front camera 201 , the in-vehicle microphone 204 , and the in-vehicle camera 205 in the dash cam 102 finished shooting (the end time of the time period). The front video file name field 704 is a field in which the file name of the video captured by the front camera 201 at the time (from the capture start time to the capture end time) is described. The in-vehicle video and audio file name field 705 describes the name of the file recorded by the in-vehicle microphone 204 and the in-vehicle camera 205 by combining the audio and video captured at the time (from the shooting start time to the shooting end time). field.

Next, the driving evaluation process executed by the driving evaluation device 105 illustrated in FIG. 5 will be described. For example, batch processing is performed at a determined time each day, such as 0:00 AM. Alternatively, the process may be executed in accordance with an instruction from the operation management terminal 107 .

FIG. 8 is a flowchart showing an example of driving evaluation processing executed by the driving evaluation device 105 .

When the driving evaluation process starts, the event detection unit 502 selects one vehicle (step 801), and extracts the vehicle driving condition table 510 generated for the vehicle 101 on the previous day using the vehicle ID of the selected vehicle 101 as a key (step 801). 802).

The driving event detection unit 507 uses the vehicle driving condition table 510 extracted in step 802 to detect events related to the driving of the vehicle (step 803 ). FIG. 9 is a diagram showing an example of a driving event table showing the driving events detected in step 803 . The driving event table has records for each detected driving event, and each record has a vehicle field 901 , an occurrence time field 902 , and an event field 903 . The vehicle field 901 is a field in which a character string of the vehicle field 601 of the vehicle driving condition table 510 in which the driving event is detected is described. The occurrence time field 902 is a field in which the occurrence time of the occurrence time field 602 of the vehicle behavior table 510 in which the driving event is detected is described. The event field 903 is a field in which the detected travel event is described. The traveling event detection unit 507 refers to, for example, the longitudinal acceleration field 603 of the table illustrated in FIG. 6 , extracts the timing at which the longitudinal acceleration changes from less than -0.4G to less than -0.4G, and detects an "emergency braking" event. For example, the record 609 illustrated in FIG. 6 is a record corresponding to the timing when a predetermined change in acceleration in the front-rear direction (for example, from less than -0.4G to -0.4G or less) occurs, so the travel event detection unit 507 records 609 The contents of the vehicle field 601 and the occurrence time field 602 are stored in the record 904 of the driving event table illustrated in FIG. 9 . In addition, the driving event detection unit 507 refers to, for example, the latitude field 606 and the longitude field 607 of the table illustrated in FIG. "Temporary suspension" is stated in

The surrounding event detection unit 508 uses the vehicle driving condition table 510 extracted in step 802 to detect events related to the surrounding of the vehicle (step 804 in FIG. 8 ). FIG. 10 shows an example of a surrounding event table showing surrounding events detected in step 804 . The surrounding event table has records for each detected surrounding event, and each record has a vehicle field 1001 , an occurrence time field 1002 , and an event field 1003 . The vehicle field 1001 is a field in which a character string of the vehicle field 701 of the vehicle driving situation table 510 in which the surrounding event is detected is described. The occurrence time field 1002 is a field in which the occurrence time of the vehicle driving situation table 510 in which the surrounding event is detected is described. The event field 1003 is a field in which the detected surrounding event is described. The surrounding event detection unit 508 refers to, for example, the occurrence time field 602 , the latitude field 606 and the longitude field 607 in the table illustrated in FIG. 6 of each vehicle 101 , and the forward image file name field in the table illustrated in FIG. 7 of the vehicle 101 . The forward video file described in 704 is used to calculate the inter-vehicle time between the vehicle 101 and the vehicle in front of the vehicle 101 . Specifically, for example, first, the surrounding event detection unit 508 first determines the location (latitude and longitude indicated by the latitude field 606 and the longitude field 607 ) and the time (the occurrence time field 602 ) described in a certain record in the table illustrated in FIG. 6 . The speed of the vehicle 101 is calculated by the difference (distance) between the indicated time) and the position and time described in the previous record of the record. Next, the surrounding event detection unit 508 reads the front video file described in the front video file name field 704 of the table exemplified in FIG. 7 , and calculates the relative distance to the front-rear direction of the front vehicle with reference to the image data of each frame of the video. For example, the surrounding event detection unit 508 detects the feature point coordinates of the vehicle ahead on the image using existing image recognition technology, and calculates the relative distance to the vehicle ahead based on the camera parameters of the front camera 201 measured in advance. The surrounding event detection unit 508 synchronizes the obtained speed of the vehicle 101 with the occurrence time of the relative distance to the preceding vehicle, and calculates the inter-vehicle time (relative distance to the preceding vehicle/speed of the vehicle 101 ). The peripheral event detection unit 508 sets the timing at which a predetermined change in the inter-vehicle time occurs (for example, the inter-vehicle time is changed from 3 seconds or more to less than 3 seconds) as the timing at which the peripheral event "Vehicle distance is short" occurs, and is recorded in record 1004 Record "the workshop distance is short". In addition, for example, the surrounding event detection unit 508 refers to the generation time field 602 , the latitude field 606 and the longitude field 607 of the table illustrated in FIG. 6 , and compares it with the map data including the latitude and longitude of the road, for example, to remove the vehicle 101 from the road. The timing at which the predetermined distance (for example, 1 meter) is separated is the timing at which the peripheral event "entry from the road to the outside of the road" occurs, and "entry from the road to the outside of the road" is described in the record 1005 .

The action event detection unit 509 uses the vehicle driving condition table 510 extracted in step 802 to detect an event related to the action of the driver (step 805 ). FIG. 11 is a diagram showing an example of an action event table showing action events detected in step 805 . The action event table has records for each detected action event, and each record has a vehicle field 1101 , an occurrence time field 1102 , and an event field 1103 . The vehicle field 1101 is a field in which a character string of the vehicle field 701 of the vehicle driving condition table 510 in which the action event is detected is described. The occurrence time field 1102 is a field in which the occurrence time of the vehicle driving situation table 510 in which the action event is detected is described. The event field 1103 is a field in which the detected action event is described. The action event detection unit 509 refers to, for example, the occurrence time field 602 , the latitude field 606 and the longitude field 607 of the table illustrated in FIG. 6 , and the in-vehicle video recorded in the in-vehicle video and audio file name fields 705 of the table illustrated in FIG. 7 . and audio files, and the driver's actions such as distraction and left-right confirmation of the driver of the vehicle 101 are detected. For example, first, the action event detection unit 509 refers to the latitude field 606 and the longitude field 607 of the table exemplified in FIG. 6 , and determines a time period in which the latitude and longitude have changed as “travelling”. Next, the action event detection unit 509 refers to the images of each frame of the in-vehicle video and audio files described in the in-vehicle video and audio file name field 705 of the table illustrated in FIG. Gaze direction (front, right or left). The action event detection unit 509 extracts, as the timing of the action event "distraction" in the "running" time period, the timing at which the image in which the driver's gaze is directed to the right or left direction continues for a predetermined time (for example, 1 second) or longer. , and record "distraction" in record 1104. In addition, for example, the action event detection unit 509 extracts the timing at which the driver's line of sight alternately repeats the right and left directions as the timing of the action event "left-right check", and records "left-right check" in the record 1105 . Furthermore, for example, the action event detection unit 509 refers to the audio data of the in-vehicle video and audio files described in the in-vehicle video and audio file name field 705 of the table exemplified in FIG. Sound, detects "sound "good" as an action event.

The sequence detection unit 503 detects the sequence of the travel event detected by the travel event detection unit 507, the surrounding event detected by the surrounding event detection unit 508, and the action event detected by the action event detection unit 509, and arranges these events in time series (step 806). ). FIG. 12 is a diagram showing an example of a time-series event table in which events are arranged in time-series.

The guidance target determination unit 505 determines that the guidance matching time series (the occurrence order of events corresponding to the guidance target) and the guidance priority, and the occurrence order and event occurrence time of the events detected by the order detection section 503 are determined as indicated by the judgment table 504. The event time sequence of the guidance object and the guidance priority (step 807 ).

FIG. 13 is a diagram showing an example of the determination table 504 .

The decision table 504 indicates that the guidance conforms to the time series. A guidance conformance time series is a time series of events that are defined as conforming to a guidance object. The judgment table 504 has records, for example, for each guideline conformity time series. A record represents a guideline conforming to a time series. Each record has a reference event field 1301, a prior event A field 1311A (occurrence timing field 1302A, event field 1303A, and presence/absence field 1304A), prior event B field 1311B (occurrence timing field 1302B, event field 1303B, and presence/absence field 1304B), Prior event C field 1311C (occurrence timing field 1302C, event field 1303C, and presence/absence field 1304C) and guidance priority field 1305. The reference event field 1301 is a field in which the type of the reference event (the reference event) of the event time series to be guided is described. In each of the fields 1311A to 1311C of the prior event (an event defined as an event occurring before the reference event), regarding the prior event corresponding to the field 1311, it is described how long before the reference event the prior event occurred, the The type of the prior event, and whether the prior event occurred before the baseline event. The guidance priority field 1305 is a field describing the guidance priority when the guidance occurs in a time series. According to the example shown in FIG. 13 , as the events before the reference event, there are three events, the prior events A to C, but the number of events before the reference event may be more or less than three. In addition, in this embodiment, since the "reference event" is an event that is the final result of a series of events, a prior event is defined in order to determine the event time series, but the "reference event" may be the beginning of a series of events. A causal event can also be a cause of an event, or an event that is the result of other events. That is, with regard to the reference event, there may be a subsequent event in place of the prior event or in addition to the prior event.

For example, the guidance target determination unit 505 first reads the guidance matching time series one by one from the judgment table 504 illustrated in FIG. 13 , and determines whether the guidance matching time series is suitable for the event time series described in the time series event table. For example, according to the record 1312 in the judgment table 504, the reference event is "emergency braking", the prior event A "short vehicle time" occurs within 30 seconds before the occurrence time of the reference event "emergency braking", and the reference event "emergency braking" The pre-event B "distraction" occurred within 30 seconds before the occurrence time of the event "emergency braking". When the records 1312 are compared with the time-series event table illustrated in FIG. 12 , the records 1201 corresponding to the reference event “emergency braking” are identified, and the records 1202 and 1203 matches the elements other than the reference event in record 1312. Then, the event time series indicated by the records 1201 to 1203 are determined as the event time series of the guidance object of the guidance priority "10". Similarly, from the record 1313 in the determination table 504, the event time series represented by the records 1204 to 1205 in the time series event table illustrated in FIG. 12 is determined as the event time series of the guidance object of the guidance priority "7" . Based on the record 1314 in the determination table 504, the event time series indicated by the record 1206 in the time series event table illustrated in FIG. 12 is determined as the event time series of the guidance object of the guidance priority "5". Based on the record 1315 in the determination table 504, the event time series represented by each of the records 1207 to 1209 in the time series event table illustrated in FIG. 12 is determined as the event time series of the guidance object of guidance priority "4".

If there is a vehicle 101 from which the vehicle driving condition table 510 generated the previous day has not been extracted (step 808 : YES), the process returns to step 802 . If there is no vehicle 101 from which the vehicle driving condition table 510 generated the day before has been extracted (step 808 : NO), the process proceeds to step 809 .

The evaluation output unit 506 transmits the driving evaluation information indicating the driving evaluation result based on the time series of the events determined as the instruction object by the instruction object determination unit 505 to the operation management terminal 107 (step 809 ). The driving evaluation information includes, for each event time series of the guidance object, at least one event (for example, a reference event to be described later) in the event time series, the occurrence time of the event, and the guidance compliance time suitable for the event time series. Sequence guidance priority information.

The driving evaluation result indicated by the driving evaluation information transmitted from the driving evaluation device 105 is displayed on the operation management terminal 107 illustrated in FIG. 4 .

FIG. 14 is a diagram showing an example of a driving evaluation result screen displayed on the display device 406 of the operation management terminal 107 .

The driving evaluation result screen includes an evaluation result 1401 in accordance with the event time series of the guidance object (the event time series suitable for the guidance conforming time series illustrated in FIG. 13 ). The evaluation result 1401 includes at least one event in the event time series of the guidance object (for example, an event suitable for a reference event), the occurrence time of the event, and the guidance priority of the guidance conforming time series suitable for the event time series. Specifically, for example, the evaluation result 1401A is the result of determining the event time series represented by the records 1201 to 1203 illustrated in FIG. 12 as the guidance objects. Similarly, the evaluation result 1401B is the result of determining the event time series represented by the records 1204 to 1205 illustrated in FIG. 12 as the object of instruction, and the evaluation result 1401C is the result of determining the event time series represented by the record 1206 illustrated in FIG. 12 as the object of instruction As a result, the evaluation result 1401D is the result of determining the event time series represented by the records 1207 to 1209 illustrated in FIG. 12 as the guidance object. As exemplified in FIG. 14 , since the guidance of emergency braking, which is caused by driver distraction and lack of time between vehicles, is displayed with a high priority, the operation manager can efficiently determine the emergency system with a high need for guidance. verb: move. Furthermore, it is possible to suppress the possibility of emergency braking, which is highly necessary for skipping guidance.

[Example 2]

Example 2 of the present invention will be described. At this time, the differences from the first embodiment will be mainly described, and the descriptions of the common points with the first embodiment will be omitted or simplified.

FIG. 15 is a diagram showing an example of the determination table 504 in the second embodiment.

The decision table 504 represents the template time series. A template time series is a time series of events defined as a template. The judgment table 504' has records for each template time series, for example. A record represents a template time series. Each record has a reference event field 1501, a prior event A field 1511A (occurrence timing field 1502A and event field 1503A), prior event B field 1511B (occurrence timing field 1502B and event field 1503B), and prior event C field 1511C (occurrence timing field 1502C and event field 1503C).

In the second embodiment, the guidance target determination in step 807 (see FIG. 8 ) is performed, for example, as follows. That is, the guidance target determination unit 505 determines whether any one of the events represented by the time-series event table illustrated in FIG. 12 is suitable for the reference event in any one of the template time-series. The guidance target determination unit 505 determines, for the template time series including the reference event, whether or not an event that occurs before an event appropriate to the reference event is appropriate for an element other than the reference event in the template time series. When the event time series represented by the time series event table illustrated in FIG. 12 is not suitable for any template time series, the event time series is determined as the event time series to be guided.

In addition, this invention is not limited to the above-mentioned embodiment, Various modification examples are included.

In addition, the above-described embodiment is an example described in detail in order to explain the present invention in an easy-to-understand manner, and is not limited to having all the structures described. In addition, a part of the structure of a certain example can be replaced with the structure of another example, and the structure of another example can also be added to the structure of a certain example. In addition, with respect to a part of the structure of each Example, addition, deletion, and replacement of other structures can be performed. In addition, each of the above-described structures, functions, processing units, processing units, and the like may be designed by, for example, an integrated circuit, and a part or all of them may be realized by hardware. In addition, each of the above-described structures, functions, and the like may be realized by software by interpreting and executing a program for realizing each function by a processor. Information such as programs, tables, and files that realize each function can be placed in a storage device, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, and a DVD.

In addition, the above description can be summarized as follows, for example. The following summary may include explanations not included in the above-mentioned explanations (for example, supplementary explanations or explanations of modified examples).

The driving evaluation device 105 includes a driving evaluation unit 520 and an evaluation output unit 506 . The driving evaluation unit 520 performs a driving evaluation including an instruction target determination that determines the vehicle driving condition data (eg, the vehicle driving condition table 510 ) based on the determination data (eg, the determination table 504 or 504 ′). Whether the event time series is suitable for instructing the object's event time series. The evaluation output unit 506 outputs driving evaluation information indicating the result of the driving evaluation by the driving evaluation unit 520 .

The vehicle driving condition data indicates a plurality of events related to the vehicle and the respective occurrence times of the plurality of events. As mentioned above, events are represented directly or indirectly. When the event is indirectly represented, as in the tables illustrated in FIGS. 6 and 7 , the vehicle driving situation data may include information representing the value detected by the sensor included in the vehicle 101 and the time of detection. When the event is directly represented, the vehicle driving situation data can represent the event and its occurrence time as in the tables illustrated in FIGS. 9 to 11 .

As described above, in the above-described embodiment, the time series of events is determined based on the vehicle driving condition data, and the determined event time series is determined as the event time series of the guidance object based on the determination data. In this way, even if there is an event that does not require guidance, whether or not it is a guidance object is determined based on the entire time series of events including the event. Therefore, it is possible to reduce the possibility that driving that does not require guidance is included in the driving evaluation result. Therefore, the user ( For example, an operation manager) can quickly determine the driving that requires instruction.

The data for determination is data representing at least one of a guidance matching time series (an event time series defined as matching the guidance object) and a template time series (an event time series defined as a template) and used for guidance object determination. That is, there may exist first judgment data (for example, the judgment table 504 ) in which the guidance matching time series is recorded and the template time series is not recorded, and the second judgment data (for example, the template time series is recorded and the guidance matching time series is not recorded) ( For example, the judgment table 504'), these judgment data may be one judgment data (that is, the guidance matching time series and the template time series may be mixed).

For example, when the driving evaluation unit 520 determines that the event time series determined based on the vehicle driving condition data is suitable for guiding the time series, the driving evaluation information output by the evaluation output unit 506 may include an instruction object indicating that the time series is suitable for guiding the time series. Information on event time series. In addition, for example, when the driving evaluation unit 520 determines that the event time series determined based on the vehicle driving condition data is not suitable for the template time series, the driving evaluation information output by the evaluation output unit 506 may include guidance indicating that it is not suitable for the template time series Information about the object's event time series.

Both guideline-compliant time series and template time series can contain events that serve as benchmarks, ie benchmark events. Baseline events can be either the cause or the effect of other events. That is, both the guidance conformance time series and the template time series include, in addition to the reference event, one or more events for which the reference event is a cause or a result. By defining the reference event in this way, it is possible to efficiently determine, as an event time series, the relationship between events existing among a plurality of events detected based on the vehicle driving condition data.

For example, the guidance conformance time series may include the presence or absence of the one or more events in addition to the reference event and one or more events for which the reference event is a cause and/or a result. Regarding the guidance conforming to the time series, the guidance object decision (eg, step 807 of FIG. 8 ) may include a first decision and a second decision. The first determination may be a determination as to whether the event detected based on the vehicle driving condition data is suitable for any one of the reference events in the time series. The second determination is made when the result of the first determination is true, and may be based on the vehicle driving condition data to detect the occurrence of the event before and/or after the detected event, and determine whether the reference event includes the reference event. Any one of the guides conforms to the determination of whether the elements other than the reference event in the time series are suitable for the detected event occurrence situation. When the result of the second determination is true, the event time series including the events suitable for the reference event (events where the result of the first determination is true) may be the event time series of the guidance object. The "event occurrence state" may be a time series of one or more events that have occurred, or may be a state in which no event has occurred.

In addition, for example, regarding the template time series, the guidance object decision may include a first decision and a second decision. The first determination may be a determination of whether the event detected according to the determined vehicle driving condition data is suitable for a reference event in any one template time series. The second determination is made when the result of the first determination is true, and may be based on the vehicle driving condition data to detect the occurrence of the event before and/or after the detected event, and determine whether the reference event includes the reference event. It is determined whether the elements other than the reference event in any one of the template time series are suitable for the detected event occurrence situation. When the result of the second determination is false, the event time series including the events suitable for the reference event (events where the result of the first determination is true) may be the event time series of the guidance object.

The plurality of events detected based on the vehicle driving condition data may include driving events and surrounding events and/or action events. The driving event may be an event related to the driving of the vehicle 101 . The surrounding event may be an event related to surrounding conditions of the vehicle 101 . The action event may be an event related to the action of the driver. In this way, in addition to driving events, surrounding events and/or action events can also be detected, and an event time series containing driving events and surrounding events and/or action events can be defined as a guide conformity time series and/or template time series. For example, it can be defined as a problematic driving event caused by a surrounding event caused by a certain action event of the driver. Therefore, it can be expected to determine an appropriate event time series as a guidance object with high accuracy.

Regarding the guidance compliance time series, the data for determination may include data indicating the guidance priority according to the guidance compliance time series. The driving evaluation information may include, for each event time series suitable for the guidance compliance time series, information indicating the guidance priority of the guidance compliance time series suitable for the event time series. Thereby, the user can judge which one of the plurality of event time series suitable for guiding the corresponding time series can be prioritized as the guidance object.

The driving evaluation unit 520 can select which of the above-mentioned first determination data (data representing the time series of the guidance) and second determination data (data representing the template time series) to be used, and use the selected one for determination. Data to guide object determination. For example, the driving evaluation unit 520 may provide a UI (eg, GUI) for accepting from the operation manager (an example of a user) the selection of which of the time series and the template time series the usage guidance matches, and based on the information input via the UI, the user may Which of the first determination data and the second determination data is to be selected. Alternatively, the driving evaluation unit 520 may determine which of the first determination data and the second determination data to select according to the period of the object of the driving evaluation. In this way, efficient driving evaluation can be expected. For example, it is possible to selectively perform a driving evaluation that is not a driving evaluation to be guided if it is neither suitable for the template time series nor suitable for the guidance conforming time series, and a driving evaluation that is not suitable for the template time series if it is not suitable for the template time series. Driving evaluation for the guidance object.

Claims (6)

1. A driving evaluation device for evaluating driving of a vehicle by a driver, characterized in that: The driving evaluation device includes: a driving evaluation section that performs a driving evaluation including an instruction object determination that determines whether the event time series determined from the vehicle driving situation data is suitable for the instruction object event time series based on the determination-use data; and an evaluation output unit that outputs driving evaluation information indicating a result of the driving evaluation, The vehicle driving condition data is data representing a plurality of events related to the vehicle and the respective occurrence times of the plurality of events. 2. The driving evaluation device according to claim 1, wherein: The data for determination is data indicating that the guidance conforms to time series, A guidance conformance time series is a time series of events defined as conformance to a guidance object, When the driving evaluation unit determines that the event time series determined based on the vehicle driving condition data is suitable for guiding the conforming time series, the driving evaluation information output by the evaluation output unit includes an indication indicating that the event time series is suitable for guiding conforming to the time series. Information that guides the object's event time series. 3. The driving evaluation device according to claim 1, wherein: The data for determination is data representing template time series, A template time series is a time series of events defined as a template, When the driving evaluation unit determines that the event time series determined based on the vehicle driving condition data is not suitable for the template time series, the driving evaluation information output by the evaluation output unit includes an information indicating that the event time series is not suitable for the template time series Information that guides the object's event time series. 4. The driving evaluation device according to claim 2, wherein: The guidance conforming time series is composed of a benchmark event, that is, a benchmark event, one or more events with the benchmark event as a cause and/or result, and the presence or absence of the one or more events, The guidance object determination includes the following contents: performing a first determination of whether the event detected based on the vehicle driving condition data is suitable for any one of the guideline-compliant reference events in the time series; In the case where the result of the first determination is true, determine the event occurrence conditions before and/or after the detected event based on the vehicle driving condition data, and carry out any one of the guidance compliance time series including the reference event. The second judgment of whether the elements other than the reference event are suitable for the detected occurrence of the event; When the result of the second determination is true, the event time series including the events suitable for the reference event is the event time series of the guidance object. 5. The driving evaluation device according to claim 3, wherein: The template time series is composed of a reference event, that is, a reference event, and one or more events that serve as a cause and/or a result of the reference event, The guidance object determination includes the following contents: performing a first determination of whether the event detected based on the vehicle driving condition data is suitable for a reference event in any one template time series; In the case that the result of the first determination is true, the event occurrence conditions before and/or after the detected event are detected based on the vehicle driving condition data, and an arbitrary template time series including the reference event is performed. The second determination of whether the elements other than the reference event are suitable for the detected occurrence of the event; When the result of the second determination is false, the event time series including the events suitable for the reference event is the event time series of the guidance object. 6. The driving evaluation device according to claim 1, wherein: As the data for determination, there are first data for determination indicating the time series of guidance conformity and second data for determination indicating the time series of templates, A guidance compliance time series is a time series of events defined as complying with the guidance object, A template time series is a time series of events defined as a template, The driving evaluation unit selects which of the first determination data and the second determination data to use, and performs the guidance object determination using the selected determination data, When the first determination data is selected and the driving evaluation unit determines that the event time series determined based on the vehicle driving condition data is suitable for the guidance conforming time series, the evaluation output unit outputs The driving evaluation information of includes information representing a time series of events suitable for instructing a guidance object that conforms to the time series, When the second determination data is selected, the evaluation output unit outputs the output when the driving evaluation unit determines that the event time series determined based on the vehicle driving condition data is not suitable for the template time series The driving evaluation information includes information representing the event time series of the guidance object that is not suitable for the template time series.

Images