KR102654055B1 - Driver evaluation device and method for improving traffic safety - Google Patents

Abstract

The present invention relates to a driver evaluation device and method for improving traffic safety, the device comprising: a data collection unit that collects driver data for each item for driver evaluation; a risk level determination unit for each item that determines the risk level for each item using the driver data for each item; a deduction point calculation unit that calculates a driver deduction score by applying the risk for each item and customized weights; and a driver evaluation unit that calculates a driver evaluation score as a result of applying the driver deduction score to the maximum score of the driver evaluation.

Description

Driver evaluation device and method for improving traffic safety {DRIVER EVALUATION DEVICE AND METHOD FOR IMPROVING TRAFFIC SAFETY}

The present invention relates to driver evaluation technology, and more specifically, to obtain data on the driver's driving behavior, comprehensively evaluate the driving pattern, and notify the driver to improve driving behavior and improve traffic safety that can contribute to traffic safety. It relates to a driver evaluation device and method for.

Due to the advancement of vehicle technology, various information can be provided to the driver during the driving process. For example, a navigation system installed in a vehicle can visualize and provide various additional information such as driving route, real-time traffic information, weather information, and nearby facility information. In addition, the navigation can also provide risk information such as accident risk areas or accident-prone areas along the driving route.

While such accident-related information is easily provided in the current system, personalized information such as the probability of an accident based on the driver's driving tendency may still be difficult to access. In other words, given that the driving patterns and tendencies of each driver are very different, the risk factors that may occur while driving may be different for each individual. As a result, the generalized accident probability is expected to be different from the actual accident probability of each individual driver. It is expected.

In addition, not only the driver's individual tendencies, but also various environmental factors, such as weather and conditions inside/outside the vehicle, can affect each individual's accident probability, so generalized accident probability information alone is not enough during driving. Sufficient information about caution factors may not be provided. Therefore, it may be necessary to develop a method for evaluating drivers by considering their individual history and a system that can manage this in an integrated manner.

Korean Patent Publication No. 10-2022-0111235 (2022.08.09)

One embodiment of the present invention provides a driver evaluation device and method for improving traffic safety that can improve driving behavior and contribute to traffic safety by acquiring data on the driver's driving behavior, comprehensively evaluating the driving pattern, and notifying the driver. We would like to provide

Among embodiments, a driver evaluation device for improving traffic safety includes a data collection unit that collects driver data for each item for driver evaluation; a risk level determination unit for each item that determines the risk level for each item using the driver data for each item; a deduction point calculation unit that calculates a driver deduction score by applying the risk for each item and customized weights; and a driver evaluation unit that calculates a driver evaluation score as a result of applying the driver deduction score to the maximum score of the driver evaluation.

The data collection unit may collect at least one of weather information, law information, accident information, and vehicle information as driver data for each item.

The risk level determination unit for each item may determine the first risk level related to weather type, the second risk level related to violation of laws, the third risk level related to driver accident history, and the fourth risk level related to vehicle type and vehicle year as the risk level for each item. .

The deduction score calculation unit may customize the risk for each event and then calculate the customized weight using the changed risk for each event.

The deduction score calculation unit may calculate the driver deduction score based on the risk related to a near miss among the customized risks.

The deduction score calculation unit may calculate the driver deduction score using the following equation.

[Equation]

(From here, is the driver's deduction score, is the customized weight, , , and is the risk level for each item.)

The deduction point calculation unit may dynamically determine the maximum deduction range for each item of the driver's deduction points according to the count distribution for each item of the driver data.

Among embodiments, a driver evaluation method for improving traffic safety includes collecting driver data for each item for driver evaluation through a data collection unit; Determining the risk level for each item using the driver data for each item through a risk level determination unit for each item; Calculating a driver deduction score by applying the risk of each item and customized weight through a deduction score calculation unit; and calculating a driver evaluation score as a result of applying the driver deduction score to the maximum score of the driver evaluation through the driver evaluation unit.

The disclosed technology can have the following effects. However, since it does not mean that a specific embodiment must include all of the following effects or only the following effects, the scope of rights of the disclosed technology should not be understood as being limited thereby.

The driver evaluation device and method for improving traffic safety according to an embodiment of the present invention can improve driving behavior and contribute to traffic safety by acquiring data on the driver's driving behavior, comprehensively evaluating the driving pattern, and notifying the driver. there is.

1 is a diagram explaining a driver evaluation system according to the present invention.
FIG. 2 is a diagram explaining the system configuration of the driver evaluation device of FIG. 1.
FIG. 3 is a diagram explaining the functional configuration of the driver evaluation device of FIG. 1.
Figure 4 is a flowchart explaining an embodiment of a driver evaluation process for improving traffic safety according to the present invention.
Figure 5 is a diagram illustrating an embodiment of a process for generating customized weights according to the present invention.
Figure 6 is a diagram illustrating an embodiment of the driver evaluation process according to the present invention.

Since the description of the present invention is only an example for structural or functional explanation, the scope of the present invention should not be construed as limited by the examples described in the text. In other words, since the embodiments can be modified in various ways and can have various forms, the scope of rights of the present invention should be understood to include equivalents that can realize the technical idea. In addition, the purpose or effect presented in the present invention does not mean that a specific embodiment must include all or only such effects, so the scope of the present invention should not be understood as limited thereby.

Meanwhile, the meaning of the terms described in this application should be understood as follows.

Terms such as “first” and “second” are used to distinguish one component from another component, and the scope of rights should not be limited by these terms. For example, a first component may be named a second component, and similarly, the second component may also be named a first component.

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected to the other component, but that other components may exist in between. On the other hand, when a component is referred to as being “directly connected” to another component, it should be understood that there are no other components in between. Meanwhile, other expressions that describe the relationship between components, such as "between" and "immediately between" or "neighboring" and "directly neighboring" should be interpreted similarly.

Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as “comprise” or “have” refer to implemented features, numbers, steps, operations, components, parts, or them. It is intended to indicate the existence of a combination, and should be understood as not precluding the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

For each step, identification codes (e.g., a, b, c, etc.) are used for convenience of explanation. The identification codes do not explain the order of each step, and each step clearly follows a specific order in context. Unless specified, events may occur differently from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the opposite order.

The present invention can be implemented as computer-readable code on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. . Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. Additionally, the computer-readable recording medium can be distributed across computer systems connected to a network, so that computer-readable code can be stored and executed in a distributed manner.

All terms used herein, unless otherwise defined, have the same meaning as commonly understood by a person of ordinary skill in the field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as consistent with the meaning they have in the context of the related technology, and cannot be interpreted as having an ideal or excessively formal meaning unless clearly defined in the present application.

1 is a diagram explaining a driver evaluation system according to the present invention.

Referring to FIG. 1 , the driver evaluation system 100 may include a vehicle 110, a driver evaluation device 130, and a database 150. Here, for convenience of explanation, the vehicle 110, the driver evaluation device 130, and the database 150 are described separately as independent devices, but they are not necessarily limited thereto and can be used to evaluate each other according to various embodiments for driver evaluation. Of course, at least two other devices can be integrated and implemented as one device.

The vehicle 110 may correspond to a means of transportation that transports passengers or cargo using power produced by an engine, and may correspond to a car as a representative example. The vehicle 110 may include not only a car, but also a motorcycle, a bicycle, etc., and may include personal mobility such as a Segway, an electric kickboard, an electric wheelchair, etc., but is not necessarily limited thereto, and may include a motorized vehicle. It can include various means of transportation that can be moved using . Additionally, the vehicle 110 may be connected to the driver evaluation device 130 through a wired or wireless network, and may transmit and receive data through the network.

In one embodiment, the vehicle 110 may be implemented to include at least one edge device that monitors the driver's driving behavior and collects driver data regarding driving behavior. Here, the edge device may correspond to various computing devices installed in the vehicle 110, and may be used to monitor the status of parts or to interact with various sensors to monitor the status and behavior of the driver and passengers. It can be implemented.

For example, edge devices can be linked to cameras that capture surrounding images, acceleration sensors related to vehicle movement, brake sensors, acceleration sensors, vibration sensors, GPS (Global Positioning System) sensors, flow sensors, and steering angle sensors, etc. It can be linked to heart rate sensors, temperature/humidity sensors, gas sensors, and air quality sensors related to the vehicle environment. Through this, the edge device can collect event detection data before and after the event occurs, and can collect various observation data about the driver's driving behavior while driving.

The driver evaluation device 130 may correspond to a computing device or server implemented to perform a driver evaluation method for improving traffic safety according to the present invention. The driver evaluation device 130 can be connected to the vehicle 110 through a wireless network such as Bluetooth, WiFi, LTE, etc. to transmit and receive data, and can be implemented to connect and operate with a plurality of vehicles 110 at the same time. .

Additionally, the driver evaluation device 130 may be implemented to operate in conjunction with a separate external system (not shown in FIG. 1) for driver evaluation according to the present invention. For example, the external system may include an environmental information (or traffic information) management system for collecting driving environment information, a navigation system (or GPS system) for tracking the vehicle's driving path, etc.

The database 150 may correspond to a storage device that stores various information required during the operation of the driver evaluation device 130. For example, the database 150 may store accident data collected from each vehicle 110 and driver data regarding driving behavior, or may store information for calculating scores regarding driver evaluation, but is not necessarily limited thereto. The driver evaluation device 130 may store information collected or processed in various forms during the process of performing the driver evaluation method according to the present invention.

Meanwhile, in FIG. 1, the database 150 is shown as a device independent of the driver evaluation device 130, but is not necessarily limited thereto, and is a logical storage device of the driver evaluation device 130. Of course, it can be included and implemented.

FIG. 2 is a diagram explaining the system configuration of the driver evaluation device of FIG. 1.

Referring to FIG. 2 , the driver evaluation device 130 may include a processor 210, a memory 230, a user input/output unit 250, and a network input/output unit 270.

The processor 210 can execute a procedure for performing a driver evaluation method for improving traffic safety according to an embodiment of the present invention, and can manage the memory 230 that is read or written in this process, and the memory ( 230), the synchronization time between volatile memory and non-volatile memory can be scheduled. The processor 210 can control the overall operation of the driver evaluation device 130 and is electrically connected to the memory 230, the user input/output unit 250, and the network input/output unit 270 to control the data flow between them. You can. The processor 210 may be implemented as a Central Processing Unit (CPU), Graphics Processing Unit (GPU), or Neural Processing Unit (NPU) of the driver evaluation device 130.

The memory 230 may be implemented as a non-volatile memory such as a solid state disk (SSD) or a hard disk drive (HDD) and may include an auxiliary memory used to store all data required for the driver evaluation device 130, It may include a main memory implemented as volatile memory such as RAM (Random Access Memory). Additionally, the memory 230 can store a set of instructions for executing the driver evaluation method for improving traffic safety according to the present invention by being executed by the electrically connected processor 210.

The user input/output unit 250 includes an environment for receiving user input and an environment for outputting specific information to the user, and includes an input adapter such as, for example, a touch pad, a touch screen, an on-screen keyboard, or a pointing device. It may include an output device including a device and an adapter such as a monitor or touch screen. In one embodiment, the user input/output unit 250 may correspond to a computing device connected through a remote connection, in which case the driver evaluation device 130 may operate as an independent server.

The network input/output unit 270 provides a communication environment for connection with other devices through a network, for example, Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), and Value Area Network (VAN). It may include an adapter for communication such as Added Network). Additionally, the network input/output unit 270 may be implemented to provide short-range communication functions such as WiFi and Bluetooth or wireless communication functions of 4G or higher for wireless transmission of data.

FIG. 3 is a diagram explaining the functional configuration of the driver evaluation device of FIG. 1.

Referring to FIG. 3, the driver evaluation device 130 can perform a driver evaluation method for improving traffic safety according to the present invention. For this purpose, the driver evaluation device 130 includes a data collection unit 310, a risk determination unit 330 for each item, a deduction score calculation unit 350, a driver evaluation unit 370, and a control unit (not shown in FIG. 3). may include.

At this time, the embodiment of the present invention does not need to include all of the above configurations at the same time, and depending on each embodiment, some of the above configurations are omitted or some or all of the above configurations are selectively included. It could be. Hereinafter, the operation of each component will be described in detail.

The data collection unit 310 may collect driver data for each item for driver evaluation. Here, the driver data for each item is data used for driver evaluation and may correspond to data related to the driver being evaluated. For data collection, the data collection unit 310 can operate in conjunction with the vehicle 110, receive driver data collected in real time from the vehicle 110, and then classify and store it according to each item. That is, driver data may be classified into one of various items for driver evaluation and stored in the database 150.

In one embodiment, the data collection unit 310 may collect at least one of weather information, law information, accident information, and vehicle information as driver data for each item. Weather information may include accident information according to weather type. For example, weather information may include fatality rate (i.e., number of deaths per 100 traffic accidents) information according to weather type. Additionally, the legal information may include information about near miss situations resulting from violation of the law. For example, near-miss situations may include situations inside the vehicle, such as drowsy driving, and situations outside the vehicle, such as lane departure or failure to secure a safe distance. Accident information may include information about the driver's accident history, and vehicle information may include information about the vehicle model and vehicle year.

The risk level determination unit 330 for each item may determine the risk level for each item using driver data for each item. The risk level determination unit 330 for each item can calculate the risk level based on driver data for each of the various evaluation items reflected in the driver evaluation. In other words, the degree of risk may correspond to the probability of risk due to an accident occurring while the driver is driving. The risk for each item calculated by the risk for each item determination unit 330 may be stored in the database 150 and used in the driver evaluation process at a later stage.

In one embodiment, the risk level determination unit 330 for each item determines a first risk level related to weather type, a second risk level related to violation of laws, a third risk level related to driver accident history, and a fourth risk level related to vehicle type and vehicle year. It can be determined as the risk level for each item. More specifically, the first risk related to the weather type can be calculated based on the fatality rate (i.e., number of deaths per 100 traffic accidents) according to the weather type. For example, the fatality rate may be determined as 8.9 for fog, 3.9 for cloudy, 3 for rain, 2.5 for snow, and 2.4 for clear, etc. based on previously collected accident data. That is, the risk level determination unit 330 for each item may calculate the first risk level by considering weather information at the time at a location corresponding to a specific latitude and longitude. To this end, the risk determination unit 330 for each item may express the weather type by combining each count of each event. For example, ‘2 signal violations’ can be expressed as ‘1 signal violation: fog’ + ‘1 signal violation: cloudy’.

Additionally, the risk level determination unit 330 for each item may express the first risk level as the sum of weather type counts for each event. That is, the first risk can be expressed as Equation 1 below.

[Equation 1]

From here, is the first risk for each event, is the weather type count for each event. At this time, is an event that occurs while driving, such as a traffic signal violation or lane departure.

Additionally, the second risk related to violation of laws can be calculated based on events that occur while driving, that is, situations inside the vehicle and situations outside the vehicle. For example, situations inside the vehicle may include the driver not looking ahead, the driver using a cell phone, drowsy driving, etc., and situations outside the vehicle may include lane departure, failure to secure a safe distance, etc. In other words, the risk level determination unit 330 for each item can calculate the second risk level by considering violation of laws and conditions inside/outside the vehicle. To this end, the risk determination unit 330 for each item can calculate the near-miss score for each event by calculating the ratio of vehicle accident counts due to violation of laws to the near-miss count for each event, expressed as the following equation 2: It can be.

[Equation 2]

From here, is the near miss score for each event, represents the degree to which each violation of law is associated with actual traffic accidents, is the near miss count for each event. At this time, is the number (count) of near miss events involved in violation of the relevant regulations. is a weight distribution coefficient that can be set differently depending on the internal/external category and the related information between the corresponding law violation and near-miss event. Therefore, the total near miss score of events corresponding to each law violation, expressed as shown in Equation 3 below, may be equal to the degree of correlation between the corresponding law violation item and the traffic accident.

[Equation 3]

Additionally, the third risk level regarding the driver's accident history can be calculated based on the driver's actual past accident history. That is, the risk level determination unit 330 for each item can calculate the third risk level by reflecting the severity, number, and time of the accident. To this end, the risk level determination unit 330 for each item may express the third risk level as the product between the individual risk level for each driver and the reduction rate over time. That is, the third risk can be expressed as Equation 4 below.

[Equation 4]

From here, is the individual risk level for each driver, is the rate of decrease over time.

Additionally, the fourth risk level regarding the driver's accident history can be calculated based on the vehicle type and vehicle year. Here, vehicle types may include passenger cars, buses, and trucks. That is, the risk level determination unit 330 for each item can define correlation coefficients related to vehicle type and vehicle year, and calculate the fourth risk level by applying each correlation coefficient to the accident rate for each vehicle type and the vehicle production year. That is, the fourth risk level can be expressed as Equation 5 below.

[Equation 5]

From here, is the fourth risk, and are the accident count and total accident count by vehicle type, respectively, is the vehicle production year, and are correlation coefficients related to vehicle type and vehicle year, respectively. also, and Can be expressed as the following equations 6 and 7.

[Equation 6]

[Equation 7]

From here, ego, am.

The deduction score calculation unit 350 can calculate the driver deduction score by applying the risk of each item and customized weight. Here, the customized weight is a weight applied to the risk for each event reflected in the calculation process of driver deduction points and may correspond to a weight that can be changed by the evaluator's selection. For example, if an evaluator wishes to perform a more rigorous evaluation of a driver's specific events, the weight may be adjusted for each event. In one embodiment, the deduction score calculation unit 350 may customize the risk for each event and then calculate the customized weight using the changed risk for each event. The customizing weight setting process is explained in more detail in FIG. 5.

In one embodiment, the deduction score calculation unit 350 may calculate the driver deduction score based on the risk of a near miss among the risks for each item. Here, the risk of near misses can correspond to the risk of violation of laws and conditions inside/outside the vehicle. In other words, the risk of near misses can indicate the possibility that violations of laws and regulations that occur due to various events while driving may lead to an accident. The deduction score calculation unit 350 may calculate the driver deduction score by reflecting the near-miss score and near-miss accident count related to the degree of risk.

In one embodiment, the deduction point calculation unit 350 may calculate the driver deduction score using Equation 8 below.

[Equation 8]

From here, is the driver's deduction score, is the customized weight, , , and is the risk level for each item.

In one embodiment, the deduction point calculation unit 350 may dynamically determine the maximum deduction range for each item of the driver's deduction points according to the count distribution for each item of driver data. That is, the maximum deduction value for each item of each event occurrence count can be dynamically determined according to the event count distribution of the actual acquired data, and can be expressed as Equation 9 below.

[Equation 9]

The driver evaluation unit 370 may calculate the driver evaluation score as a result of applying the driver deduction score to the maximum driver evaluation score. That is, the driver evaluation unit 390 can calculate an evaluation score for each driver by subtracting the driver's deduction points based on a predefined target score (i.e., maximum score) of the driver evaluation. Additionally, the driver evaluation score can be expressed as Equation 10 below.

[Equation 10]

Here, Driver Score is the driver evaluation score, A is the driver, is the target score (maximum score).

In one embodiment, the driver evaluation unit 370 may calculate driver evaluation scores and then classify them according to predefined evaluation grades. The evaluation grade may correspond to a classification defined by dividing the evaluation score into grades within a certain range. Additionally, the driver evaluation unit 370 can provide driver evaluation scores and evaluation grades to the user or driver, and for this purpose, it can operate in conjunction with the user terminal.

The control unit (not shown in FIG. 3) controls the overall operation of the driver evaluation device 130 and includes a data collection unit 310, a risk level determination unit 330 for each item, a deduction score calculation unit 350, and a driver evaluation unit. Control flow or data flow between 370 can be managed.

Figure 4 is a flowchart explaining an embodiment of a driver evaluation process for improving traffic safety according to the present invention.

Referring to FIG. 4, the driver evaluation device 130 may collect driver data for each item for driver evaluation through the data collection unit 310 (step S410). The driver evaluation device 130 may determine the risk for each item using the driver data for each item through the risk for each item determination unit 330 (step S430). The driver evaluation device 130 may calculate the driver deduction score by applying the customized weight for each item to the risk of each item through the deduction score calculation unit 350 (step S450). The driver evaluation device 130 may calculate the driver evaluation score as a result of applying the driver deduction score to the maximum driver evaluation score through the driver evaluation unit 370 (step S470).

Figure 5 is a diagram illustrating an embodiment of a process for generating customized weights according to the present invention.

Referring to FIG. 5, the driver evaluation device 130 can adjust the individual risk of each event 1 to n when applying strict standards to a driver's specific event while driving, and customize each event based on the adjusted risk. The weight value can be calculated. For example, the driver evaluation device 130 may calculate a customized weight by applying a Softmax function to the adjusted risk. In this case, the customized weight can be expressed as Equation 11 below: there is.

[Equation 11]

Figure 6 is a diagram illustrating an embodiment of the driver evaluation process according to the present invention.

Referring to FIG. 6 , the driver evaluation device 130 may collect various accident detection data and driver behavior detection data collected from each vehicle 110. To this end, the driver evaluation device 130 may operate in conjunction with the vehicle 110 and may also directly interact with various sensors installed in the vehicle 110. The driver evaluation device 130 can collect driver data necessary for driver evaluation by classifying the collected data. At this time, collection of driver data may be performed through the data collection unit 310 of the driver evaluation device 130. Driver data collected by the data collection unit 310 may be used for subsequent operations.

The driver evaluation device 130 can determine the risk level for each item using driver data classified by item, and the corresponding operation can be performed through the risk level determination unit 330 for each item. In addition, the driver evaluation device 130 can calculate the driver deduction score by applying the risk of each item and customized weight through the deduction score calculation unit 350.

In one embodiment, the deduction score calculation unit 350 may be linked with a separate and independent weight module 610 for customizing the weight used in the driver deduction score calculation process. That is, the weight module 610 can receive setting information adjusted by an evaluator (or manager), and use the adjusted setting information to calculate customized weights used in driver evaluation. The deduction score calculation unit 350 may calculate the driver deduction score using the customized weight received from the weight module 610 and the risk for each item.

The driver evaluation device 130 can finally calculate the driver evaluation score through the driver evaluation unit 370 and provide various notifications and services for the driver's safe driving based on the driver evaluation score. Additionally, the driver evaluation device 130 can collect evaluation information for each driver and generate information about the driving behavior of drivers within a specific organization.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that you can do it.

100: Driver evaluation system
110: vehicle 130: driver evaluation device
150: database
210: Processor 230: Memory
250: user input/output unit 270: network input/output unit
310: data collection unit 330: risk determination unit for each item
350: Penalty score calculation unit 370: Driver evaluation unit

Claims (8)

A data collection unit that collects driver data for each item for driver evaluation;
a risk level determination unit for each item that determines the risk level for each item using the driver data for each item;
The driver's deduction score is calculated by applying the risk for each item and the customized weight, and among the risks for each item to which the customized weight is applied, the Near Miss Score and Near Miss related to the risk of near miss are calculated. a deduction score calculation unit that reflects the accident count and calculates the driver deduction score using the following equation; and
Including a driver evaluation unit that calculates a driver evaluation score as a result of applying the driver deduction score to the maximum score of the driver evaluation,
The driver evaluation device for improving traffic safety, wherein the deduction score calculation unit dynamically determines the maximum deduction range for each item of the driver deduction score according to the count distribution for each item of the driver data.
[Equation]

(From here, is the driver's deduction score, is the customized weight, , , and is the risk for each item.)
The method of claim 1, wherein the data collection unit
A driver evaluation device for improving traffic safety, characterized in that it collects at least one of weather information, law information, accident information, and vehicle information as driver data for each item.
The method of claim 1, wherein the risk determination unit for each item
Improving traffic safety, characterized by determining the first risk level related to weather type, the second risk level related to violation of laws, the third risk level related to driver accident history, and the fourth risk level related to vehicle type and vehicle year as the risk level for each of the above items. Driver evaluation device for.
The method of claim 1, wherein the deduction score calculation unit
A driver evaluation device for improving traffic safety, characterized by customizing the risk for each event and then calculating the customized weight using the changed risk for each event.
delete delete delete In the driver evaluation method performed in the driver evaluation device,
Collecting driver data for each item for driver evaluation through a data collection unit;
Determining the risk level for each item using the driver data for each item through a risk level determination unit for each item;
Through the deduction score calculation unit, the driver deduction score is calculated by applying the risk for each item and the customized weight, and the near miss score associated with the risk for near miss among the risks for each item to which the customized weight is applied ( Calculating the driver deduction score through the following equation by reflecting the Near Miss Score) and the near miss count; and
Comprising a step of calculating a driver evaluation score as a result of applying the driver deduction score to the maximum score of the driver evaluation through the driver evaluation unit,
The step of calculating the driver deduction points includes dynamically determining the maximum deduction range for each item of the driver deduction points according to the count distribution for each item of the driver data. .
[Equation]

(From here, is the driver's deduction score, is the customized weight, , , and is the risk for each item.)