A method, device, electronic equipment and system for evaluating dangerous driving behavior

By analyzing current and historical sensing data, using discriminant models to evaluate the level and comprehensive performance of dangerous driving behavior, the problem of partial evaluation results in the existing technology is solved, and a comprehensive assessment and targeted intervention of drivers' dangerous driving behavior is achieved. .

CN113298361BActive Publication Date: 2024-11-19SHENZHEN STREAMING VIDEO TECH
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202110490283.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-06
Publication Date
2024-11-19
Estimated Expiration
2041-05-06

AI Technical Summary

Technical Problem

The evaluation methods for dangerous driving behavior in the existing technology only rely on some evaluation indicators when or after the danger occurs, which is difficult to fully reflect the driver's danger perception and decision-making ability, resulting in one-sided evaluation results and it is difficult to effectively intervene at high-risk drivers. and training.

Method used

By obtaining the sensing data before and after the current alarm event, combining historical data, using discriminant models to analyze driving behavior levels, comprehensively assessing driving performance, including obtaining sensing data, calculating evaluation indicators, inputting discriminant function relationships to determine traffic conflict indicators, and Comprehensive driving performance is calculated based on the number of historical behaviors.

Benefits of technology

A more comprehensive evaluation of drivers' dangerous driving behavior is achieved, which can more accurately reflect the driver's risk perception and decision-making ability, and provide targeted intervention and training measures, which improves the reliability of evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113298361B_ABST
    Figure CN113298361B_ABST
Patent Text Reader

Abstract

The present application is applicable to the field of automobile safe driving research, and relates to a method, device, electronic equipment and system for evaluating dangerous driving behavior. The method includes: obtaining first sensor data before and after the current alarm event; obtaining the level of the current dangerous driving behavior according to the first sensor data; and determining the comprehensive driving performance according to the level of the current dangerous driving behavior and the historical dangerous driving behavior. The present application can comprehensively analyze the performance of the driver in the alarm event based on the comprehensive driving performance, and make a more comprehensive evaluation of the driver's dangerous driving behavior in the alarm event; and the first sensor data before and after the alarm event is easy to obtain, making the determined comprehensive driving performance more reliable.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of automobile safe driving research, and in particular, relates to a dangerous driving behavior evaluation method, device, electronic equipment and system. Background Art

[0002] Drivers have different abilities to perceive dangerous factors in the environment during driving, which will lead to different driving behaviors when dealing with dangerous scenarios. By analyzing the indicators representing these different driving behaviors, it is possible to judge the danger perception abilities of different drivers and make a reasonable evaluation of their dangerous driving behaviors.

[0003] Danger perception refers to the process by which drivers identify and respond to various explicit and hidden danger information that affects their driving safety. It includes the entire process of drivers responding to dangers, emphasizing the ability to identify dangers in the environment in advance and take certain evasive actions. Drivers will have different driving actions when they recognize dangers, and they will also have different driving actions when they avoid dangers. Their differences in a series of information perception, information decision-making, and operational responses constitute the differences in dangerous driving behaviors.

[0004] However, current evaluation methods for drivers' dangerous driving behaviors often focus on analyzing some evaluation indicators when or after a danger occurs. These only evaluate the driver's ability to respond to operations, ignoring the more important information perception and information decision-making indicators that better reflect driving ability, that is, to perceive danger in advance and take certain preventive actions before the danger occurs. This results in the results of dangerous driving behaviors obtained by relying solely on some evaluation indicators when or after the danger occurs being one-sided, making it difficult to truly reflect the driver's dangerous driving behavior, and thus making it difficult to provide targeted intervention and training for drivers with high risk levels. Summary of the invention

[0005] The embodiments of the present application provide a method, device, electronic device and system for evaluating dangerous driving behavior, which can solve the technical problem that the evaluation method of dangerous driving behavior in the prior art only relies on some evaluation indicators when or after the danger occurs to obtain dangerous driving behavior results that are biased and difficult to truly reflect the driver's dangerous driving behavior.

[0006] In a first aspect, an embodiment of the present application provides a method for evaluating dangerous driving behavior, comprising:

[0007] Acquire first sensor data before and after a current alarm event; the current alarm event is triggered by a current dangerous driving behavior;

[0008] Obtaining the level of the current dangerous driving behavior according to the first sensor data;

[0009] The comprehensive driving performance is determined based on the level of the current dangerous driving behavior and the historical dangerous driving behavior.

[0010] In an achievable manner of the first aspect, obtaining the level of the current dangerous driving behavior according to the first sensor data includes:

[0011] Obtaining a first evaluation index according to the first sensing data;

[0012] Inputting the first evaluation index into a discriminant model and outputting a first traffic conflict index;

[0013] The level of the current dangerous driving behavior is determined according to the first traffic conflict indicator.

[0014] The training process of the discriminant model includes:

[0015] Acquire multiple sets of second sensor data before and after historical alarm events;

[0016] Obtaining, according to each group of the second sensor data, a second evaluation index and a second traffic conflict index corresponding to each group of the second sensor data;

[0017] Determining a preset value range to which each group of second traffic conflict indicator data belongs;

[0018] Substitute multiple groups of the second traffic conflict indicators in the same preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the same preset numerical range into the discriminant function relationship formula to calculate the coefficient value of each coefficient in the multiple discriminant function relationship formulas.

[0019] Exemplarily, the step of substituting multiple groups of the second traffic conflict indicators in the same preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the same preset numerical range into a discriminant function relationship formula to calculate the coefficient value of each coefficient in the multiple discriminant function relationship formulas includes:

[0020] Substitute multiple groups of the second traffic conflict indicators in the first preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the first preset numerical range into the first discriminant function relational formula, and calculate the coefficient values ​​of each coefficient in the first discriminant function relational formula; wherein the first discriminant function relational formula is:

[0021] Y1=a1x1+b1x2+...+c1x n +d1

[0022] Wherein, Y1 represents the second traffic conflict index within the first preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the first preset value range, n represents the number of the second evaluation index data, a1, b1...c1 represent the coefficients of the first discriminant function relationship, and d1 represents the constant of the first discriminant function relationship;

[0023] Substitute multiple groups of the second traffic conflict indicators in the second preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the second preset numerical range into a second discriminant function relational expression, and calculate the coefficient value of each coefficient in the second discriminant function relational expression; wherein the second discriminant function relational expression is:

[0024] Y2=a2x1+b2x2+...+c2x n +d2

[0025] Wherein, Y2 represents the second traffic conflict index in the second preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the second preset value range, n represents the number of the second evaluation index data, a2, b2...c2 represent coefficients of the second discriminant function relationship, and d2 represents a constant of the second discriminant function relationship;

[0026] Substituting multiple groups of the second traffic conflict indicators in a third preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the third preset numerical range into a third discriminant function relational expression, the coefficient value of each coefficient in the third discriminant function relational expression is calculated; wherein the third discriminant function relational expression is:

[0027] Y3=a3x1+b3x2+...+c3x n +d3

[0028] Wherein, Y3 represents the second traffic conflict index in the third preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the third preset numerical range, n represents the number of the second evaluation index data, a3, b3...c3 represent the coefficients of the third discriminant function relationship, and d3 represents the constant of the third discriminant function relationship.

[0029] The step of inputting the first evaluation index into a discrimination model and outputting a first traffic conflict index comprises:

[0030] Inputting the first evaluation index into a plurality of the discriminant function relationship equations respectively, and outputting a plurality of the first traffic conflict indexes;

[0031] The minimum value among the plurality of first traffic conflict indicators is used as the optimal first traffic conflict indicator.

[0032] Exemplarily, the step of inputting the first evaluation index into a discriminant model and outputting a first traffic conflict index includes:

[0033] Input the first evaluation index into the three discriminant function relationship formulas respectively, and output three first traffic conflict indexes;

[0034] The minimum value among the three first traffic conflict indicators is used as the optimal first traffic conflict indicator.

[0035] Wherein, determining the level of the current dangerous driving behavior according to the first traffic conflict indicator includes:

[0036] According to the first preset corresponding relationship, the level of the current dangerous driving behavior corresponding to the optimal first traffic conflict index is determined.

[0037] Exemplarily, the first preset corresponding relationship includes a corresponding relationship between the preset value range and the preset level, and determining the level of the current dangerous driving behavior corresponding to the optimal first traffic conflict indicator according to the first preset corresponding relationship includes:

[0038] The preset value range to which the optimal first traffic conflict indicator belongs is determined, and the preset level corresponding to the preset value range is used as the level of the current dangerous driving behavior.

[0039] Wherein, obtaining the comprehensive driving performance according to the level of the current dangerous driving behavior and the historical dangerous driving behavior includes:

[0040] Determining a target value corresponding to the level of the current dangerous driving behavior;

[0041] Counting the number of historical dangerous driving behaviors;

[0042] The target value and the number of times are combined to calculate an evaluation value of the comprehensive driving performance.

[0043] Wherein, determining the target value corresponding to the level of the current dangerous driving behavior includes:

[0044] The target value corresponding to the level of the current dangerous driving behavior is determined according to a second preset corresponding relationship, wherein the second preset corresponding relationship includes a corresponding relationship between a preset level and a preset target value.

[0045] Exemplarily, determining the target value corresponding to the level of the current dangerous driving behavior according to the second preset corresponding relationship includes:

[0046] When the level of the current dangerous driving behavior is a first preset level, determining the target value of the current dangerous driving behavior to be a first value;

[0047] When the level of the current dangerous driving behavior is a second preset level, determining the target value of the current dangerous driving behavior to be a second value;

[0048] When the level of the current dangerous driving behavior is a third preset level, the target value of the current dangerous driving behavior is determined to be a third value.

[0049] The step of combining the target value and the number of times to calculate the evaluation value of the comprehensive driving performance includes:

[0050] Obtaining a first weight of a target value of the current dangerous driving behavior and a second weight of the number of times of the historical dangerous driving behavior;

[0051] An evaluation value of the comprehensive driving performance is obtained according to the target value, the number of times, the first weight and the second weight.

[0052] Exemplarily, obtaining the evaluation value of the comprehensive driving performance according to the target value, the number of times, the first weight, and the second weight includes:

[0053] Substituting the target value, the number of times, the first weight and the second weight into the evaluation value formula of the comprehensive driving performance, the evaluation value of the comprehensive driving performance is obtained; the evaluation value formula of the comprehensive driving performance is:

[0054] Comprehensive driving performance evaluation value = αY-βm-γn-...-ρl

[0055] Wherein, Y represents the target value, m, n, ..., l represent the number of historical dangerous driving behaviors respectively, α represents the first weight, β, γ, ... ρ represent the second weight.

[0056] In the second aspect, the present applicant provides an evaluation device for dangerous driving behavior, including:

[0057] An acquisition module, used to acquire first sensor data before and after a current alarm event; the current alarm event is triggered by a current dangerous driving behavior;

[0058] A processing module, configured to obtain the level of the current dangerous driving behavior according to the first sensing data;

[0059] The evaluation module is used to determine the comprehensive driving performance according to the level of the current dangerous driving behavior and the historical dangerous driving behavior.

[0060] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method for evaluating dangerous driving behavior as described in the first aspect when executing the computer program.

[0061] In a fourth aspect, an embodiment of the present application provides a dangerous driving behavior evaluation system, including an evaluation device for dangerous driving behavior as described in the second aspect or an electronic device as described in the third aspect, the evaluation system also includes a sensor and an alarm, the sensor is used to collect environmental data inside and outside the vehicle, and the alarm is used to sound an alarm when an event is triggered.

[0062] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0063] The present application obtains the first sensor data before and after the current alarm event; obtains the level of the current dangerous driving behavior based on the first sensor data; and determines the comprehensive driving performance based on the level of the current dangerous driving behavior and the historical dangerous driving behavior. The driver's performance in the alarm event can be comprehensively analyzed based on the comprehensive driving performance, and a more comprehensive evaluation of the driver's dangerous driving behavior in the alarm event can be made; and the first sensor data before and after the alarm event is easy to obtain, making the determined comprehensive driving performance more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0065] Figure 1 It is a structural schematic diagram of a dangerous driving behavior evaluation system provided in an embodiment of the present application;

[0066] Figure 2 is a flow chart of a method for training a discriminant model provided in an embodiment of the present application;

[0067] Figure 3 is a flowchart of the steps of a dangerous driving behavior evaluation method provided by an embodiment of the present application;

[0068] Figure 4is a flowchart of a method step for obtaining the level of current dangerous driving behavior according to first sensor data provided by an embodiment of the present application;

[0069] Figure 5 is a flowchart of steps for determining comprehensive driving performance provided by an embodiment of the present application;

[0070] Figure 6 An evaluation device for dangerous driving behavior is provided in one embodiment of the present application. DETAILED DESCRIPTION

[0071] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0072] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0073] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0074] References to "an embodiment of the present application" or "some embodiments" described in the specification of the present application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in other embodiments", "an embodiment of the present application", "other embodiments of the present application", etc. that appear in different places in the specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0075] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0076] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0077] Please refer to Figure 1 , Figure 1 1 is a schematic diagram of a dangerous driving behavior evaluation system provided in an embodiment of the present application, including a sensor 110, an alarm 120 and an electronic device 130. The sensor 110, the alarm 120 and the electronic device 130 are interconnected via a controller area network (CAN) bus.

[0078] The sensor 110 includes one or more of a camera, a radar, a laser, and an ultrasonic wave, etc. The sensor continuously collects first sensing data inside and outside the vehicle, and stores the first sensing data in a certain data format in the memory of the electronic device 130 through the CAN bus. The data format includes but is not limited to a data frame, a remote frame, an error frame, an overload frame, a frame interval, etc.

[0079] The first sensor data includes, but is not limited to, one or more of speed, braking time, braking depth, throttle depth, steering wheel rotation angle, turn signal signal, relative distance, relative speed, images and videos; images and videos include images and videos containing dangerous driving behaviors, or images and videos containing alarm events. Sensors are usually installed on the front and rear bumpers, side mirrors or windshields of vehicles. The embodiments of the present application do not limit the type of sensors. In some embodiments, sensor 110 is used to identify dangerous driving behaviors of the driver during driving, and when dangerous driving behaviors trigger an alarm event, an alarm will be triggered. Exemplarily, the sensor continuously collects images or videos inside and outside the vehicle. When the sensor identifies that the collected images or videos contain images or videos of dangerous driving behaviors, and at the same time identifies images or videos containing alarm events, the alarm will be triggered.

[0080] The alarm 120 may include one or more of a magnetic switch alarm, a vibration alarm, an ultrasonic alarm, etc., and may also include an active alarm and a passive alarm, for issuing an alarm to effectively prevent accidents. The embodiment of the present application does not limit the type of alarm.

[0081] The electronic device 130 can be a computing device such as an on-board computer (electronic control unit, ECU), a desktop computer, a notebook, a PDA, and a cloud server. The electronic device may include, but is not limited to, a processor 131, a memory 132, and a computer program stored in the memory 132 and executable on the processor 131. When the processor 131 executes the computer program, on the one hand, it can identify the driver's dangerous driving behavior during driving. When the dangerous driving behavior triggers an alarm event, the alarm will be triggered. Exemplarily, the sensor continuously collects images or videos inside and outside the vehicle, and stores the collected images or videos in the memory 132. When the processor identifies that the image or video stored in the memory 132 contains an image or video of dangerous driving behavior, and at the same time identifies an image or video containing an alarm event, the alarm will be triggered. On the other hand, the steps in the embodiment of the evaluation method for dangerous driving behavior in the following embodiment can be implemented. Those skilled in the art will understand that, Figure 1 This is merely an example of the electronic device 130 and does not constitute a limitation on the electronic device 130 . The electronic device 130 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0082] The processor 131 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0083] In some embodiments, the memory 132 may be an internal storage unit of the electronic device 130, such as a hard disk or memory of the electronic device 130. In other embodiments, the memory 132 may also be an external storage device of the electronic device 130, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FC), etc. equipped on the electronic device 130. Further, the memory 132 may also include both an internal storage unit and an external storage device of the electronic device 130. The memory 132 is used to store an operating system, an application program, a boot loader (BL), data, and other programs, such as program codes of a computer program. The memory 132 may also be used to temporarily store data that has been output or is to be output, for example, to store first sensor data collected by a sensor inside and outside the vehicle, to store alarm information, and to store the alarm type, alarm generation time, alarm duration, alarm evidence, etc. of the alarm information.

[0084] This application document does not limit the specific composition of the dangerous driving behavior evaluation system. The dangerous driving behavior evaluation system may include: Figure 1 The examples shown may have more or fewer components, or may combine certain components, or may have different components. Figure 1 This is only an exemplary description and should not be interpreted as a specific limitation of the present application.

[0085] The evaluation system of the embodiment of the present application collects first sensor data inside and outside the vehicle through sensors, and stores the first sensor data in the memory of the electronic device. When the sensor or electronic device recognizes that the first sensor data contains dangerous driving behavior and triggers an alarm event, the electronic device obtains the first sensor data before and after the alarm event collected by the sensor, and obtains the level of the current dangerous driving behavior based on the first sensor data; the comprehensive driving performance is determined based on the level of the current dangerous driving behavior and the historical dangerous driving behavior. Based on the comprehensive driving performance, the driver's performance in the alarm event can be comprehensively analyzed, and the driver's dangerous driving behavior in the alarm event can be more comprehensively evaluated. In addition, the first sensor data before and after the alarm event is easy to obtain, making the determined comprehensive driving performance more reliable.

[0086] The evaluation method of dangerous driving behavior in the embodiment of the present application can be Figure 1 The evaluation method of dangerous driving behavior in the embodiment of the present application requires training a discriminant model and storing the trained discriminant model in the electronic device. Figure 2 , Figure 2 1 is a flow chart of a method for training a discriminant model provided in an embodiment of the present application. The method includes steps S201 to S204.

[0087] S201, obtaining multiple groups of second sensor data before and after historical alarm events.

[0088] Specifically, the historical alarm events in the embodiments of the present application are triggered by historical dangerous driving behaviors. Historical alarm events are alarm events that have occurred, including alarm events that have occurred in the current vehicle and alarm events that have occurred in other vehicles. Historical dangerous driving behaviors are dangerous driving behaviors of the driver in historical alarm events. Dangerous driving behaviors include talking on the phone while driving, playing with the phone while driving, smoking while driving, eating while driving, driving fatigue, distracted driving, etc. Alarm events include lane departure, vehicle distance is too close, collision with the vehicle in front, pedestrian collision, etc. When the driver has one or more behaviors such as talking on the phone while driving, playing with the phone while driving, smoking while driving, eating while driving, driving fatigue, distracted driving, etc., it will cause alarm events such as lane departure, vehicle distance is too close, collision with the vehicle in front, or collision with pedestrians.

[0089] When a historical alarm event occurs, the electronic device obtains second sensor data collected by the sensor before and after the historical alarm event. The second sensor data includes, but is not limited to, one or more of speed, braking time, braking depth, throttle depth, steering wheel rotation angle, turn signal signal, relative distance, and relative speed.

[0090] For example, in a historical alarm event, the driver's distracted driving caused the vehicle to collide with a conflicting vehicle. The electronic device obtained the vehicle's speed, braking time, braking depth, throttle depth, etc. collected by the sensor before and after the driver braked, and used this set of data as the second sensor data.

[0091] For example, in another historical alarm event, the driver's smoking while driving caused the vehicle to collide with a pedestrian. The electronic device acquires sensors to collect the vehicle's speed, braking time, steering wheel rotation angle, etc. for a period of time before and after the driver's sudden steering wheel turn, and uses this set of data as the second sensor data. In this way, multiple sets of second sensor data can be acquired.

[0092] S202: Obtain, according to each group of second sensor data, a second evaluation index and a second traffic conflict index corresponding to each group of second sensor data.

[0093] Specifically, by calculating each set of second sensor data among the multiple sets of second sensor data acquired in step S201, the second evaluation index and the second traffic conflict index corresponding to each set of second sensor data can be obtained.

[0094] Among them, the second evaluation index refers to the vehicle's average speed, braking duration, average braking depth, average throttle depth, steering wheel rotation rate, number of turn signal flashes, etc. when the historical alarm event occurs.

[0095] In some embodiments, the average speed of the vehicle is the ratio of the displacement difference between the current vehicle and the conflicting vehicle to the time difference between the current vehicle and the conflicting vehicle.

[0096] Braking duration is calculated based on braking time, which refers to the moment of braking, a time point, such as 12:40. Braking duration is a time period, such as 5 minutes.

[0097] The average throttle depth is calculated based on the throttle depth. The throttle depth refers to the throttle depth at a point in time, and the average throttle depth refers to the average value of the throttle depth within a period of time.

[0098] The steering wheel rotation rate refers to the rotation angle of the steering wheel within a period of time.

[0099] The number of turn signal flashes refers to the number of times the turn signal flashes within a period of time.

[0100] The second traffic conflict indicator data (time to collision, TTC) is the ratio of the relative distance and relative speed between the current vehicle and the conflicting vehicle.

[0101] S203: Determine a preset value range to which each set of second traffic conflict indicator data belongs.

[0102] Specifically, a numerical range of TTC is preset in the processor.

[0103] As an implementation method, the preset numerical range includes a first preset numerical range, a second preset numerical range and a third preset numerical range; the first preset numerical range is TTC<3s; the second preset numerical range is 3≤TTC<5.5s; and the third preset numerical range is TTC≥5.5.

[0104] As another implementation method, the preset numerical range includes a first preset numerical range, a second preset numerical range, a third preset numerical range and a fourth preset numerical range; the first preset numerical range is TTC<3s; the second preset numerical range is 3≤TTC<4.5s; the third preset numerical range is 4.5≤TTC<5.5s; and the fourth preset numerical range is TTC≥5.5.

[0105] Of course, the preset value range includes more than the two cases listed above, and may also include 2 preset value ranges, 5 preset value ranges, etc. The embodiment of the present application does not limit this.

[0106] By calculating each set of second traffic conflict indicator data using the method in step S202 , the data range of each set of second traffic conflict indicator data can be determined according to a preset data range.

[0107] S204, substituting multiple groups of second traffic conflict indicators in the same preset numerical range and multiple groups of second evaluation indicators corresponding to the multiple groups of second traffic conflict indicators in the same preset numerical range into the discriminant function relationship formula, and calculating the coefficient value of each coefficient in the multiple discriminant function relationship formulas.

[0108] Specifically, the discriminant function relational expression is pre-set in the processor. The embodiment of the present application is illustrated by taking the preset numerical range including the first preset numerical range, the second preset numerical range and the third preset numerical range as an example.

[0109] The multiple groups of TTC in the first preset numerical range TTC<3s are used as the dependent variable Y1 in the first discriminant function relationship, and the multiple groups of second evaluation indicators corresponding to the multiple groups of TTC in the first preset numerical range TTC<3s are used as the independent variable x1 in the first discriminant function relationship. Substitute them into the first discriminant function relationship to calculate the coefficient values ​​of each coefficient in the first discriminant function relationship; wherein the first discriminant function relationship is:

[0110] Y1=a1x1+b1x2+...+c1x n +d1.

[0111] Wherein, Y1 represents the second traffic conflict index in the first preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the first preset numerical range, n represents the number of second evaluation index data, a1, b1...c1 represent the coefficients of the first discriminant function relationship, and d1 represents the constant of the first discriminant function relationship.

[0112] The multiple groups of TTC in the second preset numerical range of 3≤TTC<5.5s are used as the dependent variable Y2 in the second discriminant function relationship, and the multiple groups of second evaluation indicators corresponding to the multiple groups of TTC in the second preset numerical range of 3≤TTC<5.5s are used as the independent variable x2 in the second discriminant function relationship. Substitute them into the second discriminant function relationship to calculate the coefficient values ​​of each coefficient in the second discriminant function relationship; wherein the second discriminant function relationship is:

[0113] Y2=a2x1+b2x2+...+c2x n +d2.

[0114] Wherein, Y2 represents the second traffic conflict index in the second preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the second preset numerical range, n represents the number of second evaluation index data, a2, b2...c2 represent the coefficients of the second discriminant function relationship, and d2 represents the constant of the second discriminant function relationship.

[0115] The multiple groups of TTC in the third preset numerical range TTC≥5.5 are used as the dependent variable Y3 in the third discriminant function relationship, and the multiple groups of second evaluation indicators corresponding to the multiple groups of TTC in the third preset numerical range TTC≥5.5 are used as the independent variable x3 in the third discriminant function relationship. Substitute them into the third discriminant function relationship to calculate the coefficient values ​​of each coefficient in the third discriminant function relationship; wherein the third discriminant function relationship is:

[0116] Y3=a3x1+b3x2+...+c3x n +d3.

[0117] Wherein, Y3 represents the second traffic conflict index in the third preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the third preset numerical range, n represents the number of second evaluation index data, a3, b3...c3 represent the coefficients of the third discriminant function relationship, and d3 represents the constant of the third discriminant function relationship.

[0118] The determined discriminant model is:

[0119] Y1=a1x1+b1x2+...+c1x n +d1

[0120] Y2=a2x1+b2x2+...+c2x n +d2.

[0121] Y3=a3x1+b3x2+...+c3x n +d3

[0122] After training the discriminant model, use it to evaluate dangerous driving behavior. Figure 3 , Figure 3 is a flowchart of the steps of the dangerous driving behavior evaluation method provided by an embodiment of the present application. The dangerous driving behavior evaluation method of the embodiment of the present application can be Figure 1 The method comprises: steps S301 to S303.

[0123] S301, obtaining first sensor data before and after the current alarm event.

[0124] Specifically, the current alarm event in the embodiment of the present application is triggered by the current dangerous driving behavior, the current alarm event is an alarm event that is occurring, and the current dangerous driving behavior is the dangerous driving behavior of the driver in the alarm event that is occurring. The types of dangerous driving behaviors and alarm events have been described in S201 and will not be repeated here.

[0125] When the current alarm event occurs, the electronic device obtains the first sensor data collected by the sensor before and after the current alarm event. The first sensor data includes, but is not limited to, one or more of speed, braking time, braking depth, throttle depth, steering wheel rotation angle, turn signal signal, relative distance, and relative speed.

[0126] S302: Obtain the level of the current dangerous driving behavior according to the first sensor data.

[0127] For specific steps of obtaining the level of the current dangerous driving behavior according to the first sensor data, please refer to Figure 4 , Figure 4 The method for obtaining the level of the current dangerous driving behavior according to the first sensor data according to an embodiment of the present application can be Figure 1 The electronic device in the embodiment of the present invention is executed. The method comprises: step S401 to step S403.

[0128] S401: Obtain a first evaluation index according to first sensor data.

[0129] Specifically, the first evaluation index refers to one or more of the average speed, braking duration, average braking depth, average throttle depth, steering wheel rotation rate, and turn signal flashing times of the vehicle when the current alarm event occurs.

[0130] The specific calculation method of the average speed, braking duration, average braking depth, average throttle depth, steering wheel rotation rate, and turn signal flashing times has been described in S202 and will not be repeated here.

[0131] S402, inputting the first evaluation index into the discrimination model, and outputting the first traffic conflict index.

[0132] Specifically, as an implementation method: the first evaluation index is input into a plurality of discriminant function relationship formulas respectively, and a plurality of first traffic conflict indexes TTC are output.

[0133] The minimum value among the plurality of first traffic conflict indicators TTC is taken as the optimal first traffic conflict indicator.

[0134] As another implementation method: the first evaluation index is respectively input into the three discriminant function relationship formulas determined in S204, and three first traffic conflict indexes TTC are output.

[0135] The minimum value among the three first traffic conflict indicators TTC is taken as the optimal first traffic conflict indicator.

[0136] S403: Determine the level of the current dangerous driving behavior according to the first traffic conflict indicator.

[0137] Specifically, a first preset corresponding relationship is pre-set in the processor.

[0138] In some embodiments, the first preset correspondence is: the first preset value range TTC<3s corresponds to the first preset level A; the second preset value range is 3≤TTC<5.5s corresponds to the second preset level B; the third preset value range is TTC≥5.5 corresponds to the third preset level C.

[0139] In other embodiments, the first preset correspondence is: the first preset numerical range TTC<3s corresponds to the first preset level A; the second preset numerical range 3≤TTC<4.5s corresponds to the second preset level B; the third preset numerical range 4.5≤TTC<5.5s corresponds to the third preset level C; the fourth preset numerical range TTC≥5.5 corresponds to the fourth preset level D.

[0140] Of course, the first preset corresponding relationship in the embodiment of the present application includes not only the above two situations, but may also include other corresponding relationships, and the embodiment of the present application is not limited to this.

[0141] According to the first preset corresponding relationship, the level of the current dangerous driving behavior corresponding to the minimum value of three or more first traffic conflict indicators TTC is determined.

[0142] S303, determining the comprehensive driving performance according to the level of the current dangerous driving behavior and the historical dangerous driving behavior.

[0143] Specifically, an embodiment of the present application determines the comprehensive driving performance according to the level of the current dangerous driving behavior and the historical dangerous driving behavior. Please refer to Figure 5 , Figure 5 It is a flowchart of the steps for determining the comprehensive driving performance provided by an embodiment of the present application, including steps S501 to S503.

[0144] S501, determining a target value corresponding to the level of the current dangerous driving behavior.

[0145] Specifically, a second preset correspondence is pre-set in the electronic device, and a target value of the dangerous driving behavior corresponding to the level of the dangerous driving behavior is determined according to the second preset correspondence. The second preset correspondence includes a correspondence between the level of the dangerous driving behavior and the score value of the dangerous driving behavior.

[0146] Exemplarily, the second preset corresponding relationship is: the first preset level A corresponds to the first value 60 points, the second preset level B corresponds to the second value 80 points, and the third preset level C corresponds to the third value 100 points.

[0147] Exemplarily, the second preset correspondence is: the first preset level A corresponds to the first value 40 points, the second preset level B corresponds to the second value 60 points, the third preset level C corresponds to the third value 80 points, and the fourth preset level D corresponds to the fourth value 100 points.

[0148] Of course, the second preset corresponding relationship in the embodiment of the present application includes more than the above two situations, and the embodiment of the present application is not limited to this.

[0149] S502, counting the number of historical dangerous driving behaviors.

[0150] Specifically, the number of historical dangerous driving behaviors is the number of dangerous driving behaviors that the driver has performed over a period of time. In an embodiment of the present application, the electronic device can obtain the number of historical dangerous driving behaviors by counting images or videos containing dangerous driving behaviors stored in a memory over a period of time.

[0151] For example, the electronic device can obtain the number of historical dangerous driving behaviors by counting images stored in the memory within a week that include talking on the phone while driving, playing with the mobile phone while driving, smoking while driving, eating while driving, driving while fatigued, or driving while distracted.

[0152] S503, calculating an evaluation value of the comprehensive driving performance by combining the target value and the number of times.

[0153] Specifically, a first weight of a target value of a current dangerous driving behavior and a second weight of the number of times of historical dangerous driving behaviors are obtained.

[0154] In some embodiments, the first weight and the second weight defined according to the severity of the impact on safe driving are pre-stored in the processor. After the processor determines the target value of the current dangerous driving behavior, it obtains the first weight of the target value of the current dangerous driving behavior, and after counting the number of historical dangerous driving behaviors, it obtains the second weight of the number of historical dangerous driving behaviors.

[0155] Exemplarily, the first weight of the target value of the current dangerous driving behavior is 45%; the second weight of the historical number of fatigue driving is 15%; the second weight of the historical number of distracted driving is 10%; the second weight of the historical number of phone-driving times is 10%; the second weight of the historical number of smoking driving times is 5%; and the second weight of the historical number of other dangerous driving behaviors is 15%.

[0156] Substituting the target value of dangerous driving behavior, the number of historical dangerous driving behaviors, the first weight, and the second weight into the following formula, the evaluation value of the comprehensive driving performance can be obtained.

[0157] Comprehensive driving performance evaluation value = αY-βm-γn-…-ρl

[0158] Among them, α represents the first weight, β…ρ represents the second weight, Y represents the target value of dangerous driving behavior, and m, n…, l represent the number of historical dangerous driving behaviors such as talking on the phone while driving, smoking while driving, fatigue driving, and distracted driving.

[0159] In summary, the embodiment of the present application obtains sensor data before and after the alarm event, and can obtain evaluation indicators for evaluating dangerous driving behavior based on the sensor data. The sensor data is speed, braking time, etc. This sensor data is easy to obtain, and it is easy to obtain evaluation indicators for evaluating dangerous driving behavior. The evaluation indicators are input into a pre-trained discriminant model to output a first traffic conflict indicator. According to the first preset corresponding relationship, the level of the current dangerous driving behavior can be determined, and the comprehensive driving performance can be determined according to the level of the current dangerous driving behavior and the historical dangerous driving behavior. According to the comprehensive driving performance, the performance of the driver in the alarm event can be comprehensively analyzed, and the dangerous driving behavior of the driver in the alarm event can be more comprehensively evaluated.

[0160] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0161] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0162] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0163] Please refer to Figure 6 , Figure 6 An evaluation device for dangerous driving behavior provided by an embodiment of the present application includes:

[0164] The acquisition module 601 is used to acquire the first sensor data before and after the current alarm event; the current alarm event is triggered by the current dangerous driving behavior.

[0165] The processing module 602 is used to obtain the level of the current dangerous driving behavior according to the first sensor data.

[0166] The evaluation module 603 is used to determine the comprehensive driving performance according to the level of the current dangerous driving behavior and the historical dangerous driving behavior.

[0167] The evaluation device of the embodiment of the present application obtains the first sensor data before and after the current alarm event through the acquisition module; obtains the level of the current dangerous driving behavior through the processing module; and determines the comprehensive driving performance through the evaluation module. According to the comprehensive driving performance, the performance of the driver in the alarm event can be comprehensively analyzed, and the dangerous driving behavior of the driver in the alarm event can be more comprehensively evaluated. In addition, the first sensor data before and after the alarm event is easy to obtain, making the determined comprehensive driving performance more reliable.

[0168] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the embodiment of the evaluation method for dangerous driving behavior can be implemented.

[0169] An embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device implements the steps in the above-mentioned dangerous driving behavior evaluation method embodiment when executing the computer program product.

[0170] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0171] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0172] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0173] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0174] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for evaluating dangerous driving behavior, characterized in that: include: Acquire the first sensor data before and after the current alarm event; The current alarm event is triggered by the current dangerous driving behavior; Obtaining a first evaluation index according to the first sensing data; Inputting the first evaluation index into a discriminant model and outputting a first traffic conflict index; Determining the level of the current dangerous driving behavior according to the first traffic conflict indicator; Determining a target value corresponding to the level of the current dangerous driving behavior; Count the number of dangerous driving behaviors in history; Obtaining a first weight of a target value of the current dangerous driving behavior and a second weight of the number of times of the historical dangerous driving behavior; Substituting the target value, the number of times, the first weight and the second weight into the evaluation value formula of the comprehensive driving performance, the evaluation value of the comprehensive driving performance is obtained; the evaluation value formula of the comprehensive driving performance is: Comprehensive driving performance evaluation value = αY-βm-γn-...-ρl Wherein, Y represents the target value, m, n..., l represent the number of historical dangerous driving behaviors, α represents the first weight, β, γ...ρ represent the second weight; The training process of the discriminant model includes: Acquire multiple sets of second sensor data before and after historical alarm events; Obtaining, according to each group of the second sensor data, a second evaluation index and a second traffic conflict index corresponding to each group of the second sensor data; Determining a preset value range to which each group of second traffic conflict indicator data belongs; Substituting multiple groups of the second traffic conflict indicators in the same preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the same preset numerical range into a discriminant function relationship formula, and calculating the coefficient value of each coefficient in the multiple discriminant function relationship formulas, including: Substitute multiple groups of the second traffic conflict indicators in the first preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the first preset numerical range into the first discriminant function relational formula, and calculate the coefficient values ​​of each coefficient in the first discriminant function relational formula; wherein the first discriminant function relational formula is: Y1=a1x1+b1x2+...+c1x n +d1 Wherein, Y1 represents the second traffic conflict index within the first preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the first preset value range, n represents the number of the second evaluation index data, a1, b1...c1 represent the coefficients of the first discriminant function relationship, and d1 represents the constant of the first discriminant function relationship; Substitute multiple groups of the second traffic conflict indicators in the second preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the second preset numerical range into a second discriminant function relational expression, and calculate the coefficient value of each coefficient in the second discriminant function relational expression; wherein the second discriminant function relational expression is: <h2 style=";text-align:left;direction:ltr">Y2 = a2x1 + b2x2 +... + c2x<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> +d2 Wherein, Y2 represents the second traffic conflict index in the second preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the second preset value range, n represents the number of the second evaluation index data, a2, b2...c2 represent coefficients of the second discriminant function relationship, and d2 represents a constant of the second discriminant function relationship; Substituting multiple groups of the second traffic conflict indicators in a third preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the third preset numerical range into a third discriminant function relational expression, the coefficient value of each coefficient in the third discriminant function relational expression is calculated; wherein the third discriminant function relational expression is: <h2 style=";text-align:left;direction:ltr">Y3 = a3x1 + b3x2 +... + c3x<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> +d3 Wherein, Y3 represents the second traffic conflict index in the third preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the third preset numerical range, n represents the number of the second evaluation index data, a3, b3...c3 represent the coefficients of the third discriminant function relationship, and d3 represents the constant of the third discriminant function relationship.

2. The method for evaluating dangerous driving behavior according to claim 1, characterized in that: The step of inputting the first evaluation index into a discrimination model and outputting a first traffic conflict index comprises: Inputting the first evaluation index into a plurality of the discriminant function relationship equations respectively, and outputting a plurality of the first traffic conflict indexes; The minimum value among the plurality of first traffic conflict indicators is used as the optimal first traffic conflict indicator.

3. The method for evaluating dangerous driving behavior according to claim 1, characterized in that: The step of inputting the first evaluation index into a discrimination model and outputting a first traffic conflict index comprises: Input the first evaluation index into the three discriminant function relationship formulas respectively, and output three first traffic conflict indexes; The minimum value among the three first traffic conflict indicators is used as the optimal first traffic conflict indicator.

4. The method for evaluating dangerous driving behavior according to claim 2 or 3, characterized in that: Determining the level of the current dangerous driving behavior according to the first traffic conflict indicator includes: According to the first preset corresponding relationship, the level of the current dangerous driving behavior corresponding to the optimal first traffic conflict index is determined.

5. The method for evaluating dangerous driving behavior according to claim 4, characterized in that: The first preset corresponding relationship includes a corresponding relationship between the preset value range and the preset level, and determining the level of the current dangerous driving behavior corresponding to the optimal first traffic conflict indicator according to the first preset corresponding relationship includes: The preset value range to which the optimal first traffic conflict indicator belongs is determined, and the preset level corresponding to the preset value range is used as the level of the current dangerous driving behavior.

6. The method for evaluating dangerous driving behavior according to claim 1, characterized in that: The determining of a target value corresponding to the level of the current dangerous driving behavior includes: The target value corresponding to the level of the current dangerous driving behavior is determined according to a second preset corresponding relationship, wherein the second preset corresponding relationship includes a corresponding relationship between a preset level and a preset target value.

7. The method for evaluating dangerous driving behavior according to claim 6, characterized in that: The step of determining a target value corresponding to the level of the current dangerous driving behavior according to the second preset corresponding relationship includes: When the level of the current dangerous driving behavior is a first preset level, determining the target value of the current dangerous driving behavior to be a first value; When the level of the current dangerous driving behavior is a second preset level, determining the target value of the current dangerous driving behavior to be a second value; When the level of the current dangerous driving behavior is a third preset level, the target value of the current dangerous driving behavior is determined to be a third value.

8. A device for evaluating dangerous driving behavior, characterized in that: include: An acquisition module, used to acquire first sensor data before and after a current alarm event; the current alarm event is triggered by a current dangerous driving behavior; A processing module, configured to obtain a first evaluation index according to the first sensing data; input the first evaluation index into a discrimination model, and output a first traffic conflict index; According to the first traffic conflict indicator, the level of the current dangerous driving behavior is determined; the training process of the discriminant model includes: Acquire multiple groups of second sensor data before and after historical alarm events; obtain the second evaluation index and the second traffic conflict index corresponding to each group of the second sensor data according to each group of the second sensor data; determine the preset value range to which each group of the second traffic conflict index data belongs; substitute multiple groups of the second traffic conflict indexes in the same preset value range and multiple groups of the second evaluation indexes corresponding to the multiple groups of the second traffic conflict indexes in the same preset value range into a discriminant function relationship, and calculate the coefficient value of each coefficient in the multiple discriminant function relationship, including: Substitute multiple groups of the second traffic conflict indicators in the first preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the first preset numerical range into the first discriminant function relational formula, and calculate the coefficient values ​​of each coefficient in the first discriminant function relational formula; wherein the first discriminant function relational formula is: Y1=a1x1+b1x2+...+c1x n +d1 Wherein, Y1 represents the second traffic conflict index within the first preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the first preset value range, n represents the number of the second evaluation index data, a1, b1...c1 represent the coefficients of the first discriminant function relationship, and d1 represents the constant of the first discriminant function relationship; Substitute multiple groups of the second traffic conflict indicators in the second preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the second preset numerical range into a second discriminant function relational expression, and calculate the coefficient value of each coefficient in the second discriminant function relational expression; wherein the second discriminant function relational expression is: <h2 style=";text-align:left;direction:ltr">Y2 = a2x1 + b2x2 +... + c2x<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> +d2 Wherein, Y2 represents the second traffic conflict index in the second preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the second preset value range, n represents the number of the second evaluation index data, a2, b2...c2 represent coefficients of the second discriminant function relationship, and d2 represents a constant of the second discriminant function relationship; Substituting multiple groups of the second traffic conflict indicators in a third preset numerical range and multiple groups of the second evaluation indicators corresponding to the multiple groups of the second traffic conflict indicators in the third preset numerical range into a third discriminant function relational expression, the coefficient value of each coefficient in the third discriminant function relational expression is calculated; wherein the third discriminant function relational expression is: <h2 style=";text-align:left;direction:ltr">Y3 = a3x1 + b3x2 +... + c3x<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> +d3 Wherein, Y3 represents the second traffic conflict index in the third preset value range, x1, x2...x n represents the second evaluation index data corresponding to the second traffic conflict index in the third preset value range, n represents the number of the second evaluation index data, a3, b3...c3 represent coefficients of the third discriminant function relationship, and d3 represents a constant of the third discriminant function relationship; An evaluation module is used to determine a target value corresponding to the level of the current dangerous driving behavior; count the number of historical dangerous driving behaviors; obtain a first weight of the target value of the current dangerous driving behavior and a second weight of the number of historical dangerous driving behaviors; substitute the target value, the number, the first weight and the second weight into an evaluation value formula of comprehensive driving performance to obtain an evaluation value of the comprehensive driving performance; the evaluation value formula of the comprehensive driving performance is: Comprehensive driving performance evaluation value = αY-βm-γn-...-ρl Wherein, Y represents the target value, m, n, ..., l represent the number of historical dangerous driving behaviors respectively, α represents the first weight, β, γ, ... ρ represent the second weight.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method for evaluating dangerous driving behavior as described in any one of claims 1 to 7 when executing the computer program.

10. A dangerous driving behavior evaluation system, characterized in that: The evaluation system comprises an evaluation device for dangerous driving behavior as described in claim 8 or an electronic device as described in claim 9, wherein the evaluation system further comprises a sensor and an alarm, wherein the sensor is used to collect environmental data inside and outside the vehicle, and the alarm is used to sound an alarm when an event is triggered.

Citation Information

Patent Citations

  • Method and device for predicting driving risk

    CN105930943A

  • Driving behavior analyzing method, device and system

    CN106534366A

  • Method and device for distinguishing abnormal driving behaviors

    CN107826118A

  • Early warning method and device for dangerous driving behaviors

    CN111627251A

  • Driving model training method and device, equipment and medium

    CN112508054A