CN109389824B

CN109389824B - Driving risk assessment method and device

Info

Publication number: CN109389824B
Application number: CN201710658808.2A
Authority: CN
Inventors: 郑坤; 陈奇; 杨辉明; 刘祖齐
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2017-08-04
Filing date: 2017-08-04
Publication date: 2021-07-09
Anticipated expiration: 2037-08-04
Also published as: CN109389824A

Abstract

The embodiment of the application discloses a driving risk assessment method and device, and the method comprises the following steps: acquiring first driving data of a vehicle to be evaluated, second driving data of a moving target, traffic environment data of a target area and historical traffic accident data of the target area; determining a dynamic risk coefficient according to first driving data of a vehicle to be evaluated and second driving data of a moving target; determining a semi-dynamic risk coefficient according to the traffic environment data; determining a static risk coefficient according to historical traffic accident data and traffic environment data; fusing the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient to obtain a comprehensive risk coefficient; and determining the traffic risk grade according to the comprehensive risk coefficient. The traffic risk grade determining method and the traffic risk grade determining device are based on the complex variability of the intersection condition and combined with various factors influencing intersection risks, so that the risk can be accurately and effectively prompted to a driver, and traffic accidents are avoided.

Description

Driving risk assessment method and device

Technical Field

The embodiment of the application relates to the technical field of communication, in particular to a driving risk assessment method and device.

Background

Crossroads are a very important scene in traffic systems and are often the places where traffic accidents occur frequently. With the advancement of information technology, advanced and real-time visual processing, reliable communication technology is also emerging in the field of view of traffic monitoring systems.

At present, the existing traffic monitoring system is installed at a crossroad, and mainly comprises a camera, a radar speed measuring device, a controller, a wireless module and an alarm prompting module. The traffic detection system detects real-time information of crossing vehicles, pedestrians and non-motor vehicles passing through the crossing by using the radar speed measuring device and the camera, for example, motion information such as vehicle speed and direction, the controller can process the real-time information of the crossing detected by the radar speed measuring device and the camera, judge the current vehicle speed, the conditions of the pedestrians and the non-motor vehicles passing through the crossing, broadcast the judgment result to the vehicles passing through the crossing through the wireless module, and start the acousto-optic prompt function by using the alarm prompt module, so that a driver can take measures in time.

The existing traffic monitoring system only takes the real-time information of vehicles, pedestrians and non-motor vehicles passing through the intersection as the standard for judging whether the intersection is risky or not. However, the actual intersection situation is complicated and changeable, and if only the real-time information of the intersection is considered, but not combined with other various factors affecting the intersection risk, the existing traffic monitoring system cannot accurately evaluate the risk of the intersection, so the existing traffic monitoring system may send the wrong risk evaluation result to the vehicles passing through the intersection, thereby causing traffic accidents.

Disclosure of Invention

The embodiment of the application provides a driving risk assessment method and device, so that accurate and effective risk prompts are provided for a driver.

The embodiment of the application is realized as follows:

in a first aspect, an embodiment of the present application provides a driving risk assessment method, where the method includes:

acquiring first driving data of a vehicle to be evaluated, second driving data of a moving target, traffic environment data of a target area and historical traffic accident data of the target area, wherein the moving target is an object in a moving state in the target area, the target area is an area away from the vehicle to be evaluated within a preset range, the traffic environment data are used for indicating the current traffic environment condition in the target area, the first driving data are driving parameters corresponding to the vehicle to be evaluated in the current driving process, and the second driving data are moving parameters corresponding to the moving target in the current driving process;

determining a dynamic risk coefficient according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target, wherein the dynamic risk coefficient is used for indicating the possibility of collision between the vehicle to be evaluated and the moving target;

determining a semi-dynamic risk coefficient according to the traffic environment data, wherein the semi-dynamic risk coefficient is used for indicating the possibility of traffic accidents in the target area under the current traffic environment condition;

determining a static risk coefficient according to the historical traffic accident data and the traffic environment data, wherein the static risk coefficient is used for indicating the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area;

fusing the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient to obtain a comprehensive risk coefficient;

and determining the traffic risk level of the current vehicle to be evaluated in the target area according to the comprehensive risk coefficient.

The moving target is an object in a moving state in the target area. The moving target can be a motor vehicle, for example, the moving target can be a car, a truck, a bus, a sprinkler, or the like; the moving target can also be a non-motor vehicle, for example, the moving target can be a battery car, a bicycle or a tricycle and the like; the moving target may also be a human or an animal, etc. Of course, the moving object is not limited to the above-mentioned contents, and the moving object may be other types of objects in a moving state.

In the first aspect, the embodiment of the application determines the dynamic risk coefficient according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target to determine the possibility of collision between the vehicle to be evaluated and the moving target, determines the semi-dynamic risk coefficient according to the traffic environment data to determine the possibility of traffic accidents occurring in the target area under the current traffic environment condition, and determines the static risk coefficient according to the historical traffic accident data and the traffic environment data to determine the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area. After the three risk coefficients are obtained, determining a comprehensive risk coefficient according to the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient, and determining the traffic risk level of the current vehicle to be evaluated in the target area according to the comprehensive risk coefficient. Therefore, the traffic risk grade is determined based on the complex variability of the intersection condition and by combining various factors influencing the intersection risk, so that the traffic risk grade can be accurately and effectively prompted to the driver, and the traffic accident is avoided.

In one possible implementation, determining the dynamic risk factor from the first driving data of the vehicle to be evaluated and the second driving data of the moving object comprises:

calculating the remaining time of collision between the vehicle to be evaluated and the moving target according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target;

calculating the brake advance time according to the remaining time and the preset brake reaction time;

and determining a dynamic risk coefficient corresponding to the early braking time according to a preset first preset rule, wherein the first preset rule is used for indicating the corresponding relation between the early braking time and the dynamic risk coefficient.

The dynamic risk coefficient is determined according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target, so that the possibility of collision between the vehicle to be evaluated and the moving target can be determined, and the possibility of accidents in the dynamic aspect is provided for calculating the comprehensive risk coefficient.

In one possible implementation, determining the semi-dynamic risk factor from the traffic environment data includes:

calculating a semi-dynamic risk initial coefficient according to the time of the vehicle to be evaluated running to a front stop position, wherein the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in a target area;

determining a compensation coefficient corresponding to the traffic environment data according to a preset second preset rule, wherein the second preset rule is used for indicating the corresponding relation between the traffic environment data and the compensation coefficient;

and calculating the semi-dynamic risk coefficient according to the semi-dynamic risk initial coefficient and the compensation coefficient.

The semi-dynamic risk coefficient is determined according to the traffic environment data, the possibility of traffic accidents occurring in the target area under the current traffic environment condition can be determined, and therefore the possibility of accidents occurring in the semi-dynamic aspect is provided for calculating the comprehensive risk coefficient.

In one possible implementation, the traffic environment data is one of a traffic flow parameter of the target area, a traffic control signal of the target area, or a driving condition parameter of the target area.

In one possible implementation manner, the determining, according to a preset second preset rule, a compensation coefficient corresponding to the traffic environment data includes:

determining a first compensation coefficient corresponding to the traffic flow parameter of the target area according to a preset third preset rule, wherein the third preset rule is used for indicating the corresponding relation between the traffic flow parameter and the first compensation coefficient;

determining a second compensation coefficient corresponding to the traffic control signal according to a preset fourth preset rule, wherein the fourth preset rule is used for indicating the corresponding relation between the traffic control signal and the second compensation coefficient;

determining a third compensation coefficient corresponding to the driving condition parameter according to a preset fifth preset rule, wherein the fifth preset rule is used for indicating the corresponding relation between the driving condition parameter and the third compensation coefficient;

and determining a compensation coefficient according to the first compensation coefficient, the second compensation coefficient and the third compensation coefficient.

In one possible implementation, determining the static risk factor based on the historical traffic accident data and the traffic environment data includes:

determining a sixth preset rule in the historical traffic accident data, wherein the sixth preset rule is used for indicating the corresponding relation between the traffic environment data and the accident occurrence probability;

determining the accident occurrence probability corresponding to the traffic environment data according to a sixth preset rule;

and determining a static risk coefficient corresponding to the accident occurrence probability according to a preset seventh preset rule, wherein the seventh preset rule is used for indicating the corresponding relation between the accident occurrence probability and the static risk coefficient.

The static risk coefficient is determined according to the historical traffic accident data and the traffic environment data, and the possibility of traffic accidents in the target area in the current traffic environment condition can be determined, so that the possibility of accidents in the static aspect is provided for calculating the comprehensive risk coefficient.

In one possible implementation, after the step of acquiring the first driving data of the vehicle to be evaluated, the second driving data of the moving target, the traffic environment data of the target area, and the historical traffic accident data of the target area, the method further includes:

determining a first distance required by the vehicle to be evaluated to reach a front stop position according to first running data of the vehicle to be evaluated, wherein the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in a target area;

and when the first distance is smaller than the safe distance, triggering the step of determining the dynamic risk coefficient according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target.

When the first distance is less than the safety distance, it is indicated that the vehicle to be evaluated is relatively close to the front stop position, and since the front stop position is usually the position of the intersection, the possibility of traffic accidents is high, and at this time, it is necessary to start to evaluate whether a target area has a high driving risk or not to determine the traffic risk level and provide the level for the driver.

In one possible implementation, determining a first distance required for the vehicle to be evaluated to reach the front stopping position according to the first travel data of the vehicle to be evaluated comprises:

acquiring first position information of the vehicle to be evaluated according to the first running data of the vehicle to be evaluated;

determining second position information of a front stop position on the map according to the first position information;

and calculating a first distance between the vehicle to be evaluated and the front stop position according to the first position information and the second position information.

acquiring a second distance between the front stop position and the rear stop position by using the map;

determining a third distance between the vehicle to be evaluated and a rear stopping position according to the first running data of the vehicle to be evaluated, wherein the rear stopping position is a stopping position indicated by a first traffic stopping line behind the vehicle to be evaluated in the target area;

and determining a first distance between the vehicle to be evaluated and the front stop position according to the second distance and the third distance.

In one possible implementation, fusing the dynamic risk coefficient, the semi-dynamic risk coefficient, and the static risk coefficient to obtain a comprehensive risk coefficient includes:

acquiring working condition characteristics of a target area;

determining a risk coefficient weight corresponding to the working condition characteristics of the target area according to a preset eighth preset rule, wherein the eighth preset rule is used for indicating the corresponding relation between the working condition characteristics and the risk coefficient weight, and the risk coefficient weight comprises a dynamic risk weight, a semi-dynamic risk weight and a static risk weight;

and calculating the comprehensive risk coefficient according to the dynamic risk coefficient, the dynamic risk weight, the semi-dynamic risk coefficient, the semi-dynamic risk weight, the static risk coefficient and the static risk weight.

And calculating a comprehensive risk coefficient according to the dynamic risk coefficient, the importance degree of the dynamic risk coefficient, the semi-dynamic risk coefficient, the importance degree of the semi-dynamic risk coefficient, the static risk coefficient and the importance degree of the static risk coefficient, so that the possibility of traffic accidents of the vehicle to be evaluated in the target area is obtained.

In one possible implementation, after the step of determining the traffic risk level of the vehicle to be currently evaluated in the target area according to the comprehensive risk coefficient, the method further includes:

and outputting the traffic risk grade.

Wherein the current traffic risk level can be displayed by a display so that the driver can see it; as another example, the current traffic risk level may also be broadcast through a speaker to be heard by the driver. In addition, there are many ways to output the traffic risk level, and the traffic risk level is not limited to be output by a display device or a voice device, but may be output by other ways.

In one possible implementation, the moving object is a motor vehicle.

In a second aspect, an embodiment of the present application provides a driving risk assessment apparatus, including:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring first driving data of a vehicle to be evaluated, second driving data of a moving target, traffic environment data of a target area and historical traffic accident data of the target area, the moving target is an object in a moving state in the target area, the target area is an area which is a preset range away from the vehicle to be evaluated, the traffic environment data is used for indicating the current traffic environment condition in the target area, the first driving data is driving parameters corresponding to the vehicle to be evaluated in the current driving process, and the second driving data is driving parameters corresponding to the moving target in the current driving process;

the first determination module is used for determining a dynamic risk coefficient according to first running data of the vehicle to be evaluated and second running data of the moving target, and the dynamic risk coefficient is used for indicating the possibility of collision between the vehicle to be evaluated and the moving target;

the second determining module is used for determining a semi-dynamic risk coefficient according to the traffic environment data, and the semi-dynamic risk coefficient is used for indicating the possibility of traffic accidents in the target area under the current traffic environment condition;

the third determining module is used for determining a static risk coefficient according to the historical traffic accident data and the traffic environment data, wherein the static risk coefficient is used for indicating the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area;

the fusion module is used for fusing the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient to obtain a comprehensive risk coefficient;

and the fourth determination module is used for determining the traffic risk level of the current vehicle to be evaluated in the target area according to the comprehensive risk coefficient.

In the second aspect, the final traffic risk level is determined based on the complexity and variability of the intersection condition and by combining various factors influencing the intersection risk, so that the risk can be accurately and effectively prompted to the driver, and traffic accidents are avoided.

In a possible implementation manner, the first determining module is specifically configured to calculate the remaining time for the collision between the vehicle to be evaluated and the moving target according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target; calculating the brake advance time according to the remaining time and the preset brake reaction time; and determining a dynamic risk coefficient corresponding to the early braking time according to a preset first preset rule, wherein the first preset rule is used for indicating the corresponding relation between the early braking time and the dynamic risk coefficient.

In a possible implementation manner, the second determining module is specifically configured to calculate a semi-dynamic risk initial coefficient according to a time when a vehicle to be evaluated travels to a front stop position, where the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in a target area; determining a compensation coefficient corresponding to the traffic environment data according to a preset second preset rule, wherein the second preset rule is used for indicating the corresponding relation between the traffic environment data and the compensation coefficient; and calculating the semi-dynamic risk coefficient according to the semi-dynamic risk initial coefficient and the compensation coefficient.

In a possible implementation manner, the second determining module is specifically configured to determine, according to a preset third preset rule, a first compensation coefficient corresponding to a traffic flow parameter of the target area, where the third preset rule is used to indicate a correspondence relationship between the traffic flow parameter and the first compensation coefficient; determining a second compensation coefficient corresponding to the traffic control signal according to a preset fourth preset rule, wherein the fourth preset rule is used for indicating the corresponding relation between the traffic control signal and the second compensation coefficient; determining a third compensation coefficient corresponding to the driving condition parameter according to a preset fifth preset rule, wherein the fifth preset rule is used for indicating the corresponding relation between the driving condition parameter and the third compensation coefficient; and determining a compensation coefficient according to the first compensation coefficient, the second compensation coefficient and the third compensation coefficient.

In a possible implementation manner, the third determining module is specifically configured to determine a sixth preset rule in the historical traffic accident data, where the sixth preset rule is used to indicate a corresponding relationship between the traffic environment data and the accident occurrence probability; determining the accident occurrence probability corresponding to the traffic environment data according to a sixth preset rule; and determining a static risk coefficient corresponding to the accident occurrence probability according to a preset seventh preset rule, wherein the seventh preset rule is used for indicating the corresponding relation between the accident occurrence probability and the static risk coefficient.

In one possible implementation, the apparatus further includes:

the fifth determining module is used for determining a first distance required by the vehicle to be evaluated to reach a front stopping position according to the first running data of the vehicle to be evaluated, wherein the front stopping position is a stopping position indicated by a first traffic stopping line in front of the vehicle to be evaluated in the target area;

and the triggering module is used for triggering the first determining module when the first distance is smaller than the safe distance.

In a possible implementation manner, the fifth determining module is specifically configured to obtain first position information of the vehicle to be evaluated according to the first driving data of the vehicle to be evaluated; determining second position information of a front stop position on the map according to the first position information; and calculating a first distance between the vehicle to be evaluated and the front stop position according to the first position information and the second position information.

In a possible implementation manner, the fifth determining module is specifically configured to obtain a second distance between the front stop position and the rear stop position by using a map; determining a third distance between the vehicle to be evaluated and a rear stopping position according to the first running data of the vehicle to be evaluated, wherein the rear stopping position is a stopping position indicated by a first traffic stopping line behind the vehicle to be evaluated in the target area; and determining a first distance between the vehicle to be evaluated and the front stop position according to the second distance and the third distance.

In a possible implementation manner, the fusion module is specifically configured to obtain a working condition characteristic of the target area; determining a risk coefficient weight corresponding to the working condition characteristics of the target area according to a preset eighth preset rule, wherein the eighth preset rule is used for indicating the corresponding relation between the working condition characteristics and the risk coefficient weight, and the risk coefficient weight comprises a dynamic risk weight, a semi-dynamic risk weight and a static risk weight; and calculating the comprehensive risk coefficient according to the dynamic risk coefficient, the dynamic risk weight, the semi-dynamic risk coefficient, the semi-dynamic risk weight, the static risk coefficient and the static risk weight.

In one possible implementation, the apparatus further includes:

and the output module is used for outputting the traffic risk grade.

In a third aspect, an embodiment of the present application provides a driving risk assessment apparatus, including: a processor and a memory, wherein the memory stores therein operating instructions executable by the processor, and the operating instructions in the memory are read by the processor for implementing the first aspect or the method described in any possible implementation manner of the first aspect.

In the third aspect, the final traffic risk level is determined based on the complexity and variability of the intersection condition and by combining various factors influencing the intersection risk, so that the risk can be accurately and effectively prompted to the driver, and the traffic accident is avoided.

Drawings

FIG. 1 is a flowchart illustrating a driving risk assessment method according to an embodiment of the present disclosure;

the embodiment shown in fig. 2 is a detailed embodiment based on step S12 in fig. 1;

the embodiment shown in fig. 3 is a detailed embodiment based on step S13 in fig. 1;

the embodiment shown in fig. 4 is a detailed embodiment based on step S14 in fig. 1;

the embodiment shown in fig. 5 is a detailed embodiment based on step S15 in fig. 1;

fig. 6 is a schematic view illustrating a driving risk assessment device according to an embodiment of the present application;

FIG. 7 is a schematic view of another driving risk assessment device provided in the embodiment of the present application;

fig. 8 is a schematic view of another driving risk assessment device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

Fig. 1 is a flowchart illustrating a driving risk assessment method according to an embodiment of the present disclosure. The driving risk assessment method shown in fig. 1 can remind the driver whether the current road section is dangerous or not through the output risk level, so that the driver can deal with the current road condition according to the output risk level, and the probability of driving accidents can be further reduced. The method comprises the following steps.

And step S11, acquiring first driving data of the vehicle to be evaluated, second driving data of the moving target, traffic environment data of the target area and historical traffic accident data of the target area.

The method provided by the embodiment of the application can be applied to the terminal, and the terminal can be vehicle-mounted computer equipment. The vehicle to be evaluated refers to a vehicle driven by a user and provided with an on-board computer device.

The first driving data is driving parameters corresponding to the vehicle to be evaluated in the driving process, wherein the first driving data of the vehicle to be evaluated can be positioning information of the vehicle to be evaluated, driving speed of the vehicle to be evaluated, driving direction of the vehicle to be evaluated and the like. The second driving data is a moving parameter corresponding to the moving target in the moving process, wherein the second driving data of the moving target may be positioning information of the moving target, a driving speed of the moving target, a driving direction of the moving target, and the like.

The target area is a peripheral geographical area which is an area target area within a preset range of the vehicle to be evaluated. For example, the target area may be a circular area having the vehicle to be evaluated as a center and a preset distance in a preset range as a radius; for another example, the target area may be an area within a preset distance from a preset range of the driving direction of the vehicle to be evaluated. The target area may be a geographical area around a preset range from the vehicle to be evaluated according to a preset rule, and is not limited to a specific manner of dividing the target area.

The traffic environment data for the target area is indicative of current traffic environment conditions within the target area, which may be comprised of one or more parameters.

For example, the traffic environment data may be a traffic flow parameter, wherein the traffic flow parameter is used to indicate a congestion level of the target area. The traffic flow parameter may indicate a current traffic environment condition within the target area.

For another example, the traffic environment data may also be a traffic control signal, wherein the traffic control signal is an indication signal such as a green light, a red light, or a yellow light for directing traffic. The traffic control signals may indicate current traffic environment conditions within the target area.

For another example, the traffic environment data may also be driving condition parameters, where the driving condition parameters are weather conditions, and the driving condition parameters include various weather parameters such as daytime rain, nighttime rain, daytime sunny day, or nighttime sunny day. The driving condition parameter may be indicative of a current traffic environment condition within the target area.

For another example, the traffic environment data may further include data such as a traffic flow parameter, a traffic control signal, and a driving condition parameter, and the current traffic environment condition in the target area is indicated together with the data such as the traffic flow parameter, the traffic control signal, and the driving condition parameter.

The historical traffic accident data of the target area is related information of traffic accidents occurring in the target area in historical time periods. For example, the historical traffic accident data of the target area may be traffic environment data of the target area at each accident occurrence within 1 year, wherein the traffic environment data may include traffic flow parameters, traffic control signals, driving condition parameters and the like.

And step S12, determining a dynamic risk coefficient according to the first running data of the vehicle to be evaluated and the second running data of the moving target, wherein the dynamic risk coefficient is used for indicating the possibility of collision between the vehicle to be evaluated and the moving target.

After the first driving data of the vehicle to be evaluated and the second driving data of the moving target are obtained, the dynamic risk coefficient can be determined according to the first driving data and the second driving data, so that the possibility of collision between the vehicle to be evaluated and the moving target is determined.

Since there are various ways of determining the dynamic risk factor based on the first travel data of the vehicle to be evaluated and the second travel data of the moving object, the following description will be given in detail by way of example.

And step S13, determining a semi-dynamic risk coefficient according to the traffic environment data, wherein the semi-dynamic risk coefficient is used for indicating the possibility of traffic accidents in the target area under the current traffic environment condition.

After the traffic environment data of the target area is acquired, the semi-dynamic risk coefficient can be determined according to the traffic environment data so as to determine the possibility of traffic accidents occurring in the target area under the current traffic environment condition.

Since there are many ways to determine the semi-dynamic risk factor based on traffic environment data, it will be described in detail later by embodiments.

And step S14, determining a static risk coefficient according to the historical traffic accident data and the traffic environment data, wherein the static risk coefficient is used for indicating the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area.

After the traffic environment data of the target area and the historical traffic accident data of the target area are obtained, the static risk coefficient can be determined according to the historical traffic accident data and the traffic environment data, so that the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area is determined.

Since there are many ways to determine the static risk factor based on historical traffic accident data and traffic environment data, it will be described in detail later by embodiments.

And S15, fusing the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient to obtain a comprehensive risk coefficient.

After the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient are calculated, the possibility that a vehicle to be evaluated collides with a moving target, the possibility that a traffic accident occurs in a target area under the current traffic environment condition and the possibility that the traffic accident occurs in the target area historically under the current traffic environment condition are determined, so that the three possibilities of the traffic accident are fused, a relatively objective comprehensive risk coefficient is obtained through the fusion of the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient, and the comprehensive risk coefficient is used for representing the possibility that the vehicle to be evaluated has the traffic accident in the target area.

And step S16, determining the traffic risk level of the current vehicle to be evaluated in the target area according to the comprehensive risk coefficient.

In order to enable a driver to understand the possibility of traffic accidents of the vehicle to be evaluated in the target area more visually, different traffic risk levels can be divided into the comprehensive risk coefficients in advance, and the traffic risk level corresponding to the current comprehensive risk coefficient of the vehicle to be evaluated is determined, so that the driver can take corresponding measures according to the traffic risk levels.

For example, please refer to table 1, which is a table of correspondence between pre-established comprehensive risk coefficients and traffic risk levels shown in table 1. After the comprehensive risk coefficient is determined, the traffic risk level corresponding to the comprehensive risk coefficient can be determined through the corresponding relation table of the comprehensive risk coefficient and the traffic risk level in table 1.

Referring to table 1, it is assumed that when the traffic risk level is level 1, the risk indicating that a traffic accident occurs to the vehicle to be evaluated is extremely low; when the traffic risk level is level 2, the traffic risk level indicates that the risk of the traffic accident of the vehicle to be evaluated is low; when the traffic risk level is 3, the general risk of the traffic accident of the vehicle to be evaluated is shown; when the traffic risk level is level 4, the traffic risk level indicates that the traffic accident risk of the vehicle to be evaluated is higher; and when the traffic risk grade is 5 grade, the traffic risk grade indicates that the traffic accident risk of the vehicle to be evaluated is extremely high. Assuming that the current comprehensive risk coefficient of the vehicle to be evaluated is calculated to be 1.5, the traffic risk grade corresponding to the comprehensive risk coefficient 1.5 can be determined to be grade 2 according to the corresponding relation of the table 1, which indicates that the risk of the vehicle to be evaluated generating traffic accidents is lower.

Comprehensive risk factor	Traffic risk rating
		(0，1]	Level 1
(1，2]	Stage 2
		(2，3]	Grade 3
(3，4]	4 stage
		(4，5]	Grade 5

TABLE 1

Of course, after the traffic risk level is determined according to the comprehensive risk coefficient, the traffic risk level may be output through a display device or a voice device, etc. For example, the current traffic risk level may be displayed by a display to be visible to the driver; as another example, the current traffic risk level may also be broadcast through a speaker to be heard by the driver. In addition, there are many ways to output the traffic risk level, and the traffic risk level is not limited to be output by a display device or a voice device, but may be output by other ways.

In the embodiment shown in fig. 1, the dynamic risk coefficient is determined according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target to determine the possibility of collision between the vehicle to be evaluated and the moving target, the semi-dynamic risk coefficient is determined according to the traffic environment data to determine the possibility of traffic accidents occurring in the target area under the current traffic environment condition, and the static risk coefficient is determined according to the historical traffic accident data and the traffic environment data to determine the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area. After the three risk coefficients are obtained, determining a comprehensive risk coefficient according to the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient, and determining the traffic risk level of the current vehicle to be evaluated in the target area according to the comprehensive risk coefficient. Therefore, the traffic risk grade is determined based on the complex variability of the intersection condition and by combining various factors influencing the intersection risk, so that the traffic risk grade can be accurately and effectively prompted to the driver, and the traffic accident is avoided.

In addition, optionally, after step S11, before step S12, the method shown in fig. 1 may further include the steps of: firstly, determining a first distance required by a vehicle to be evaluated to reach a front stop position according to first running data of the vehicle to be evaluated; next, when the first distance is smaller than the safety distance, step S12 is performed.

After the first running data of the vehicle to be evaluated, a first distance required by the vehicle to be evaluated to reach a front stopping position can be determined according to the first running data of the vehicle to be evaluated, and the front stopping position is a stopping position indicated by a first traffic stopping line in front of the vehicle to be evaluated in the target area. When the first distance is less than the safety distance, which indicates that the vehicle to be evaluated is relatively close to the front stop position, and the front stop position is usually the position of the intersection, so that the possibility of a traffic accident is high, and it is necessary to start evaluating whether the target area has a high driving risk, steps S12 to S16 are performed to determine the traffic risk level and provide the level to the driver.

Since there are various ways to determine the first distance required for the vehicle to be evaluated to reach the forward stopping position based on the first travel data of the vehicle to be evaluated, two ways are briefly described below.

First, determining a first distance between the vehicle under evaluation and the forward stop line may include the steps of: the method comprises the steps that first position information of a vehicle to be evaluated is obtained according to first driving data of the vehicle to be evaluated; a second step of determining second position information of the front stop position on the map based on the first position information; and thirdly, calculating a first distance between the vehicle to be evaluated and the front stop position according to the first position information and the second position information.

In the first mode, since the first travel data of the vehicle to be evaluated may include the positioning information of the vehicle to be evaluated, the travel speed of the vehicle to be evaluated, the travel direction of the vehicle to be evaluated, and the like, the first position information of the vehicle to be evaluated may be obtained according to the first travel data of the vehicle to be evaluated. The first position information may be a GPS (Global Positioning System) signal of the vehicle to be evaluated. After the GPS signal of the vehicle to be evaluated is obtained, the position of the vehicle to be evaluated on the map can be obtained, so that second position information of the front stop position of the vehicle to be evaluated can be obtained, and the second position information of the front stop position is the GPS signal of the front stop position. Then, a first distance between the vehicle to be evaluated and the front stop position can be calculated according to the GPS signal of the vehicle to be evaluated and the GPS signal of the front stop position.

For example, suppose that the first position information of the vehicle to be evaluated is { x, 0, 0} obtained according to the first running data of the vehicle to be evaluated, an ENU coordinate system is adopted, and the vehicle to be evaluated is assumed to run at a constant speed from a south line to a north line; then, second position information of the front stop position is determined to be { x, 100, 0} on the map according to the first position information { x, 0, 0 }; and finally, calculating the first distance between the vehicle to be evaluated and the front stop position to be 100 meters according to the first position information { x, 0, 0} of the vehicle to be evaluated and the second position information { x, 100, 0} of the front stop position.

Second, determining a first distance between the vehicle under evaluation and the forward stop line may include the steps of: the method comprises the steps of firstly, acquiring a second distance between a front stop position and a rear stop position by using a map; secondly, determining a third distance between the vehicle to be evaluated and a rear stop position according to the first running data of the vehicle to be evaluated, wherein the rear stop position is a stop position indicated by a first traffic stop line behind the vehicle to be evaluated in the target area; and thirdly, determining a first distance between the vehicle to be evaluated and the front stop position according to the second distance and the third distance.

In the second mode, first, the second distance between the front stop position and the rear stop position can be directly acquired by the map. Then, after the vehicle to be evaluated passes through the rear stopping position, the first time used by the vehicle to be evaluated needs to be recorded, and the first running data of the vehicle to be evaluated contains the running speed of the vehicle to be evaluated, so that the third distance between the rear stopping position and the vehicle to be evaluated can be calculated according to the first time and the running speed of the vehicle to be evaluated. And finally, calculating the difference between the second distance and the third distance to obtain the first distance between the vehicle to be evaluated and the front stop line.

For example, it is assumed that the second distance between the front stop position and the rear stop position is 10 km, which can be directly obtained through the map. Then, after the vehicle to be evaluated passes through the rear stopping position, the first time used by the vehicle to be evaluated needs to be recorded to be 6 minutes, namely the first time is 0.1 hour, and the first running data of the vehicle to be evaluated contains the running speed of the vehicle to be evaluated 60 km/h, so that the third distance between the rear stopping position and the vehicle to be evaluated can be calculated to be 6 km according to the first time of 0.1 hour and the running speed of the vehicle to be evaluated 60 km/h. And finally, calculating the difference between the second distance of 10 kilometers and the third distance of 6 kilometers to obtain that the first distance between the vehicle to be evaluated and the front stop line is 4 kilometers.

Referring to fig. 2, the embodiment shown in fig. 2 is an embodiment refined based on step S12 in fig. 1, so the same contents as those in fig. 1 can be referred to the embodiment shown in fig. 1. The method shown in fig. 2 is a specific implementation manner of "determining a dynamic risk coefficient according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target" in step S12 of fig. 1, where "determining a dynamic risk coefficient according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target" may further include the following steps.

And step S21, calculating the remaining time of the collision between the vehicle to be evaluated and the moving target according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target.

The first driving data of the vehicle to be evaluated can be positioning information of the vehicle to be evaluated, driving speed of the vehicle to be evaluated, driving direction of the vehicle to be evaluated and the like. The second traveling data of the moving object may be positioning information of the moving object, a traveling speed of the moving object, a traveling direction of the moving object, and the like.

After the first driving data of the vehicle to be evaluated and the second driving data of the moving target are obtained, the motion trail of the vehicle to be evaluated and the moving target in a future period can be estimated. And according to the estimated motion trail, the residual time of the collision between the vehicle to be evaluated and the moving target can be calculated. The less the remaining time of the collision between the vehicle to be evaluated and the moving target, the higher the possibility of the collision between the vehicle to be evaluated and the moving target in a period of time in the future, the greater the dynamic risk, and the greater the dynamic risk coefficient; the more the remaining time of the collision between the vehicle to be evaluated and the moving target, the smaller the possibility of the collision between the vehicle to be evaluated and the moving target in a future period of time, the smaller the dynamic risk, and the smaller the dynamic risk coefficient.

Of course, if there is a vehicle with a large driving risk, such as a motorcycle, among the moving objects, it is necessary to multiply a risk adjustment coefficient by the remaining time of collision of the vehicle to be evaluated with the moving object to obtain a new remaining time. The risk adjustment coefficient is selected from the range of 0 to 1, the greater the risk of the target vehicle is, the smaller the risk adjustment coefficient is, and the smaller the new remaining time after calculation is; the smaller the risk of the target vehicle is, the larger the risk adjustment factor is, and the larger the new remaining time after calculation is.

And step S22, calculating the brake advance time according to the remaining time and the preset brake reaction time.

The preset brake reaction time refers to the minimum reaction time reserved for the driver to avoid collision. For example, the braking response time may be set to 2 seconds in advance.

The early braking time is the time that the driver needs to brake in advance in order to avoid collision, and the early braking time is the difference between the remaining time and the braking reaction time. The smaller the braking time in advance is, the higher the possibility that the vehicle to be evaluated collides with the moving target in a period of time in the future is, the greater the dynamic risk is, and the greater the dynamic risk coefficient is; the more the braking time is advanced, the smaller the possibility that the vehicle to be evaluated collides with the moving target in a future period is, the smaller the dynamic risk is, and the smaller the dynamic risk coefficient is.

Step S23, determining a dynamic risk coefficient corresponding to the early braking time according to a preset first preset rule, where the first preset rule is used to indicate a corresponding relationship between the early braking time and the dynamic risk coefficient.

After the early braking time is calculated, the dynamic risk coefficient corresponding to the early braking time can be determined according to a preset first preset rule.

For example, please refer to table 2, which is a table showing the correspondence between the braking time in advance and the dynamic risk coefficient in table 2. Assuming that the early braking time is 0-3 seconds, the probability that the vehicle to be evaluated collides with the moving target in a future period is highest, and the dynamic risk is maximum, so that the dynamic risk coefficient is 5; when the early braking time is 3-4 seconds, the probability of collision between the vehicle to be evaluated and the moving target in a future period is high, the dynamic risk is high, and therefore the dynamic risk coefficient is 4; when the early braking time is 4-5 seconds, the possibility that the vehicle to be evaluated collides with the moving target in a period of time in the future is general, the dynamic risk is general, and therefore the dynamic risk coefficient is 3; when the early braking time is 5 to 6 seconds, the possibility that the vehicle to be evaluated collides with the moving target in a future period is low, and the dynamic risk is low, so the dynamic risk coefficient is 2; when the braking time is 6 to 10 seconds in advance, the possibility that the vehicle to be evaluated collides with the moving target in a future period is the lowest, the dynamic risk is the minimum, and therefore the dynamic risk coefficient is 1. Assuming that the braking advance time is calculated to be 3.5 seconds, the dynamic risk coefficient corresponding to the braking advance time of 3.5 can be determined to be 4 according to the corresponding relation of the table 2, which indicates that the possibility of collision between the vehicle to be evaluated and the moving target in a future period of time is high, and therefore, the driver needs to be prompted to pay attention to safety.

Brake time in advance (unit: second)	Dynamic risk factor
		(0，3]	5
(3，4]	4
		(4，5]	3
(5，6]	2
		(6，10]	1

TABLE 2

In the embodiment shown in fig. 2, the dynamic risk coefficient is determined according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target, so that how high the possibility of collision between the vehicle to be evaluated and the moving target can be determined, and a dynamic possibility of accidents is provided for calculating the comprehensive risk coefficient.

Referring to fig. 3, the embodiment shown in fig. 3 is an embodiment refined based on step S13 in fig. 1, so the same contents as those in fig. 1 can be referred to the embodiment shown in fig. 1. The method shown in fig. 3 is a specific implementation of "determining a semi-dynamic risk coefficient according to traffic environment data" in step S13 of fig. 1, wherein "determining a semi-dynamic risk coefficient according to traffic environment data" may further include the following steps.

And step S31, calculating a semi-dynamic risk initial coefficient according to the time when the vehicle to be evaluated runs to a front stop position, wherein the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in the target area.

In the following, briefly described, how to calculate the initial semi-dynamic risk factor according to the time of the vehicle to be evaluated traveling to the front stop position.

For example, it is assumed that the time during which the vehicle to be evaluated travels to the front stop position is the first time. Assuming that the first time is 5 seconds and the inverse of the first time is 1/5, the greater the inverse of the first time, the faster the vehicle under evaluation reaches the front stop position, and the smaller the inverse of the first time, the slower the vehicle under evaluation reaches the front stop position.

A constraint range [ A, B ] is set so that the reciprocal of the first time falls within the constraint range [ A, B ]. Setting a constraint range [ A, B ] as [0.05,0.5], wherein B is 0.5 and 1/2, corresponding to the lowest collision response time of 2 seconds, and B represents the meaning that the vehicle to be evaluated reaches the maximum risk of non-normalization of the stop line and is used for maximum protection; and a is 0.05 and 1/20, corresponds to a collision response time of 20 seconds and is mainly used for minimum protection. Finally, the semi-dynamic risk initial coefficient (the inverse of the first time × the control coefficient)/B ═ (1/5 × 0.6)/0.5 ═ 0.24, where the control coefficient is used to control the initial value of the semi-dynamic risk coefficient.

Step S32, determining a compensation coefficient corresponding to the traffic environment data according to a preset second preset rule, where the second preset rule is used to indicate a correspondence between the traffic environment data and the compensation coefficient.

The traffic environment data may be one of a traffic flow parameter of the target area, a traffic control signal of the target area, or a driving condition parameter of the target area. The traffic environment data may also include traffic flow parameters for the target zone, traffic control signals for the target zone, and driving condition parameters for the target zone. The following briefly describes embodiments when the traffic environment data are different parameters.

In the first case, when the traffic environment data is the traffic flow parameter of the target area, the second preset rule is used for indicating the corresponding relationship between the traffic flow parameter and the compensation coefficient. At this time, a compensation coefficient corresponding to the traffic flow parameter may be determined according to a second preset rule, the compensation coefficient being used to indicate a congestion degree of the target area. The higher the traffic flow parameter indicates the congestion degree of the target area, the greater the driving risk is, and the higher the compensation coefficient is; the lower the traffic flow parameter indicates that the congestion degree of the target area is lower, indicating that the driving risk is smaller, the lower the compensation coefficient is.

For example, please refer to table 3, which shows a table of correspondence between traffic flow parameters and compensation coefficients in table 3. Wherein, assuming that when the traffic flow parameter is normal, the driving risk is minimum, so the compensation coefficient is also minimum, and the compensation coefficient is 0.05; when the traffic flow parameter is light congestion, the driving risk is small, so that the compensation coefficient is also small and is 0.1; when the traffic flow parameter is heavily congested, the driving risk is high, so that the compensation coefficient is also high and is 0.02; when the traffic flow parameter is traffic paralysis, the driving risk is the greatest, so the compensation coefficient is also the greatest, and the compensation coefficient is 0.3. Assuming that the traffic flow parameter in the target area is heavy congestion, the compensation coefficient corresponding to heavy congestion may be determined to be 0.2 according to the correspondence relationship in table 3, which indicates that the driving risk is large.

Traffic flow parameters	Compensation factor
		Is normal	0.05
Light congestion	0.1
		Severe congestion	0.2
Traffic paralysis	0.3

TABLE 3

In the second case, when the traffic environment data is the traffic control signal of the target area, then the second preset rule is used to indicate the correspondence between the traffic control signal and the compensation coefficient. At this time, a compensation coefficient corresponding to the traffic control signal may be determined according to a second preset rule, and the compensation coefficient is used for indicating an indication signal such as a green light, a red light, or a yellow light for directing traffic. When the traffic control signal is a red light, the driving risk is maximum, and the compensation coefficient is also highest; when the traffic control signal is a yellow light, the driving risk is moderate, and the compensation coefficient is moderate; when the traffic control signal is green, the driving risk is minimum, and the compensation coefficient is also minimum.

For example, please refer to table 4, which shows a table of correspondence between traffic control signals and compensation coefficients in table 4. Wherein, assuming that the driving risk is the largest when the traffic control signal is red, the compensation coefficient is the highest, namely the compensation coefficient is 0.6; when the traffic control signal is a yellow light, the driving risk is high, and the compensation coefficient is high, namely the compensation coefficient is 0.5; when the traffic control signal is green, it indicates that the driving risk is minimum, and the compensation coefficient is also the lowest, i.e. the compensation coefficient is 0.1. Assuming that the traffic control signal in the target area is yellow light, the compensation factor corresponding to the yellow light may be determined to be 0.5 according to the correspondence of table 4, indicating that the driving risk is high.

Traffic control signal	Compensation factor
		Green lamp	0.1
Yellow light	0.5
		Red light	0.6

TABLE 4

In a third case, when the traffic environment data is the driving condition parameter of the target area, the second preset rule is used for indicating the corresponding relation between the driving condition parameter and the compensation coefficient. At this time, a compensation coefficient corresponding to the driving condition parameter may be determined according to a second preset rule, and the compensation coefficient is used to indicate various weather parameters such as daytime rainfall, nighttime rainfall, sunny day or nighttime sunny day. When the driving condition parameter is rainy at night, the driving risk is maximum, and the compensation coefficient is also highest; when the driving condition parameter is rainy in the daytime, the driving risk is high, and the compensation coefficient is high; when the driving condition parameters are in sunny days at night, the driving risk is low, and the compensation coefficient is low; when the driving condition parameters are in sunny days in the daytime, the driving risk is minimum, and the compensation coefficient is also minimum.

For example, please refer to table 5, which is a table showing the corresponding relationship between the driving condition parameters and the compensation coefficients in table 5. Wherein, assuming that when the driving condition parameter is rainy at night, the driving risk is maximum, and the compensation coefficient is also the highest, namely the compensation coefficient is 0.8; when the driving condition parameter is rainy in the daytime, the driving risk is large, and the compensation coefficient is high, namely the compensation coefficient is 0.5; when the driving condition parameter is clear at night, the driving risk is low, and the compensation coefficient is low, namely the compensation coefficient is 0.3; when the driving condition parameter is in a sunny day, the driving risk is minimum, the compensation coefficient is also minimum, and the compensation coefficient is 0.1. Assuming that the driving condition parameter in the target area is rainy at night, the compensation coefficient corresponding to the rainy at night can be determined to be 0.8 according to the correspondence of table 5, which indicates that the driving risk is the greatest.

Parameters of driving conditions	Compensation factor
		Sunny day	0.1
Clear day at night	0.3
		Rainy day	0.5
Raining at night	0.8

TABLE 5

In a fourth case, when the traffic environment data includes a traffic flow parameter of the target area, a traffic control signal of the target area, and a driving condition parameter of the target area, determining the compensation coefficient corresponding to the traffic environment data according to a preset second preset rule may include the following steps: determining a first compensation coefficient corresponding to the traffic flow parameter of the target area according to a preset third preset rule, wherein the third preset rule is used for indicating the corresponding relation between the traffic flow parameter and the first compensation coefficient; determining a second compensation coefficient corresponding to the traffic control signal according to a preset fourth preset rule, wherein the fourth preset rule is used for indicating the corresponding relation between the traffic control signal and the second compensation coefficient; determining a third compensation coefficient corresponding to the driving condition parameter according to a preset fifth preset rule, wherein the fifth preset rule is used for indicating the corresponding relation between the driving condition parameter and the third compensation coefficient; and determining a compensation coefficient according to the first compensation coefficient, the second compensation coefficient and the third compensation coefficient.

In the fourth case, the traffic environment data includes three kinds of parameters, which are different from the aforementioned three cases, and the traffic environment data of the aforementioned three cases is only one kind of parameter. In a fourth case, according to a preset third preset rule, the process of determining the first compensation coefficient corresponding to the traffic flow parameter of the target area may refer to the first case; according to a preset fourth preset rule, the process of determining the second compensation coefficient corresponding to the traffic control signal can be referred to the second case; the process of determining the third compensation coefficient corresponding to the driving condition parameter according to the preset fifth preset rule may refer to the third case.

How to determine the compensation coefficient based on the first compensation coefficient, the second compensation coefficient, and the third compensation coefficient in the fourth case is explained below by way of example.

For example, if it is assumed that the first compensation coefficient corresponding to the traffic flow parameter of the target area is determined to be 0.05 according to a third preset rule, the second compensation coefficient digit 0.1 corresponding to the traffic control signal is determined according to a fourth preset rule, and the third compensation coefficient digit 0.1 corresponding to the driving condition parameter is determined according to a fifth preset rule, the compensation coefficient is (1+ first compensation coefficient) × (1+ second compensation coefficient) × (1+ third compensation coefficient) × (1+0.05) × (1+0.1) × (1+0.1) ═ 1.27.

And step S33, calculating the semi-dynamic risk coefficient according to the semi-dynamic risk initial coefficient and the compensation coefficient.

After the semi-dynamic risk initial coefficient and the compensation coefficient are obtained, the semi-dynamic risk coefficient can be calculated according to the semi-dynamic risk initial coefficient and the compensation coefficient. Since there are many ways to calculate a semi-dynamic risk factor, one way is briefly described below.

Firstly, calculating a non-normalized semi-dynamic risk coefficient according to the semi-dynamic risk initial coefficient and the compensation coefficient.

For example, as shown in table 3, it is assumed that the semi-dynamic risk initial coefficient is 0.24, the traffic environment data is a traffic flow parameter of the target area, and the traffic flow parameter is light congestion, so that the compensation coefficient corresponding to the light congestion is 0.1. In table 3, the maximum value of the compensation coefficient is 0.3. Then the unnormalized semi-dynamic risk factor x (1+ offset factor) is 0.24 x (1+0.1) is 0.264.

And secondly, calculating the maximum value of the semi-dynamic coefficient according to the preset control coefficient and the maximum value of the compensation coefficient.

For example, as shown in table 3, it is assumed that the control coefficient is set to 0.6 in advance, the semi-dynamic risk initial coefficient is 0.24, the traffic environment data is a traffic flow parameter of the target area, and the traffic flow parameter is light congestion, so that the compensation coefficient corresponding to the light congestion is 0.1. In table 3, the maximum value of the compensation coefficient is 0.3. Then the maximum value of the semi-dynamic coefficient is 0.6 × (1+0.3) × (0.78) for the control coefficient × (1+ maximum value of the compensation coefficient).

And finally, calculating the semi-dynamic risk coefficient according to the non-normalized semi-dynamic risk coefficient and the maximum value of the semi-dynamic coefficient.

For example, assume that the non-normalized semi-dynamic risk factor is 0.264 and the maximum value of the semi-dynamic factor is 0.78. The half-dynamic risk factor is then the non-normalized half-dynamic risk factor/maximum extremum of the half-dynamic factor 0.264/0.78/0.338.

In the embodiment shown in fig. 3, the semi-dynamic risk coefficient is determined according to the traffic environment data, so that the possibility of the traffic accident occurring in the target area under the current traffic environment condition can be determined, and thus, the possibility of the traffic accident occurring in the semi-dynamic aspect is provided for calculating the comprehensive risk coefficient.

Referring to fig. 4, the embodiment shown in fig. 4 is an embodiment refined based on step S14 in fig. 1, so the same contents as those in fig. 1 can be referred to the embodiment shown in fig. 1. The method shown in fig. 4 is a specific implementation of "determining a static risk coefficient according to historical traffic accident data and traffic environment data" in step S14 of fig. 1, wherein "determining a static risk coefficient according to historical traffic accident data and traffic environment data" may further include the following steps.

And step S41, determining a sixth preset rule in the historical traffic accident data, wherein the sixth preset rule is used for indicating the corresponding relation between the traffic environment data and the accident occurrence probability.

The historical traffic accident data of the target area is related information of traffic accidents occurring in the target area in historical time periods. The traffic environment data may be one of a traffic flow parameter, a traffic control signal, and a driving condition parameter, and the traffic environment data may also include data such as the traffic flow parameter, the traffic control signal, and the driving condition parameter.

There are many ways to determine the sixth preset rule in the historical traffic accident data, and one way is briefly described below: firstly, acquiring the total number of accidents in historical traffic accident data; then, determining the number of accidents corresponding to each traffic environment data in historical traffic accident data; secondly, calculating the accident occurrence probability corresponding to each kind of traffic environment data according to the number of accidents corresponding to each kind of traffic environment data and the total number of accidents; and finally, determining the corresponding relation between the traffic environment data and the accident occurrence probability as a sixth preset rule.

How to determine the sixth preset rule in the historical traffic accident data, the sixth preset rule being used for indicating the correspondence relationship between the traffic environment data and the accident occurrence probability, is explained by way of example below. For simplicity of description, the traffic environment data is assumed as the driving condition parameter.

For example, assume that the historical traffic accident data is accident information of a target area over the past year. The historical traffic accident data comprises the total number of accidents and the number of accidents occurring in each driving condition parameter. Assuming that the total number of accidents is 100, when the driving condition parameter is rainy at night, the number of accidents is 40; when the driving condition parameters are rainy in the daytime, the number of accidents is 30; when the driving condition parameters are at night on sunny days, the number of accidents is 20; when the driving condition parameters are in fine days in the daytime, the number of accidents is 10. Then the probability of an accident occurring in the target area in rainy nights is 40/100 ═ 0.4, the probability of an accident occurring in rainy nights in the target area in daytime is 30/100 ═ 0.3, the probability of an accident occurring in the target area in sunny nights is 20/100 ═ 0.2, and the probability of an accident occurring in the target area in sunny days is 10/100 ═ 0.1. Based on the above-mentioned corresponding relationship between the driving condition parameters and the accident occurrence probability in 4, please refer to table 6, where the corresponding relationship between the driving condition parameters and the accident occurrence probability shown in table 6 is a sixth preset rule.

Parameters of driving conditions	Probability of occurrence of accident
		Sunny day	0.1
Clear day at night	0.2
		Rainy day	0.3
Raining at night	0.4

TABLE 6

And step S42, determining the accident occurrence probability corresponding to the traffic environment data according to a sixth preset rule.

After the sixth preset rule is determined in the historical traffic accident data, namely the corresponding relation between the traffic environment data and the accident occurrence probability is determined, the accident occurrence probability corresponding to the current traffic environment data can be determined based on the corresponding relation between the traffic environment data and the accident occurrence probability.

Referring to table 6, if the traffic environment data is the driving condition parameter and the current driving condition parameter is daytime rain, the accident occurrence probability corresponding to the current driving condition parameter is 0.3.

And step S43, determining a static risk coefficient corresponding to the accident occurrence probability according to a preset seventh preset rule, wherein the seventh preset rule is used for indicating the corresponding relation between the accident occurrence probability and the static risk coefficient.

After the accident occurrence probability corresponding to the traffic environment data is determined, the static risk coefficient corresponding to the accident occurrence probability can be determined according to a seventh preset rule set in advance.

For example, please refer to table 7, which shows a table of correspondence between accident occurrence probability and static risk coefficient in table 7. Wherein, when the accident occurrence probability is between 0 and 0.2, the driving risk is minimum, and the static risk coefficient is also minimum, namely the static risk coefficient is 1; when the accident occurrence probability is between 0.2 and 0.4, the driving risk is small, and the static risk coefficient is small, namely the static risk coefficient is 2; when the accident occurrence probability is between 0.4 and 0.6, the driving risk is moderate, and the static risk coefficient is moderate, namely the static risk coefficient is 3; when the accident occurrence probability is between 0.6 and 0.8, the driving risk is high, and the static risk coefficient is also high, namely the static risk coefficient is 4; when the accident occurrence probability is between 0.8 and 1, the driving risk is maximum, and the static risk coefficient is also maximum, namely the static risk coefficient is 5. Assuming that the accident occurrence probability corresponding to the current traffic environment data is 0.5, the static risk coefficient corresponding to the accident occurrence probability of 0.5 can be determined to be 3 according to the corresponding relationship of table 7, which indicates that the driving risk is moderate.

Probability of occurrence of accident	Static risk factor
		(0，0.2]	1
(0.2，0.4]	2
		(0.4，0.6]	3
(0.6，0.8]	4
		(0.8，1]	5

TABLE 7

In the embodiment shown in fig. 4, the static risk coefficient is determined according to the historical traffic accident data and the traffic environment data, and the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area can be determined, so that a static possibility of the occurrence of the accidents is provided for calculating the comprehensive risk coefficient.

Referring to fig. 5, the embodiment shown in fig. 5 is an embodiment refined based on step S15 in fig. 1, so the same contents as those in fig. 1 can be referred to the embodiment shown in fig. 1. The method shown in fig. 5 is a specific implementation manner of "fusing the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient to obtain the comprehensive risk coefficient" in step S15 of fig. 1, where "fusing the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient to obtain the comprehensive risk coefficient" may further include the following steps.

And step S51, acquiring the working condition characteristics of the target area.

The operating condition characteristics of the target area comprise traffic order, natural conditions and historical accidents, dynamic risk weight can be set based on the traffic order, semi-dynamic risk weight can be set based on the natural conditions, and static risk weight can be set based on the historical accidents. The purpose of determining the dynamic risk weight, the semi-dynamic risk weight and the static risk weight is to judge how much the effect of the coefficients in the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient is according to the working condition characteristics. Judging that the larger the effect of the coefficient is according to the working condition characteristics, the larger the weight corresponding to the coefficient is; the smaller the function of the coefficient is judged according to the working condition characteristics, the smaller the weight corresponding to the coefficient is.

The two attributes of the traffic order are to comply with the traffic order and not comply with the traffic order, and the traffic order can be acquired through a camera in a target area. The two attributes of the natural condition are normal and difficult, the natural condition is a weather condition, and the natural condition can be acquired through a meteorological server. The two attributes of the historical accident are higher than a threshold value and lower than the threshold value, and the historical accident can be acquired through a traffic server.

Step S52, determining a risk coefficient weight corresponding to the operating condition characteristic of the target area according to a preset eighth preset rule, where the eighth preset rule is used to indicate a corresponding relationship between the operating condition characteristic and the risk coefficient weight.

The eighth preset rule is preset and used for indicating the corresponding relation between the working condition characteristics and the risk coefficient weight. The risk coefficient weights include dynamic risk weights, semi-dynamic risk weights, and static risk weights.

For example, please refer to table 8, where table 8 shows an eighth preset rule, that is, a table of correspondence between the operating condition characteristics and the risk coefficient weights.

TABLE 8

For example, please refer to table 8, it is assumed that the operating condition characteristics include a traffic order, a natural condition and a historical accident, wherein the traffic order of the target area is obeyed with the traffic order, the natural condition is normal, and the number of the historical accidents is lower than a threshold value. Since the number of historical accidents is lower than the threshold, the static risk weight may be configured to be lower, and the dynamic risk weight and the semi-dynamic risk weight may be configured to be higher, that is, the dynamic risk weight is set to 0.4, the semi-dynamic risk weight is set to 0.5, and the static risk weight is set to 0.1.

For another example, please refer to table 8, assume that the operating condition characteristics include a traffic order, a natural condition and a historical accident, wherein the traffic order of the target area is not obeyed by the traffic order, the natural condition is normal, and the number of the historical accidents is lower than a threshold. Since the traffic order is not in compliance with traffic, the dynamic risk weight can be configured to be higher, and the semi-dynamic risk weight and the static risk weight can be configured to be lower, that is, the dynamic risk weight is set to 0.6, the semi-dynamic risk weight is set to 0.3, and the static risk weight is set to 0.1.

For another example, please refer to table 8, it is assumed that the operating condition characteristics include a traffic order, a natural condition and a historical accident, wherein the traffic order of the target area is not followed by the traffic order, the natural condition is normal, and the number of the historical accidents cannot be obtained. Since the number of historical accidents cannot be obtained, only the dynamic risk weight and the semi-dynamic risk weight need to be configured, that is, the dynamic risk weight is set to 0.5, the semi-dynamic risk weight is set to 0.5, and the static risk weight is not set.

And step S53, calculating a comprehensive risk coefficient according to the dynamic risk coefficient, the dynamic risk weight, the semi-dynamic risk coefficient, the semi-dynamic risk weight, the static risk coefficient and the static risk weight.

After the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient are obtained, the risk coefficient weight is obtained, namely the dynamic risk weight, the semi-dynamic risk weight and the static risk weight are obtained, so that the comprehensive risk coefficient can be calculated according to the dynamic risk coefficient, the dynamic risk weight, the semi-dynamic risk coefficient, the semi-dynamic risk weight, the static risk coefficient and the static risk weight.

Since there are many ways to calculate the composite risk factor, one way is provided below: the integrated risk coefficient is the dynamic risk coefficient x the dynamic risk weight + the semi-dynamic risk coefficient x the semi-dynamic risk weight + the static risk coefficient x the static risk weight.

In the embodiment shown in fig. 5, a comprehensive risk coefficient may be calculated according to the dynamic risk coefficient, the importance degree of the dynamic risk coefficient, the semi-dynamic risk coefficient, the importance degree of the semi-dynamic risk coefficient, the static risk coefficient, and the importance degree of the static risk coefficient, so as to obtain the possibility that the vehicle to be evaluated has a traffic accident in the target area.

Fig. 6 is a schematic view of a driving risk assessment device according to an embodiment of the present application. Fig. 6 is an embodiment of the apparatus corresponding to fig. 1, and the same contents in fig. 6 as those in fig. 1 may refer to the embodiment corresponding to fig. 1. Referring to fig. 6, the apparatus includes the following modules:

the system comprises an acquisition module 11, a storage module and a display module, wherein the acquisition module is used for acquiring first driving data of a vehicle to be evaluated, second driving data of a moving target, traffic environment data of a target area and historical traffic accident data of the target area, the moving target is an object in a moving state in the target area, the target area is an area away from the vehicle to be evaluated within a preset range, the traffic environment data is used for indicating the current traffic environment condition in the target area, the first driving data is driving parameters corresponding to the vehicle to be evaluated in the current driving process, and the second driving data is driving parameters corresponding to the moving target in the current driving process;

the first determining module 12 is configured to determine a dynamic risk coefficient according to first driving data of the vehicle to be evaluated and second driving data of the moving target, where the dynamic risk coefficient is used to indicate a possibility of collision between the vehicle to be evaluated and the moving target;

a second determining module 13, configured to determine a semi-dynamic risk coefficient according to the traffic environment data, where the semi-dynamic risk coefficient is used to indicate a possibility of a traffic accident occurring in the target area under the current traffic environment condition;

a third determining module 14, configured to determine a static risk coefficient according to the historical traffic accident data and the traffic environment data, where the static risk coefficient is used to indicate a proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area;

the fusion module 15 is configured to fuse the dynamic risk coefficient, the semi-dynamic risk coefficient, and the static risk coefficient to obtain a comprehensive risk coefficient;

and the fourth determining module 16 is configured to determine a traffic risk level of the current vehicle to be assessed in the target area according to the comprehensive risk coefficient.

Optionally, the first determining module 12 is specifically configured to calculate a remaining time of collision between the vehicle to be evaluated and the moving target according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target; calculating the brake advance time according to the remaining time and the preset brake reaction time; and determining a dynamic risk coefficient corresponding to the early braking time according to a preset first preset rule, wherein the first preset rule is used for indicating the corresponding relation between the early braking time and the dynamic risk coefficient.

Optionally, the second determining module 13 is specifically configured to calculate a semi-dynamic risk initial coefficient according to a time when the vehicle to be evaluated travels to a front stop position, where the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in the target area; determining a compensation coefficient corresponding to the traffic environment data according to a preset second preset rule, wherein the second preset rule is used for indicating the corresponding relation between the traffic environment data and the compensation coefficient; and calculating the semi-dynamic risk coefficient according to the semi-dynamic risk initial coefficient and the compensation coefficient.

Optionally, the second determining module 13 is specifically configured to determine, according to a preset third preset rule, a first compensation coefficient corresponding to the traffic flow parameter of the target area, where the third preset rule is used to indicate a correspondence between the traffic flow parameter and the first compensation coefficient; determining a second compensation coefficient corresponding to the traffic control signal according to a preset fourth preset rule, wherein the fourth preset rule is used for indicating the corresponding relation between the traffic control signal and the second compensation coefficient; determining a third compensation coefficient corresponding to the driving condition parameter according to a preset fifth preset rule, wherein the fifth preset rule is used for indicating the corresponding relation between the driving condition parameter and the third compensation coefficient; and determining a compensation coefficient according to the first compensation coefficient, the second compensation coefficient and the third compensation coefficient.

Optionally, the third determining module 14 is specifically configured to determine a sixth preset rule in the historical traffic accident data, where the sixth preset rule is used to indicate a correspondence between the traffic environment data and the accident occurrence probability; determining the accident occurrence probability corresponding to the traffic environment data according to a sixth preset rule; and determining a static risk coefficient corresponding to the accident occurrence probability according to a preset seventh preset rule, wherein the seventh preset rule is used for indicating the corresponding relation between the accident occurrence probability and the static risk coefficient.

Optionally, the fusion module 15 is specifically configured to obtain operating condition characteristics of the target area; determining a risk coefficient weight corresponding to the working condition characteristics of the target area according to a preset eighth preset rule, wherein the eighth preset rule is used for indicating the corresponding relation between the working condition characteristics and the risk coefficient weight, and the risk coefficient weight comprises a dynamic risk weight, a semi-dynamic risk weight and a static risk weight; and calculating the comprehensive risk coefficient according to the dynamic risk coefficient, the dynamic risk weight, the semi-dynamic risk coefficient, the semi-dynamic risk weight, the static risk coefficient and the static risk weight.

Optionally, the driving risk assessment device provided in the embodiment of the present application may further include the following modules: and the output module is used for outputting the traffic risk grade.

Fig. 7 is a schematic view of another driving risk assessment device according to an embodiment of the present application. Fig. 7 is an embodiment of the apparatus corresponding to fig. 1, and the same contents in fig. 7 as those in fig. 1 may refer to the embodiment corresponding to fig. 1. Referring to fig. 7, the apparatus includes the following modules:

the system comprises an acquisition module 21, a storage module and a display module, wherein the acquisition module is used for acquiring first driving data of a vehicle to be evaluated, second driving data of a moving target, traffic environment data of a target area and historical traffic accident data of the target area, the moving target is an object in a moving state in the target area, the target area is a surrounding geographical area of the vehicle to be evaluated, and the traffic environment data is used for indicating the current traffic environment condition in the target area;

the fifth determining module 22 is configured to determine, according to the first driving data of the vehicle to be evaluated, a first distance required for the vehicle to be evaluated to reach a front stopping position, where the front stopping position is a stopping position indicated by a first traffic stopping line in front of the vehicle to be evaluated in the target area;

the triggering module 23 is configured to trigger the first determining module 24 when the first distance is smaller than the safety distance;

the first determining module 24 is configured to determine a dynamic risk coefficient according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target, where the dynamic risk coefficient is used to indicate a possibility that the vehicle to be evaluated collides with the moving target;

a second determining module 25, configured to determine a semi-dynamic risk coefficient according to the traffic environment data, where the semi-dynamic risk coefficient is used to indicate a possibility of a traffic accident occurring in the target area under the current traffic environment condition;

a third determining module 26, configured to determine a static risk coefficient according to the historical traffic accident data and the traffic environment data, where the static risk coefficient is used to indicate a possibility that a traffic accident occurs in the target area historically under the current traffic environment condition;

a fusion module 27, configured to fuse the dynamic risk coefficient, the semi-dynamic risk coefficient, and the static risk coefficient to obtain a comprehensive risk coefficient;

and a fourth determining module 28, configured to determine a traffic risk level according to the comprehensive risk coefficient.

Optionally, the fifth determining module 22 is specifically configured to obtain first position information of the vehicle to be evaluated according to the first driving data of the vehicle to be evaluated; determining second position information of a front stop position on the map according to the first position information; and calculating a first distance between the vehicle to be evaluated and the front stop position according to the first position information and the second position information.

Optionally, the fifth determining module 22 is specifically configured to obtain a second distance between the front stop position and the rear stop position by using a map; determining a third distance between the vehicle to be evaluated and a rear stopping position according to the first running data of the vehicle to be evaluated, wherein the rear stopping position is a stopping position indicated by a first traffic stopping line behind the vehicle to be evaluated in the target area; and determining a first distance between the vehicle to be evaluated and the front stop position according to the second distance and the third distance.

Fig. 8 is a schematic view of another driving risk assessment device according to an embodiment of the present application. Fig. 8 is a view of the embodiment corresponding to fig. 1, and the same contents in fig. 8 as those in fig. 1 may refer to the embodiment corresponding to fig. 1. Referring to fig. 8, the apparatus includes a processor 31 and a memory 32, where the memory 32 stores operation instructions that can be executed by the processor 31, and the processor 31 reads the operation instructions in the memory 32 to implement any one of the methods shown in fig. 1 to 5.

It should be noted that the embodiments provided in this application are only optional embodiments described in this application, and those skilled in the art can design many more embodiments based on this description, and therefore, the details are not described herein.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for assessing driving risk, the method comprising:

acquiring first driving data of a vehicle to be evaluated, second driving data of a moving target, traffic environment data of a target area and historical traffic accident data of the target area, wherein the moving target is an object in a moving state in the target area, the target area is an area which is away from the vehicle to be evaluated within a preset range, the traffic environment data are used for indicating the current traffic environment condition in the target area, the first driving data are driving parameters corresponding to the vehicle to be evaluated in the current driving process, the second driving data are moving parameters corresponding to the moving target in the current driving process, and the historical traffic accident data are corresponding relations between the traffic environment data of the target area and accident occurrence probability in a historical time period;

determining a dynamic risk coefficient corresponding to a brake-ahead time according to the first running data of the vehicle to be evaluated, the second running data of the moving target and a preset brake-ahead time, wherein the brake-ahead time is a minimum response time reserved for a driver to avoid collision, the brake-ahead time is a time required by the driver to brake ahead to avoid collision, and the dynamic risk coefficient is used for indicating the possibility of collision between the vehicle to be evaluated and the moving target;

calculating a semi-dynamic risk coefficient according to the time when the vehicle to be evaluated runs to a front stop position and a compensation coefficient corresponding to the traffic environment data, wherein the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in the target area, and the semi-dynamic risk coefficient is used for indicating the possibility of traffic accidents in the target area under the current traffic environment condition;

determining a static risk coefficient corresponding to the traffic environment data according to the corresponding relation between the traffic environment data and the accident occurrence probability in the historical traffic accident data and the corresponding relation between the accident occurrence probability and the static risk coefficient, wherein the static risk coefficient is used for indicating the proportion of the current traffic environment condition in the total number of traffic accidents occurring in the historical target area;

calculating a comprehensive risk coefficient according to a risk coefficient weight corresponding to the working condition characteristics of the target area, the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient, wherein the working condition characteristics comprise traffic order, natural conditions and historical accidents, and the risk coefficient weight comprises a dynamic risk weight, a semi-dynamic risk weight and a static risk weight;

2. The method for assessing driving risk according to claim 1, wherein determining a dynamic risk coefficient corresponding to an early braking time according to the first driving data of the vehicle to be assessed, the second driving data of the moving target and a preset braking reaction time comprises:

3. The method for assessing driving risk according to claim 1, wherein calculating a semi-dynamic risk factor from the time when the vehicle to be assessed travels to a forward stop position and a compensation factor corresponding to the traffic environment data includes:

calculating a semi-dynamic risk initial coefficient according to the time of the vehicle to be evaluated running to a front stop position;

and calculating a semi-dynamic risk coefficient according to the semi-dynamic risk initial coefficient and the compensation coefficient.

4. The driving risk evaluation method according to claim 3, characterized in that:

the traffic environment data is one of a traffic flow parameter of the target area, a traffic control signal of the target area or a driving condition parameter of the target area.

5. The method for assessing driving risk according to claim 3, wherein the traffic environment data includes a traffic flow parameter of the target area, a traffic control signal of the target area, and a driving condition parameter of the target area, and determining a compensation coefficient corresponding to the traffic environment data according to a second preset rule comprises:

6. The method for assessing driving risk according to claim 1, wherein determining the static risk coefficient corresponding to the traffic environment data based on the correspondence between the traffic environment data and the accident occurrence probability and the correspondence between the accident occurrence probability and the static risk coefficient in the historical traffic accident data includes:

determining the accident occurrence probability corresponding to the traffic environment data according to the sixth preset rule;

7. The method for assessing driving risk according to claim 1, wherein after the step of acquiring first traveling data of a vehicle to be assessed, second traveling data of a moving target, traffic environment data of a target area, historical traffic accident data of the target area, the method further comprises:

determining a first distance required by the vehicle to be evaluated to reach a front stop position according to first running data of the vehicle to be evaluated, wherein the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in the target area;

and when the first distance is smaller than a safe distance, triggering the step of determining a dynamic risk coefficient according to the first driving data of the vehicle to be evaluated and the second driving data of the moving target.

8. The method for assessing driving risk according to claim 7, wherein determining a first distance required for the vehicle to be assessed to reach a forward stopping position from the first travel data of the vehicle to be assessed comprises:

determining second position information of a front stop position on a map according to the first position information;

9. The method for assessing driving risk according to claim 7, wherein determining a first distance required for the vehicle to be assessed to reach a forward stopping position from the first travel data of the vehicle to be assessed comprises:

acquiring a second distance between the front stop position and the rear stop position by using a map;

determining a third distance between the vehicle to be evaluated and the rear stopping position according to the first running data of the vehicle to be evaluated, wherein the rear stopping position is a stopping position indicated by a first traffic stopping line behind the vehicle to be evaluated in the target area;

10. The method for assessing driving risk according to claim 1, wherein calculating a composite risk factor according to the risk factor weight corresponding to the operating condition characteristic of the target region, the dynamic risk factor, the semi-dynamic risk factor, and the static risk factor comprises:

acquiring working condition characteristics of the target area;

determining a risk coefficient weight corresponding to the working condition characteristics of the target area according to a preset eighth preset rule, wherein the eighth preset rule is used for indicating the corresponding relation between the working condition characteristics and the risk coefficient weight;

and calculating a comprehensive risk coefficient according to the dynamic risk coefficient, the dynamic risk weight, the semi-dynamic risk coefficient, the semi-dynamic risk weight, the static risk coefficient and the static risk weight.

11. The driving risk assessment method according to claim 1, wherein after the step of determining the traffic risk level of the vehicle to be assessed currently in the target area according to the composite risk factor, the method further comprises:

and outputting the traffic risk level.

12. The driving risk assessment method according to claim 1, wherein the moving object is a motor vehicle.

13. An evaluation device for driving risk, characterized in that the device comprises:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring first driving data of a vehicle to be evaluated, second driving data of a moving target, traffic environment data of a target area and historical traffic accident data of the target area, the moving target is an object in a moving state in the target area, the target area is an area which is a preset range away from the vehicle to be evaluated, the traffic environment data is used for indicating the current traffic environment condition in the target area, the first driving data is a driving parameter corresponding to the vehicle to be evaluated in the current driving process, the second driving data is a moving parameter corresponding to the moving target in the current moving process, and the historical traffic accident data is a corresponding relation between the traffic environment data of the target area and the accident occurrence probability in a historical time period;

the first determining module is used for determining a dynamic risk coefficient corresponding to an advanced braking time according to first running data of the vehicle to be evaluated, second running data of the moving target and a preset braking reaction time, wherein the braking reaction time is the minimum reaction time reserved for a driver to avoid collision, the advanced braking time is the time required for the driver to brake in advance to avoid collision, and the dynamic risk coefficient is used for indicating the possibility of collision between the vehicle to be evaluated and the moving target;

the second determination module is used for calculating a semi-dynamic risk coefficient according to the time when the vehicle to be evaluated runs to a front stop position and a compensation coefficient corresponding to the traffic environment data, wherein the front stop position is a stop position indicated by a first traffic stop line in front of the vehicle to be evaluated in the target area, and the semi-dynamic risk coefficient is used for indicating the possibility of traffic accidents in the target area under the current traffic environment condition;

a third determining module, configured to determine a static risk coefficient corresponding to the traffic environment data according to a correspondence between the traffic environment data and the accident occurrence probability in the historical traffic accident data and a correspondence between the accident occurrence probability and a static risk coefficient, where the static risk coefficient is used to indicate a proportion of the current traffic environment condition in a total number of traffic accidents occurring in the historical target area;

the fusion module is used for calculating a comprehensive risk coefficient according to a risk coefficient weight corresponding to the working condition characteristics of the target area, the dynamic risk coefficient, the semi-dynamic risk coefficient and the static risk coefficient, wherein the working condition characteristics comprise traffic order, natural conditions and historical accidents, and the risk coefficient weight comprises a dynamic risk weight, a semi-dynamic risk weight and a static risk weight;

14. The driving risk assessment device according to claim 13, characterized in that:

the first determining module is specifically configured to calculate a remaining time of collision between the vehicle to be evaluated and the moving target according to first driving data of the vehicle to be evaluated and second driving data of the moving target; calculating the brake advance time according to the remaining time and the preset brake reaction time; and determining a dynamic risk coefficient corresponding to the early braking time according to a preset first preset rule, wherein the first preset rule is used for indicating the corresponding relation between the early braking time and the dynamic risk coefficient.

15. The driving risk assessment device according to claim 13, characterized in that:

the second determination module is specifically used for calculating a semi-dynamic risk initial coefficient according to the time of the vehicle to be evaluated running to the front stop position; determining a compensation coefficient corresponding to the traffic environment data according to a preset second preset rule, wherein the second preset rule is used for indicating the corresponding relation between the traffic environment data and the compensation coefficient; and calculating a semi-dynamic risk coefficient according to the semi-dynamic risk initial coefficient and the compensation coefficient.

16. The driving risk assessment device according to claim 15, characterized in that:

the second determining module is specifically configured to determine a first compensation coefficient corresponding to the traffic flow parameter of the target area according to a preset third preset rule, where the third preset rule is used to indicate a corresponding relationship between the traffic flow parameter and the first compensation coefficient; determining a second compensation coefficient corresponding to the traffic control signal according to a preset fourth preset rule, wherein the fourth preset rule is used for indicating the corresponding relation between the traffic control signal and the second compensation coefficient; determining a third compensation coefficient corresponding to the driving condition parameter according to a preset fifth preset rule, wherein the fifth preset rule is used for indicating the corresponding relation between the driving condition parameter and the third compensation coefficient; and determining a compensation coefficient according to the first compensation coefficient, the second compensation coefficient and the third compensation coefficient.

17. The driving risk assessment device according to claim 13, characterized in that:

the third determining module is specifically configured to determine a sixth preset rule in the historical traffic accident data, where the sixth preset rule is used to indicate a correspondence between traffic environment data and accident occurrence probability; determining the accident occurrence probability corresponding to the traffic environment data according to the sixth preset rule; and determining a static risk coefficient corresponding to the accident occurrence probability according to a preset seventh preset rule, wherein the seventh preset rule is used for indicating the corresponding relation between the accident occurrence probability and the static risk coefficient.

18. The driving risk assessment device according to claim 13, characterized in that said device further comprises:

the fifth determining module is used for determining a first distance required by the vehicle to be evaluated to reach a front stopping position according to first running data of the vehicle to be evaluated, wherein the front stopping position is a stopping position indicated by a first traffic stopping line in front of the vehicle to be evaluated in the target area;

19. The driving risk assessment device according to claim 18, characterized in that:

the fifth determining module is specifically configured to acquire first position information of the vehicle to be evaluated according to the first driving data of the vehicle to be evaluated; determining second position information of a front stop position on a map according to the first position information; and calculating a first distance between the vehicle to be evaluated and the front stop position according to the first position information and the second position information.

20. The driving risk assessment device according to claim 18, characterized in that:

the fifth determining module is specifically configured to obtain a second distance between the front stop position and the rear stop position by using a map; determining a third distance between the vehicle to be evaluated and a rear stopping position according to the first running data of the vehicle to be evaluated, wherein the rear stopping position is a stopping position indicated by a first traffic stopping line behind the vehicle to be evaluated in the target area; and determining a first distance between the vehicle to be evaluated and the front stop position according to the second distance and the third distance.

21. The driving risk assessment device according to claim 13, characterized in that:

the fusion module is specifically used for acquiring the working condition characteristics of the target area; determining a risk coefficient weight corresponding to the working condition characteristics of the target area according to a preset eighth preset rule, wherein the eighth preset rule is used for indicating the corresponding relation between the working condition characteristics and the risk coefficient weight; and calculating a comprehensive risk coefficient according to the dynamic risk coefficient, the dynamic risk weight, the semi-dynamic risk coefficient, the semi-dynamic risk weight, the static risk coefficient and the static risk weight.

22. The driving risk assessment device according to claim 13, characterized in that said device further comprises:

and the output module is used for outputting the traffic risk grade.

23. An evaluation device for driving risk, characterized by comprising: a processor and a memory, wherein the memory stores operating instructions executable by the processor, and the operating instructions in the memory are read by the processor to implement the method according to any one of claims 1 to 12.