A method, system, terminal and medium for identifying highway traffic risk status

Abstract

The present invention discloses a method, system, terminal and medium for identifying highway traffic risk status, and relates to the field of intelligent transportation technology. The key points of the technical solution are as follows: the present invention analyzes the state risk probability of a target vehicle having a traffic accident under the influence of actual road linear data, actual weather data and actual vehicle micro-trajectory data based on the confidence space of all historical vehicle micro-trajectory data under a preset confidence level in historical accident data, and comprehensively considers the differences in the mechanism of triggering traffic accidents by different vehicle micro-trajectory characteristics, road morphology and weather conditions from a micro perspective, so that the highway traffic risk status identification is more accurate, which is conducive to the realization of accurate prevention and control of highway traffic safety.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and more specifically, to a method, system, terminal and medium for identifying highway traffic risk status. Background Art

[0002] In recent years, with the continuous increase in the mileage of expressways in my country and the sharp growth in road traffic volume, traffic congestion on expressways has become normalized and traffic accidents have occurred frequently, seriously affecting the role of expressways as the main transportation channel for interconnection between cities and urban areas. In order to improve the active prevention and control capabilities of expressway traffic safety, it is necessary to effectively identify the traffic risk status of expressways, so as to reduce the occurrence of traffic accidents by regulating the vehicle status of high-risk vehicles.

[0003] The prior art records a vehicle risk driving analysis technology that determines speed thresholds for different road sections based on road types and weather conditions, and judges that the vehicle is in a risky state when the actual driving speed of the vehicle exceeds the speed threshold. The road types are mainly divided from the perspective of the overall speed limit of the road, such as expressways, main roads, and auxiliary roads. The impact of road morphology on vehicle risk driving is ignored. For example, sudden acceleration at bends and driving at higher speeds on downhill sections are more likely to cause traffic accidents. In addition, in addition to speed factors, the factors that actually affect the occurrence of traffic accidents also include vehicle micro-trajectory characteristics such as acceleration, vehicle spacing, and vehicle offset, such as sudden acceleration when the vehicle spacing is small, continuous lane changes on expressways, etc., and the mechanism of triggering traffic accidents by different vehicle micro-trajectory characteristics under different road morphologies is obviously different. This leads to large analysis errors in the above-mentioned vehicle risk driving analysis technology, making it difficult to achieve precise prevention and control of highway traffic safety.

[0004] Therefore, how to research and design a highway traffic risk status identification method, system, terminal and medium that can overcome the above-mentioned defects is a problem that we urgently need to solve. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the purpose of the present invention is to provide a method, system, terminal and medium for identifying highway traffic risk status, which comprehensively considers the differences in the mechanism of triggering traffic accidents caused by the microscopic trajectory characteristics of different vehicles, road morphology and weather conditions from a microscopic perspective, so that the highway traffic risk status identification is more accurate, which is conducive to the precise prevention and control of highway traffic safety.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions:

[0007] In a first aspect, a method for identifying a highway traffic risk state is provided, comprising the following steps:

[0008] Obtain historical accident data, which includes historical road alignment data, historical weather data, and historical vehicle micro-trajectory data;

[0009] An accident discrete graph is established with historical road linear data and historical weather data as coordinate axes. Each discrete point in the accident discrete graph contains the corresponding historical vehicle micro-trajectory data.

[0010] After cluster analysis of the accident dispersion map, the cluster area is obtained, and the historical road linear data and historical weather data corresponding to the cluster area are used to determine a dangerous road section type;

[0011] Determine the micro-feature weight sequence of the corresponding dangerous road section type according to the risk micro-feature distribution of all historical vehicle micro-trajectory data in a single clustering area;

[0012] Statistically analyze the confidence space of all historical vehicle micro-trajectory data in historical accident data under a preset confidence level;

[0013] Collect the driving status data of the target vehicle, which includes actual road alignment data, actual weather data, and actual vehicle micro-trajectory data;

[0014] Match the dangerous road section type according to the actual road linear data and actual weather data to obtain the corresponding micro-feature weight sequence;

[0015] The trajectory risk probability is determined according to the distribution position of the actual vehicle micro-trajectory data in the corresponding confidence space, and the state risk probability is obtained by weight calculation combined with the micro-feature weight sequence;

[0016] When the state risk probability exceeds the probability threshold, a warning signal is outputted indicating that the target vehicle has a driving risk on the dangerous road section type.

[0017] Furthermore, the historical road alignment data and / or actual road alignment data include at least one road alignment parameter of road slope, road curvature, road width and road sight distance.

[0018] Furthermore, if the historical road alignment data and / or the actual road alignment data include at least two road alignment parameters of road slope, road curvature, road width and road sight distance, the process of establishing the accident discrete map is specifically as follows:

[0019] All road alignment parameters are normalized to obtain the standard value of each road alignment parameter;

[0020] The standard quantity is used as the coordinate axis to replace the historical road alignment data. At the same time, a discrete point is generated corresponding to the standard quantity of each road alignment parameter. Accident dispersion diagram of discrete points;

[0021] in, Represents the number of samples in the historical accident data; Represents the number of road alignment parameters in the historical road alignment data.

[0022] Furthermore, the historical vehicle micro-trajectory data and / or the actual vehicle micro-trajectory data include at least two micro-trajectory features of speed, acceleration, vehicle spacing and vehicle offset.

[0023] Furthermore, the process of determining the micro-feature weight sequence is specifically as follows:

[0024] Determine the judgment threshold of each micro-trajectory feature for risk assessment;

[0025] If the characteristic value of the micro-trajectory feature exceeds the corresponding judgment threshold, the corresponding micro-trajectory feature is determined to be a risk micro-feature;

[0026] The number of each risk micro-feature in a single cluster area is counted, and the micro-feature weight parameters of the corresponding micro-trajectory features in the corresponding dangerous road section type are allocated according to the proportion of the number of each risk micro-feature to form a micro-feature weight sequence.

[0027] Furthermore, if the actual vehicle microscopic trajectory data is within the corresponding confidence space, the determined trajectory risk probability value range is (0,1);

[0028] If the actual vehicle micro-trajectory data is less than or equal to the lower endpoint value of the corresponding confidence space, the corresponding determined trajectory risk probability value is 0;

[0029] If the actual vehicle micro-trajectory data is greater than or equal to the upper endpoint value of the corresponding confidence space, the corresponding determined trajectory risk probability value is 1.

[0030] Furthermore, if the actual vehicle microscopic trajectory data is within the corresponding confidence space, the process of determining the trajectory risk probability is specifically as follows:

[0031] If the actual vehicle micro-trajectory data is speed, acceleration or vehicle offset, the closer the actual vehicle micro-trajectory data is to the upper endpoint value of the confidence space, the greater the corresponding determined trajectory risk probability;

[0032] If the actual vehicle micro-trajectory data is the vehicle spacing, the closer the actual vehicle micro-trajectory data is to the lower endpoint value of the confidence space, the greater the corresponding determined trajectory risk probability.

[0033] In a second aspect, a highway traffic risk status identification system is provided, the system is used to implement a highway traffic risk status identification method as described in any one of the first aspects, including:

[0034] A data acquisition module is used to acquire historical accident data, which includes historical road alignment data, historical weather data, and historical vehicle micro-trajectory data;

[0035] A discrete graph construction module is used to establish an accident discrete graph using historical road linear data and historical weather data as coordinate axes. Each discrete point in the accident discrete graph contains the corresponding historical vehicle micro-trajectory data.

[0036] The cluster analysis module is used to obtain cluster areas after cluster analysis on the accident dispersion map, and determine a dangerous road section type based on the historical road linear data and historical weather data corresponding to the cluster area;

[0037] A weight determination module is used to determine a micro-feature weight sequence corresponding to a dangerous road section type according to the risk micro-feature distribution of all historical vehicle micro-trajectory data within a single clustering area;

[0038] A statistical analysis module is used to statistically analyze the confidence space of all historical vehicle micro-trajectory data in historical accident data under a preset confidence level;

[0039] A data acquisition module is used to collect driving status data of the target vehicle, and the driving status data includes actual road linear data, actual weather data and actual vehicle micro-trajectory data;

[0040] A data matching module is used to match the dangerous road section type according to the actual road linear data and the actual weather data to obtain the corresponding micro-feature weight sequence;

[0041] The probability analysis module is used to determine the trajectory risk probability according to the distribution position of the actual vehicle micro-trajectory data in the corresponding confidence space, and to calculate the weights in combination with the micro-feature weight sequence to obtain the state risk probability;

[0042] The risk warning module is used to output a warning signal indicating that there is a driving risk on the dangerous road section type of the target vehicle when the state risk probability exceeds the probability threshold.

[0043] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for identifying highway traffic risk status as described in any one of the first aspects is implemented.

[0044] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement a method for identifying highway traffic risk status as described in any one of the first aspects.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. A highway traffic risk state identification method provided by the present invention analyzes the state risk probability of a target vehicle having a traffic accident under the influence of actual road linear data, actual weather data and actual vehicle micro-trajectory data based on the confidence space of all historical vehicle micro-trajectory data under a preset confidence level in historical accident data. It comprehensively considers the differences in the mechanism of triggering traffic accidents by different vehicle micro-trajectory characteristics, road morphology and weather conditions from a microscopic perspective, making the highway traffic risk state identification more accurate, which is conducive to the realization of accurate prevention and control of highway traffic safety;

[0047] 2. When establishing the accident discrete map, the present invention normalizes all road alignment parameters and uses standard quantities as coordinate axes to replace historical road alignment data. At the same time, a discrete point is generated corresponding to the standard quantity of each road alignment parameter, so that the clustering area obtained by cluster analysis can simultaneously consider the influence of multiple road alignment parameters on the occurrence of traffic accidents, further improving the accuracy of highway traffic risk state identification;

[0048] 3. The present invention also counts the number of each risk micro-feature in a single cluster area, and allocates the micro-feature weight parameters of the corresponding micro-trajectory features in the corresponding dangerous road section type according to the number ratio of each risk micro-feature, and realizes dynamic calculation of state risk probability by combining trajectory risk probability and micro-feature weight sequence, which can realize real-time tracking and identification of highway traffic risk status in roads with complex and changeable dangerous road section types;

[0049] 4. The present invention can adjust the confidence space of each vehicle micro-trajectory by adjusting the preset confidence, thereby flexibly adjusting the sensitivity of highway traffic risk state identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0051] Figure 1 is a flow chart of Embodiment 1 of the present invention;

[0052] Figure 2 It is a system block diagram in Example 2 of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0054] Example 1: A method for identifying highway traffic risk status, such as Figure 1 As shown, the following steps are included:

[0055] S1: Obtain historical accident data, which includes historical road alignment data, historical weather data, and historical vehicle micro-trajectory data;

[0056] S2: Using historical road alignment data and historical weather data as coordinate axes, an accident discrete graph is established. Each discrete point in the accident discrete graph contains the corresponding historical vehicle micro-trajectory data.

[0057] S3: After clustering analysis of the accident dispersion map, a cluster area is obtained, and a dangerous road section type is determined based on the historical road linear data and historical weather data corresponding to the cluster area;

[0058] S4: Determine the micro-feature weight sequence of the corresponding dangerous road section type according to the risk micro-feature distribution of all historical vehicle micro-trajectory data in a single clustering area;

[0059] S5: Statistically analyze the confidence space of all historical vehicle micro-trajectory data in the historical accident data under the preset confidence level;

[0060] S6: collecting driving status data of the target vehicle, the driving status data including actual road linear data, actual weather data and actual vehicle micro-trajectory data;

[0061] S7: Match the dangerous road section type according to the actual road linear data and the actual weather data to obtain the corresponding micro-feature weight sequence;

[0062] S8: Determine the trajectory risk probability according to the distribution position of the actual vehicle micro-trajectory data in the corresponding confidence space, and calculate the weights in combination with the micro-feature weight sequence to obtain the state risk probability;

[0063] S9: When the state risk probability exceeds the probability threshold, a warning signal is outputted indicating that the target vehicle has a driving risk on the dangerous road section type.

[0064] It should be noted that the present invention is not limited to expressways but also to main roads in cities.

[0065] In step S1, the historical road alignment data includes but is not limited to road slope, road curvature, road width and road sight distance. The road alignment parameters used in the actual road alignment data must be consistent with the road alignment parameters used in the historical road alignment data.

[0066] In step S2, as an optional implementation, the road alignment data may adopt any one of the road alignment parameters of road slope, road curvature, road width and road sight distance, and the corresponding road alignment parameter is used as the ordinate when establishing the accident discrete map.

[0067] As an optional implementation, if the road alignment data includes two or more road alignment parameters of road slope, road curvature, road width and road sight distance, considering the differences in road alignment parameters in the sample data, it is difficult to integrate them into a discrete graph, and the amount of data after unified processing of different road alignment parameters is different. The specific process of establishing the accident discrete graph in the present invention is as follows: normalize all road alignment parameters to obtain the standard quantity of each road alignment parameter; replace the historical road alignment data with the standard quantity as the coordinate axis, and generate a discrete point corresponding to the standard quantity of each road alignment parameter, and establish a discrete point with The accident dispersion diagram of discrete points; Represents the number of samples in the historical accident data; Represents the number of road alignment parameters in the historical road alignment data.

[0068] It should be noted that the discrete points mainly include historical vehicle micro-trajectory data, so the discrete points generated by the same sample data are copies of the corresponding historical vehicle micro-trajectory data.

[0069] When establishing an accident discrete map, the present invention normalizes all road alignment parameters and replaces historical road alignment data with standard quantities as coordinate axes. At the same time, a discrete point is generated corresponding to the standard quantity of each road alignment parameter, so that the clustering area obtained by cluster analysis can simultaneously consider the impact of multiple road alignment parameters on the occurrence of traffic accidents, further improving the accuracy of highway traffic risk status identification.

[0070] In step S3, multiple discrete points can be clustered to form a cluster area with a width on the coordinate axis, and one or more road line parameters and weather data corresponding to the cluster area can determine a dangerous road section type, thereby achieving dangerous road section type subdivision.

[0071] For example, dangerous road sections can be divided into sharp bend rain sections, sharp bend snow sections, sharp bend fog sections, long steep slope rain sections, long steep slope snow sections, continuous bends and heavy fog sections, rain, snow and fog sections with poor visibility, strong wind sections on mountain roads, heavy rain and snow sections on mountain roads, rain, snow and frozen sections on bridges, and other dangerous road section types.

[0072] In step S4, the process of determining the micro-feature weight sequence is specifically as follows: determining the judgment threshold of each micro-trajectory feature for risk judgment; if the characteristic value of the micro-trajectory feature exceeds the corresponding judgment threshold, the corresponding micro-trajectory feature is judged to be a risk micro-feature; counting the number of each risk micro-feature in a single clustering area, and allocating the micro-feature weight parameters of the corresponding micro-trajectory feature in the corresponding dangerous road section type according to the proportion of the number of each risk micro-feature, to form a micro-feature weight sequence.

[0073] For example, the number of risk micro-features existing in the three micro-trajectory features is distributed as 2, 3, and 5, and the constructed micro-feature weight sequence is {0.2, 0.3, 0.5}.

[0074] It should be noted that the historical vehicle micro-trajectory data and the actual vehicle micro-trajectory data include but are not limited to speed, acceleration, vehicle spacing and vehicle offset. At least two of the micro-trajectory features are selected in actual application.

[0075] In step S5, the larger the preset confidence is, the wider the confidence space is, the higher the sensitivity of highway traffic risk state recognition is, and each micro-trajectory feature forms a corresponding confidence space. Taking speed as an example, the confidence space with a preset confidence of 90% is [40,100], which means that 90% of the speeds when traffic accidents occur are within the range of [40,100].

[0076] The present invention can adjust the confidence space of each vehicle micro-trajectory by adjusting the preset confidence, thereby flexibly adjusting the sensitivity of highway traffic risk state recognition.

[0077] In step S6, the driving status data is collected in a manner including but not limited to analyzing the image data collected by the camera, collecting the data through the roadside sensor and / or the vehicle-mounted sensor, and is not limited here.

[0078] In step S7, if the actual vehicle micro-trajectory data is within the corresponding confidence space, the determined trajectory risk probability value range is (0,1); if the actual vehicle micro-trajectory data is less than or equal to the lower limit endpoint value of the corresponding confidence space, the corresponding determined trajectory risk probability value is 0; if the actual vehicle micro-trajectory data is greater than or equal to the upper limit endpoint value of the corresponding confidence space, the corresponding determined trajectory risk probability value is 1.

[0079] In addition, when the actual vehicle micro-trajectory data is within the corresponding confidence space, if the actual vehicle micro-trajectory data is speed, acceleration or vehicle offset, the closer the actual vehicle micro-trajectory data is to the upper endpoint value of the confidence space, the greater the corresponding determined trajectory risk probability.

[0080] For example, the trajectory risk probability may be taken as the ratio of the difference between the actual vehicle micro-trajectory data and the lower endpoint value of the confidence space and the width value of the confidence space.

[0081] In addition, if the actual vehicle micro-trajectory data is the vehicle spacing, the closer the actual vehicle micro-trajectory data is to the lower endpoint value of the confidence space, the greater the corresponding determined trajectory risk probability.

[0082] For example, the trajectory risk probability may be taken as the ratio of the difference between the actual vehicle micro-trajectory data and the upper endpoint value of the confidence space and the width value of the confidence space.

[0083] The present invention also counts the number of each risk micro-feature in a single clustering area, and allocates micro-feature weight parameters of the corresponding micro-trajectory features in the corresponding dangerous road section type according to the proportion of the number of each risk micro-feature, and realizes dynamic calculation of state risk probability by combining trajectory risk probability and micro-feature weight sequence, which can realize real-time tracking and identification of highway traffic risk status in roads with complex and changeable dangerous road section types.

[0084] In step S8, the weight calculation is to multiply the trajectory risk probability with the corresponding micro-feature weight parameter, and then sum the multiplication results of each micro-trajectory feature.

[0085] Therefore, multiple micro-trajectory features are ultimately calculated to obtain a unique state risk probability.

[0086] In step S9, the output warning signal can be fed back to the target vehicle in a timely manner to remind the driver to drive safely.

[0087] Embodiment 2: A highway traffic risk state identification system, the system is used to implement a highway traffic risk state identification method as described in Embodiment 1, such as Figure 2 As shown, it includes a data acquisition module, a discrete graph construction module, a cluster analysis module, a weight determination module, a statistical analysis module, a data collection module, a data matching module, a probability analysis module and a risk warning module.

[0088] Among them, the data acquisition module is used to obtain historical accident data, which includes historical road alignment data, historical weather data and historical vehicle micro-trajectory data; the discrete graph construction module is used to establish an accident discrete graph with historical road alignment data and historical weather data as coordinate axes, and each discrete point in the accident discrete graph contains the corresponding historical vehicle micro-trajectory data; the cluster analysis module is used to obtain a cluster area after cluster analysis on the accident discrete graph, and determine a dangerous road section type based on the historical road alignment data and historical weather data corresponding to the cluster area; the weight determination module is used to determine the micro-feature weight sequence of the corresponding dangerous road section type according to the risk micro-feature distribution of all historical vehicle micro-trajectory data in a single cluster area; the statistical analysis module is used to statistically analyze the confidence space of all historical vehicle micro-trajectory data in the historical accident data under a preset confidence level.

[0089] The data acquisition module is used to collect the driving status data of the target vehicle, and the driving status data includes actual road alignment data, actual weather data and actual vehicle micro-trajectory data; the data matching module is used to match the dangerous road section type according to the actual road alignment data and the actual weather data to obtain the corresponding micro-feature weight sequence; the probability analysis module is used to determine the trajectory risk probability according to the distribution position of the actual vehicle micro-trajectory data in the corresponding confidence space, and calculate the weight in combination with the micro-feature weight sequence to obtain the state risk probability; the risk warning module is used to output a warning signal indicating that the target vehicle has a driving risk on the dangerous road section type when the state risk probability exceeds the probability threshold.

[0090] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for identifying highway traffic risk status as described in Example 1 is implemented.

[0091] The present invention also records a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement a method for identifying highway traffic risk status as described in Example 1.

[0092] Working principle: The present invention analyzes the state risk probability of a traffic accident of a target vehicle under the influence of actual road linear data, actual weather data and actual vehicle micro-trajectory data based on the confidence space of all historical vehicle micro-trajectory data in historical accident data at a preset confidence level. From a microscopic perspective, it comprehensively considers the differences in the mechanism of triggering traffic accidents by different vehicle micro-trajectory characteristics, road morphology and weather conditions, making the identification of highway traffic risk status more accurate, which is conducive to the precise prevention and control of highway traffic safety.

[0093] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying highway traffic risk status, characterized in that: The following steps are involved: Obtain historical accident data, which includes historical road alignment data, historical weather data, and historical vehicle micro-trajectory data; An accident discrete graph is established with historical road linear data and historical weather data as coordinate axes. Each discrete point in the accident discrete graph contains the corresponding historical vehicle micro-trajectory data. After cluster analysis of the accident dispersion map, the cluster area is obtained, and the historical road linear data and historical weather data corresponding to the cluster area are used to determine a dangerous road section type; Determine the micro-feature weight sequence of the corresponding dangerous road section type according to the risk micro-feature distribution of all historical vehicle micro-trajectory data in a single clustering area; Statistically analyze the confidence space of all historical vehicle micro-trajectory data in historical accident data under a preset confidence level; Collect the driving status data of the target vehicle, which includes actual road alignment data, actual weather data, and actual vehicle micro-trajectory data; Match the dangerous road section type according to the actual road linear data and actual weather data to obtain the corresponding micro-feature weight sequence; The trajectory risk probability is determined according to the distribution position of the actual vehicle micro-trajectory data in the corresponding confidence space, and the state risk probability is obtained by weight calculation combined with the micro-feature weight sequence; When the state risk probability exceeds the probability threshold, a warning signal is outputted indicating that the target vehicle has a driving risk on the dangerous road section type; The historical road alignment data and / or actual road alignment data include at least two road alignment parameters of road slope, road curvature, road width and road sight distance. The process of establishing the accident discrete map is specifically as follows: All road alignment parameters are normalized to obtain the standard value of each road alignment parameter; The standard quantity is used as the coordinate axis to replace the historical road alignment data. At the same time, a discrete point is generated corresponding to the standard quantity of each road alignment parameter. Accident dispersion diagram of discrete points; in, Represents the number of samples in the historical accident data; Represents the number of road alignment parameters in the historical road alignment data.

2. A highway traffic risk state identification method according to claim 1, characterized in that: The historical vehicle micro-trajectory data and / or the actual vehicle micro-trajectory data include at least two micro-trajectory features of speed, acceleration, vehicle spacing, and vehicle offset.

3. A highway traffic risk state identification method according to claim 1, characterized in that: The process of determining the micro-feature weight sequence is specifically as follows: Determine the judgment threshold of each micro-trajectory feature for risk assessment; If the characteristic value of the micro-trajectory feature exceeds the corresponding judgment threshold, the corresponding micro-trajectory feature is determined to be a risk micro-feature; The number of each risk micro-feature in a single cluster area is counted, and the micro-feature weight parameters of the corresponding micro-trajectory features in the corresponding dangerous road section type are allocated according to the proportion of the number of each risk micro-feature to form a micro-feature weight sequence.

4. A highway traffic risk state identification method according to claim 1, characterized in that: If the actual vehicle micro-trajectory data is within the corresponding confidence space, the determined trajectory risk probability value range is (0,1); If the actual vehicle micro-trajectory data is less than or equal to the lower endpoint value of the corresponding confidence space, the corresponding determined trajectory risk probability value is 0; If the actual vehicle micro-trajectory data is greater than or equal to the upper endpoint value of the corresponding confidence space, the corresponding determined trajectory risk probability value is 1.

5. A method for identifying highway traffic risk status according to claim 4, characterized in that: If the actual vehicle microscopic trajectory data is within the corresponding confidence space, the process of determining the trajectory risk probability is specifically as follows: If the actual vehicle micro-trajectory data is speed, acceleration or vehicle offset, the closer the actual vehicle micro-trajectory data is to the upper endpoint value of the confidence space, the greater the corresponding determined trajectory risk probability; If the actual vehicle micro-trajectory data is the vehicle spacing, the closer the actual vehicle micro-trajectory data is to the lower endpoint value of the confidence space, the greater the corresponding determined trajectory risk probability.

6. A highway traffic risk status identification system, characterized in that: The system is used to implement a highway traffic risk state identification method as described in any one of claims 1 to 5, comprising: A data acquisition module is used to acquire historical accident data, which includes historical road alignment data, historical weather data, and historical vehicle micro-trajectory data; A discrete graph construction module is used to establish an accident discrete graph using historical road linear data and historical weather data as coordinate axes. Each discrete point in the accident discrete graph contains the corresponding historical vehicle micro-trajectory data. The cluster analysis module is used to obtain cluster areas after cluster analysis on the accident dispersion map, and determine a dangerous road section type based on the historical road linear data and historical weather data corresponding to the cluster area; A weight determination module is used to determine a micro-feature weight sequence corresponding to a dangerous road section type according to the risk micro-feature distribution of all historical vehicle micro-trajectory data within a single clustering area; A statistical analysis module is used to statistically analyze the confidence space of all historical vehicle micro-trajectory data in historical accident data under a preset confidence level; A data acquisition module is used to collect driving status data of the target vehicle, and the driving status data includes actual road linear data, actual weather data and actual vehicle micro-trajectory data; A data matching module is used to match the dangerous road section type according to the actual road linear data and the actual weather data to obtain the corresponding micro-feature weight sequence; The probability analysis module is used to determine the trajectory risk probability according to the distribution position of the actual vehicle micro-trajectory data in the corresponding confidence space, and to calculate the weights in combination with the micro-feature weight sequence to obtain the state risk probability; The risk warning module is used to output a warning signal indicating that there is a driving risk on the dangerous road section type of the target vehicle when the state risk probability exceeds the probability threshold.

7. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements a highway traffic risk status identification method as described in any one of claims 1-5.

8. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement a method for identifying highway traffic risk status as described in any one of claims 1-5.

Images