Multi-source traffic operation data analysis method and system based on AI sensor fusion

Abstract

The invention provides a multi-source traffic operation data analysis method and system based on AI sensor fusion. Accurate reconstruction and dynamic monitoring of an interchange space scene of a highway section can be realized. A traffic operation data flow is generated through an AI sensor fusion acquisition technology, a detailed traffic dynamic change map is further analyzed, meanwhile, driving behavior data blocks and non-driving behavior data blocks are effectively separated through block mapping and fine extraction of road domain sensing data, a data basis is provided for deep analysis of traffic state influence factors, and the traffic state influence factors are effectively analyzed. The further optimized traffic dynamic change map is combined with an interchange space scene to accurately estimate a traffic safety risk trend and generate forward-looking traffic safety risk trend data, so that targeted safety prompt suggestions can be generated in time, the traffic safety management level and the emergency response capability of the expressway section are remarkably improved, and the traffic safety risk of the expressway section is improved. The occurrence of traffic accidents is effectively prevented and reduced, and the public travel safety is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a multi-source traffic operation data analysis method and system based on AI sensor fusion. Background Art

[0002] With the acceleration of urbanization and the continuous expansion of transportation networks, highways, as important links connecting cities, have increasing traffic volume and increasingly complex traffic conditions. In particular, interchanges in highway sections often become traffic bottlenecks and accident-prone areas due to their complex structures and frequent traffic flows. Therefore, in-depth analysis of traffic operation data in interchanges in highway sections to grasp traffic conditions in real time and predict potential risks is of great significance for improving traffic management efficiency and ensuring driving safety.

[0003] Most of the related technologies rely on a single data source, such as traffic flow monitoring data, vehicle speed data, etc. Although these data can provide a certain degree of traffic status information, it is difficult to fully reflect the complexity and dynamics of traffic operation. In addition, the related technologies are inefficient when processing large amounts of data, making it difficult to achieve real-time analysis of traffic status and risk prediction. Summary of the invention

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a multi-source traffic operation data analysis method based on AI sensor fusion, the method comprising:

[0005] Reconstruct the interchange space scene of the expressway section to generate the interchange space scene, perform AI sensor fusion collection on the expressway section based on the interchange space scene to generate the traffic operation data stream, and analyze the traffic dynamic change map of the interchange space scene based on the traffic operation data stream to generate the traffic dynamic change map;

[0006] Mapping the road domain perception data blocks of the expressway section to generate the road domain block perception data, extracting the driving behavior data blocks from the road domain block perception data to generate the driving behavior data blocks, and extracting the non-driving behavior data blocks from the road domain block perception data to generate the non-driving behavior data blocks;

[0007] Analyze the traffic status influencing factors of the expressway section based on the driving behavior data block and the non-driving behavior data block to generate the traffic status influencing factors;

[0008] The traffic dynamic change map is optimized based on the road block perception data and traffic status influencing factors to generate an optimized traffic dynamic change map, and the traffic safety risk trend of the expressway section is estimated based on the optimized traffic dynamic change map and the interchange space scenario to generate traffic safety risk trend data, and safety tips and suggestions for the interchange space scenario are generated based on the traffic safety risk trend data.

[0009] On the other hand, an embodiment of the present invention also provides a multi-source traffic operation data analysis system based on AI sensor fusion, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0010] Based on the above aspects, the embodiment of the present application can realize the accurate reconstruction and dynamic monitoring of the interchange space scene of the expressway section. The traffic operation data stream is generated through the AI ​​sensor fusion acquisition technology, and then a detailed traffic dynamic change map is parsed. At the same time, through the block mapping and fine extraction of the road domain perception data, the driving behavior data block and the non-driving behavior data block are effectively separated, which provides a data basis for in-depth analysis of the factors affecting the traffic state. The further optimized traffic dynamic change map, combined with the interchange space scene, can accurately estimate the traffic safety risk trend and generate forward-looking traffic safety risk trend data, thereby being able to generate targeted safety tips and suggestions in a timely manner, significantly improving the traffic safety management level and emergency response capabilities of the expressway section, effectively preventing and reducing the occurrence of traffic accidents, and ensuring the safety of public travel. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a schematic diagram of the execution flow of the multi-source traffic operation data analysis method based on AI sensor fusion provided in an embodiment of the present invention.

[0012] Figure 2 It is a schematic diagram of the hardware architecture of a multi-source traffic operation data analysis system based on AI sensor fusion provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0013] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1 It is a flow chart of a multi-source traffic operation data analysis method based on AI sensor fusion provided by an embodiment of the present invention. The multi-source traffic operation data analysis method based on AI sensor fusion is introduced in detail below.

[0014] Step S110, reconstruct the interchange space scene of the expressway section to generate the interchange space scene, perform AI sensor fusion collection on the expressway section based on the interchange space scene to generate a traffic operation data stream, and perform traffic dynamic change map analysis on the interchange space scene based on the traffic operation data stream to generate a traffic dynamic change map.

[0015] In this embodiment, the server starts the operation after receiving the task instructions such as reconstructing the spatial scene of the interchange on the highway section. For a specific highway section, for example, a section of the G1 highway section connecting multiple cities contains an interchange. The server first performs a partitioned drone aerial scan of the highway section. The server will dispatch multiple drones equipped with high-definition cameras to scan according to a pre-set partitioning scheme, such as one partition per square kilometer. During the flight, the drone continuously captures information such as the terrain, road structure, layout of the interchange, and surrounding landforms of the highway section to generate partitioned drone aerial scanning data. For example, the data of a certain partition contains information such as the number of ramps of the interchange in the area, the angle of the curve, the connection method with the adjacent sections, and whether there are mountains, rivers, and other landform features that affect the traffic layout in the surrounding area.

[0016] Next, the server merges the drone aerial scanning data from many partitions. This process involves operations such as data calibration and splicing. The server analyzes key information such as geographic coordinates and road connection features in the partition data and integrates them into target drone aerial scanning data. For example, by identifying the continuity of roads in adjacent partitions and the docking relationship of interchange ramps, it ensures that the data can accurately reflect the complete structure of the interchange of the entire highway section after fusion.

[0017] Then, the interchange space scene of the highway section is reconstructed based on the target drone aerial scanning data. The server uses special modeling software to construct the interchange space scene based on the road size, interchange height, slope and other parameters in the aerial scanning data. This scene is a three-dimensional model that contains detailed information such as road entities, spatial coordinates, and traffic sign locations. For example, in the model, you can clearly see how lanes in different directions interweave and diverge at the interchange, the location of traffic lights and the directions they indicate, etc.

[0018] Afterwards, AI sensor fusion data is collected on the highway section based on the interchange space scene. The server first configures traffic observation points on the highway section. For example, sensor observation points are set at key locations such as the entrance, exit, bend, and lane merging and separation points of the interchange. These sensors include video surveillance sensors, vehicle speed sensors, traffic flow counters, etc., and the data collected by each of them constitutes the traffic observation point data. Then, the longitudinal traffic section of the section is analyzed for the interchange space scene based on the traffic observation point data. The server analyzes the vehicle's driving direction, lane distribution, vehicle spacing and other information on the longitudinal section where each observation point is located, and generates traffic observation point section data. At the same time, the observation point traffic flow is monitored on the highway section based on the traffic observation point data. For example, the number of vehicles passing through each observation point per hour is counted by the traffic flow counter to generate the observation point traffic flow data.

[0019] Next, the traffic flow of the interchange is calculated based on the cross-sectional data of the traffic observation point and the traffic flow data of the observation point. The server uses an algorithm to consider the distribution and flow speed of vehicles in different cross-sectional areas, calculates the traffic flow situation within the entire interchange, and generates the traffic flow data of the observation point. For example, the traffic volume entering the interchange from a certain entrance ramp and heading to a specific exit, as well as the number of vehicle transfers between different lanes, etc. are calculated. Finally, based on the traffic flow data of the observation point and the traffic flow data of the observation point, the observation point data of the highway section is fused to generate a traffic operation data stream. This traffic operation data stream contains the comprehensive traffic information of each observation point of the entire highway section, such as the traffic volume, speed distribution, and vehicle type ratio in different time periods.

[0020] Then, the traffic dynamic change map of the interchange space scene is analyzed based on the traffic operation data flow. First, the traffic flow and speed analysis is performed on the traffic operation data flow. The server analyzes the data of different time periods to determine the traffic flow differences between peak and trough periods, as well as the speed change patterns of different sections, and generates traffic flow characteristic data. For example, it is found that 8-10 am every day is the peak of traffic flow from the city to the suburbs, and the speed drops significantly at some bends in the interchange. Then, based on the traffic flow characteristic data, the speed impact characteristics of the interchange space scene are simulated. The server simulates the speed changes of vehicles passing through the interchange under different traffic flows, and generates speed impact characteristic data taking into account the influence of factors such as road slope and curve radius on vehicle speed.

[0021] Then, the traffic flow characteristic data and the vehicle speed impact characteristic data are mapped to generate a traffic flow change characteristic map. This traffic flow change characteristic map shows the changing relationship between traffic flow and vehicle speed in the interchange space scene in a visual way. For example, different colored lines are used to represent the speed change trend of different lanes, and the thickness of the lines is used to represent the size of the traffic flow. After that, the traffic operation data stream is analyzed for traffic congestion and smooth conditions. The server determines the areas and time periods of traffic congestion and smoothness based on indicators such as traffic flow, speed, and vehicle queue length, and generates traffic status data. For example, when the traffic flow at a certain exit ramp is too large and the speed is lower than a certain threshold, it is judged to be in a congested state.

[0022] Then, the traffic situation of the interchange space scene is simulated based on the traffic status data. The server simulates the spread and impact range of traffic congestion or unblocked status in the interchange and generates traffic situation data. For example, when a certain entrance ramp is congested, the impact on the entire interchange and adjacent sections of traffic is simulated. Finally, the traffic flow change feature map and the traffic situation map are integrated to generate a traffic dynamic change map. This map comprehensively reflects the dynamic change information such as traffic flow, vehicle speed, congestion status, etc. in the interchange space scene.

[0023] Step S120, mapping the road domain perception data blocks of the expressway section to generate road domain block perception data, extracting the driving behavior data blocks from the road domain block perception data to generate driving behavior data blocks, extracting the non-driving behavior data blocks from the road domain block perception data to generate non-driving behavior data blocks.

[0024] In this embodiment, the server performs a road domain perception data block mapping operation on the expressway section. For example, for the G1 expressway section mentioned above, the server will use multiple video surveillance devices deployed on the expressway section to perform road domain detection video surveillance on the expressway section. These video surveillance devices cover different road section areas, including straight sections, curves, interchange areas, etc., continuously collect video streams, and generate expressway section road domain detection video streams. The video stream contains information such as the vehicle's driving trajectory, lane occupancy, and visibility of traffic signs.

[0025] Then, the highway section road detection video stream is mapped to road area blocks. The server divides the entire highway section into multiple blocks, for example, one block every 100 meters. By analyzing the geographic location information in the video stream (such as by comparing it with a known road coordinate system), the vehicles and road elements in the video stream are mapped to the corresponding road area blocks to generate road area block perception data. For example, the data of a certain road area block includes information such as the number of vehicles in the area, the direction of vehicle travel, and whether there is abnormal parking.

[0026] Then, the driving behavior data block is extracted from the road block perception data. First, the driving operation feature is extracted from the road block perception data. The server first extracts the block dynamic feature of the road block perception data, such as analyzing the dynamic behaviors of the vehicle in each block, such as acceleration, deceleration, lane change, etc., to generate block perception dynamic feature data. Then, based on the block perception dynamic feature data, the road block perception data is analyzed for traffic area dynamic features, the dynamic behavior characteristics of the vehicle in different traffic areas (such as acceleration lanes, main lanes, overtaking lanes, etc.) are determined, and the traffic area dynamic features are generated.

[0027] Afterwards, the non-traffic area features are extracted from the road area block perception data based on the dynamic characteristics of the traffic area. For example, the behavior characteristics of vehicles in non-traffic areas such as service area entrances and emergency parking strips are analyzed to generate non-traffic area feature data. Then, regular driving pattern features are extracted from the non-traffic area feature data, such as analyzing the deceleration and parking patterns of vehicles at the service area entrances to generate regular driving pattern feature data. Based on the regular driving pattern feature data, the road area block perception data is analyzed for regular driving area features, such as determining the common speed range, following distance and other regular features of vehicles in normal driving areas (such as the main lane), and generating regular driving area features. Finally, the dynamic characteristics of the traffic area and the regular characteristics of the normal driving area are fused to generate driving operation feature data.

[0028] Based on the driving operation characteristic data, the driving behavior data block is extracted from the road area block perception data to generate a driving behavior data block. For example, the vehicle data with similar driving operation characteristics (such as frequent lane changes, stable following, etc.) are classified into a driving behavior data block. At the same time, based on the driving operation characteristic data, the non-driving behavior data block is extracted from the road area block perception data to generate a non-driving behavior data block. For example, the road facility status that is not related to vehicle driving (such as damaged traffic signs, road conditions, etc.), abnormal parking, pedestrian intrusion, etc. data are classified as non-driving behavior data blocks.

[0029] Step S130 , analyzing the traffic state influencing factors of the expressway section according to the driving behavior data block and the non-driving behavior data block to generate the traffic state influencing factors.

[0030] In this embodiment, the server analyzes the traffic state influencing factors of the highway section based on the driving behavior data block and the non-driving behavior data block. First, the driving behavior data block is analyzed for the normal driving feature vector. For example, for the normal driving data of the vehicle in the driving behavior data block, the server analyzes the average speed of the vehicle, the speed fluctuation range, the average value of the following distance, and other parameters to generate the normal driving feature vector of the driving behavior.

[0031] The factors affecting the traffic flow of the expressway are analyzed based on the normal driving feature vector of driving behavior. For example, if the average speed of vehicles in a certain area is high and the speed fluctuation is small, and the following distance is reasonable, the server will determine that the driving behavior in this area has a positive impact on the traffic flow of the section and generate a driving behavior impact traffic flow vector. This vector may include factors affecting the speed of traffic flow, traffic flow stability, etc.

[0032] Then, the non-driving behavior data block is parsed for abnormal parking ratio. The server counts the number of abnormal parking events in the non-driving behavior data block and compares it with the total number of vehicles to generate the abnormal parking ratio. For example, within a certain time period, there are 5 abnormal parking events on a certain road section, and the total number of vehicles is 1,000, then the abnormal parking ratio is 0.5%.

[0033] The congestion impact vector of the highway section is analyzed based on the abnormal parking ratio. If the abnormal parking ratio is high, the server will determine that the section is more likely to be congested and generate a congestion impact vector for the section. This vector includes factors that affect the possibility of congestion formation and the scope of congestion spread.

[0034] Then, the factors affecting the traffic flow in the normal driving section of the expressway are analyzed based on the non-driving behavior area. For example, for the distribution of traffic facilities in the non-driving behavior area, the server identifies the distribution of traffic facilities. Suppose that the traffic signs are found to be unreasonable or the signal light cycle is too long on a certain section of road. The server calculates the section signal cycle for the distribution of traffic facilities and generates the section signal cycle. Then, the traffic duration extension analysis is performed on the expressway section based on the section signal cycle. If the signal light cycle is too long, it will increase the waiting time of vehicles and extend the traffic duration.

[0035] The server further performs an incremental analysis of vehicle lane changes on the highway section based on the extended traffic time data. Due to the extended traffic time, vehicles may frequently change lanes to find a faster passage, generating incremental lane change data. The reduction in the number of vehicles in normal driving on the highway section is calculated based on the incremental lane change data. Because the increase in vehicle lane changes may lead to a decrease in the number of vehicles in normal driving, the reduction in the number of vehicles in normal driving is generated. Finally, based on the reduction in the number of vehicles in normal driving, the traffic flow influencing factors of the highway section are analyzed to generate a vector affecting the traffic flow in normal driving.

[0036] Finally, the weighted fusion of the road congestion impact vector and the normal driving impact traffic flow vector is performed to generate the non-driving behavior impact traffic flow vector. The server assigns different weights to the road congestion impact vector and the normal driving impact traffic flow vector based on the actual traffic conditions and empirical data. For example, during peak traffic hours, the weight of the congestion impact vector may be higher. The two are then weighted and summed to generate the non-driving behavior impact traffic flow vector. The driving behavior impact traffic flow vector and the non-driving behavior impact traffic flow vector are then fused to generate the traffic state impact factor. This traffic state impact factor comprehensively considers the impact of driving behavior and non-driving behavior on the traffic state of the highway section.

[0037] Step S140, optimize the traffic dynamic change map based on the road area block perception data and the traffic status influencing factors to generate an optimized traffic dynamic change map, and estimate the traffic safety risk trend of the expressway section based on the optimized traffic dynamic change map and the interchange space scene to generate traffic safety risk trend data, and generate safety tips and suggestions for the interchange space scene based on the traffic safety risk trend data.

[0038] In this embodiment, the server optimizes the traffic dynamic change map based on the road block perception data and traffic state influencing factors. First, the road facilities are extracted from the road block perception data. For example, the road curve type (such as sharp curve, slow curve), road width, traffic signs (such as speed limit signs, lane indication signs) and other types of road facility features are identified from the road block perception data.

[0039] The traffic dynamic change map is optimized based on the characteristics of various types of road facilities and traffic status influencing factors. For example, if a road section has a sharp curve and the traffic status influencing factors show that the road section is prone to congestion, the server will strengthen the identification of the road section in the traffic dynamic change map, such as using more eye-catching colors to indicate areas with higher congestion risks, and add detailed information on the impact of curves on vehicle speed to the map to generate an optimized traffic dynamic change map.

[0040] Then, the traffic flow impact trend of the interchange space scene is simulated based on the optimized traffic dynamic change map. Based on the traffic information in the optimized map, the server simulates the flow trend of vehicles in the interchange space scene under different time periods and traffic conditions, and generates a trend model of traffic flow impacting the highway section. For example, it predicts the diversion of vehicles coming from a certain city at the interchange during peak hours during holidays, as well as possible congestion points.

[0041] The traffic safety risk trend of the highway section is estimated based on the trend model of traffic flow affecting the highway section, and traffic safety risk trend data is generated. For example, if the model shows that a vehicle collision accident is prone to occur at a certain exit ramp due to excessive traffic flow and limited road facilities, the server will generate corresponding traffic safety risk trend data, including the possibility of an accident, the number of vehicles that may be affected, etc.

[0042] Finally, based on the traffic safety risk trend data, safety tips and suggestions for the interchange space scenario are generated. For example, if the traffic safety risk trend data of a certain area indicates that the accident risk is high, the server will generate safety tips and suggestions such as "There is heavy traffic and sharp curves at Exit A of the interchange, please slow down and pay attention to the distance between vehicles", which can be conveyed to the driver through traffic broadcasts, electronic display screens, etc.

[0043] Based on the above steps, the embodiment of the present application can realize the accurate reconstruction and dynamic monitoring of the interchange space scene of the expressway section. The traffic operation data stream is generated through the AI ​​sensor fusion acquisition technology, and then a detailed traffic dynamic change map is parsed. At the same time, through the block mapping and fine extraction of the road domain perception data, the driving behavior data block and the non-driving behavior data block are effectively separated, which provides a data basis for in-depth analysis of the factors affecting the traffic state. The further optimized traffic dynamic change map, combined with the interchange space scene, can accurately estimate the traffic safety risk trend and generate forward-looking traffic safety risk trend data, thereby being able to generate targeted safety tips and suggestions in a timely manner, significantly improving the traffic safety management level and emergency response capabilities of the expressway section, effectively preventing and reducing the occurrence of traffic accidents, and ensuring the safety of public travel.

[0044] In a possible implementation, step S110 includes:

[0045] Step S111, performing a partitioned drone aerial photography scan on the highway section to generate partitioned drone aerial photography scan data.

[0046] Step S112, fusing the partitioned UAV aerial photography and scanning data to generate target UAV aerial photography and scanning data.

[0047] Step S113, reconstructing the interchange space scene of the expressway section according to the target drone aerial scanning data to generate an interchange space scene.

[0048] Step S114, performing AI sensor fusion collection on the highway section according to the interchange space scene to generate a traffic operation data stream.

[0049] Step S115, analyzing the traffic dynamic change map of the interchange space scene according to the traffic operation data flow to generate a traffic dynamic change map.

[0050] In a possible implementation, step S114 includes:

[0051] Step S1141, configure traffic observation points on the expressway section to generate traffic observation point data, perform longitudinal traffic section analysis on the interchange space scene based on the traffic observation point data to generate traffic observation point section data, and monitor the traffic flow at the observation points on the expressway section based on the traffic observation point data to generate traffic flow data at the observation points.

[0052] Step S1142, performing interchange traffic flow calculation on the traffic observation point data based on the traffic observation point section data and the observation point vehicle flow data, and generating the observation point traffic flow data.

[0053] Step S1143, performing observation point data fusion on the expressway section based on the observation point vehicle flow data and the observation point traffic flow data to generate a traffic operation data flow.

[0054] In a possible implementation, step S115 includes:

[0055] Step S1151, analyze and parse the traffic flow and speed of the traffic operation data flow to generate traffic flow characteristic data, simulate the vehicle speed impact characteristics of the interchange space scene based on the traffic flow characteristic data to generate vehicle speed impact characteristic data, construct a graph of the traffic flow characteristic data and the vehicle speed impact characteristic data to generate a traffic flow change characteristic graph.

[0056] Step S1152, analyzing the traffic congestion and smooth traffic conditions of the traffic operation data stream to generate traffic status data.

[0057] Step S1153, performing traffic situation simulation on the interchange space scene according to the traffic status data to generate traffic situation data, constructing a map of the traffic status data and the traffic situation data to generate a traffic situation map.

[0058] Step S1154, the traffic flow change characteristic map and the traffic situation map are integrated to generate a traffic dynamic change map.

[0059] In this embodiment, for a specific highway section (such as a section of the G2 highway that connects multiple cities and has a large traffic volume, which contains a complex interchange structure), first, the server performs a partitioned drone aerial scan of the highway section to generate partitioned drone aerial scan data. The server will pre-plan the scanning plan and partition it according to the length of the highway section, the complexity of the terrain, and the distribution of interchanges. For example, the entire highway section is divided into 500-meter partition units. Multiple drones equipped with high-resolution cameras, laser radars and other equipment fly along a predetermined route to perform detailed scans of each partition. The camera can capture information such as the surface condition of the road (such as whether there are cracks, potholes, etc.), the clarity of the lane lines, the location and status of traffic signs, etc.; the laser radar can obtain three-dimensional spatial information of the road and surrounding terrain, including the height, slope, and curvature of the interchange. The scanning data of each partition will contain these multi-dimensional information to form partitioned drone aerial scan data.

[0060] Next, the server fuses the partitioned drone aerial scanning data to generate the target drone aerial scanning data. Since there may be some differences in the data of different partitions (such as overlapping data at the partition boundaries), the server needs to calibrate and integrate these data. It will align the data of each partition by identifying key features in the data (such as specific identification points on the road, iconic features of the terrain, etc.). At the same time, the data of the overlapping parts are optimized and the most accurate and complete data are selected for retention. For example, in the overlapping area of ​​adjacent partitions, if the data of one partition shows that the road width is 10 meters and the other partition shows 10.1 meters, the server will combine other relevant data (such as the continuity of the lane line, etc.) to determine the final road width value. After such a series of processing, the data of all partitions are fused into a complete target drone aerial scanning data, which can accurately and comprehensively reflect the status of the entire highway section, especially the overall structure and detailed information of the interchange.

[0061] Then, the interchange space scene of the highway section is reconstructed based on the target drone aerial scanning data to generate the interchange space scene. The server uses professional 3D modeling software to construct the interchange space scene based on various parameters in the target drone aerial scanning data. For each lane in the interchange, the lane width, length, slope and other information in the scan data are accurately constructed in the model; the connection relationship of the ramp, the turning radius and the connection point with the main road are also accurately modeled based on the data. At the same time, the location and orientation of traffic signs (such as speed limit signs, signs, etc.), the distribution of street lights and other surrounding facilities are also reflected in the model. This interchange space scene is a highly accurate 3D digital model, which provides a basic spatial framework for subsequent traffic analysis.

[0062] Afterwards, AI sensor fusion is performed on the highway section according to the interchange space scene to generate a traffic operation data stream. This process includes multiple sub-steps. First, the server configures traffic observation points on the highway section and generates traffic observation point data. The server sets observation points at key locations according to the characteristics of the interchange space scene. For example, observation points are set at the entrance ramp, exit ramp, confluence point, divergence point, start and end points of the curve, and specific intervals of the main road of the interchange. Each observation point is equipped with multiple types of sensors, such as video sensors, radar sensors, geomagnetic sensors, etc. Video sensors can obtain information such as the appearance characteristics, license plate number, and driving trajectory of the vehicle; radar sensors can accurately measure parameters such as the speed and distance of the vehicle; and geomagnetic sensors can detect the passage of the vehicle. The data collected by these sensors together constitute the traffic observation point data.

[0063] Based on the traffic observation point data, the longitudinal traffic section of the interchange space scene is analyzed to generate traffic observation point section data. The server will analyze the distribution and flow of vehicles in the longitudinal direction with each observation point as the center. For example, at an observation point located on the entrance ramp, the server will analyze the queue length of vehicles entering the main road from the ramp within a certain period of time, the distance between vehicles, the acceleration of vehicles, and other information. At the same time, the impact of factors such as the slope of the road and the number of lanes on vehicle driving will also be considered, and this information will be integrated to generate traffic observation point section data.

[0064] Based on the traffic observation point data, the traffic flow of the observation point on the highway section is monitored to generate the traffic flow data of the observation point. The sensors at each observation point continuously collect vehicle flow information. For example, the geomagnetic sensor can accurately count the number of vehicles passing through the observation point in a unit of time, and the radar sensor can assist in verifying the passing of the vehicle to avoid misjudgment. The server organizes this data to generate the traffic flow data of the observation point, which includes the number of vehicles passing through each observation point in different time periods (such as every 5 minutes, every 10 minutes, etc.), as well as the proportion information of vehicle types (such as small cars, large trucks, etc.).

[0065] The traffic flow of the interchange is calculated based on the cross-sectional data of the traffic observation point and the traffic flow data of the observation point, and the traffic flow data of the observation point is generated. The server uses a complex algorithm to combine the vehicle driving status in the cross-sectional data of the traffic observation point and the traffic flow information in the traffic flow data of the observation point to calculate the traffic flow situation within the entire interchange. For example, when calculating the traffic flow from an entrance ramp to an exit ramp, the merging, merging, and lane changes of vehicles between various observation points, as well as the distribution of traffic flow between different lanes, are taken into account. By comprehensively analyzing these factors, the traffic flow data of the observation point is generated, which can reflect the flow direction, flow rate and other information of the traffic flow in each area of ​​the interchange.

[0066] The observation point data of the highway section is fused based on the observation point vehicle flow data and the observation point traffic flow data to generate a traffic operation data stream. The server fuses the observation point vehicle flow data and the observation point traffic flow data generated previously. For example, the vehicle flow information of each observation point is combined with the traffic flow direction, flow speed and other information in the area where the observation point is located, taking into account the relationship and influence between different observation points. During the fusion process, the data will also be quality checked and corrected to remove possible erroneous data or outliers. The traffic operation data stream finally generated contains the comprehensive traffic information of each observation point in the entire highway section, such as detailed information such as vehicle flow, speed, and vehicle type distribution in different lanes and different time periods.

[0067] Then, the traffic dynamic change map of the interchange space scene is analyzed based on the traffic operation data stream to generate a traffic dynamic change map. First, the traffic flow and speed analysis of the traffic operation data stream is performed to generate traffic flow characteristic data. The server will conduct an in-depth analysis of the vehicle flow and speed data in the traffic operation data stream. For example, analyze the traffic flow change pattern in different time periods within 24 hours a day to find out the peak and trough periods of traffic; at the same time, analyze the speed distribution of different sections of the road (such as different ramps of the interchange, different sections of the main road, etc.) to determine which areas are prone to slower speeds (such as curves, confluence points, etc.). These analysis results are integrated to generate traffic flow characteristic data, which can clearly reflect the distribution characteristics of traffic flow and speed in time and space.

[0068] The speed impact characteristics of the interchange space scene are simulated based on the traffic flow characteristic data to generate speed impact characteristic data. The server simulates the speed impact characteristics based on the traffic volume, lane distribution and other information in the traffic flow characteristic data, combined with factors such as road slope and curve radius in the interchange space scene. For example, at a ramp with a small curve radius, when the traffic volume is large, the reasonable speed range of the vehicle is calculated through simulation, as well as the changing trend of the speed affected by the traffic volume and road conditions. These simulation results form speed impact characteristic data, which can accurately reflect the impact of various factors on the speed.

[0069] The traffic flow characteristic data and the vehicle speed impact characteristic data are mapped to generate a traffic flow change characteristic map. The server uses professional map construction tools to present the traffic flow characteristic data and the vehicle speed impact characteristic data in a visual way. In the traffic flow change characteristic map, different colors and lines are used to represent the traffic flow and speed changes in different lanes and areas. For example, red lines are used to represent areas with heavy traffic and slow speeds, and blue lines are used to represent areas with light traffic and fast speeds; the thickness of the lines can represent the size of the traffic flow. Such a map can intuitively show the changing trend of traffic flow in the interchange space scene.

[0070] The traffic operation data stream is analyzed for traffic congestion and smooth traffic conditions to generate traffic status data. The server determines traffic congestion and smooth traffic conditions by analyzing multiple indicators such as vehicle flow, vehicle speed, and vehicle queue length in the traffic operation data stream. For example, when the vehicle flow in a certain area exceeds a certain threshold, and the vehicle speed is lower than a certain set value, and the length of the vehicle queue reaches a certain standard, the area is judged to be congested; conversely, when the vehicle flow is within the normal range and the vehicle speed is stable and high, it is judged to be smooth. These judgment results and related quantitative indicators (such as the level of congestion, the length of the smooth period, etc.) are organized into traffic status data.

[0071] The traffic situation of the interchange space scene is simulated based on the traffic status data to generate traffic situation data. The server simulates the traffic situation in the interchange space scene based on the congestion and smooth traffic information in the traffic status data. For example, when simulating the congestion state, the queueing form of vehicles in the congested area and the slow movement trajectory of vehicles will be displayed; when simulating the smooth traffic state, the normal driving trajectory of vehicles and the lane utilization will be displayed. Through such simulation, traffic situation data is generated, which can reflect the propagation and evolution trend of traffic status in the interchange space scene.

[0072] The traffic status data and traffic situation data are mapped to generate a traffic situation map. Similar to the construction of traffic flow change characteristic maps, professional tools are used to visualize the traffic status data and traffic situation data into a traffic situation map. In this map, different colors and patterns are used to represent different traffic conditions (such as red for congestion and green for smooth traffic), and the changes in traffic conditions in different time periods and regions can be displayed.

[0073] Finally, the traffic flow change characteristic map and the traffic situation map are integrated to generate a traffic dynamic change map. The server integrates and fuses the information in the traffic flow change characteristic map and the traffic situation map. For example, the vehicle speed and traffic volume information in the traffic flow change characteristic map is combined with the traffic congestion and smooth flow status information in the traffic situation map, so that the traffic dynamic change map can fully and accurately reflect the dynamic change information such as traffic flow, vehicle speed, congestion status in the interchange space scene. This traffic dynamic change map provides an important basis for subsequent traffic analysis, management and decision-making.

[0074] In a possible implementation, step S120 includes:

[0075] Step S121, performing road area detection video monitoring on the expressway section to generate a road area detection video stream of the expressway section.

[0076] Step S122, performing road block mapping on the highway section road area detection video stream to generate road area block perception data.

[0077] Step S123, extracting driving operation features from the road area block perception data to generate driving operation feature data.

[0078] Step S124 , extracting driving behavior data blocks from the road area block perception data according to the driving operation feature data to generate driving behavior data blocks.

[0079] Step S125 , extracting non-driving behavior data blocks from the road area block perception data according to the driving operation feature data to generate non-driving behavior data blocks.

[0080] In a possible implementation, step S123 includes:

[0081] Step S1231, extracting block dynamic features from the road block perception data to generate block perception dynamic feature data.

[0082] Step S1232, analyzing the traffic area dynamic characteristics of the road block perception data according to the block perception dynamic characteristic data to generate the traffic area dynamic characteristics.

[0083] Step S1233, extracting non-traffic area features from the road area block perception data based on the dynamic features of the traffic area to generate non-traffic area feature data.

[0084] Step S1234, extracting regular driving pattern features from the non-traffic area feature data to generate regular driving pattern feature data.

[0085] Step S1235, analyzing the regular characteristics of the normal driving area of ​​the road block perception data according to the regular driving pattern characteristic data, and generating the regular characteristics of the normal driving area.

[0086] Step S1236, the dynamic characteristics of the traffic area and the regular characteristics of the normal driving area are integrated to generate driving operation characteristic data.

[0087] In this embodiment, for a busy expressway section (such as a G3 expressway section that connects multiple important cities, has a large traffic flow and complex road conditions), the expressway section is firstly subjected to road detection video monitoring to generate a highway section road detection video stream. Along the expressway section, the server controls multiple high-definition video monitoring devices, which are carefully arranged to cover various key areas of the entire expressway section, including interchanges, long straight roads, curves, tunnel entrances and exits, etc. Each video monitoring device has high resolution, wide viewing angle, and the ability to adapt to different lighting conditions. They continuously shoot the situation on the expressway section at a fixed frame rate (such as 30 frames per second), thereby generating a highway section road detection video stream. The video stream contains rich information, such as the driving trajectory of each vehicle, the position of the vehicle in the lane, the appearance of the vehicle (which can be used to roughly determine the type of vehicle, such as a car, truck, bus, etc.), the distance between vehicles, the position relationship of the vehicle relative to traffic signs (such as lane lines, speed limit signs, etc.), and any visible objects on the road (such as scattered debris, etc.).

[0088] Next, the server maps the road domain detection video stream of the highway section to road domain blocks and generates road domain block perception data. The server divides the entire highway section into multiple road domain blocks. The basis for the division can be based on geographic coordinates, fixed distance intervals, or according to the structural characteristics of the road (such as division based on each interchange). For example, each 1-kilometer section is divided into a road domain block. Then, the server analyzes the image information in the video stream and uses image recognition technology and geographic positioning information to accurately map the vehicles, traffic signs and other road elements in the video stream to the corresponding road domain blocks. In this process, the server will identify the coordinate position of the vehicle and determine the road domain block where the vehicle is located according to the pre-set block division rules. For traffic signs, the server will also determine the location of the road domain block where it is located and record the type of sign (such as a speed limit of 60 kilometers per hour sign is located in a specific road domain block). At the same time, special situations on the road (such as road surface damage in a road domain block) will also be marked. In this way, each road domain block has corresponding perception data containing various road element information, thereby generating road domain block perception data.

[0089] Then, the server extracts driving operation features from the road block perception data and generates driving operation feature data. This process includes multiple sub-steps. First, the server extracts block dynamic features from the road block perception data and generates block perception dynamic feature data. The server analyzes the dynamic behavior of vehicles in each road block, such as the vehicle's acceleration, deceleration, and constant speed driving state changes, the vehicle's lane change operations (including the starting position of the lane change, the direction of the lane change, and the duration of the lane change), and the vehicle's steering operations (such as the steering angle and steering speed at the curve). By monitoring and analyzing these dynamic behaviors, the server can obtain the dynamic characteristics of vehicles in each road block, such as the average acceleration amplitude and lane change frequency of vehicles in a certain road block, thereby generating block perception dynamic feature data.

[0090] According to the block perception dynamic feature data, the road block perception data is analyzed for the dynamic characteristics of the traffic area to generate the dynamic characteristics of the traffic area. Based on the previously obtained block perception dynamic feature data, the server further analyzes the dynamic behavior characteristics of the vehicle in different traffic areas (such as acceleration lanes, normal driving lanes, overtaking lanes, exit ramps, entrance ramps, etc.). In the acceleration lane, the server will focus on the acceleration of the vehicle, such as counting the average time for the vehicle to reach the specified speed of the expressway section; in the normal driving lane, the speed stability of the vehicle and the change of the following distance will be analyzed; in the overtaking lane, the frequency and safety of the vehicle's overtaking operation will be paid attention to (such as whether the distance with the front and rear vehicles when overtaking meets the safety standards); in the exit ramp and entrance ramp, the standardization of the vehicle's deceleration, merging and exiting operations will be analyzed. Through such analysis, the server can obtain the dynamic behavior pattern of the vehicle in different traffic areas, thereby generating dynamic characteristics of the traffic area.

[0091] Based on the dynamic characteristics of the traffic area, the non-traffic area features of the road area block perception data are extracted to generate non-traffic area feature data. Based on the dynamic characteristics of the traffic area, the server extracts features from the non-traffic areas (such as service areas, emergency parking strips, road construction areas, etc.) in the road area block perception data. For the service area, the server will analyze the time distribution of vehicles entering and leaving the service area, the length of stay in the service area, and the driving operations of the vehicles at the entrance and exit of the service area (such as deceleration, parking, turning, etc.); for the emergency parking strip, the reasons for the vehicles stopping in the emergency parking strip (by analyzing the previous driving status and surrounding environment of the vehicle, such as whether it is due to a sudden failure) and the length of parking time will be monitored; for the road construction area, attention will be paid to the speed adjustment and lane change of the vehicle when approaching and passing the construction area. These feature information about non-traffic areas are integrated to generate non-traffic area feature data.

[0092] Regular driving pattern features are extracted from the non-traffic area feature data to generate regular driving pattern feature data. The server conducts in-depth analysis of the non-traffic area feature data to find out the regular driving patterns. For example, in terms of service areas, the server may find that most vehicles will enter the service area to rest after driving a certain mileage (such as every 2-3 hours of driving mileage), and the stay time in the service area shows a certain distribution pattern (such as most vehicles stay for 15-30 minutes); in terms of emergency parking strips, it is found that the proportion of vehicles stopping due to vehicle failures and the waiting time for rescue of these faulty vehicles also have certain regularities; for road construction areas, there are also certain common patterns in the speed adjustment amplitude and lane change method of vehicles when passing through the construction area. Summarize these rules and generate regular driving pattern feature data.

[0093] According to the regular driving pattern feature data, the road area block perception data is analyzed for regular driving area features to generate regular driving area features. The server further analyzes the regular features of vehicles in normal driving areas (such as the main lane of a highway section) based on the regular driving pattern feature data. For example, by analyzing the speed distribution of vehicles in normal driving areas, it is found that most vehicles will maintain a certain speed range (such as 90-110 kilometers per hour) in the absence of special circumstances (such as traffic congestion, weather changes, etc.); in terms of following distance, the average following distance between vehicles also has a relatively stable range; at the same time, the lane keeping of vehicles (such as rarely changing lanes frequently during normal driving) also shows certain regularities. These regular features of the normal driving area are extracted to generate regular features of the normal driving area.

[0094] Finally, the dynamic characteristics of the traffic area and the regular characteristics of the normal driving area are fused to generate driving operation characteristic data. The server fuses the previously obtained dynamic characteristics of the traffic area and the regular characteristics of the normal driving area. For example, during the fusion process, the relationship between the vehicle in different traffic areas (such as the acceleration operation of the acceleration lane) and the normal driving area (such as the speed stability of the main lane) will be considered. If the acceleration of the vehicle in the acceleration lane is too slow or too fast, it may affect its speed stability after entering the main lane. By comprehensively analyzing these factors, the relevant information in the dynamic characteristics of the traffic area and the regular characteristics of the normal driving area are integrated to generate driving operation characteristic data. This driving operation characteristic data can comprehensively reflect the driving operation characteristics of the vehicle in various areas of the entire highway section, including the comprehensive characteristics of the vehicle's acceleration, deceleration, lane change, following, lane keeping and other operations, providing an important data basis for subsequent driving behavior analysis.

[0095] The driving behavior data block is extracted from the road block perception data based on the driving operation characteristic data to generate a driving behavior data block. The server classifies the road block perception data according to the similarity in the driving operation characteristic data, and classifies the vehicle data with similar driving operation characteristics into one driving behavior data block. For example, vehicles that frequently change lanes, have large speed fluctuations, and follow vehicles at a close distance are classified into one driving behavior data block. Such vehicles may represent drivers with aggressive driving behavior; vehicles with stable speeds, few lane changes, and moderate following distances are classified into another driving behavior data block. Such vehicles may represent more stable driving behavior.

[0096] Based on the driving operation characteristic data, the non-driving behavior data blocks are extracted from the road area block perception data to generate non-driving behavior data blocks. The server also extracts the road area block perception data that is not related to the vehicle driving operation based on the driving operation characteristic data to form non-driving behavior data blocks. For example, information such as the damage of traffic signs on the road, the accumulation of water or snow on the road surface, and temporary traffic control caused by non-vehicle reasons (such as wild animals intruding) are classified as non-driving behavior data blocks. These data blocks help to conduct a comprehensive analysis of the traffic conditions on the highway section, taking into account not only the driver's driving behavior, but also non-driving related factors such as the road environment.

[0097] In a possible implementation, step S130 includes:

[0098] Step S131, performing normal driving feature vector analysis on the driving behavior data block to generate a normal driving feature vector of the driving behavior.

[0099] Step S132, analyzing the traffic flow influencing factors of the expressway section according to the normal driving feature vector of the driving behavior, and generating a driving behavior influencing traffic flow vector.

[0100] Step S133, performing abnormal parking ratio analysis on the non-driving behavior data block to generate an abnormal parking ratio.

[0101] Step S134, analyzing the road congestion impact vector of the expressway section according to the abnormal parking ratio to generate a road congestion impact vector.

[0102] Step S135, analyzing the traffic flow influencing factors of the normal driving section of the expressway section according to the non-driving behavior area, and generating a normal driving influencing traffic flow vector.

[0103] Step S136, weighting and fusing the road congestion impact vector and the normal driving impact traffic flow vector to generate a non-driving behavior impact traffic flow vector.

[0104] Step S137: The traffic flow vector affected by driving behavior and the traffic flow vector affected by non-driving behavior are integrated to generate a traffic state impact factor.

[0105] In this embodiment, for the G3 expressway section mentioned above, the server analyzes the traffic state influencing factors of the expressway section based on the driving behavior data block and the non-driving behavior data block to generate the traffic state influencing factors.

[0106] First, the server performs a normal driving feature vector analysis on the driving behavior data block to generate a normal driving feature vector of the driving behavior. The server will deeply analyze the data in the driving behavior data block, focusing on the various features of the vehicle when it is driving normally. For example, for each driving behavior data block, the server will count the average speed of the vehicle in normal driving state. This speed is obtained by averaging the speed data of a large number of vehicles in the data block on normal driving sections (such as straight sections without traffic control, road construction or other abnormal conditions). At the same time, the server will calculate the standard deviation of the speed to measure the fluctuation of the speed. If the standard deviation is small, it means that the vehicle's driving speed is relatively stable; otherwise, it means that the speed fluctuation is large. In addition, the server will also analyze the following distance of the vehicle, calculate the average following distance and the distribution of the following distance. For example, through analysis, it is found that the proportion of the following distance of most vehicles is within a certain safety interval. In addition, the lane keeping of the vehicle is also an important factor. The server will count the proportion of time that the vehicle stays in the same lane during normal driving. If this proportion is high, it means that the vehicle has good lane keeping performance. These normal driving characteristics such as average speed, speed fluctuation, following distance, lane keeping, etc. are combined to form a multi-dimensional vector, namely the normal driving characteristic vector of driving behavior. This vector can comprehensively describe the comprehensive characteristics of normal driving of the vehicle under a specific driving behavior data block.

[0107] Next, the factors affecting the traffic flow of the expressway section are analyzed based on the normal driving feature vector of driving behavior, and a driving behavior affecting traffic flow vector is generated. The server uses the previously generated normal driving feature vector of driving behavior to analyze its impact on the traffic flow of the expressway section. Taking the average speed as an example, if the average speed of vehicles in a certain driving behavior data block is high and the speed fluctuation is small, this may mean that the driving efficiency of vehicles on this section is high and the overall flow rate of traffic is fast. In this case, the server will calculate the positive impact of this factor on the traffic flow of the section based on the pre-set algorithm and traffic flow model. For example, it may improve the traffic capacity of the section and reduce mutual interference between vehicles, which is reflected in the driving behavior affecting traffic flow vector as a positive contribution to the speed and smoothness of the traffic flow. As for the following distance and lane keeping, if the following distance of the vehicle is reasonable and the lane keeping is good, this will help maintain the stability of the traffic flow, reduce the risk of traffic accidents, and thus increase the traffic capacity of the section. The server generates a driving behavior impact traffic flow vector by comprehensively considering the performance of these factors in the normal driving feature vector of driving behavior. This vector reflects the impact of driving behavior on the speed, stability, and capacity of traffic on the road section.

[0108] Then, the server analyzes the abnormal parking ratio of the non-driving behavior data block and generates the abnormal parking ratio. The server will carefully comb the data in the non-driving behavior data block and focus on finding information related to abnormal parking. For example, all parking events on the highway section are recorded in the non-driving behavior data block. The server will determine which parking is abnormal based on the reason, location and time of the parking. The basis for judging abnormal parking may include parking in a non-emergency parking zone, no reasonable parking reason (such as non-fault, non-emergency), etc. The server counts the number of these abnormal parking events and then divides it by the total number of parking events (including normal parking and abnormal parking) to obtain the abnormal parking ratio. Assuming that within a certain period of time, a total of 100 parking events occurred on the highway section, of which 10 were abnormal parking after analysis, then the abnormal parking ratio is 10%. This abnormal parking ratio is an important indicator that can reflect the degree of interference of non-driving behavior factors on the traffic order on the highway section.

[0109] The congestion impact vector of the expressway section is analyzed based on the abnormal parking ratio to generate the congestion impact vector of the section. When the server obtains the abnormal parking ratio, it will analyze the impact of this ratio on the congestion of the expressway section. A higher abnormal parking ratio usually increases the risk of congestion in the section. For example, if the abnormal parking ratio reaches 10%, the server will evaluate the impact on the congestion of the section in this case based on traffic flow theory and historical data. Abnormal parking may cause the rear vehicle to slow down and change lanes, thereby disrupting the normal traffic order. The server will consider the impact of this interference on congestion-related factors such as traffic speed, traffic density and queue length, and construct the congestion impact vector of the section. This vector may include components such as the increase in the probability of congestion formation, the degree of influence on the speed of congestion diffusion, and the range of sections that may be affected by congestion. For example, when the abnormal parking ratio is 10%, the probability of congestion formation may increase by 20%, the speed of congestion diffusion may increase by 10%, and the information such as the 500-meter section before and after the abnormal parking point may be affected.

[0110] The factors affecting the traffic flow of the normal driving section are analyzed for the highway section based on the non-driving behavior area, and the vector affecting the traffic flow of the normal driving section is generated. The server will deeply analyze the impact of the data related to the non-driving behavior area on the traffic flow of the normal driving section. For example, the distribution of traffic facilities is included in the non-driving behavior area. The server first identifies the distribution of traffic facilities. Assume that on a certain section of the road, the server identifies the distribution of traffic signs (such as speed limit signs, lane indication signs, etc.) and finds that the speed limit signs of some sections are set unreasonably, resulting in frequent deceleration or acceleration of vehicles. At the same time, the server calculates the signal cycle of the section for the distribution of traffic facilities. For example, at the entrance or exit of the section controlled by traffic lights, the cycle duration of the signal light is calculated. If the signal light cycle is long, the waiting time of the vehicle increases, which will affect the traffic flow of the normal driving section. The server performs traffic duration extension analysis on the highway section based on the section signal cycle. When the signal light cycle is long, the vehicle stays in the area for a longer time, and the traffic duration is extended. This traffic duration extension will cause the distance between vehicles to change, thereby affecting the continuity of the traffic flow.

[0111] The server further analyzes the lane change increment of the highway section based on the traffic time extension data of the highway section. Due to the extension of traffic time, vehicles may increase lane change behavior due to impatience or in order to find a faster passage. The server generates the lane change increment data of vehicles by analyzing the changes in the number of lane changes of vehicles before and after the traffic time extension. For example, originally under normal traffic time, 10 out of every 100 vehicles on a certain section have lane change behavior, and after the traffic time extension, 20 out of every 100 vehicles have lane change behavior, then the lane change increment of vehicles is 10. The reduction of normal driving vehicles on the highway section is calculated based on the lane change increment data of vehicles, because the increase in lane changes of vehicles may lead to a decrease in the number of normal driving vehicles. For example, mutual interference between vehicles during the lane change process may cause some vehicles to slow down or even stop, thereby reducing the number of effective vehicles in normal driving. Assuming that the number of normal driving vehicles is reduced by 5% due to the lane change increment of vehicles, this is the reduction of normal driving vehicles. Finally, the traffic flow influencing factors of the highway section are analyzed based on the reduction of normal driving vehicles to generate the normal driving influencing traffic flow vector. This vector reflects the impact of non-driving behavior area-related factors (such as traffic facilities and traffic duration) on the number of vehicles, traffic speed and stability of traffic on normal driving sections.

[0112] After that, the weighted fusion of the road congestion impact vector and the normal driving impact traffic flow vector is performed to generate the non-driving behavior impact traffic flow vector. The server will assign different weights to the road congestion impact vector and the normal driving impact traffic flow vector according to the actual traffic conditions and experience data. For example, during peak traffic hours or on congested sections, the weight of the road congestion impact vector may be set higher, because in these cases the impact of congestion on traffic flow is more critical; while in periods or sections with relatively smooth traffic, the weight of the normal driving impact traffic flow vector may be relatively high. Assume that in a specific scenario, the weight of the road congestion impact vector is set to 0.6, and the weight of the normal driving impact traffic flow vector is set to 0.4. The server multiplies each component of the road congestion impact vector (such as the increase in congestion probability, the impact of congestion diffusion speed, etc.) by 0.6, and each component of the normal driving impact traffic flow vector (such as the reduction ratio of the number of vehicles, the change in traffic speed, etc.) by 0.4, and then adds the corresponding components to obtain the non-driving behavior impact traffic flow vector. This vector comprehensively considers the impact of non-driving behavior factors on traffic flow in both congestion and normal driving conditions.

[0113] Finally, the traffic flow vector affected by driving behavior and the traffic flow vector affected by non-driving behavior are fused to generate the traffic state influencing factor. The server integrates the information in the traffic flow vector affected by driving behavior and the traffic flow vector affected by non-driving behavior. For example, the speed-related components in the traffic flow vector affected by driving behavior and the speed-related components in the traffic flow vector affected by non-driving behavior are combined for consideration. If the normal driving speed of the vehicle indicated in the traffic flow vector affected by driving behavior helps to increase the traffic speed, while the traffic speed in the traffic flow vector affected by non-driving behavior is reduced due to abnormal parking or traffic facility problems, the server will combine the impact of these two aspects to determine the final impact on the traffic speed. The same is true for other aspects such as traffic stability and capacity. Through this comprehensive fusion method, the traffic state influencing factor is generated, which can comprehensively reflect the comprehensive impact of driving behavior and non-driving behavior on the traffic state of the highway section in terms of traffic speed, stability, capacity, etc., and provide an important basis for subsequent traffic management, planning and risk assessment.

[0114] In a possible implementation, step S135 includes:

[0115] Step S1351, identifying the distribution of traffic facilities in the non-driving behavior area and generating a distribution of traffic facilities.

[0116] Step S1352, calculating the road section signal period for the traffic facility distribution to generate the road section signal period.

[0117] Step S1353, performing traffic time extension analysis on the expressway section according to the road section signal cycle, and generating expressway section traffic time extension data.

[0118] Step S1354, performing vehicle lane change increment analysis on the expressway section based on the expressway section traffic duration extension data, and generating vehicle lane change increment data.

[0119] Step S1355, calculating the reduction amount of vehicles traveling normally on the expressway section based on the vehicle lane change increment data, and generating the reduction amount data of vehicles traveling normally.

[0120] Step S1356, analyzing the traffic flow influencing factors of the expressway section based on the normal driving vehicle volume reduction data, and generating a normal driving influencing traffic flow vector.

[0121] In this embodiment, for the aforementioned expressway section (such as the G3 expressway section), first, the server identifies the distribution of traffic facilities in the non-driving behavior area and generates the distribution of traffic facilities. The non-driving behavior area of ​​the expressway section contains many traffic-related facilities. The server uses the detailed map data of the expressway section stored therein and the image recognition technology (if there is image information from the monitoring device to assist) to identify the distribution of these traffic facilities. For example, the server will accurately determine the location of the speed limit sign, the specific section coordinates of each speed limit sign, the section range corresponding to different speed limit values, and other information. For lane indicator signs, the server can identify the type of indicator sign of each lane (such as straight lane, left turn lane, right turn lane sign) and their exact location in the section. At the same time, the distribution of traffic lights is also an important part. The server will record the specific location of each traffic light, whether it is located at the entrance ramp, exit ramp or a certain position on the main road. In addition, the distribution of traffic facilities such as traffic monitoring equipment, emergency parking strip signs, service area signs, etc. will also be identified and recorded in detail, and this information is integrated together to generate the distribution of traffic facilities. This traffic facility distribution data comprehensively and accurately describes the layout of various types of traffic facilities in the non-driving behavior area of ​​the expressway section, providing a basis for subsequent analysis.

[0122] Next, the server calculates the road signal cycle for the distribution of traffic facilities and generates the road signal cycle. In the distribution of traffic facilities, the signal cycle of traffic lights has an important impact on traffic flow. The server calculates the road signal cycle for each traffic light according to its pre-set control logic and related parameters. For example, for a traffic light located at the junction of the entrance ramp of a highway section and the main road, the server obtains that its red light duration is 30 seconds, the green light duration is 60 seconds, and the yellow light duration is 3 seconds, then a complete cycle of this light is 93 seconds. For complex lights with multi-phase control (such as lights near some large interchanges), the server will analyze the duration of each phase in detail and combine all phases to calculate the total road signal cycle. This calculation process involves the interpretation of the logic of the signal light control program and the distinction between different time periods (such as peak hours and off-peak hours may have different signal cycle settings). Through such calculations, the server can accurately obtain the road signal cycle corresponding to each traffic light, and these road signal cycle data reflect the time control characteristics of the traffic light on the traffic flow.

[0123] Then, the traffic time extension analysis of the expressway section is performed according to the signal cycle of the section, and the traffic time extension data of the expressway section is generated. When the server obtains the signal cycle of the section, it starts to analyze its impact on the traffic time of the expressway section. Take a traffic light as an example. If the signal cycle of the section is long, then the vehicle needs to wait longer when passing this signal light. Assume that when there is no signal light, the average time for vehicles to pass a certain section is 1 minute, but because there is a signal light with a signal cycle of 93 seconds, the average waiting time of vehicles at the signal light is 30 seconds (calculated based on the red light duration of the signal light and the probability distribution of vehicles reaching the signal light), then the actual time for vehicles to pass this section is extended to 1.5 minutes. The server will perform such analysis on all sections of the expressway affected by traffic lights, taking into account the randomness of the time when different vehicles arrive at the signal light and the influence of different phases in the signal light cycle, and calculate the traffic time extension of each affected section. At the same time, similar analysis will be performed on other traffic facilities that may affect traffic time (such as speed bumps, special road signs that cause vehicles to slow down, etc.). By combining the traffic time extension caused by all these factors, we generate the highway traffic time extension data, which can accurately reflect the additional increase in traffic time caused by traffic facilities.

[0124] Afterwards, the vehicle lane change increment of the highway section is analyzed based on the traffic duration extension data of the highway section to generate the vehicle lane change increment data. The server uses the traffic duration extension data of the highway section to analyze the changes in the vehicle lane change behavior. When the traffic duration is extended, the driving state of the vehicle will change. For example, under normal traffic duration, the vehicle can maintain a relatively stable lane driving, but due to the extension of traffic duration, the vehicle may become impatient or try to change lanes in order to find a faster passage. The server analyzes the driving trajectory data of a large number of vehicles on the highway section (these data can be obtained from monitoring equipment) and compares the differences in vehicle lane change behavior before and after the traffic duration is extended. Assuming that under normal circumstances, the number of lane changes for every 100 vehicles on a certain section is 10 times, and after the traffic duration is extended, this number becomes 20 times, then the vehicle lane change increment is 10 times. The server will conduct such analysis on each section of the highway, taking into account the impact of factors such as traffic flow and road structure on vehicle lane changing behavior in different sections, and accurately calculate the incremental number of vehicle lane changes caused by the extension of traffic time on each section. By integrating these data, it generates the incremental vehicle lane change data, which reflects the degree of impact of the extension of traffic time on the vehicle lane changing behavior.

[0125] Then, the reduction of the number of vehicles in normal driving on the expressway is calculated based on the vehicle lane change increment data to generate the reduction of vehicles in normal driving. The vehicle lane change increment will affect the number of vehicles in normal driving. When vehicles change lanes frequently, a series of chain reactions will be triggered. For example, vehicles need to maintain a safe distance between each other during the lane change process, which may cause the rear vehicle to slow down or the front vehicle to accelerate. This change in speed will break the original traffic balance. In some cases, due to the mutual interference when vehicles change lanes, some vehicles may not be able to drive at normal speeds, or even be forced to stop and wait for the right time to change lanes. The server calculates the reduction of vehicles in normal driving by analyzing the vehicle lane change increment data and the vehicle's driving speed, spacing and other related data (these data can be obtained from monitoring equipment or calculated through traffic flow models). Assuming that due to the vehicle lane change increment, the driving speed of 5 vehicles out of every 100 vehicles is reduced to a level where they cannot drive normally (for example, the speed is lower than the minimum safe driving speed or they are stagnant for a long time), then the reduction of vehicles in normal driving is 5%. The server will perform such calculations for each section of the highway, taking into account the differences in traffic conditions on different sections, and generate accurate data on the reduction in the number of vehicles in normal operation. This data reflects the reduction in the number of vehicles in normal operation due to the increase in vehicle lane changes.

[0126] Finally, the factors affecting the traffic flow of the expressway section are analyzed based on the data of the reduction of the number of vehicles in normal driving, and the vector of the traffic flow affected by normal driving is generated. The server uses the data of the reduction of the number of vehicles in normal driving to analyze its impact on the traffic flow of the expressway section, thereby generating the vector of the traffic flow affected by normal driving. The reduction of the number of vehicles in normal driving will affect many aspects of the traffic flow. For example, from the perspective of traffic speed, the distance between vehicles in the traffic flow will change due to the reduction of the number of vehicles in normal driving, which may lead to a decrease in the overall traffic speed. Assuming that the original traffic speed is 100 kilometers per hour, due to the increase in the distance between vehicles after the reduction of the number of vehicles in normal driving, the vehicles need more time to accelerate and decelerate, and the traffic speed may be reduced to 80 kilometers per hour. From the perspective of traffic stability, the reduction of vehicles in normal driving may destroy the continuity of traffic flow, resulting in more gaps and fluctuations in traffic flow, increasing the risk of traffic accidents. From the perspective of traffic capacity, the reduction of vehicles in normal driving means that the number of vehicles passing through a certain section of road per unit time is reduced, which reduces the traffic capacity of the section. By considering these factors, the server calculates the impact of the reduction in the number of normal vehicles on the speed, stability and capacity of traffic flow based on the data of the reduction in the number of normal vehicles, combined with traffic flow theory and historical data, and integrates these impacts into a vector, namely the normal driving impact traffic vector. This vector comprehensively reflects the comprehensive impact of the reduction in the number of normal vehicles on the traffic flow of the highway section due to factors such as traffic facilities in the non-driving behavior area.

[0127] In a possible implementation, step S140 includes:

[0128] Step S141, extracting road facilities from the road area block perception data and generating features of various types of road facilities.

[0129] Step S142, optimizing the traffic dynamic change map according to the characteristics of various types of road facilities and traffic status influencing factors to generate an optimized traffic dynamic change map.

[0130] Step S143, simulating the traffic flow impact trend on the interchange space scene according to the optimized traffic dynamic change map, and generating a traffic flow impact trend model for the highway section.

[0131] Step S144, estimating the traffic safety risk trend of the expressway section based on the trend model of traffic flow affecting the expressway section, and generating traffic safety risk trend data.

[0132] In this embodiment, for the expressway section mentioned above (such as the G3 expressway section), first, the server extracts road facilities from the road area block perception data and generates various types of road facility features. The road area block perception data contains rich information about the expressway section, and the server extracts data related to road facilities from it. In this process, the server will identify various road facilities and analyze their characteristics. For example, for the curve section, the server will accurately determine the radius of curvature of the curve, which can be obtained by measuring the road shape information in the road area block perception data. At the same time, the server will also obtain information such as the length of the curve, the slope at the curve, and the specific location of the curve (expressed in road section coordinates). For road signs, the server will identify in detail the specific value of the speed limit sign, the location of the sign, and the visibility of the sign (by analyzing factors such as the clarity of the sign in the surveillance video). For the road divider, the server will determine its width, material (such as concrete, metal guardrail, etc.) and whether it is damaged. In addition, like the distribution of street lights, the server will record information such as the location, brightness level, and lighting range of each street light. The relevant information of the service area is also included in the extraction scope, including the entrance and exit locations of the service area, the scale of the service area (such as the number of parking spaces, types of service facilities, etc.). By integrating various characteristic information about road facilities such as curves, signs, dividing strips, street lights, and service areas, the characteristics of various types of road facilities are generated. This data of various types of road facility characteristics comprehensively and meticulously describes the road facility conditions of the expressway section, providing an important basis for subsequent analysis.

[0133] Next, the traffic dynamic change map is optimized according to the characteristics of various types of road facilities and the factors affecting traffic status, and an optimized traffic dynamic change map is generated. The traffic dynamic change map originally contains information on traffic flow, vehicle speed, congestion, and other aspects. The server integrates the characteristics of various types of road facilities and the factors affecting traffic status into this map for optimization. For example, considering the characteristics of road facilities such as the curvature radius and slope of the curve, if the curvature radius of the curve is small and the slope is large, and the traffic status influencing factor shows that the traffic speed in this area is fast and the distance between vehicles is small, then the server will highlight this curve area in the traffic dynamic change map. The color of the area in the map may be adjusted (such as adjusting the original green color indicating normal to yellow indicating higher risk), and adding detailed information annotations about this curve to the map, such as "the curvature radius of the curve is small, the slope is large, the traffic speed is fast, pay attention to slow down." For speed limit signs, if the speed limit sign value of a certain road section is low, and the traffic status influencing factor shows that the average speed of vehicles on this road section is close to or exceeds the speed limit, the server will highlight the speed limit sign and the corresponding road section in the map to remind relevant personnel to pay attention to the speed management of this road section. Similarly, near the entrance of the service area, if the road facility characteristics show that the entrance is narrow and the traffic status influencing factor indicates that vehicles in this area are prone to congestion when merging into the main road, the server will display the traffic dynamic changes around the entrance of the service area in more detail in the map, such as adding trajectory simulations of vehicles merging into the main road. By combining the road facility characteristics and traffic status influencing factors with the traffic dynamic change map in this way, an optimized traffic dynamic change map is generated. This optimized map can more comprehensively and accurately reflect the traffic conditions of the expressway section, especially considering the impact of road facilities on traffic.

[0134] Then, the traffic flow impact trend of the interchange space scene is simulated based on the optimized traffic dynamic change map, and a traffic flow impact trend model of the highway section is generated. The server uses the information in the optimized traffic dynamic change map to simulate the traffic flow impact trend based on the interchange space scene. In the interchange space scene, detailed road structure information such as each ramp, main road, confluence point, and divergence point is included. The server simulates the flow trend of vehicles in the interchange based on the traffic flow, vehicle speed, congestion condition, and road facilities in the optimized traffic dynamic change map. For example, if the optimized traffic dynamic change map shows that the traffic flow of a certain entrance ramp is large and the speed is slow, and the road facilities of the ramp (such as narrow lane width) are not conducive to the rapid merging of vehicles into the main road, the server will simulate the queuing of vehicles at this entrance ramp in the traffic flow impact trend model of the highway section, including the length of the queue, the type distribution of queued vehicles (such as the ratio of small cars and large cars), etc. For the diverging point, if the map shows that the traffic flow in one direction is large and the lanes in that direction are about to be reduced, the server will simulate the lane-changing behavior of the vehicle at the diverging point, such as how long in advance the vehicle starts to change lanes, the speed change during the lane change, etc. At the same time, considering the traffic differences in different time periods (such as peak hours and non-peak hours), the server will simulate separately in the trend model of traffic flow affecting highway sections to accurately reflect the trend of traffic flow in different time periods. This trend model of traffic flow affecting highway sections can dynamically display the flow trend of vehicles in the interchange space scene and the impact of various factors (such as traffic flow, road facilities, etc.) on traffic.

[0135] Finally, the traffic safety risk trend of the highway section is estimated based on the trend model of traffic flow affecting the highway section, and traffic safety risk trend data is generated. The server estimates the traffic safety risk trend based on the simulation results in the trend model of traffic flow affecting the highway section. For example, if the model finds that vehicles frequently come into close contact at a certain confluence point (the distance between vehicles is less than the safe distance), this indicates that there is a high risk of collision in this area. The server will calculate the probability of a collision accident based on factors such as the vehicle speed, flow, and road structure at the confluence point. Assume that at this confluence point, the probability of a collision accident per hour calculated by the model is 0.1%. For the curved area, if the model shows that the speed of vehicles at the curve is generally high and exceeds the safe speed (the safe speed determined by factors such as the curvature radius and slope of the curve), the server will evaluate the risk of vehicle loss of control or skidding, and may calculate that the probability of vehicle loss of control in this case is 0.05%. At the same time, for areas with problems in road facilities (such as damaged road signs or unlit street lights), the server will consider the impact of these factors on traffic safety and increase the corresponding risk value. For example, if the speed limit sign on a certain road section is damaged, it may increase the risk of speeding on that road section. Based on historical data and traffic flow theory, the server estimates that the risk of speeding accidents caused by damaged speed limit signs has increased by 0.03%. By integrating the probabilities of various traffic safety risks such as collision, loss of control, speeding, and related risk factors, traffic safety risk trend data is generated. This data can comprehensively reflect the traffic safety risk trend of expressway sections, and provides an important basis for traffic management departments to formulate safety strategies and take preventive measures.

[0136] Figure 2 The hardware structure of the multi-source traffic operation data analysis system 100 based on AI sensor fusion for implementing the multi-source traffic operation data analysis method based on AI sensor fusion provided by an embodiment of the present invention is shown as follows: Figure 2 As shown, the multi-source traffic operation data analysis system 100 based on AI sensor fusion may include a processor 110 , a machine-readable storage medium 120 , a bus 130 , and a communication unit 140 .

[0137] The machine-readable storage medium 120 may store data and / or instructions. In some embodiments, the machine-readable storage medium 120 may store data acquired from an external terminal. In some embodiments, the machine-readable storage medium 120 may store data and / or instructions that the multi-source traffic operation data analysis system 100 based on AI sensor fusion uses to execute or use to complete the exemplary method described in the present invention.

[0138] During the specific implementation process, one or more processors 110 execute computer executable instructions stored in the machine-readable storage medium 120, so that the processor 110 can execute the multi-source traffic operation data analysis method based on AI sensor fusion in the above method embodiment. The processor 110, the machine-readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processor 110 can be used to control the sending and receiving actions of the communication unit 140.

[0139] The specific implementation process of the processor 110 can refer to the various method embodiments executed by the above-mentioned multi-source traffic operation data analysis system 100 based on AI sensor fusion. The implementation principles and technical effects are similar, and this embodiment will not be repeated here.

[0140] In addition, an embodiment of the present invention also provides a readable storage medium, in which computer executable instructions are preset. When the processor executes the computer executable instructions, the multi-source traffic operation data analysis method based on AI sensor fusion as above is implemented.

[0141] It should be noted that in order to simplify the description of the present invention and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present invention, various features are sometimes combined into one embodiment, drawing or description thereof.

Claims

1. A multi-source traffic operation data analysis method based on AI sensor fusion, characterized in that: The method comprises: Reconstruct the interchange space scene of the expressway section to generate the interchange space scene, perform AI sensor fusion collection on the expressway section based on the interchange space scene to generate the traffic operation data stream, and analyze the traffic dynamic change map of the interchange space scene based on the traffic operation data stream to generate the traffic dynamic change map; Mapping the road domain perception data blocks of the expressway section to generate the road domain block perception data, extracting the driving behavior data blocks from the road domain block perception data to generate the driving behavior data blocks, and extracting the non-driving behavior data blocks from the road domain block perception data to generate the non-driving behavior data blocks; Analyze the traffic status influencing factors of the expressway section based on the driving behavior data block and the non-driving behavior data block to generate the traffic status influencing factors; The traffic dynamic change map is optimized based on the road block perception data and traffic status influencing factors to generate an optimized traffic dynamic change map, and the traffic safety risk trend of the expressway section is estimated based on the optimized traffic dynamic change map and the interchange space scenario to generate traffic safety risk trend data, and safety tips and suggestions for the interchange space scenario are generated based on the traffic safety risk trend data.

2. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 1 is characterized in that: The steps of reconstructing the interchange space scene of the expressway section to generate the interchange space scene, performing AI sensor fusion collection on the expressway section according to the interchange space scene to generate a traffic operation data stream, and performing traffic dynamic change map analysis on the interchange space scene according to the traffic operation data stream to generate a traffic dynamic change map include: Conduct drone aerial photography scanning of highway sections to generate drone aerial photography scanning data; Fuse the partitioned UAV aerial scanning data to generate the target UAV aerial scanning data; Reconstruct the interchange space scene of the expressway section based on the target drone aerial scanning data to generate the interchange space scene; AI sensor fusion is used to collect data on highway sections based on interchange space scenarios to generate traffic operation data streams; The traffic dynamic change map of the interchange space scene is analyzed based on the traffic operation data flow to generate a traffic dynamic change map.

3. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 2 is characterized in that: The step of performing AI sensor fusion collection on the highway section according to the interchange space scene to generate a traffic operation data stream includes: Configure traffic observation points on expressway sections and generate traffic observation point data; Based on the traffic observation point data, the longitudinal traffic section of the interchange space scene is analyzed to generate traffic observation point section data; Carry out traffic flow monitoring at observation points on expressway sections based on traffic observation point data and generate traffic flow data at observation points; Based on the cross-sectional data of the traffic observation point and the traffic flow data of the observation point, the traffic flow of the interchange is calculated for the traffic observation point data to generate the traffic flow data of the observation point; The observation point data of the expressway section is fused based on the vehicle flow data and traffic flow data of the observation point to generate a traffic operation data stream.

4. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 2 is characterized in that: The step of analyzing the traffic dynamic change map of the interchange space scene according to the traffic operation data flow to generate the traffic dynamic change map includes: Analyze and resolve traffic flow and speed on traffic operation data streams to generate traffic flow characteristic data; Based on the traffic flow characteristic data, the vehicle speed impact characteristics of the interchange space scene are simulated to generate vehicle speed impact characteristic data; Construct a map of traffic flow characteristic data and vehicle speed impact characteristic data to generate a traffic flow change characteristic map; Analyze traffic congestion and smooth traffic conditions of traffic operation data streams to generate traffic status data; Based on the traffic status data, the traffic situation of the interchange space scene is simulated to generate traffic situation data; Construct a map of traffic status data and traffic situation data to generate a traffic situation map; The traffic flow change characteristic map and the traffic situation map are integrated to generate a traffic dynamic change map.

5. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 1 is characterized in that: The steps of mapping the road domain perception data blocks on the highway section to generate the road domain block perception data, extracting the driving behavior data blocks from the road domain block perception data to generate the driving behavior data blocks, and extracting the non-driving behavior data blocks from the road domain block perception data to generate the non-driving behavior data blocks include: Conduct road detection video monitoring on the expressway section and generate the expressway section road detection video stream; Map the road area blocks of the highway section road area detection video stream to generate road area block perception data; Extract driving operation features from the road area block perception data to generate driving operation feature data; Extracting driving behavior data blocks from the road area block perception data based on the driving operation characteristic data to generate driving behavior data blocks; The non-driving behavior data blocks are extracted from the road area block perception data according to the driving operation characteristic data to generate non-driving behavior data blocks.

6. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 5 is characterized in that: The step of extracting driving operation features from the road area block perception data to generate driving operation feature data includes: Extract block dynamic features from road block perception data to generate block perception dynamic feature data; According to the block perception dynamic feature data, the traffic area dynamic feature analysis is performed on the road area block perception data to generate the traffic area dynamic feature; Extract non-traffic area features from the road block perception data based on the dynamic characteristics of the traffic area to generate non-traffic area feature data; Extracting regular driving pattern features from the non-traffic area feature data to generate regular driving pattern feature data; According to the regular driving pattern feature data, the road area block perception data is analyzed for regular driving area features to generate regular driving area features; The dynamic characteristics of the traffic area and the regular characteristics of the normal driving area are integrated to generate driving operation characteristic data.

7. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 1 is characterized in that: The step of analyzing the traffic state influencing factors of the highway section based on the driving behavior data block and the non-driving behavior data block to generate the traffic state influencing factors includes: Performing normal driving feature vector analysis on the driving behavior data block to generate a normal driving feature vector of the driving behavior; According to the normal driving characteristic vector of driving behavior, the traffic flow influencing factors of the expressway section are analyzed to generate the driving behavior influencing traffic flow vector; Analyze the abnormal parking ratio of the non-driving behavior data block to generate the abnormal parking ratio; Analyze the congestion impact vector of the expressway section according to the abnormal parking ratio and generate the congestion impact vector of the section; According to the non-driving behavior area, the factors affecting the traffic flow of the normal driving section of the highway are analyzed to generate the normal driving affecting traffic flow vector; The weighted fusion of the impact vector of road congestion and the impact vector of normal driving on traffic flow is performed to generate the impact vector of non-driving behavior on traffic flow; The traffic flow vectors affected by driving behavior and the traffic flow vectors affected by non-driving behavior are fused to generate traffic status influencing factors.

8. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 7 is characterized in that: The step of analyzing the traffic flow influencing factors of the normal driving section on the highway section according to the non-driving behavior area and generating the normal driving influencing traffic flow vector comprises: Identify the distribution of traffic facilities in non-driving areas and generate the distribution of traffic facilities; Calculate the road section signal cycle based on the distribution of traffic facilities and generate the road section signal cycle; Analyze the traffic time extension of the expressway section according to the road section signal cycle and generate the traffic time extension data of the expressway section; Carry out lane change increment analysis on the expressway section based on the extended traffic time data of the expressway section to generate lane change increment data of the vehicle; The reduction amount of vehicles traveling normally on the expressway is calculated based on the vehicle lane change increment data to generate the reduction amount data of vehicles traveling normally; The factors affecting the traffic flow on the expressway section are analyzed based on the reduced volume data of vehicles in normal driving, and the vector of traffic flow affected by normal driving is generated.

9. The multi-source traffic operation data analysis method based on AI sensor fusion according to claim 1 is characterized in that: The steps of optimizing the traffic dynamic change map based on the road area block perception data and the traffic state influencing factors to generate the optimized traffic dynamic change map, estimating the traffic safety risk trend of the expressway section based on the optimized traffic dynamic change map and the interchange space scene to generate traffic safety risk trend data include: Extract road facilities from road area block perception data and generate features of various types of road facilities; Optimize the traffic dynamic change map based on the characteristics of various types of road facilities and factors affecting traffic conditions to generate an optimized traffic dynamic change map; Based on the optimized traffic dynamic change map, the traffic flow impact trend of the interchange space scene is simulated to generate a trend model of traffic flow impact on the highway section; Based on the trend model of traffic flow affecting highway sections, the traffic safety risk trend of highway sections is estimated to generate traffic safety risk trend data.

10. A multi-source traffic operation data analysis system based on AI sensor fusion, characterized in that: The multi-source traffic operation data analysis system based on AI sensor fusion includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the multi-source traffic operation data analysis method based on AI sensor fusion as described in any one of claims 1 to 9 above.

Images