Road network analysis system relating to intelligent traffic

Abstract

The invention discloses a road network analysis system related to intelligent traffic, and relates to the technical field of intelligent traffic, and the system comprises a traffic road network range determination module, a road network analysis module, a control personnel processing end, a driving personnel client and a driving recommendation module. Comprehensive acquisition, dynamic analysis and accurate early warning of traffic data are realized; the system can calculate a congestion risk coefficient and an accident risk coefficient of a road in real time, identifies and manages a high-risk road based on a traffic safety index, and quickly sends early warning information to control personnel and driving personnel to guarantee the smoothness and safety of the road; particularly, the driving recommendation module provides a safe and efficient driving path for the user through a path optimization technology in combination with real-time road condition data, so that the driving experience and the operation efficiency of the traffic system are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of smart transportation technology, and specifically to a road network analysis system related to smart transportation. Background Art

[0002] With the acceleration of urbanization and the rapid growth of vehicle ownership, traffic congestion and traffic accidents have become important issues affecting social and economic development and the quality of life of the public. Traditional traffic management systems often rely on manual monitoring or fixed-rule signal control, lacking the ability to perceive and respond to traffic conditions in real time and dynamically, making it difficult to effectively cope with complex and changing traffic environments. In addition, due to the single means of traffic data collection and insufficient analysis accuracy, the existing system is difficult to fully grasp the operating status of roads, and cannot accurately identify and quickly intervene in high-risk roads, further exacerbating the irrational use of road resources and traffic safety issues.

[0003] In this context, the introduction of smart transportation technology provides a possible solution to the above problems. Based on technologies such as big data, the Internet of Things, and artificial intelligence, the smart transportation system can dynamically perceive traffic flow, accident risks, and road network status through real-time collection and analysis of road traffic data, providing scientific decision-making support for traffic management personnel and personalized travel guidance for drivers.

[0004] However, existing technologies still have shortcomings in the collection, analysis and feedback of traffic data, such as low real-time and accuracy of data, untimely response to traffic incidents, and lack of flexibility in route recommendation schemes. There is an urgent need for a more intelligent, efficient and comprehensive traffic network analysis system to further improve road traffic efficiency and traffic safety. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a road network analysis system involving smart transportation, which solves the problems in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A road network analysis system involving smart transportation, comprising: A traffic network range determination module, used to determine the traffic network range; A multi-road network segmentation determination module is used to segment the traffic road network range into multiple small road networks; The road network analysis module is used to collect information about each road in each small road network, perform data analysis on the road based on the collected road information, obtain real-time congestion risk coefficients and real-time accident risk coefficients, and determine traffic safety indicators. Based on the specific values ​​of the traffic safety indicators, it is determined whether to generate warning information; The controller processing end is used to determine the specific road according to the generated warning information and dispatch traffic management personnel to the road to maintain traffic order; The driver client is used to obtain the specific road network where the current driver is located, and obtain the congestion risk of all roads in the road network through the road network analysis module; The driving recommendation module is used to obtain the specific location of the current driver and the location information of the driver's destination, and determine the optimal path between the specific location of the current driver and the location information of the driver's destination.

[0007] As a further solution of the present invention: the road network analysis module includes a data collection unit, a data analysis unit, a traffic safety index determination unit and a warning notification unit; A data collection unit, used to collect information of each road in each small road network; A data analysis unit, used to perform data analysis on the road according to the collected road information, and obtain a real-time congestion risk coefficient and a real-time accident risk coefficient; Traffic safety index determination unit: used to classify the risk level of roads according to the real-time congestion risk coefficient, and determine the traffic safety index by combining the real-time congestion risk coefficient and the real-time accident risk coefficient; The warning notification unit is used to determine whether to generate warning information based on the specific values ​​of traffic safety indicators. When warning information is generated, it is sent to the controller for processing.

[0008] As a further solution of the present invention: in the data collection unit, the road information includes: real-time traffic flow data: and recorded as ; Road capacity: and recorded as ; Real-time vehicle speed data: and record it as ; Road length: and record as ; Real-time weather information: including rainfall, visibility, and temperature, which are recorded as: , and ; Real-time traffic event data: including the specific number of accidents, construction, and traffic control that occur on the road at the current time; and recorded as: , and ; Historical accident data: the number of accidents that occurred on the road in the past week, recorded as .

[0009] As a further solution of the present invention: in the data analysis unit, the specific method of performing data analysis on the road according to the collected road information is: AS1: Each small road network is analyzed as a target road network; AS2: Mark each road in the target road network as ,in, , is the total number of roads in the target road network; AS3: Get individual roads road information, and determine each road based on the road information The congestion risk factor and accident risk factor of the Determining each road according to the road information The specific form of the congestion risk coefficient is: AS3-a1: Extract roads Real-time traffic flow data and road capacity in road information are calculated by formula , and obtain the traffic flow ratio ; AS3-a2: Extract roads The real-time vehicle speed data in the road information is calculated by the formula , get the real-time vehicle speed index ;in, is the preset value, indicating the maximum vehicle speed; AS3-a3: Extract roads The real-time traffic flow data, real-time vehicle speed data and road length in the road information are calculated by the formula , get the real-time traffic density ; AS3-a4: Get traffic flow ratio , Real-time vehicle speed index and real-time traffic density , the real-time congestion risk coefficient is determined by the following formula: ; in, Expressed as the real-time congestion risk coefficient, , and is the weight coefficient.

[0010] As a further solution of the present invention: also include: Determining each road according to the road information The real-time accident risk factor is: AS3-b1: Extract roads Real-time weather information in road information, the weather impact factor is determined by the following formula : ; in, , and is the weight coefficient; AS3-b2: Extract roads The real-time traffic event data in the road information is used to determine the real-time traffic event factor using the following formula : ; AS3-b3: Get weather impact factors and real-time traffic event factors , and extract roads The historical accident data in the road information is used to determine the real-time accident risk factor using the following formula: ; in, Expressed as the real-time accident risk coefficient, , and is the weight coefficient.

[0011] As a further solution of the present invention: in the traffic safety index determination unit, the specific method of dividing the risk level of the road according to the real-time congestion risk coefficient and determining the traffic safety index in combination with the real-time congestion risk coefficient and the real-time accident risk coefficient is: BS1: Get real-time congestion risk factor , and classify its risk levels: like , at this time, it is judged that the road Hi is a road without congestion risk; like , at this time, the road Hi is judged to be a low-risk blocking risk road; like , at this time, the road Hi is judged to be a high-risk blocking risk road; in, and is the default value, and ; BS2: Then, the traffic safety index is determined by combining the real-time congestion risk coefficient and the real-time accident risk coefficient through the following formula: ; in, Expressed as a traffic safety index, Expressed as the overall adjustment coefficient, Expressed as accident risk weight ratio.

[0012] As a further solution of the present invention: in the early warning notification unit, the specific value of the traffic safety index of the traffic safety index determination unit is obtained. ,Will With the preset threshold For comparison: If , then an early warning message is generated and sent to the controller for processing; otherwise, no processing is done.

[0013] As a further solution of the present invention: in the driving recommendation module, the specific content of determining the optimal path between the specific location of the current driver and the location information of the driver's destination includes: CS1: Get the specific location of the current driver, and at the same time, get the location information of the driver's destination, and determine whether the location information of the destination is in the small road network where the driver is located; CS2: If it is determined that the location information of the target destination is in the small road network where the driver is located; determine the optimal path from the current specific location of the driver to the location information of the target destination of the driver by the following methods, including: Model the small road network where drivers are located as a weighted directed graph ,in, It is a set of nodes, representing the intersections of roads in the small road network where the drivers are located; is an edge set, indicating the road connections in the small road network where the driver is located, and the edge set Each edge in ; represents a road from node i to node j, i represents the starting node, indicating the starting position of the road, and j represents the end node, indicating the end position of the road; Gather at the edge Filter valid edges : ;in, It is expressed as the congestion risk of the edge: 0 for roads without congestion risk, 1 for roads with low congestion risk, and 2 for roads with high congestion risk; Constructing a subgraph , and in the subgraph In the process, a weighted shortest path algorithm is used to find the optimal path from the specific location of the current driver to the location information of the driver's destination; The specific method of finding the optimal path from the current specific location of the driver to the location information of the driver's destination is: For each edge Weight Determined by the following formula: ; in, Represented as edge The length of the road, and Expressed as weight coefficient; Then obtain all feasible paths from the current driver's specific location to the driver's destination, and calculate the total weight of all feasible paths: ; Where P is the set of feasible paths, , Represents a feasible path The total weight of Finally, determine the optimal path from the current driver's specific location to the driver's destination: ; in, It represents the optimal path from the current specific location of the driver to the location information of the driver's destination.

[0014] As a further solution of the present invention: also include: CS3: If it is determined that the location information of the target destination is not in the small road network where the driver is located, the map software function is called through the API to obtain a recommended route from the current specific location of the driver to the location information of the driver's target destination, and the specific small road network passed by the recommended route is obtained. The corresponding starting point and end point are determined in each specific small road network. The optimal path from the current specific location of the driver to the location information of the driver's target destination is determined through step CS2, and the path from the corresponding starting point to the end point of each small road network is re-determined to obtain the optimal path of each small road network. The optimal paths of each small road network are merged to determine the optimal path from the current specific location of the driver to the location information of the driver's target destination when it is determined that the location information of the target destination is not in the small road network where the driver is located.

[0015] The present invention provides a road network analysis system related to intelligent transportation. Compared with the prior art, it has the following beneficial effects: The present invention realizes the comprehensive collection, dynamic analysis and accurate early warning of traffic data through the coordinated work of the traffic network range determination module, the road network analysis module, the control personnel processing terminal, the driver client and the driving recommendation module; the system can calculate the road congestion risk coefficient and the accident risk coefficient in real time, identify and manage high-risk roads based on traffic safety indicators, and quickly send early warning information to control personnel and drivers to ensure the smoothness and safety of the road; in particular, the driving recommendation module, through path optimization technology, combined with real-time road condition data, provides users with safe and efficient driving routes, which greatly improves the driving experience and the operation efficiency of the traffic system.

[0016] At the same time, the present invention takes real-time and accuracy as its core advantages, forming a complete closed-loop management process from data collection to risk assessment to route planning, solving the problems of untimely traffic information feedback, low risk assessment accuracy, and inflexible route recommendation in the prior art; the design of the overall system focuses on practicality and intelligence, which not only improves the traffic management personnel's ability to quickly deal with risky roads, but also greatly optimizes the travel efficiency and safety of drivers, providing efficient and reliable technical support for smart traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention will be further described below in conjunction with the accompanying drawings.

[0018] Figure 1 This is a structural framework diagram of a road network analysis system involving intelligent transportation in the present invention; Figure 2 A schematic diagram of road network segmentation of a road network analysis system involving intelligent transportation in the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1 See also Figure 1-Figure 2 ,The present invention provides a road network analysis system involving intelligent transportation, including; A traffic network range determination module, used to determine the traffic network range; A multi-road network segmentation determination module is used to segment the traffic road network range into multiple small road networks; It should be noted that the scope of the traffic road network can be all roads of a provincial city or all roads of a county city. All roads of provincial city traffic or all roads of county city traffic can be determined as the scope of the traffic road network, and the specific determination of the scope of the traffic road network is determined by professional staff according to actual conditions. As for the division into multiple small road networks, it can be considered that the entire determined traffic road network scope is divided into regional small road network modes through the setting of professional staff. At the same time, each small road network includes many roads; for example: Figure 2 As mentioned above, the area framed by dotted lines in the figure is a small road network; The road network analysis module is used to collect information about each road in each small road network, perform data analysis on the road based on the collected road information, obtain a real-time congestion risk coefficient and a real-time accident risk coefficient, and determine a traffic safety index. According to the specific value of the traffic safety index, it is determined whether to generate warning information; the road network analysis module includes a data collection unit, a data analysis unit, a traffic safety index determination unit, and a warning notification unit; A data collection unit, used to collect information of each road in each small road network; Among them, road information includes: real-time traffic flow data: the number of vehicles passing through the road per unit time, recorded as ; Road capacity: The maximum capacity of a road under ideal conditions, recorded as ; Real-time vehicle speed data: the average speed of the vehicle per unit time, recorded as ; Road Length: The total length of the road, recorded as ; Real-time weather information: including rainfall, visibility, and temperature, which are recorded as: , and ; Real-time traffic event data: including the specific number of accidents, construction, and traffic control that occur on the road at the current time; recorded as: , and ; Historical accident data: The number of accidents that occurred on the road in the past week, recorded as ; It should be noted that: the data acquisition unit obtains data through corresponding physical equipment. Specifically, real-time traffic flow data is obtained by video analysis technology (such as computer vision and image recognition) to count the number of vehicles passing through the road in real time; cameras can be installed at intersections, bridges or elevated roads to cover key traffic nodes; road capacity is usually pre-set based on road design parameters (such as the number of lanes, road width, signal cycle, etc.) and stored in a geographic information system (GIS) or traffic management database. Real-time vehicle speed data uses video analysis technology to identify the position changes of the same vehicle at different time points and calculate its driving speed. The overall average speed of all vehicles on the road is calculated based on the driving speed of all vehicles on the road, which is the real-time vehicle speed data. The road length is obtained by using existing map data and GIS technology to accurately obtain the length information of each road; real-time meteorological information is monitored in real time by meteorological stations installed near the road, such as rainfall, visibility, temperature and other meteorological parameters; A data analysis unit, used to perform data analysis on the road according to the collected road information, and obtain a real-time congestion risk coefficient and a real-time accident risk coefficient; The specific method of performing data analysis on the road according to the collected road information is as follows: AS1: Each small road network is analyzed as a target road network; AS2: Mark each road in the target road network as Hi, where , is the total number of roads in the target road network; AS3: Obtain road information of each road Hi, and determine a congestion risk coefficient and an accident risk coefficient of each road Hi according to the road information; The specific method of determining the congestion risk coefficient of each road Hi according to the road information is: AS3-a1: Extract the real-time traffic flow data and road capacity from the road information of road Hi, and calculate it by the formula: ; Get the traffic flow ratio ; AS3-a2: Extract roads The real-time vehicle speed data in the road information is calculated by the formula: ; Get the real-time vehicle speed index ;in, It is a preset value, which indicates the maximum vehicle speed. The specific parameters are determined by the staff based on the road type and traffic regulations. AS3-a3: Extract roads The real-time traffic flow data, real-time vehicle speed data and road length in the road information are calculated by the formula: , get the real-time traffic density ; AS3-a4: Get traffic flow ratio , Real-time vehicle speed index and real-time traffic density , the real-time congestion risk coefficient is determined by the following formula: ; in, Expressed as the real-time congestion risk coefficient, , and is the weight coefficient; The real-time accident risk coefficient of each road Hi is determined according to the road information as follows: AS3-b1: Extract real-time weather information from road Hi road information and determine the weather impact factor using the following formula : ; in, , and is the weight coefficient; AS3-b2: Extract the real-time traffic event data from the road information of road Hi and determine the real-time traffic event factor by the following formula : ; AS3-b3: Get weather impact factors and real-time traffic event factors , and extract roads The historical accident data in the road information is used to determine the real-time accident risk factor using the following formula: ; in, Expressed as the real-time accident risk coefficient, , and is the weight coefficient; Traffic safety index determination unit: used to classify the risk level of roads according to the real-time congestion risk coefficient, and determine the traffic safety index by combining the real-time congestion risk coefficient and the real-time accident risk coefficient; The specific method of classifying the risk level of roads according to the real-time congestion risk coefficient and determining the traffic safety index in combination with the real-time congestion risk coefficient and the real-time accident risk coefficient is as follows: BS1: Get real-time congestion risk factor , and classify its risk levels: like , at this time, it is judged that the road Hi is a road without congestion risk; like , at this time, the road Hi is judged to be a low-risk blocking risk road; like , at this time, the road Hi is judged to be a high-risk blocking risk road; in, and is the default value, and The specific parameters are determined by professional staff; BS2: Then, the traffic safety index is determined by combining the real-time congestion risk coefficient and the real-time accident risk coefficient through the following formula: ; in, It is expressed as a traffic safety index, and its value range is , the closer the value is to 1, the safer the road is. Expressed as the overall adjustment coefficient, It is expressed as accident risk weight ratio; The warning notification unit is used to determine whether to generate warning information based on the specific values ​​of the traffic safety indicators, and when the warning information is generated, it is sent to the controller for processing; Specifically, obtain the specific value of the traffic safety index of the traffic safety index determination unit ,Will With the preset threshold For comparison: If , then generate warning information and send it to the controller for processing, otherwise, no processing will be done; is a preset value, and the specific parameters are determined by professional staff. is 0.5; The road network analysis module can comprehensively and efficiently collect and analyze various real-time data in the traffic network (such as traffic flow, vehicle speed, weather information and accident information, etc.) through the data collection unit, data analysis unit, traffic safety index determination unit and early warning notification unit, so as to accurately calculate the congestion risk coefficient and accident risk coefficient, and further derive traffic safety indicators to help quickly identify high-risk roads; the risk information is sent to relevant management personnel in a timely manner through the early warning notification unit. This module realizes the complete process from real-time data collection to efficient analysis and dynamic early warning, effectively improving the real-time monitoring capability and safety of the traffic system, and providing reliable data support and decision-making basis for smart traffic management; The controller processing end is used to determine the specific road according to the generated warning information and dispatch traffic management personnel to the road to maintain traffic order; The controller processing end can accurately receive the warning information generated by the road network analysis module, understand the specific location, risk type and degree of high-risk roads in real time, and quickly dispatch traffic management personnel to deal with the specific situation; this precise risk notification mechanism shortens the response time from risk occurrence to on-site intervention, avoids the further spread of accident risks, and alleviates possible traffic congestion and accidents.

[0021] Embodiment 2 In the specific implementation process, this embodiment is based on the first embodiment and is different from the first embodiment in that this embodiment further includes a driver client and a driving recommendation module: The driver client is used to determine the specific road network where the current driver is located, and obtain the congestion risk of all roads in the road network through the road network analysis module; Specifically, through the traffic safety index determination unit in the road network module, the congestion risk of each road in all the roads in the small road network is divided into: no congestion risk road, low risk congestion risk road and high risk road; The driver client can obtain and display the risk information of all roads in the user's small road network in real time, including roads with no congestion risk, roads with low congestion risk, and roads with high risk, so as to help drivers fully understand the current road network conditions; by providing clear and intuitive road network information, drivers can avoid high-risk roads in advance and choose safer driving routes; The driving recommendation module is used to obtain the specific location of the current driver and the location information of the driver's destination, and determine the optimal path between the specific location of the current driver and the location information of the driver's destination; The specific content of determining the optimal path between the current specific position of the driver and the location information of the driver's destination includes: CS1: Get the specific location of the current driver, and at the same time, get the location information of the driver's destination, and determine whether the location information of the destination is in the small road network where the driver is located; CS2: If it is determined that the location information of the target destination is in the small road network where the driver is located; determine the optimal path from the current specific location of the driver to the location information of the target destination of the driver by the following methods, including: Model the small road network where drivers are located as a weighted directed graph ,in, It is a set of nodes, representing the intersections of roads in the small road network where the drivers are located; is an edge set, indicating the road connections in the small road network where the driver is located, and the edge set Each edge in ; Represents a road from node i to node j, which is mathematically called an edge in a directed graph. i is the starting node, indicating the starting position of the road, and j is the end node, indicating the end position of the road. Gather at the edge Filter valid edges : ;in, It is expressed as the congestion risk of the edge: 0 for roads without congestion risk, 1 for roads with low congestion risk, and 2 for roads with high congestion risk; Constructing a subgraph , and in the subgraph In the process, a weighted shortest path algorithm is used to find the optimal path from the specific location of the current driver to the location information of the driver's destination; The specific method of finding the optimal path from the current specific location of the driver to the location information of the driver's destination is: For each edge Weight Determined by the following formula: ; in, Represented as edge The length of the road, and Expressed as weight coefficient; Then obtain all feasible paths from the current driver's specific location to the driver's destination, and calculate the total weight of all feasible paths: ; Where P is the set of feasible paths, , Represents a feasible path The total weight of Finally, determine the optimal path from the current driver's specific location to the driver's destination: ; in, It is represented as the optimal path from the current specific location of the driver to the location information of the driver's destination; CS3: If it is determined that the location information of the target destination is not in the small road network where the driver is located, the map software function is called through the API to obtain a recommended route from the current specific location of the driver to the location information of the driver's target destination, and the specific small road network through which the recommended route passes is obtained. The corresponding starting point and end point are determined in each specific small road network. The optimal path from the current specific location of the driver to the location information of the driver's target destination is determined by step CS2, and the path from the corresponding starting point to the end point of each small road network is re-determined to obtain the optimal path of each small road network. The optimal paths of each small road network are merged to determine the optimal path from the current specific location of the driver to the location information of the driver's target destination when it is determined that the location information of the target destination is not in the small road network where the driver is located; It should be noted that when determining the corresponding starting point and end point in each specific path network, for a recommended route, when it passes through multiple specific path networks, for one of the specific path networks, the recommended route will have a starting point entering the path network and an end point exiting the path network, and the starting point and end point remain unchanged, so the path from the starting point to the end point may be diverse, and the route of the recommended route in this path network is not optimal. In this case, the optimal path from the specific location of the current driver to the location information of the driver's destination can be determined in step CS2, and the path from the corresponding starting point to the end point of each path network can be re-determined; The driving recommendation module can intelligently generate safe and efficient travel routes based on the driver's real-time location and destination information, by screening roads with no congestion risk and roads with low congestion risk, avoiding the selection of high-risk roads and significantly improving driving safety; when the destination is not in the small road network where the driver is currently located, the module can automatically determine and dynamically plan the travel route across the small road network, giving priority to the globally optimal safe travel plan; by combining multiple factors such as path length and congestion risk, the module realizes efficient path recommendation, helping drivers to reach their destination quickly and safely, especially in complex road networks and dynamic traffic environments, providing drivers with reliable path guidance, improving the operating efficiency and driving experience of the entire transportation system.

[0022] Embodiment 3 The specific implementation process of this embodiment includes the entire implementation process of the above two groups of embodiments.

[0023] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0024] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A road network analysis system involving intelligent transportation, characterized in that: include: A traffic network range determination module, used to determine the traffic network range; A multi-road network segmentation determination module is used to segment the traffic road network range into multiple small road networks; The road network analysis module is used to collect information about each road in each small road network, perform data analysis on the road based on the collected road information, obtain real-time congestion risk coefficients and real-time accident risk coefficients, and determine traffic safety indicators. Based on the specific values ​​of the traffic safety indicators, it is determined whether to generate warning information; The controller processing end is used to determine the specific road according to the generated warning information and dispatch traffic management personnel to the road to maintain traffic order; The driver client is used to obtain the specific road network where the current driver is located, and obtain the congestion risk of all roads in the road network through the road network analysis module; The driving recommendation module is used to obtain the specific location of the current driver and the location information of the driver's destination, and determine the optimal path between the specific location of the current driver and the location information of the driver's destination.

2. A road network analysis system involving intelligent transportation according to claim 1, characterized in that: The road network analysis module includes a data collection unit, a data analysis unit, a traffic safety index determination unit and a warning notification unit; A data collection unit, used to collect information of each road in each small road network; A data analysis unit, used to perform data analysis on the road according to the collected road information, and obtain a real-time congestion risk coefficient and a real-time accident risk coefficient; Traffic safety index determination unit: used to classify the risk level of roads according to the real-time congestion risk coefficient, and determine the traffic safety index by combining the real-time congestion risk coefficient and the real-time accident risk coefficient; The warning notification unit is used to determine whether to generate warning information based on the specific values ​​of traffic safety indicators. When warning information is generated, it is sent to the controller for processing.

3. A road network analysis system involving intelligent transportation according to claim 2, characterized in that: In the data collection unit, the road information includes: real-time traffic flow data: and recorded as ; Road capacity: and recorded as ; Real-time vehicle speed data: and record it as ; Road length: and record as ; Real-time weather information: including rainfall, visibility, and temperature, which are recorded as: , and ; Real-time traffic event data: including the specific number of accidents, construction, and traffic control that occur on the road at the current time; and recorded as: , and ; Historical accident data: the number of accidents that occurred on the road in the past week, recorded as .

4. A road network analysis system involving intelligent transportation according to claim 3, characterized in that: In the data analysis unit, the specific method of performing data analysis on the road according to the collected road information is: AS1: Each small road network is analyzed as a target road network; AS2: Mark each road in the target road network as ,in, , is the total number of roads in the target road network; AS3: Get individual roads road information, and determine each road based on the road information The congestion risk factor and accident risk factor; Determining each road according to the road information The specific form of the congestion risk coefficient is: AS3-a1: Extract roads Real-time traffic flow data and road capacity in road information are calculated by formula , and obtain the traffic flow ratio ; AS3-a2: Extract roads The real-time vehicle speed data in the road information is calculated by the formula , get the real-time vehicle speed index ;in, is the preset value, indicating the maximum vehicle speed; AS3-a3: Extract roads The real-time traffic flow data, real-time vehicle speed data and road length in the road information are calculated by the formula , get the real-time traffic density ; AS3-a4: Get traffic flow ratio , Real-time vehicle speed index and real-time traffic density , the real-time congestion risk coefficient is determined by the following formula: ； in, Expressed as the real-time congestion risk coefficient, , and is the weight coefficient.

5. A road network analysis system involving intelligent transportation according to claim 4, characterized in that: Also includes: Determining each road according to the road information The real-time accident risk factor is: AS3-b1: Extract roads Real-time weather information in road information, the weather impact factor is determined by the following formula : ； in, , and is the weight coefficient; AS3-b2: Extract roads The real-time traffic event data in the road information is used to determine the real-time traffic event factor using the following formula : ； AS3-b3: Get weather impact factors and real-time traffic event factors , and extract roads The historical accident data in the road information is used to determine the real-time accident risk factor through the following formula: ； in, Expressed as the real-time accident risk coefficient, , and is the weight coefficient.

6. A road network analysis system involving intelligent transportation according to claim 5, characterized in that: In the traffic safety index determination unit, the specific method of classifying the risk level of the road according to the real-time congestion risk coefficient and determining the traffic safety index in combination with the real-time congestion risk coefficient and the real-time accident risk coefficient is: BS1: Get real-time congestion risk factor , and classify its risk levels: like , at this time, it is judged that the road Hi is a road without congestion risk; like , at this time, the road Hi is judged to be a low-risk blocking risk road; like , at this time, the road Hi is judged to be a high-risk blocking risk road; in, and is the default value, and ; BS2: Then, the traffic safety index is determined by combining the real-time congestion risk coefficient and the real-time accident risk coefficient through the following formula: ； in, Expressed as a traffic safety index, Expressed as the overall adjustment coefficient, Expressed as accident risk weight ratio.

7. A road network analysis system involving intelligent transportation according to claim 6, characterized in that: In the warning notification unit, the specific value of the traffic safety index of the traffic safety index determination unit is obtained. ,Will With the preset threshold For comparison: If , then an early warning message is generated and sent to the controller for processing; otherwise, no processing is done.

8. A road network analysis system involving intelligent transportation according to claim 6, characterized in that: In the driving recommendation module, the specific content of determining the optimal path between the specific location of the current driver and the location information of the driver's destination includes: CS1: Get the specific location of the current driver, and at the same time, get the location information of the driver's destination, and determine whether the location information of the destination is in the small road network where the driver is located; CS2: If it is determined that the location information of the target destination is in the small road network where the driver is located; determine the optimal path from the current specific location of the driver to the location information of the target destination of the driver by the following methods, including: Model the small road network where drivers are located as a weighted directed graph ,in, It is a set of nodes, representing the intersections of roads in the small road network where the drivers are located; is an edge set, indicating the road connections in the small road network where the driver is located, and the edge set Each edge in ; represents a road from node i to node j, i represents the starting node, indicating the starting position of the road, and j represents the end node, indicating the end position of the road; Gather at the edge Filter valid edges : ;in, It is expressed as the congestion risk of the edge: 0 for roads without congestion risk, 1 for roads with low congestion risk, and 2 for roads with high congestion risk; Constructing a subgraph , and in the subgraph In the process, a weighted shortest path algorithm is used to find the optimal path from the specific location of the current driver to the location information of the driver's destination; The specific method of finding the optimal path from the current specific location of the driver to the location information of the driver's destination is: For each edge Weight Determined by the following formula: ； in, Represented as edge The length of the road, and Expressed as weight coefficient; Then obtain all feasible paths from the current driver's specific location to the driver's destination, and calculate the total weight of all feasible paths: ; Where P is the set of feasible paths, , Represents a feasible path The total weight of Finally, determine the optimal path from the current driver's specific location to the driver's destination: ； in, It represents the optimal path from the current specific location of the driver to the location information of the driver's destination.

9. A road network analysis system involving intelligent transportation according to claim 8, characterized in that: Also includes: CS3: If it is determined that the location information of the target destination is not in the small road network where the driver is located, the map software function is called through the API to obtain a recommended route from the current specific location of the driver to the location information of the driver's target destination, and the specific small road network passed by the recommended route is obtained. The corresponding starting point and end point are determined in each specific small road network. The optimal path from the current specific location of the driver to the location information of the driver's target destination is determined through step CS2, and the path from the corresponding starting point to the end point of each small road network is re-determined to obtain the optimal path of each small road network. The optimal paths of each small road network are merged to determine the optimal path from the current specific location of the driver to the location information of the driver's target destination when it is determined that the location information of the target destination is not in the small road network where the driver is located.

Images