Traffic collaborative management method and device under multi-intersection intelligent monitoring

Abstract

The invention discloses a traffic collaborative management method and device under multi-intersection intelligent monitoring, and relates to the technical field of intelligent traffic control, and the method comprises the steps: obtaining intersection monitoring data through a multi-source collection device, and carrying out the compensation fusion according to a data compensation relation, and obtaining multi-intersection traffic monitoring data; constructing a multi-region traffic network, adding the fused data into the multi-region traffic network, carrying out regional traffic recognition, and generating regional traffic management information; and based on the multi-region traffic network, analyzing the multi-region cooperation relationship, and finally obtaining global traffic cooperation management information. The technical problems of insufficient multi-intersection traffic data fusion and low inter-region cooperation efficiency in the prior art are solved, and the technical effects of optimal configuration of global traffic resources and improvement of multi-region cooperation efficiency are achieved.

Description

Technical Field

[0001] This application relates to the field of intelligent traffic control technology, and particularly to a traffic collaborative management method and device under multi-intersection intelligent monitoring. Background Art

[0002] With the acceleration of the urbanization process, traditional traffic management methods rely on fixed timing rules or manual experience adjustment, making it difficult to cope with the dynamically changing traffic demands. In the prior art, there are problems such as single data source, insufficient perception accuracy, and information islands between regions in multi-intersection collaborative control, resulting in unbalanced allocation of traffic resources. For example, a single-scenario model lacks cross-regional collaborative capabilities, and data collected by different devices are difficult to effectively integrate due to differences in accuracy and frequency, further exacerbating the fragmentation of regional traffic states and decision-making lag. Therefore, how to achieve precise fusion of multi-intersection data and global collaborative optimization has become a technical problem to be urgently solved.

[0003] In the current related technologies, there are technical problems of insufficient fusion of multi-intersection traffic data and low collaborative efficiency between regions. Summary of the Invention

[0004] This application solves the technical problems of insufficient fusion of multi-intersection traffic data and low collaborative efficiency between regions by providing a traffic collaborative management method and device under multi-intersection intelligent monitoring.

[0005] This application provides a traffic collaborative management method under multi-intersection intelligent monitoring, including:

[0006] Obtaining monitoring data of intersections through multi-source acquisition devices; compensating and fusing the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data; constructing a multi-region traffic network; adding the multi-intersection traffic monitoring data into the multi-region traffic network according to the intersection positioning relationship, and performing traffic identification for each partition based on the multi-region traffic network to obtain regional traffic management information; performing multi-region collaborative relationship analysis through the multi-region traffic network according to each regional traffic management information to obtain global traffic collaborative management information.

[0007] This application provides a traffic collaborative management device under multi-intersection intelligent monitoring, including:

[0008] Monitoring data acquisition module, which is used to obtain the monitoring data of intersections through multi-source acquisition devices; compensation fusion module, which is used to compensate and fuse the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data; multi-region traffic network construction module, which is used to construct a multi-region traffic network; partition traffic recognition module, which is used to add the multi-intersection traffic monitoring data into the multi-region traffic network according to the intersection positioning relationship, and perform traffic recognition for each partition based on the multi-region traffic network to obtain regional traffic management information; collaborative relationship analysis module, which is used to perform multi-region collaborative relationship analysis through the multi-region traffic network according to each regional traffic management information to obtain global traffic collaborative management information.

[0009] It is intended to propose a traffic collaborative management method and device under multi-intersection intelligent monitoring through this application. First, obtain intersection monitoring data through multi-source acquisition devices, and perform compensation fusion according to the data compensation relationship to obtain multi-intersection traffic monitoring data; construct a multi-region traffic network, add the fused data into it, perform partition traffic recognition, and generate regional traffic management information; analyze the multi-region collaborative relationship based on the multi-region traffic network, and finally obtain global traffic collaborative management information, achieving the technical effects of optimizing the allocation of global traffic resources and improving the collaborative efficiency of multiple regions. Brief Description of the Drawings

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0011] Figure 1 It is a schematic flowchart of the traffic collaborative management method under multi-intersection intelligent monitoring provided by the embodiments of the present application;

[0012] Figure 2 It is a schematic structural diagram of the traffic collaborative management device under multi-intersection intelligent monitoring provided by the embodiments of the present application.

[0013] Explanation of reference numerals: Monitoring data acquisition module 10, compensation fusion module 20, multi-region traffic network construction module 30, partition traffic recognition module 40, collaborative relationship analysis module 50. Detailed Embodiments

[0014] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below.

[0015] In order to make the purpose, technical solution and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0016] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0017] The embodiments of this application provide a traffic collaborative management method under multi-intersection intelligent monitoring, as Figure 1 shown, the method includes:

[0018] Step S100: Obtain the monitoring data of the intersection through multi-source acquisition devices. Specifically, to obtain the monitoring data of the intersection through multi-source acquisition devices, equipment selection and layout planning should be carried out first. The selection includes video surveillance cameras with functions such as high resolution and wide viewing angle, high-precision radar sensors, easily installable geomagnetic sensors, and ultrasonic sensors for specific scenarios, etc.; the layout needs to reasonably determine the installation positions according to the shape, size and traffic flow of the intersection, avoid monitoring blind spots and ensure the coordinated operation of the devices. Then, carry out equipment installation and debugging, install and wire strictly in accordance with the specifications, and conduct commissioning such as parameter setting and image calibration after installation, and ensure normal data acquisition through testing. After that, carry out data acquisition and transmission. Each device collects data and performs preliminary processing according to the settings, and transmits it to the data processing center through wired or wireless methods, and uses appropriate protocols and encryption technologies to ensure security. Finally, establish a data quality monitoring mechanism, set indicators to evaluate the data, and use analysis techniques to detect anomalies; at the same time, regularly maintain and service the equipment, and update and upgrade the software and hardware of the equipment and the data processing center according to requirements and technological development.

[0019] Step S200: Compensate and fuse the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data. Specifically, to compensate and fuse the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data, first analyze the data characteristics of the multi-source acquisition devices, identify the categories of their monitoring data, data accuracy and monitoring frequency, and evaluate these characteristics. Then, conduct data compensation relationship analysis, determine the target traffic monitoring data and parse to obtain the descriptive data, match it with the categories of the monitoring data of each device. If it is a unique acquisition device match, take the corresponding data as the selected data. If it is a match of multiple devices, conduct compensation analysis according to the data accuracy and monitoring frequency to obtain the compensated data. Then, carry out data compensation fusion. First, preprocess the selected and compensated data, and then select a suitable fusion method such as the weighted average method, Kalman filtering method or neural network method for fusion operation. Finally, conduct quality assessment on the fused data, determine evaluation indicators such as accuracy and integrity, and use methods such as comparison or verification for evaluation. If the quality does not meet the standard, analyze the problems and optimize and adjust the data compensation relationship and fusion method to improve the data quality.

[0020] In a possible implementation, the monitoring data is compensated and fused according to the data compensation relationship of the multi-source acquisition device to obtain multi-intersection traffic monitoring data. Step S200 further includes step S210 of identifying the data acquisition characteristics of the multi-source acquisition device, where the data acquisition characteristics include the monitoring data category, data accuracy, and monitoring frequency. Specifically, to identify the data acquisition characteristics of the multi-source acquisition device, it is necessary to first determine the device scope, covering video surveillance cameras, radar sensors, etc., and establish a device information file. Then, identify the monitoring data category. Video surveillance cameras can obtain vehicle, pedestrian, and traffic scene data; radar sensors can provide speed, distance, and angle data; geomagnetic sensors are used for traffic flow and vehicle presence detection; ultrasonic sensors can perform vehicle presence detection and distance measurement. Next, evaluate the data accuracy through comparative tests, long-term monitoring and statistical analysis, and impact factor analysis, and take adjustment and optimization measures for the impact factors. Finally, determine the monitoring frequency. First, analyze the device technical parameters, then evaluate according to the traffic monitoring requirements, and find the best frequency that meets the requirements and reasonably controls the data volume through actual tests and optimization, providing a basis for subsequent data processing, improving the quality and utilization efficiency of traffic monitoring data, and assisting urban traffic management decision-making.

[0021] Step S220: Centering on the target traffic monitoring data, analyze the compensation relationship according to the data acquisition characteristics to determine the selected data and compensation data of each acquisition device. Specifically, to determine the selected data and compensation data of each acquisition device centering on the target traffic monitoring data, it is first necessary to clarify the target traffic monitoring data, define the core indicators, and determine the data granularity and time range. Then, sort out and analyze the data acquisition characteristics, review its monitoring data category, accuracy, and frequency, and evaluate the matching degree with the target. After that, conduct a compensation relationship analysis, analyze the target data, match the acquisition characteristics with the target parameters, handle the multi-device matching situation, and consider data complementarity. Then, filter out the selected data that can directly meet the requirements and is accurate and reliable based on this, determine the part that needs to be compensated and obtain the compensation data, and mark and record the data at the same time. Finally, verify the selected and compensated data by comparing it with the actual traffic situation or other reliable data sources. If problems are found, re-analyze the compensation relationship and adjust and optimize the data selection and compensation strategy to ensure that the data accurately reflects the target traffic monitoring data.

[0022] Step S230: Perform compensation fusion based on the selected data and compensation data of each acquisition device to obtain the multi-intersection traffic monitoring data. Specifically, to perform compensation fusion based on the selected data and compensation data of each acquisition device to obtain multi-intersection traffic monitoring data, data preprocessing needs to be carried out first, including cleaning the data to remove noise, outliers, and duplicate data, converting the data format to make it unified, and normalizing the data to eliminate the influence of dimensions. Then, select a compensation fusion method. If the data has strong correlation and a stable error distribution, the weighted average method can be used; when the traffic data changes dynamically and has uncertainty, the Kalman filtering method is used; when the data relationship is complex and nonlinear, the neural network method is used. After that, perform the compensation fusion operation, input the preprocessed data into the corresponding model according to the selected method, perform fusion calculation and output the result. Finally, conduct quality assessment on the fused data, determine evaluation indicators such as accuracy and integrity, use statistical analysis and other methods for evaluation, and optimize and adjust the compensation fusion method and parameters according to the results to improve the quality of multi-intersection traffic monitoring data.

[0023] In a possible implementation manner, centering on the target traffic monitoring data, analyze the compensation relationship according to the data acquisition characteristics to determine the selected data and compensation data of each acquisition device. Step S220 further includes step S221: Parse the target traffic monitoring data to obtain descriptive data. Specifically, to parse the target traffic monitoring data to obtain descriptive data, first, clarify its scope and source, define the coverage scope in combination with traffic management requirements, consider the time and space dimensions, and sort out the data acquisition channels. Then, perform data preprocessing, including cleaning to remove noise, outliers, and duplicate data, integrating data from different data sources and unifying the format and timestamp, and standardizing the data to eliminate the influence of dimensions. Then, carry out data parsing, perform structural analysis to identify the hierarchical structure, understand the semantics in combination with professional knowledge, and extract key features and information. After that, organize and classify the descriptive data, and select a suitable way such as tables, charts, or texts to represent it. Finally, conduct verification and optimization, ensure the accuracy and reliability of the data through comparison, cross-validation, or expert evaluation, adjust the parsing process and descriptive data according to the results, and improve the data quality to support subsequent traffic data processing and decision-making.

[0024] Step S222: Use the description data to match with the monitoring data categories to obtain the matching relationship. Specifically, to use the description data to match with the monitoring data categories to obtain the matching relationship, preparatory work needs to be done first, that is, to clarify the description data and sort out the monitoring data categories of multi-source acquisition devices. Then enter the matching process, compare the description data parameters with the monitoring data categories one by one, establish reasonable matching rules, and record the matching relationship in detail. For the situation where multiple devices match the same description data, analyze the characteristics and advantages of each device; if there is no matching device, re-evaluate the description data or seek supplementary data sources. After that, verify the matching relationship, check the accuracy through actual data collection and comparison, optimize and adjust according to the results, and update in a timely manner as the devices change. Finally, apply the matching relationship to subsequent data processing, determine the selected data and compensation data accordingly, accurately utilize the data of multi-source acquisition devices, and improve the accuracy and reliability of traffic monitoring.

[0025] Step S223: When the matching relationship is a single acquisition device, use the monitoring data category corresponding to the acquisition device as the selected data. Specifically, when the matching relationship is a single acquisition device, first confirm this matching relationship, trace back and review the previous matching process, and verify its uniqueness and reliability from multiple dimensions. Then clarify the monitoring data category corresponding to the acquisition device, analyze the data characteristics of the device and accurately define the data category. After that, conduct a quality assessment of the data, analyze indicators such as accuracy and integrity, and perform preprocessing according to the assessment results, such as cleaning, conversion, and normalization. Subsequently, record the selected data, covering information such as the source and acquisition time, and select a suitable storage method and establish a backup and recovery mechanism. Finally, apply the selected data to traffic data processing and analysis tasks, and at the same time collect feedback information. If problems are found, adjust and optimize the matching, assessment, and preprocessing links in a timely manner to improve the data quality and utilization efficiency and enhance the traffic monitoring and management level.

[0026] Step S224: When the matching relationship is multiple acquisition devices, conduct data compensation analysis based on the data accuracy and monitoring frequency to obtain compensation data. Specifically, when the matching relationship is multiple acquisition devices, first review the matching relationship to ensure accuracy, collect the relevant data of each device and integrate them. Then evaluate the data accuracy, set comparison criteria, calculate the errors and classify them; at the same time, evaluate the monitoring frequency, analyze the business requirements, compare the device frequencies and evaluate their adaptability. After that, conduct data compensation analysis, identify the dominant devices, formulate compensation strategies for the devices with insufficient accuracy and frequency, and construct a data compensation model. Finally, verify the compensation data, determine the verification indicators, implement verification using appropriate methods, optimize and adjust the compensation strategies and models according to the results, and improve the quality of the compensation data to accurately reflect the actual traffic conditions.

[0027] Step S300: Construct a multi - area transportation network. Specifically, to construct a multi - area transportation network, first, the goals and requirements need to be clarified, that is, determine the construction goals and collect the demand information of relevant stakeholders. Then, data collection and analysis are carried out, covering data such as geographical information, current transportation situation, economic and social data, and analyze and mine them to predict transportation trends. Next, the network architecture design is carried out, reasonably divide the regions and locate the functions, and select an appropriate network topology. Then, determine the nodes and links, select the layout of nodes and plan and design the links. Establish a traffic flow model, select an appropriate model and conduct simulation and prediction. Construct a communication and information system, including the construction of a communication network and the development of an information system. After that, simulation and optimization are carried out, establish a simulation model, conduct experimental analysis and formulate an optimization plan. Finally, enter the implementation and maintenance stage, organize the project implementation, complete the system commissioning and acceptance, establish a daily maintenance management mechanism and adjust and optimize it in a timely manner.

[0028] In a possible implementation, in step S300 of constructing a multi - area transportation network, it further includes step S310: obtaining the target traffic topology. Specifically, obtaining the target traffic topology goes through four stages: data collection, data processing, topology construction, and verification and optimization. In terms of data collection, it is necessary to obtain geographical information data (such as terrain and landform, land use, administrative division data), transportation infrastructure data (road, public transportation facilities, transportation hub data), and traffic flow data (historical and real - time data). When processing the data, first clean the data to remove noise and correct errors, then integrate the data into a unified format and associate the information, and finally standardize the numerical and categorical data. In the topology construction stage, define the key positions of transportation infrastructure as nodes, the connection channels as links, determine the node connection relationships, set directions and weights, and construct a topology model using graphical tools and mathematical languages. Finally, conduct verification and optimization. Verify through on - site investigation and data comparison, use the simulation model to simulate and analyze and evaluate the indicators, and make local and global optimization adjustments according to the results to ensure that the topology meets the requirements of transportation planning and management.

[0029] Step S320: Divide the target area according to the traffic anomaly event records to obtain multiple divided areas. Specifically, to divide the target area according to the traffic anomaly event records to obtain multiple divided areas, relevant records need to be collected first. Data is obtained from multiple channels such as official departments, intelligent transportation systems, social media, and public feedback, and information such as the time and location of the event is detailedly recorded and stored for management. Then, feature analysis is carried out, including spatial features (drawing a hotspot map, analyzing regional differences), time features (periodic and trend analysis), and influence scope (determining direct and indirect influence areas) analysis. Then, the division principle is determined, following the principles of spatial aggregation, similarity of influence scope, traffic network connectivity, and functional consistency. Next, a division method is selected, and methods based on clustering analysis (selecting an algorithm, determining parameters), graph theory (constructing a model, performing segmentation), or rules can be used. Finally, the multiple divided areas are determined. First, a preliminary division is made, then indicators are selected to evaluate the division result, and adjustments are made according to the evaluation, and finally the multiple divided areas are determined.

[0030] Step S330: Perform multi - area division on the target traffic topology structure according to the division positioning boundaries of the multiple divided areas to construct the multi - area traffic network. Specifically, to construct the multi - area traffic network according to the division positioning boundaries of the multiple divided areas, first, the boundaries need to be matched with the target traffic topology structure, including sorting out boundary data, parsing the topology structure, and completing the element matching between the two. Then, a multi - area sub - traffic network is constructed by screening the nodes and links within the area, adjusting the attributes of the sub - network, and checking its integrity. Then, the connection design between areas is carried out, including identifying connection points, planning connection methods, and setting the attributes of the connection links. After that, the multi - area traffic network is integrated and optimized by integrating the sub - networks and connection links, simulating and analyzing the traffic flow, and adjusting and optimizing the network according to the results. Finally, network verification and implementation are carried out, verifying the network performance, making preparations for implementation, implementing according to the plan, and monitoring in real time to ensure that the network is put into use on time and in quality and operates stably.

[0031] In a possible implementation, the target area is divided according to traffic anomaly event records to obtain multiple divided areas. Step S320 further includes step S321 of obtaining a traffic anomaly event record library for the target area. Specifically, to obtain a traffic anomaly event record library for the target area, it is necessary to first clarify the data collection scope, including geographical and time ranges, and then collect data through multiple channels. In terms of official data sources, cooperate with traffic management, meteorological, and road administration departments to obtain information such as accidents, meteorology, and construction; for intelligent transportation system data sources, traffic sensors and video surveillance systems can be used to collect data such as traffic flow and vehicle speed; social public data sources obtain user feedback from social media platforms and traffic-related applications. Then, data preprocessing is carried out, cleaning the data to remove duplicates, handling missing values, and correcting errors, standardizing the data to unify the format and encoding, classifying the data, and then correlating and integrating the data from different data sources. Finally, data storage and management are carried out, selecting a suitable database or data warehouse storage method, designing the data table structure and establishing indexes, and at the same time formulating a regular backup strategy and taking security measures to ensure data security.

[0032] Step S322, according to the traffic anomaly event record library, divide the target area according to traffic anomaly event attributes and anomaly event frequencies to obtain the multiple divided areas, where the traffic anomaly event attributes include traffic congestion, traffic accidents, social events, weather disasters, and technical failures. Specifically, to divide the target area according to the traffic anomaly event record library to obtain multiple divided areas, it is necessary to first prepare the data, familiarize with the content of the record library and clean and preprocess it to unify the format. Then analyze the traffic anomaly event attributes, classify and count the number of various events and extract key features; at the same time, count the anomaly event frequencies, initially divide the areas, and then calculate the occurrence frequencies of events with different attributes in each sub-area. Then determine the method and standard for type division, and clustering analysis or hierarchical clustering methods can be selected, and the division standard can be set according to actual needs. After that, implement the division, classify and evaluate the preliminary results using the method. Finally, adjust the division results according to the actual geographical, traffic, etc. conditions, and finally determine the multiple divided areas and assign clear type labels to provide a basis for subsequent traffic management.

[0033] Step S340: Identify the traffic impact relationships between regions based on the multi-region traffic network. Specifically, to identify the traffic impact relationships between regions based on the multi-region traffic network, data collection and integration must be carried out first. Obtain data such as the topology, traffic flow, and operation of the multi-region traffic network, as well as relevant data such as land use, population employment, and public transportation, and clean, unify, and correlate the data. Then analyze the network structure, evaluate the importance of regional nodes and the connectivity of links, and analyze the topological characteristics of the network. Next, select an appropriate traffic flow model, calibrate and verify it, and simulate the traffic flow under normal and abnormal conditions. Then construct an impact relationship index system, use correlation and causal relationship analysis to identify the traffic impact relationships between regions, and conduct on-site investigations for verification and dynamic adjustment. Finally, visualize the results and apply them to aspects such as traffic planning optimization, management strategy formulation, and emergency response plan formulation.

[0034] Step S350: Based on the multi-region traffic network, starting from traffic monitoring data, perform regional traffic management objective - traffic impact relationship - full-objective regional traffic management objective node analysis to obtain a traffic management data link. Specifically, to obtain a traffic management data link based on the multi-region traffic network, traffic monitoring data must be collected and preprocessed first. Obtain data from multiple sources and cover all regions, and perform cleaning, standardization, and fusion processing. Then determine the regional traffic management objectives, clarify the types of objectives such as safety, efficiency, and environmental protection, and refine the indicators. Then analyze the traffic impact relationships, study the impacts of variables on regions through correlation analysis and model construction. After that, perform full-objective regional traffic management objective node analysis, identify key nodes, and decompose the objectives. Then construct a traffic management data link, design the data flow links, and integrate the system for implementation. Finally, conduct evaluation and optimization, establish an evaluation index system, continuously improve based on the results, and new technologies can also be introduced to improve the intelligent level.

[0035] Step S360: Deploy edge computing nodes according to the data propagation timeliness constraints of the traffic management data link. Specifically, to deploy edge computing nodes according to the data propagation timeliness constraints of the traffic management data link, the constraints must be clarified first. Communicate with the traffic management department about business requirements and determine the data propagation time threshold. Then evaluate the data link, analyze the topological structure, traffic characteristics, and monitor the existing delays. Then determine the node requirements, analyze the computing and storage capabilities, and estimate the number of nodes. Next, select the deployment locations, which are determined based on the delay bottlenecks, data acquisition source distributions, and network communication conditions. Then implement the deployment, complete equipment selection and procurement, installation and configuration, and network connection debugging. Finally, conduct testing and optimization, carry out functional testing, verify the timeliness constraints, and conduct long-term monitoring and adjust the node configuration, location, and number as needed.

[0036] Step S400: According to the intersection location relationship, add the multi-intersection traffic monitoring data to the multi-zone traffic network, and based on the multi-zone traffic network, perform traffic identification for each zone to obtain regional traffic management information. Specifically, to obtain regional traffic management information, it is necessary to first sort out the multi-intersection traffic monitoring data and the intersection location relationship, collect the multi-intersection traffic monitoring data and clarify its geographical location and connection relationship with the surrounding roads and regions. Then add the multi-intersection traffic monitoring data to the multi-zone traffic network, unify the data format and perform correlation fusion according to the location relationship. After that, based on the multi-zone traffic network, perform traffic identification for each zone, define traffic state indicators, extract and analyze the zonal data, and identify traffic patterns. Finally, integrate the traffic identification results of each zone, generate a detailed report including current situation assessment, problem warning and management suggestions, and use visualization technology to intuitively display the regional traffic management information to assist in scientific decision-making.

[0037] Step S500: According to the regional traffic management information of each region, perform multi-regional coordination relationship analysis through the multi-zone traffic network to obtain global traffic coordination management information. Specifically, to obtain global traffic coordination management information according to the regional traffic management information of each region, it is necessary to first integrate the regional traffic management information, collect and clean the data, perform standardization and unified fusion storage. Then analyze the multi-zone traffic network, study the topological structure, traffic flow and its impacts. Next, carry out multi-regional coordination relationship analysis, understand the coordination mechanism between regions through correlation analysis, coordination pattern recognition and coordination effect evaluation. Then mine the global traffic coordination management information, extract key information, generate decision support information and visualize it. Finally, conduct information evaluation and feedback, evaluate the accuracy of the information and the management effect, update the information according to the results of the feedback, and form a closed-loop management decision-making process.

[0038] In a possible implementation manner, according to the regional traffic management information of each region, perform multi-regional coordination relationship analysis through the multi-zone traffic network to obtain global traffic coordination management information. Step S500 further includes step S510: According to the regional traffic management information of each region, perform cross-zonal impact analysis to obtain the impact scope and impact parameters. Specifically, to perform cross-zonal impact analysis according to the regional traffic management information of each region and obtain the impact scope and impact parameters, it is necessary to first collect multi-source data covering aspects such as traffic monitoring, meteorology, geographical information and social activities, and clean, standardize and integrate it. Then select a suitable impact analysis model according to the analysis purpose, data characteristics and complexity of the traffic system, such as traffic simulation, macroscopic traffic or machine learning models, and complete model construction and parameter calibration. After that, determine abnormal events and set simulation scenarios, run the model and analyze the results. Then determine the spatial and temporal scope of the impact according to the analysis results combined with geographical information, and extract and quantify impact parameters such as the traffic flow change rate. Finally, compare the results with the actual data and verify them after expert evaluation. If there are deviations, optimize the model and correct the parameters.

[0039] Step S520: Construct the management benefit function for each region with the abnormal traffic events as the participants. Specifically, to construct the management benefit function for each region with the abnormal traffic events as the participants, first, it is necessary to clarify the traffic management objectives of each region, communicate with the management department and study the policies and regulations, and classify and refine the objectives into specific indicators such as safety, efficiency, and environmental protection. Then, identify the types of abnormal traffic events and analyze their influencing factors, including event characteristics and their impacts on each objective. Next, collect historical and monitoring data, use statistical methods and others to establish a quantitative model, and determine the influence coefficients of the influencing factors on the objectives. After that, design the function structure, which is expressed as the weighted sum of multi-objective functions, define the forms of each objective function, and determine the weights through expert consultation or the analytic hierarchy process. Finally, verify the model with historical data. If there are deviations, check and correct them, and optimize the function according to the results to make it adapt to different situations.

[0040] Step S530: Based on the traffic management information of each region, calculate the benefit losses of the management benefit functions of each region according to the influence scope and influence parameters to obtain the regional loss values. Specifically, based on the traffic management information of each region, when calculating the regional loss values according to the influence scope and influence parameters, it is necessary to first do a good job in data preparation and integration, collect the traffic management information of each region, sort out the influence scope and parameters and unify the data format. Then, clarify the management benefit function of each region, review its construction method and determine the meaning of the parameters. After that, calculate the benefit losses of each region, analyze the changes in the information within the influence scope, substitute the changed data into the function to calculate the function values under abnormal and normal conditions, and the difference between the two is the loss value. At the same time, the influence of the time dimension on the loss should be considered, and sensitivity analysis is used to handle the uncertainty. Finally, verify the results, compare them with the actual situation. If the deviation is large, recheck, adjust the loss value according to the verification results and record it to provide an accurate basis for traffic management decisions.

[0041] Step S540: Conduct a global benefit equilibrium search based on the regional loss values to obtain the global traffic collaborative management information. Specifically, to obtain the global traffic collaborative management information based on the regional loss values, it is necessary to first do a good job in data preparation and preprocessing, collect and integrate the regional loss values and associate other relevant information, and clean and standardize the data. Then, determine the global benefit equilibrium objective, clarify the overall objective and refine the indicators, and set the constraint conditions. Next, select a suitable search algorithm and set the parameters, and iteratively search in the initialized search space, and output the optimal solution according to the convergence conditions. Subsequently, generate the global traffic collaborative management information, interpret and analyze the solution, integrate and present the information and formulate an implementation plan. Finally, evaluate the implementation effect of the solution, optimize the management information according to the results feedback, and continuously improve the global traffic collaborative management level.

[0042] In the embodiments of the present application, intersection monitoring data is obtained through multi-source acquisition devices, and compensation fusion is performed according to the data compensation relationship to obtain multi-intersection traffic monitoring data; a multi-region traffic network is constructed, the fused data is added thereto, regional traffic identification is performed, and regional traffic management information is generated; based on the multi-region traffic network, the multi-region collaboration relationship is analyzed, and finally global traffic collaboration management information is obtained, achieving the technical effects of optimizing the allocation of global traffic resources and improving the collaboration efficiency of multiple regions.

[0043] In the foregoing, reference has been made to Figure 1 describe in detail the traffic collaboration management method under multi-intersection intelligent monitoring according to the embodiments of the present invention. Next, reference will be made to Figure 2 describe the traffic collaboration management device under multi-intersection intelligent monitoring according to the embodiments of the present invention.

[0044] The traffic collaboration management device under multi-intersection intelligent monitoring according to the embodiments of the present invention is used to solve the technical problems of insufficient fusion of existing multi-intersection traffic data and low collaboration efficiency between regions, achieving the technical effects of optimizing the allocation of global traffic resources and improving the collaboration efficiency of multiple regions. The traffic collaboration management device under multi-intersection intelligent monitoring includes: a monitoring data acquisition module 10, a compensation fusion module 20, a multi-region traffic network construction module 30, a regional traffic identification module 40, and a collaboration relationship analysis module 50.

[0045] The monitoring data acquisition module 10 is used to obtain the monitoring data of the intersection through multi-source acquisition devices.

[0046] The compensation fusion module 20 is used to perform compensation fusion on the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data.

[0047] The multi-region traffic network construction module 30 is used to construct a multi-region traffic network.

[0048] The regional traffic identification module 40 is used to add the multi-intersection traffic monitoring data to the multi-region traffic network according to the intersection positioning relationship, and perform regional traffic identification on each region based on the multi-region traffic network to obtain regional traffic management information.

[0049] The collaboration relationship analysis module 50 is used to analyze the multi-region collaboration relationship through the multi-region traffic network according to the regional traffic management information of each region to obtain global traffic collaboration management information.

[0050] Next, the specific configuration of the compensation fusion module 20 will be described in detail. As described above, the monitoring data is compensated and fused according to the data compensation relationship of the multi-source acquisition device to obtain the multi-intersection traffic monitoring data. The compensation fusion module 20 further includes: a data acquisition unit for identifying the data acquisition characteristics of the multi-source acquisition device, where the data acquisition characteristics include the monitoring data category, data accuracy, and monitoring frequency; a compensation relationship analysis unit for analyzing the compensation relationship based on the target traffic monitoring data according to the data acquisition characteristics to determine the selected data and compensation data of each acquisition device; and a compensation fusion unit for performing compensation fusion based on the selected data and compensation data of each acquisition device to obtain the multi-intersection traffic monitoring data.

[0051] Among them, based on the target traffic monitoring data, the compensation relationship is analyzed according to the data acquisition characteristics to determine the selected data and compensation data of each acquisition device. The compensation relationship analysis unit further includes: a data parsing subunit for parsing the target traffic monitoring data to obtain description data; a matching relationship acquisition subunit for using the description data to match with the monitoring data category to obtain a matching relationship; a data selection subunit for taking the monitoring data category corresponding to the acquisition device as the selected data when the matching relationship is a unique acquisition device; and a compensation data acquisition subunit for performing data compensation analysis according to the data accuracy and monitoring frequency to obtain compensation data when the matching relationship is multiple acquisition devices.

[0052] Next, the specific configuration of the multi-region traffic network construction module 30 will be described in detail. As described above, a multi-region traffic network is constructed. The multi-region traffic network construction module 30 further includes: a target traffic topology structure acquisition unit for obtaining a target traffic topology structure; a target area division unit for dividing the target area according to the traffic anomaly event record to obtain multiple divided areas; and a multi-region division unit for performing multi-region division on the target traffic topology structure according to the division positioning boundaries of the multiple divided areas to construct the multi-region traffic network.

[0053] Among them, the target area is divided according to traffic anomaly event records to obtain multiple divided areas. The target area division unit further includes: an anomaly event record library acquisition subunit, which is used to obtain the traffic anomaly event record library of the target area; a type division subunit, which is used to divide the target area according to the traffic anomaly event record library according to traffic anomaly event attributes and anomaly event frequencies to obtain the multiple divided areas, where the traffic anomaly event attributes include traffic congestion, traffic accidents, social events, weather disasters, and technical failures.

[0054] Among them, the multi-area traffic network construction module 30 further includes: an influence relationship recognition unit, which is used to recognize the traffic influence relationships between regions according to the multi-area traffic network; a target node analysis unit, which is used to start from traffic monitoring data based on the multi-area traffic network and perform regional traffic management objective - traffic influence relationship - full target area traffic management target node analysis to obtain a traffic management data link; a temporal constraint unit, which is used to deploy edge computing nodes according to the data propagation temporal constraints of the traffic management data link.

[0055] Next, the specific configuration of the collaborative relationship analysis module 50 will be described in detail. As described above, according to the traffic management information of each region, multi-region collaborative relationship analysis is performed through the multi-area traffic network to obtain global traffic collaborative management information. The collaborative relationship analysis module 50 further includes: a cross-sub-region influence analysis unit, which is used to perform cross-sub-region influence analysis according to the traffic management information of each region to obtain an influence range and influence parameters; a management benefit function construction unit, which is used to construct the management benefit function of each region with the abnormal traffic events of each region as participants; a benefit loss calculation unit, which is used to calculate the benefit loss of the management benefit function of each region based on the traffic management information of each region according to the influence range and influence parameters to obtain a regional loss value; a benefit balance search unit, which is used to perform global benefit balance search based on the regional loss value to obtain the global traffic collaborative management information.

[0056] The traffic collaborative management device under multi-intersection intelligent monitoring provided by the embodiments of the present invention can execute the traffic collaborative management method under multi-intersection intelligent monitoring provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0057] Although this application makes various references to certain modules in the system according to the embodiments of this application, however, any number of different modules can be used and run on the user terminal and / or the server. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0058] The above specific implementation manners do not constitute a limitation to the protection scope of this application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A traffic collaborative management method under multi-intersection intelligent monitoring, characterized in that Including: Obtaining monitoring data of intersections through multi-source acquisition devices; Compensating and fusing the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data; Constructing a multi-region traffic network; According to the intersection positioning relationship, adding the multi-intersection traffic monitoring data to the multi-region traffic network, and performing traffic identification for each partition based on the multi-region traffic network to obtain regional traffic management information; According to the regional traffic management information of each region, performing multi-region collaboration relationship analysis through the multi-region traffic network to obtain global traffic collaboration management information.

2. The traffic collaborative management method under multi-intersection intelligent monitoring according to claim 1, characterized in that The constructing of the multi-region traffic network includes: Obtaining a target traffic topology structure; Performing target area division according to traffic anomaly event records to obtain multiple divided areas; Performing multi-region division on the target traffic topology structure according to the division positioning boundaries of the multiple divided areas to construct the multi-region traffic network.

3. The traffic collaborative management method under multi-intersection intelligent monitoring according to claim 2, characterized in that, Performing target area division according to traffic anomaly event records to obtain multiple divided areas, including: Obtaining a traffic anomaly event record library of the target area; According to the traffic anomaly event record library, classifying the target area according to traffic anomaly event attributes and anomaly event frequencies to obtain the multiple divided areas, where the traffic anomaly event attributes include traffic congestion, traffic accidents, social events, weather disasters, and technical failures.

4. The traffic collaborative management method under multi-intersection intelligent monitoring according to claim 1, characterized in that, Compensating and fusing the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data, including: Identifying the data acquisition characteristics of the multi-source acquisition devices, where the data acquisition characteristics include monitoring data categories, data accuracy, and monitoring frequency; Taking the target traffic monitoring data as the center, performing compensation relationship analysis according to the data acquisition characteristics to determine the selected data and compensation data of each acquisition device; Performing compensation fusion according to the selected data and compensation data of each acquisition device to obtain the multi-intersection traffic monitoring data.

5. The traffic collaborative management method under multi-intersection intelligent monitoring according to claim 4, characterized in that, Taking the target traffic monitoring data as the center, performing compensation relationship analysis according to the data acquisition characteristics to determine the selected data and compensation data of each acquisition device, including: Analyzing the target traffic monitoring data to obtain descriptive data; Using the descriptive data to match with the monitoring data categories to obtain a matching relationship; When the matching relationship is a single acquisition device, taking the monitoring data category corresponding to the acquisition device as the selected data; When the matching relationship is multiple acquisition devices, performing data compensation analysis according to the data accuracy and monitoring frequency to obtain compensation data.

6. The traffic collaborative management method under multi-intersection intelligent monitoring according to claim 1, characterized in that, After constructing the multi-region traffic network, it further includes: Identifying the traffic influence relationships between regions according to the multi-region traffic network; Based on the multi-region traffic network, starting from traffic monitoring data, performing regional traffic management objective - traffic influence relationship - full target area traffic management objective node analysis to obtain a traffic management data link; Deploying edge computing nodes according to the data propagation timeliness constraints of the traffic management data link.

7. The traffic collaborative management method under multi-intersection intelligent monitoring according to claim 1, characterized in that According to the regional traffic management information of each region, performing multi-region collaboration relationship analysis through the multi-region traffic network to obtain global traffic collaboration management information, including: According to the traffic management information of each region, perform cross-regional impact analysis to obtain the impact scope and impact parameters; Taking the abnormal traffic events in each region as participants, construct the management benefit function of each region; Based on the traffic management information of each region, calculate the benefit loss of the management benefit function of each region according to the impact scope and impact parameters to obtain the regional loss value; Based on the regional loss value, perform global benefit balance search to obtain the global traffic collaborative management information.

8. Traffic collaborative management device under multi-intersection intelligent monitoring, characterized in that, The device is used to implement the traffic collaborative management method under multi-intersection intelligent monitoring according to any one of claims 1-7. The device includes: A monitoring data acquisition module, which is used to obtain the monitoring data of the intersection through multi-source acquisition devices; A compensation fusion module, which is used to compensate and fuse the monitoring data according to the data compensation relationship of the multi-source acquisition devices to obtain multi-intersection traffic monitoring data; A multi-region traffic network construction module, which is used to construct a multi-region traffic network; A partition traffic identification module, which is used to add the multi-intersection traffic monitoring data into the multi-region traffic network according to the intersection positioning relationship, and perform traffic identification for each partition based on the multi-region traffic network to obtain regional traffic management information; A collaborative relationship analysis module, which is used to perform multi-region collaborative relationship analysis through the multi-region traffic network according to the regional traffic management information to obtain global traffic collaborative management information.

Images