Traffic data workflow analysis method based on intelligent highway management and control system
By collecting and analyzing space-time state information in the smart high-speed management and control system, combining real-time rules and scheduling engines, dynamically update workflows and displaying three-dimensional models, the problem of fragmentation and collaborative application of smart transportation systems is solved, and the expressways is improved Real-time management and emergency response capabilities.
Patent Information
- Application Number
- CN202310559330.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-16
- Publication Date
- 2024-11-22
AI Technical Summary
The existing smart transportation systems are independent of each other, the traffic data is fragmented, the information utilization rate is low, and the collaborative application is difficult, resulting in a gap between the application effect of smart transportation and expectations, making it difficult to understand the highway road surface and traffic flow in real time, and quickly and efficiently from emergency During the incident, traffic flow was guided to resume normal traffic.
Using the traffic data workflow analysis method based on the intelligent high-speed management and control system, the space-time state information is collected through the IoT base, and the vehicle behavior prediction model of the real-time analysis engine is input. Combined with the real-time rule engine and the real-time scheduling engine, the workflow is dynamically created and updated. And integrate data through three-dimensional model management and display modules to help operation and maintenance management personnel to comprehensively analyze and judge.
The integration of data of different smart transportation systems has been achieved, the analysis and decision-making capabilities of operation and maintenance management personnel have been improved, and the normal traffic of the expressway has been quickly responded and restored.
Smart Images

Figure CN119003103A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of traffic data workflow analysis, and in particular to a traffic data workflow analysis method based on an intelligent highway management and control system. Background Art
[0002] With the continuous increase in the mileage of highway construction in my country and the growth in the total number of cars purchased by the public, the control of inter-city highways has become an important issue in the construction of smart highways. Traffic congestion, driving safety, frequent traffic accidents and other issues have always been the key issues that plague traffic management departments. How to understand the road surface and traffic conditions of highways in real time, how to quickly and efficiently guide traffic from emergency events and restore normal traffic have become issues that need to be urgently solved in current highway management.
[0003] Currently, different smart transportation systems are independent of each other, traffic data is fragmented, and information utilization is low; the degree of interoperability between software and hardware infrastructure is limited, collaborative application is difficult, and there is a certain gap between the application effect of smart transportation and expectations. Summary of the invention
[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a traffic data workflow analysis method based on an intelligent highway control system.
[0005] The purpose of the present invention can be achieved by the following technical solutions:
[0006] A traffic data workflow analysis method based on a smart highway control system, wherein the smart highway control system includes an IoT base and a digital twin engine that communicate with each other, wherein the digital twin engine includes a rule engine, a real-time analysis engine, a real-time rule engine, a real-time scheduling engine, a three-dimensional model management module, and a three-dimensional model display module, and the method includes:
[0007] S1, collecting spatiotemporal state information, and storing the collected data in a database, wherein the database is an IoT base;
[0008] S2, input the spatiotemporal state information collected in S1 into the vehicle behavior prediction model of the real-time analysis engine to obtain the prediction result;
[0009] S3. Input the prediction results into the real-time scheduling engine. Based on the workflow of the real-time rule engine and combined with the timed scheduling method, sort the priorities of the tasks corresponding to the prediction results, set the task flow priority, dynamically create and update the workflow in batches, and send and execute the workflow to the 3D model management module.
[0010] Furthermore, the process of establishing the vehicle behavior prediction model of S2 is as follows: based on the traffic rule model, a decision tree or random forest algorithm is used to predict the direction of traffic flow, and then a vehicle behavior prediction model is established in combination with historical data.
[0011] Furthermore, the traffic flow rule model is constructed based on the rules expressed in the programmatic language of the rule engine and combined with the spatiotemporal state information collected by S1;
[0012] The rule engine uses the spatiotemporal state information collected by S1 to segment highway scenarios, construct multiple specific events, establish rules based on the characteristics of each event, and express the rules in a programming language.
[0013] Furthermore, the workflow establishment process of the real-time rule engine is as follows:
[0014] Establish predefined semantic modules, use abstract methods to write rules based on the semantic modules, and output workflows.
[0015] Furthermore, the road condition three-dimensional model in the three-dimensional model management module is established based on the building information model and the geographic information system, and the three-dimensional model management module is used to perform relationship editing of the three-dimensional model, three-dimensional model action script management and three-dimensional model action binding.
[0016] Furthermore, the three-dimensional model management module updates the three-dimensional model of the road condition based on the spatiotemporal state information and workflow collected by S1.
[0017] Furthermore, based on the three-dimensional model display module, the updated three-dimensional model of road conditions is displayed, and the specific contents displayed are: the spatiotemporal distribution status of passenger flow and vehicle flow of the highway traffic system under the current situation and the prediction results within a period of time.
[0018] Furthermore, the real-time scheduling engine is built based on the Dolphin scheduling system. When the real-time scheduling engine receives a query instruction, it sends the task status, task type, number of retries, task running machine and visualization variable information to the display.
[0019] Furthermore, the spatiotemporal status information is collected based on video surveillance systems, microwave radars, integrated radar and visual perception devices, and meteorological monitoring equipment.
[0020] Furthermore, the spatiotemporal status information includes the spatiotemporal status information of the geographical environment, the spatiotemporal status information of the vehicle and meteorological information, and the spatiotemporal status information of the vehicle includes the vehicle's own information, vehicle operation information and the vehicle's real-time position.
[0021] Compared with the prior art, the present invention has the following advantages:
[0022] The present invention inputs the collected spatiotemporal state information into the vehicle behavior prediction model of the real-time analysis engine to obtain the prediction results, then executes the workflow based on the prediction results, and integrates the data into a three-dimensional model, integrating the data of different intelligent transportation systems to help operation and maintenance managers conduct comprehensive analysis and judgment. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 is a flow chart of the present invention;
[0024] Figure 2 It is a schematic diagram of the system operation architecture of the present invention;
[0025] Figure 3 This is a communication structure diagram between the IoT base and the digital twin engine of the present invention. DETAILED DESCRIPTION
[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.
[0027] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.
[0028] The present invention proposes a traffic data workflow analysis method based on a smart highway control system. The flowchart of the method is as follows: Figure 1 shown.
[0029] The intelligent highway management and control system includes an IoT base and a digital twin engine that communicate with each other. The digital twin engine includes a rule engine, a real-time analysis engine, a real-time rule engine, a real-time scheduling engine, a three-dimensional model management module and a three-dimensional model display module.
[0030] The method comprises the following steps:
[0031] S1, collecting spatiotemporal state information, and storing the collected data in a database, wherein the database is an IoT base;
[0032] S2, input the spatiotemporal state information collected in S1 into the vehicle behavior prediction model of the real-time analysis engine to obtain the prediction result;
[0033] S3. Input the prediction results into the real-time scheduling engine. Based on the workflow of the real-time rule engine and combined with the timed scheduling method, sort the priorities of the tasks corresponding to the prediction results, set the task flow priority, dynamically create and update the workflow in batches, and send and execute the workflow to the 3D model management module.
[0034] The present invention builds a microservice architecture based on Spring Cloud, creates multiple microservice interfaces, deploys different services on different servers, and the IoT base transmits the collected spatiotemporal state information to the digital twin engine through the server. The communication structure diagram of the system and the server is shown in Figure 3 shown.
[0035] The structure diagram of the intelligent highway control system is as follows: Figure 2 As shown. Among them, the IoT base is constructed using IoT technology, and based on the information collection device, it realizes the collection of spatiotemporal status information of roads, vehicles, traffic equipment, climate and meteorology, etc., aggregates the original data from the highway, and stores it in the time series database and relational database to realize the data base of the intelligent highway management and control system. The collection of spatiotemporal status information includes the collection of spatiotemporal status information of the vehicle and the spatiotemporal status information of the geographical environment (road surface, bridges). In addition, it also includes the collection of meteorological information, such as atmospheric temperature, wind force, wind direction, visibility data, etc. The spatiotemporal status information of the vehicle includes the vehicle's own information, vehicle operation information, and vehicle real-time location.
[0036] A rule engine is built based on Kafka and Flink technologies to achieve real-time response to event data streams such as vehicle operation status, traffic equipment status, personnel status tracking, and environmental data. Stream processing such as spilled object detection, abnormal vehicle parking, and abnormal personnel appearance is achieved through stream processing, visual computing, and data association integration of the real-time computing engine. The specific construction process includes:
[0037] Using the spatiotemporal information and vehicle information obtained in step S1, the highway scene is segmented to construct multiple specific events, so that the rules are initially established according to the characteristics of each event. Subsequently, the information is abstracted according to the established rules and the rules are described in an agreed programming language.
[0038] Build a real-time analysis engine. The specific process includes:
[0039] Based on the rules expressed in the programming language, combined with the vehicle operation data obtained in step S1, a traffic flow rule model is constructed; the traffic flow direction is predicted and deduced using algorithms such as decision trees and random forests, and a targeted vehicle behavior prediction model is established in combination with a large amount of historical data, and the vehicle behavior is calculated and expressed in a regularized language. In addition, multiple algorithm templates are used to predict the operation of the same vehicle, and the result with the highest consistency is selected as the prediction result to ensure the reliability of the result.
[0040] A real-time rule engine is built based on Flink and Drools to separate the decision-making part of the highway business and use predefined semantic modules to write business decisions. The specific construction process includes:
[0041] First, the predefined semantic modules are established, which is also the management of business rules. Then, the rules are written using abstract methods and the workflow is output. This step is repeated to complete the definition of multiple custom workflows, combined with time information, to build a real-time rule engine.
[0042] A real-time scheduling engine is built based on DolphinScheduler and Azkaban to solve the complex dependencies in the highway data processing process. Through the visual scheduling of DophinScheduler, key information such as the status of each task, task type, number of retries, task running machine, and visual variables can be easily viewed. The specific construction process includes:
[0043] Based on the real-time analysis engine and the timed scheduling method, the priorities of various tasks are sorted, the task flow priorities are set, and the workflows are dynamically and batch created and updated. Combined with the task flow visualization technology, the running status of the tasks can be monitored.
[0044] Based on GIS and BIM, a 3D model management module is built to complete the annotation, import and binding of highway-related 3D models. In addition, the relationship editing of 3D models, the management of 3D model action scripts, and the action binding of 3D models are also completed in this step. The 3D model management module uses 3D modeling software to perform refined 3D modeling of each facility in the highway scene, and describes its geometric parameters in detail to make it highly consistent with the actual physical entity. In addition, the positional relationship between each model needs to be adjusted so that the model as a whole is close to the distribution characteristics of the real physical entity.
[0045] In the 3D model display module, the model display is based on WebGL and AR. The generated 3D model will be displayed, and the spatiotemporal distribution of passenger and vehicle flows in the current highway traffic system will be presented in real time based on real-time data. In addition, the short-term prediction results obtained after the calculation engine processing will be visualized. First, the surface textures of different physical entities should be mapped to make them closer to the real visual effect. In addition, in order to make the model have a better use effect, interactive events should be added to it so that the perspective rotation, zooming in and out, process loading, etc. can be realized.
[0046] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.
Claims
1. A traffic data workflow analysis method based on a smart highway control system, characterized in that: The intelligent highway control system includes an IoT base and a digital twin engine that communicate with each other. The digital twin engine includes a rule engine, a real-time analysis engine, a real-time rule engine, a real-time scheduling engine, a three-dimensional model management module, and a three-dimensional model display module. The method includes: S1, collecting spatiotemporal state information, and storing the collected data in a database, wherein the database is an IoT base; S2, input the spatiotemporal state information collected in S1 into the vehicle behavior prediction model of the real-time analysis engine to obtain the prediction result; S3. Input the prediction results into the real-time scheduling engine. Based on the workflow of the real-time rule engine and combined with the timed scheduling method, sort the priorities of the tasks corresponding to the prediction results, set the task flow priority, dynamically create and update the workflow in batches, and send and execute the workflow to the 3D model management module.
2. A traffic data workflow analysis method based on a smart highway control system according to claim 1, characterized in that: The specific process of establishing the S2 vehicle behavior prediction model is as follows: based on the traffic rule model, the decision tree or random forest algorithm is used to predict the direction of traffic flow, and then the vehicle behavior prediction model is established in combination with historical data.
3. A traffic data workflow analysis method based on a smart highway control system according to claim 2, characterized in that: The traffic flow rule model is constructed based on the rules expressed in the programmatic language of the rule engine and combined with the spatiotemporal state information collected by S1; The rule engine uses the spatiotemporal state information collected by S1 to segment highway scenarios, construct multiple specific events, establish rules based on the characteristics of each event, and express the rules in a programming language.
4. The method for analyzing traffic data workflow based on a smart highway control system according to claim 1 is characterized in that: The process of establishing the workflow of the real-time rule engine is as follows: Establish predefined semantic modules, use abstract methods to write rules based on the semantic modules, and output workflows.
5. The method for analyzing traffic data workflow based on a smart highway control system according to claim 1 is characterized in that: The three-dimensional model of road conditions in the three-dimensional model management module is established based on the building information model and the geographic information system. The three-dimensional model management module is used to perform relationship editing of the three-dimensional model, three-dimensional model action script management and three-dimensional model action binding.
6. A traffic data workflow analysis method based on a smart highway control system according to claim 5, characterized in that: The 3D model management module updates the 3D model of road conditions based on the spatiotemporal status information and workflow collected by S1.
7. A traffic data workflow analysis method based on a smart highway control system according to claim 6, characterized in that: The updated three-dimensional model of road conditions is displayed based on the three-dimensional model display module. The specific contents of the display are: the spatiotemporal distribution status of passenger and vehicle flows in the highway traffic system under the current situation and the prediction results within a period of time.
8. The method for analyzing traffic data workflow based on a smart highway control system according to claim 1 is characterized in that: The real-time scheduling engine is built based on the Dolphin scheduling system. When the real-time scheduling engine receives a query instruction, it sends the task status, task type, number of retries, task running machine and visualization variable information to the display.
9. The method for analyzing traffic data workflow based on a smart highway control system according to claim 1 is characterized in that: The spatiotemporal status information is collected based on video surveillance systems, microwave radars, integrated radar and meteorological monitoring equipment.
10. A traffic data workflow analysis method based on a smart highway control system according to claim 9, characterized in that: The spatiotemporal status information includes the spatiotemporal status information of the geographical environment, the spatiotemporal status information of the vehicle and the meteorological information. The spatiotemporal status information of the vehicle includes the vehicle's own information, the vehicle's operation information and the vehicle's real-time position.
