Intelligent traffic digital twin processing method and system based on big data

Abstract

The application belongs to the technical field of intelligent transportation, and discloses an intelligent traffic digital twin processing method and system based on big data, which comprises the following steps: acquiring dynamic sensing information of a vehicle and a specific position where the vehicle is located; extracting historical traffic data of a road section where the vehicle is located, acquiring basic geographic information data of a required road section, and performing position matching and data correlation; performing data fusion to obtain fused data of multiple sources, heterogeneous, and multiple time states; realizing real-time simulation based on the fused data in a virtual environment; fusing and presenting digital twin data, simulation calculation results, and decision information, and building a signal control system to perform real-time control on traffic facilities in a real space. Through the digital twin processing method, the collected information is corresponded to the virtual environment, the virtual and real are combined, the comprehensiveness and accuracy of predicting the traffic state based on complex data are further improved, and the road traffic state can be better predicted and the congestion road section can be better optimized and controlled.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of intelligent transportation, and particularly relates to an intelligent transportation digital twin processing method and system based on big data. BACKGROUND

[0002] In recent years, intelligent transportation systems have attracted a lot of attention. As a comprehensive application product, intelligent transportation systems involve technologies including information technology, communication technology, control technology, computer technology, and sensing technology. On the other hand, the progress of science and technology has led to an increase in the types of traffic data, and the detection equipment for traffic flow in urban roads is also becoming more diverse. However, data-driven intelligent transportation systems are limited by the quality of existing urban road traffic data, and the quality of multi-source traffic data may have a disastrous impact on the later traffic signal control.

[0003] In modern urban road networks with a large amount of multi-source traffic data, the same traffic flow characteristic parameter can be detected and extracted by a large number of different detector devices (such as average speed in a specified time period, which can be detected by microwave detectors, road junctions, and GPS detectors of vehicles currently passing through the road section). It is very difficult to directly apply multi-source data because the quality of multi-source traffic data representing the same meaning is uneven, and directly selecting the data with the highest confidence level is still affected by the current detector itself. Therefore, multi-source data needs to be fused, and the data fusion method adaptively selects the optimal data combination method for fusion according to the confidence level of each data source, that is, data fusion is needed when analyzing and processing traffic big data. However, a large amount of data generated in various fields cannot be shared, resulting in low data utilization, and the data dimension of a single field is also limited due to different dimensions between fields, which further leads to defects in the overall data consideration when developing solutions, resulting in insufficient reliability of the developed solutions.

[0004] In order to solve the above problems in the prior art, digital twin technology is used to process intelligent transportation data. Digital twin is a simulation process that fully utilizes physical models, sensor updates, and operation history data, integrates multi-disciplinary, multi-physical, multi-scale, and multi-probability, and completes mapping in a virtual space to reflect the full life cycle process of the corresponding entity equipment. Digital twin is a concept beyond reality and can be regarded as a digital mapping system of one or more important and interdependent equipment systems. Digital twin transportation is achieved by collecting real-time traffic data to simulate, monitor, diagnose, predict, and control traffic, helping to solve the complexity and uncertainty problems in the transportation planning-design-construction-management-service closed-loop process, improving the safety of traffic resource effective allocation and operation state, and realizing the internal development power of intelligent transportation.

[0005] Chinese patent CN114419896A, entitled "Traffic Signal Light Control Method, Device, Equipment, and Medium Based on Digital Twin," published on April 29, 2022, discloses a method for constructing an environmental model using digital twin technology and identifying dynamic elements within that model. The environmental model includes a target intersection, upstream or downstream intersections, and the road between the target intersection and the upstream or downstream intersection. Dynamic elements include at least one of motor vehicles, non-motor vehicles, and pedestrians. Based on the environmental model and dynamic elements, the method predicts the number and direction of movement of target dynamic elements arriving at the target intersection at the next moment. Based on the number and direction of movement of the target dynamic elements, the method determines whether the original control scheme for the traffic lights at the target intersection at the next moment is reasonable. If unreasonable, a target control scheme is generated, and the traffic lights at the target intersection are controlled according to the target control scheme at the next moment. This scheme can intelligently regulate traffic lights and improve the traffic efficiency of intersections. Chinese patent CN112700639A discloses an intelligent traffic path planning method based on federated learning and digital twins, published on April 23, 2021. The method includes the following steps: S1: Registering vehicles in the vehicle system and verifying vehicle identity information; S2: Training a local model by participating in federated learning based on the vehicle's local historical data; S3: Aggregating the local models of all vehicles to obtain an aggregated model.

[0006] S4: Determine whether the aggregation model has converged to the predetermined accuracy or exceeded the time limit. If yes, proceed to step S5; otherwise, return to step S2. S5: Establish a global digital twin model for the vehicle-to-everything (V2X) network. S6: Periodically update the global digital twin model for the V2X network. S7: Initiate a pathfinding request to the roadside unit and update the optimal path and local prediction model in real time. This planning method can solve the problems of low accuracy, high latency, and privacy leakage risks in current road traffic systems for traffic prediction and path planning.

[0007] However, with the rapid pace of urbanization in my country, the number of urban roads has gradually increased, while the increase in the number of motor vehicles far exceeds the speed of urban road construction, resulting in frequent traffic congestion in cities across the country. This traffic congestion is gradually spreading to larger areas. In the aforementioned intelligent traffic data processing methods based on digital twins, inconsistencies easily arise between the actual physical design of objects and the theoretical simulation in the virtual space, leading to inaccurate predictions of complex data and hindering effective prediction of road traffic conditions and optimized control of congested road sections. Summary of the Invention

[0008] To overcome the problems existing in related technologies, the present invention discloses an embodiment of a digital twin processing method and system for intelligent transportation based on big data.

[0009] The technical solution is as follows: The intelligent transportation digital twin processing method based on big data includes the following steps:

[0010] S1, based on multi-source sensing devices and fast communication, acquires vehicle information, monitoring information and weather information in real time to determine the dynamic sensing information of the vehicle and its specific location.

[0011] S2 connects to the city traffic management system and extracts historical traffic data of the road segment where the vehicle is located, including road length, number of vehicles, vehicle size, road pressure and distance between each vehicle, to obtain the traffic congestion coefficient for the historical time period.

[0012] S3: Obtain basic geographic information data of the required road segment, and perform location matching and data association of basic geographic information data, real-time traffic big data and transportation network data through the Beidou Traffic Information Service Platform;

[0013] S4 integrates the acquired vehicle dynamic perception information, the traffic congestion coefficient of the vehicle's location over a historical time period, real-time traffic big data, and transportation network data to obtain multi-source, heterogeneous, and multi-temporal fused data.

[0014] S5. Based on digital twin technology, a digital twin traffic hierarchical model is constructed. In a virtual environment, the digital twin traffic hierarchical model is used to realize real-time simulation based on fused data, and the experimental results are analyzed and real-time decision feedback is obtained.

[0015] S6 integrates digital twin data, simulation results, and decision-making information, and builds a signal control system to control traffic facilities in the real space in real time.

[0016] In step S1, determining the vehicle's dynamic perception information includes:

[0017] The system uses image recognition to automatically detect traffic incidents, quickly identifying incident footage of abnormal congestion and traffic accidents.

[0018] The system obtains real-time vehicle speed information, vehicle speed information for the current road segment, and the number of vehicles passing through per unit time using GPS.

[0019] In one embodiment, determining the vehicle's dynamic perception information further includes: vehicle non-compliance information, which includes traffic data information where the vehicle's instantaneous speed is greater than a reasonable value, traffic data information where the video sampling time and storage time are different, and traffic data information where the vehicle's latitude and longitude in GPS positioning exceed a reasonable range.

[0020] In step S2, the traffic congestion coefficient for the historical time period is calculated using the following formula:

[0021]

[0022] In the formula, Y di is the traffic congestion coefficient, a is the length influence factor, L i is the road length between the front and rear intersections, L0 is the average road length, S q is the distance between each vehicle, S0 is the standard vehicle spacing, c is the vehicle quantity influence coefficient, β is the vehicle trip influence factor, A i is the number of vehicles on the road, A0 is the standard number of vehicles, γ is the vehicle volume influence coefficient, W i is the vehicle volume on the road, W0 is the average vehicle volume, b is the pressure influence coefficient, F i is the pressure on the road, F0 is the average pressure on the road.

[0023] In step S3, the specific steps of matching the basic geographic information data, traffic real-time big data and traffic transportation network data in position and correlating data include:

[0024] (1) Obtain and organize basic geographic information data and traffic real-time big data;

[0025] (2) Take the basic geographic information data as the framework basis, and use attribute matching method to automatically match the spatial position coordinates of all point information in the traffic transportation network data;

[0026] (3) Use the road network matching algorithm to perform route fitting, fit the traffic real-time big data to generate a traffic transportation network line graph, and match the position with the basic geographic information data;

[0027] (4) After position matching, perform geometric correction and data optimization, and obtain the traffic transportation network data associated with the spatial position information through data matching fusion.

[0028] In step S5, the digital twin traffic hierarchical model includes:

[0029] Traffic data fusion model, which fuses data sensed by different traffic sensors to form unified traffic flow data;

[0030] Traffic situation analysis model, which analyzes and predicts traffic according to historical data and real-time sensing traffic data;

[0031] Signal control model, which optimizes intersection signal timing according to real-time traffic flow data and prediction of traffic flow;

[0032] Traffic planning model, which is based on the four-stage method of traffic planning and combines traffic trip mobile internet big data to predict road network traffic volume;

[0033] The bus priority model is based on bus lines to predict bus trips.

[0034] The parking guidance model provides regional parking optimization guidance information according to the regional parking space occupancy state and parking demand prediction.

[0035] The intelligent road model forms a high-definition dynamic map of the road according to real-time sensing data of the intelligent road, and assists the safe driving of the connected vehicle.

[0036] The traffic flow simulation model simulates the real-time running traffic flow in combination with the vehicle dynamics characteristics.

[0037] The accident analysis model analyzes the traffic accident in combination with the main factors of the accident and evaluates the road safety.

[0038] In the real-time control of the traffic facilities in the real space in step S6, the prompt information and control parameters are directly sent to the driver and the intelligent connected vehicle through the network communication mode including the mobile phone APP and the Internet of Vehicles, so as to realize the guidance and control of the traffic flow.

[0039] Another object of the application is to provide an intelligent traffic digital twin processing system based on big data, which implements the intelligent traffic digital twin processing method based on big data.

[0040] The dynamic sensing module is used for collecting the dynamic sensing information of the vehicle by using the multi-source sensing device.

[0041] The big data platform is used for collecting and managing the traffic big data of the city, and the traffic big data includes the city road information data, the city automobile management information data, the city meteorological data, the city automobile real-time positioning data and the city traffic monitoring video data.

[0042] The data preprocessing module is used for data preprocessing of the various types of traffic real-time data, and realizes load balancing, resource virtualization and distributed data storage management.

[0043] The data fusion and correlation module is used for clustering and fusion processing of the data using the fusion model, and for correlation verification of the data to obtain the traffic real-time road condition data.

[0044] The meteorological data module is used for accessing meteorological data to supplement weather element information.

[0045] The data processing module is used for processing the traffic data to obtain the traffic congestion coefficient, and the data processing module sends the calculated traffic congestion coefficient to the data analysis module for analysis.

[0046] The data analysis module is configured to compare the traffic congestion coefficient with a set traffic standard congestion coefficient after receiving the traffic congestion coefficient obtained by the data processing module. If the traffic congestion coefficient is greater than the traffic standard congestion coefficient, the data analysis module sends a traffic congestion signal to the digital twin module, the digital twin module alarms the staff, and sends an execution signal to the vehicle terminal.

[0047] The digital twin module is configured to perform efficient digital mapping among the physical model, the virtual model, the twin data, and the service system, realize real-time simulation based on data driving, and obtain experimental results for analysis and real-time feedback.

[0048] The data display module is configured to display the traffic real-time big data through a data visualization platform.

[0049] In one embodiment, the dynamic perception information is divided into dynamic information and static information. The dynamic information includes Beidou navigation data, vehicle fixed-point monitoring data, signal control data, and event accident data. The static information includes Beidou map road network data and traffic management and management object data.

[0050] In one embodiment, the data fusion and association module includes:

[0051] The information acquisition unit is configured to acquire basic geographic information data and traffic real-time big data.

[0052] The data conversion unit is configured to perform data format conversion through the Beidou traffic information service platform.

[0053] The coordinate matching unit is configured to take the basic geographic information data as a frame basis, and automatically match spatial position coordinates for the traffic transportation network data and the traffic real-time big data.

[0054] The fusion processing unit is configured to perform data fusion and edge processing on the vector data.

[0055] The data association unit is configured to perform geometric correction and data optimization, and obtain traffic transportation network data associated with spatial position information through data matching and fusion.

[0056] In combination with all the technical solutions described above, the application has the advantages and positive effects that: by adopting the digital twin processing mode, on the basis of traffic congestion state data, the congestion state of the traffic system is detected on one hand, and on the other hand, the corresponding congestion evaluation data and other state information are obtained in real time according to the correlation between virtual and real space information. The collected information is corresponded to the virtual environment, and the virtual and real combination is realized. Through the mapping of the virtual and real traffic congestion state prediction and control information, the equivalent expression of the virtual traffic space to the actual physical space is realized, and the comprehensiveness and accuracy of the traffic state prediction based on complex data are further improved, so that the road traffic state prediction and the optimization control of the congestion section are better.

[0057] The application collects traffic data information in different data sources, extracts features of different traffic information after processing, forms traffic feature data of different data sources, and then fuses different traffic feature data to generate traffic fusion data, so that the city traffic condition analysis data can be obtained through evaluation. Through the fusion of traffic data information of multiple data sources, the accuracy of the final fusion of multi-source data in city traffic big data processing can be significantly improved, and the problem of excessive data error caused by inevitable abnormal situations caused by the influence of single data fusion by device environment factors and the like is avoided.

[0058] The application processes the acquired detection data through data fusion, which can effectively identify false detection data, thereby reducing the situation that the detection data has errors caused by sensor accuracy, measurement error and environmental noise.

[0059] The application can make the radiation range of city service larger under the support of digital twin technology and information technology, break the limitation of practice and space, and make the audience of the service more diverse and the radix larger, so as to create a new city traffic scene, and provide personalized, high-quality and intelligent traffic service for the public. BRIEF DESCRIPTION OF DRAWINGS

[0060] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure;

[0061] Figure 1 is a flow chart of the intelligent traffic digital twin processing method based on big data provided by the embodiment of the application;

[0062] Figure 2 is a flow chart of the method for position matching and data association of basic geographic information data, real-time traffic big data and traffic transportation network data provided by the embodiment of the application;

[0063] Figure 3is a structural schematic diagram of a digital twin traffic hierarchical model provided by an embodiment of the present application;

[0064] Figure 4 is a structural block diagram of an intelligent traffic digital twin processing system based on big data provided by an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. In the following description, a large number of specific details are set forth in order to provide a sufficient understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the scope of the present application, so the present application is not limited to the specific implementations disclosed below.

[0066] Embodiment 1, as shown in the present application, the intelligent traffic digital twin processing method based on big data provided by an embodiment of the present application includes: Figure 1

[0067] S101, based on multi-source sensing devices and fast communication, real-time acquisition of vehicle information, monitoring information and weather information, determination of dynamic perception information of vehicles and specific positions thereof;

[0068] S102, access to the city traffic management system, extract the historical traffic data of the position section where the vehicle is located, including road length, vehicle quantity, vehicle volume, road bearing pressure and distance between each vehicle, obtain the traffic congestion coefficient of the historical time period;

[0069] S103, obtain the basic geographic information data of the required road section, and match the basic geographic information data, traffic real-time big data and traffic transportation network data in position and associate the data through the Beidou traffic information service platform;

[0070] S104, data fusion of the obtained dynamic perception information of the vehicle, traffic congestion coefficient of the historical time period where the vehicle is located, and traffic real-time big data, traffic transportation network data, to obtain multi-source, heterogeneous, multi-temporal fusion data;

[0071] S105, according to the digital twin technology, a digital twin traffic hierarchical model is constructed, and the digital twin traffic hierarchical model is used in the virtual environment to realize real-time simulation based on the fusion data, and the experimental results are analyzed and real-time decision feedback is obtained;

[0072] S106, fusion and presentation of digital twin data, simulation calculation results and decision information, and building of a signal control system to realize real-time control of traffic facilities in real space.

[0073] ​The dynamic perception information of the vehicle in step S101 of this embodiment of the invention includes:

[0074] The system uses image recognition to automatically detect traffic incidents, quickly identifying incident footage of abnormal congestion and traffic accidents.

[0075] The system obtains real-time vehicle speed information, vehicle speed information for the current road segment, and the number of vehicles passing through per unit time through GPS.

[0076] It also includes information on vehicle non-compliance, such as traffic data where the instantaneous speed of the vehicle exceeds the reasonable value, traffic data where the video sampling time and storage time are different, and traffic data where the vehicle's latitude and longitude in GPS positioning exceed the reasonable range.

[0077] In this embodiment of the invention, the traffic congestion coefficient for the historical time period in step S102 is calculated using the following formula:

[0078]

[0079] In the formula, Y di L is the traffic congestion coefficient, α is the length influence factor, and L is the length factor. i L0 is the road length between the two intersections, and S is the average road length. q S0 is the distance between each vehicle, c is the vehicle number influence coefficient, β is the vehicle travel influence factor, and A is the distance between each vehicle. i Let A0 be the number of vehicles on the road, γ be the standard number of vehicles, and W be the vehicle volume influence coefficient. i Where W is the volume of vehicles on the road, W0 is the average vehicle volume, b is the pressure influence coefficient, and F is the average vehicle volume. i F0 represents the pressure exerted on the road where it is located, and F0 represents the average pressure exerted on the road.

[0080] like Figure 2 As shown, the specific steps in step S103 of this embodiment of the invention, which involve location matching and data association of basic geographic information data, real-time traffic big data, and transportation network data, include:

[0081] S201, acquire and organize basic geographic information data and real-time traffic big data;

[0082] S202, based on basic geographic information data, uses attribute matching to automatically match spatial location coordinates for all point information in transportation network data.

[0083] S203 uses a road network matching algorithm to fit the route, and uses real-time traffic big data to generate a transportation network route map, and performs location matching with basic geographic information data.

[0084] S204, after position matching, geometric correction and data optimization are carried out, and traffic transportation network data associated with spatial position information is obtained through data matching fusion.

[0085] As shown in Figure 3 The digital twin traffic hierarchical model in step S105 in the embodiment of the application includes:

[0086] A traffic data fusion model fuses data perceived by different traffic sensors to form unified traffic flow data.

[0087] A traffic situation analysis model analyzes and predicts traffic according to historical data and real-time perceived traffic data.

[0088] A signal control model optimizes intersection signal timing according to real-time traffic flow data and prediction of traffic flow.

[0089] A traffic planning model predicts road network traffic volume based on the four-stage method of traffic planning and in combination with traffic travel mobile internet big data.

[0090] A public transport priority model predicts public transport travel based on public transport lines.

[0091] A parking guidance model provides regional parking optimization guidance information according to regional parking space occupancy status and parking demand prediction.

[0092] An intelligent road model forms a high-definition dynamic map of a road based on intelligent road real-time perception data to assist safe driving of a connected vehicle.

[0093] A traffic flow simulation model simulates real-time running traffic flow in combination with vehicle dynamics characteristics.

[0094] An accident analysis model analyzes traffic accidents and evaluates road safety in combination with main factors of accident occurrence.

[0095] In real-time control of traffic facilities in the real space in step S106 in the embodiment of the application, prompt information and control parameters are directly sent to drivers and intelligent connected vehicles through network communication modes including a mobile phone APP and a vehicle network, so that the traffic flow is induced and controlled.

[0096] As shown in Figure 4 The intelligent traffic digital twin processing system based on big data provided in the embodiment of the application includes:

[0097] A dynamic perception module is configured to collect dynamic perception information of a vehicle by using a multi-source perception device.

[0098] The big data platform is used for collecting and managing traffic big data of a city, wherein the traffic big data comprises city road information data, city automobile management information data, city meteorological data, city automobile real-time positioning data and city traffic monitoring video data.

[0099] The data preprocessing module is used for pre-processing the various types of real-time traffic data, and realizes load balancing, resource virtualization and distributed data storage management.

[0100] The data fusion and correlation module is used for clustering and fusing the data using a fusion model, and verifying the correlation of the data to obtain real-time traffic condition data.

[0101] The meteorological data module is used for accessing meteorological data to supplement weather element information.

[0102] The data processing module is used for processing the traffic data to obtain a traffic congestion coefficient, and sending the calculated traffic congestion coefficient to the data analysis module for analysis.

[0103] The data analysis module is used for comparing the traffic congestion coefficient with a set traffic standard congestion coefficient after receiving the traffic congestion coefficient obtained by the data processing module, and if the traffic congestion coefficient is greater than the traffic standard congestion coefficient, the data analysis module sends a traffic congestion signal to the digital twin module, the digital twin module alarms a staff and sends an execution signal to a vehicle terminal.

[0104] The digital twin module is used for efficiently digitally mapping between a physical model, a virtual model, twin data and a service system, realizing real-time simulation based on data driving, and obtaining experimental results for analysis and real-time feedback.

[0105] The data display module is used for displaying real-time traffic big data through a data visualization platform.

[0106] The dynamic perception information in the embodiment of the application is divided into dynamic information and static information, wherein the dynamic information comprises Beidou navigation data, vehicle fixed-point monitoring data, signal control data and event accident data, and the static information comprises Beidou map road network data, traffic management and management object data.

[0107] The data fusion and correlation module in the embodiment of the application comprises:

[0108] The information acquisition unit is used for acquiring basic geographic information data and real-time traffic big data.

[0109] The data conversion unit is used for data format conversion through a Beidou traffic information service platform.

[0110] A coordinate matching unit is configured to automatically match spatial position coordinates of the traffic transportation network data and the traffic real-time big data based on the basic geographic information data as a framework.

[0111] A fusion processing unit is configured to perform data fusion edge processing on the vector data.

[0112] A data association unit is configured to perform geometric correction and data optimization, and obtain traffic transportation network data associated with spatial position information through data matching fusion.

[0113] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in a certain embodiment can be referred to the related description of other embodiments.

[0114] The information interaction and execution process between the above devices / units are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought by them can be referred to the method embodiment part, which will not be repeated here.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific name of each functional unit and module is only for easy distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the above system can be referred to the corresponding process in the foregoing method embodiment.

[0116] Based on the technical solutions described in the above embodiments of the present application, the following application examples can be further proposed.

[0117] According to the embodiments of the present application, the present application further provides a computer device, which comprises at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above method embodiments when executing the computer program.

[0118] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the steps in the above method embodiments.

[0119] The embodiments of the present application also provide an information data processing terminal, which is used to provide a user input interface to implement the steps in the above method embodiments when executed on an electronic device, and the information data processing terminal is not limited to a mobile phone, a computer or a switch.

[0120] The embodiments of the present application also provide a server, which is used to provide a user input interface to implement the steps in the above method embodiments when executed on an electronic device.

[0121] The embodiments of the present application also provide a computer program product, which, when executed on an electronic device, enables the electronic device to perform the steps in the above method embodiments.

[0122] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above method embodiments by a computer program to instruct related hardware, and the computer program can be stored in a computer readable storage medium, and the computer program, when executed by a processor, can implement the steps in the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc.

[0123] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0124] The above description is only the preferred and specific embodiments of the present application, but the protection scope of the present application is not limited to this. Any modification, equivalent replacement and improvement made by any person skilled in the art within the technical range disclosed by the present application, as long as it is within the spirit and principle of the present application, should be covered within the protection scope of the present application.

Claims

1. A method for intelligent transportation digital twin processing based on big data, characterized in that, The method includes the following steps: S1, based on multi-source sensing devices and fast communication, acquires vehicle information, monitoring information and weather information in real time to determine the dynamic sensing information of the vehicle and its specific location. S2 connects to the city traffic management system and extracts historical traffic data of the road segment where the vehicle is located, including road length, number of vehicles, vehicle size, road pressure and distance between each vehicle, to obtain the traffic congestion coefficient for the historical time period. S3: Obtain basic geographic information data of the required road segment, and perform location matching and data association of basic geographic information data, real-time traffic big data and transportation network data through the Beidou Traffic Information Service Platform; S4 integrates the acquired vehicle dynamic perception information, the traffic congestion coefficient of the vehicle's location over a historical time period, real-time traffic big data, and transportation network data to obtain multi-source, heterogeneous, and multi-temporal fused data. S5. Based on digital twin technology, a digital twin traffic hierarchical model is constructed. In a virtual environment, the digital twin traffic hierarchical model is used to realize real-time simulation based on fused data, and the experimental results are analyzed and real-time decision feedback is obtained. S6 integrates digital twin data, simulation results, and decision-making information, and builds a signal control system to control traffic facilities in the real space in real time. In step S2, the traffic congestion coefficient for the historical time period is calculated using the following formula: ； In the formula, The traffic congestion coefficient. As a length-related factor, The length of the road between the two intersections. The average road length, The distance between each vehicle, Standard vehicle spacing, The influence coefficient of the number of vehicles. As a factor influencing vehicle travel, The number of vehicles on the road. For the standard number of vehicles, This is the vehicle volume influence coefficient. For the volume of vehicles on the road, The average volume of the vehicle. This is the pressure influence coefficient. The pressure borne by the road it is on. To provide the average pressure on the road; In step S3, location matching and data association are performed on basic geographic information data, real-time traffic big data, and transportation network data. This specifically includes the following steps: (1) Acquire and organize basic geographic information data and real-time traffic big data; (2) Based on the basic geographic information data, the spatial location coordinates of all points in the transportation network data are automatically matched by attribute matching. (3) Use the road network matching algorithm to fit the route, fit the real-time traffic big data to generate a transportation network route map, and match the location with the basic geographic information data. (4) After location matching, geometric correction and data optimization are performed, and transportation network data associated with spatial location information is obtained through data matching and fusion; In step S5, the digital twin traffic hierarchical model includes: Traffic data fusion models combine data from different traffic sensors to form unified traffic flow data; Traffic situation analysis models analyze and predict traffic based on historical data and real-time perceived traffic data; The signal control model optimizes the signal timing at intersections based on real-time traffic flow data and traffic flow predictions. The traffic planning model is based on the four-stage method of traffic planning and combines mobile internet big data on traffic and travel to predict the traffic volume of the road network. The bus priority model predicts public transport trips based on bus routes. The parking guidance model provides optimized parking guidance information for the area based on the occupancy status of parking spaces and parking demand predictions. Intelligent road models generate high-definition dynamic maps of roads based on real-time intelligent road perception data to assist connected vehicles in driving safely. Traffic flow simulation model, which combines vehicle dynamics characteristics to simulate real-time traffic flow; The accident analysis model analyzes traffic accidents and evaluates road safety by combining the main factors that cause accidents. In step S6, during the real-time control of traffic facilities in the physical space, prompts and control parameters are sent directly to drivers and intelligent connected vehicles through network communication methods including mobile apps and vehicle-to-everything (V2X) networks, thereby enabling the guidance and control of traffic flow.

2. The intelligent transportation digital twin processing method based on big data according to claim 1, characterized in that, In step S1, determining the vehicle's dynamic perception information includes: The system uses image recognition to automatically detect traffic incidents, identifying event footage of abnormal congestion and traffic accidents. The system obtains real-time vehicle speed information, vehicle speed information for the current road segment, and the number of vehicles passing through per unit time using GPS.

3. The intelligent transportation digital twin processing method based on big data according to claim 2, characterized in that, Determining the dynamic perception information of a vehicle also includes: vehicle non-compliance information, which includes traffic data information where the vehicle's instantaneous speed is greater than the reasonable value, traffic data information where the video sampling time and storage time are different, and traffic data information where the vehicle's latitude and longitude in GPS positioning exceed the reasonable range.

4. A digital twin processing system for intelligent transportation based on big data, characterized in that: The intelligent transportation digital twin processing method based on big data, as described in any one of claims 1-3, comprises: The dynamic perception module is used to collect dynamic perception information of the vehicle using multi-source perception devices; The big data platform is used to collect and manage urban traffic big data, which includes urban road information data, urban vehicle management information data, urban meteorological data, urban vehicle real-time location data, and urban traffic monitoring video data. The data preprocessing module is used to preprocess various types of real-time transportation data to achieve load balancing, resource virtualization, and distributed data storage management. The data fusion and association module is used to cluster and fuse data using a fusion model, and to verify the association of data to obtain real-time traffic data. The meteorological data module is used to access meteorological data to supplement weather element information; The data processing module is used to process traffic data, obtain traffic congestion coefficients, and send the calculated traffic congestion coefficients to the data analysis module for analysis. The data analysis module is used to compare the traffic congestion coefficient obtained from the data processing module with the set traffic standard congestion coefficient. If the traffic congestion coefficient is greater than the traffic standard congestion coefficient, the data analysis module sends a traffic congestion signal to the digital twin module. The digital twin module then alarms the staff and sends an execution signal to the vehicle terminal. The digital twin module is used to perform efficient digital mapping between physical models, virtual models, twin data, and service systems, enabling data-driven real-time simulation and obtaining experimental results for analysis and real-time feedback. The data visualization module is used to display real-time traffic big data through a data visualization platform.

5. The intelligent transportation digital twin processing system based on big data according to claim 4, characterized in that, The dynamic sensing information is divided into dynamic information and static information. The dynamic information includes BeiDou navigation data, vehicle fixed-point monitoring data, signal control data, and event and accident data. The static information includes BeiDou map road network data, traffic management, and management object data.

6. The intelligent transportation digital twin processing system based on big data according to claim 4, characterized in that, The data fusion and association module includes: The information acquisition unit is used to acquire basic geographic information data and real-time traffic big data. The data conversion unit is used to convert data formats through the BeiDou Traffic Information Service Platform. The coordinate matching unit is used to automatically match spatial location coordinates for transportation network data and real-time traffic big data, based on basic geographic information data as a framework. The fusion processing unit is used to perform data fusion and edge-joining processing on vector data; The data association unit is used for geometric correction and data optimization, and obtains transportation network data associated with spatial location information through data matching and fusion.

Images