Intelligent traffic data processing method and system based on 5G communication system

Abstract

The invention discloses an intelligent traffic data processing method and system based on a 5G communication system, and relates to the technical field of traffic data processing, and the method comprises the steps: collecting data based on a 5G communication network; preprocessing the collected traffic data through an edge computing node; real-time prediction and risk assessment are carried out on traffic flow based on the cloud platform; sending real-time traffic information and optimization suggestions to a traffic management center and related vehicles; when an emergency occurs, a rapid response mechanism is triggered through a 5G network, and traffic resources are scheduled. The system collects, processes and analyzes traffic data in real time through the characteristics of high bandwidth and low delay of the 5G communication network and the distributed processing capability of edge calculation, achieves the real-time prediction and management of traffic flow and accident risks, and can improve the road utilization efficiency, reduce traffic accidents and improve the traffic safety through the intelligent decision and optimization control strategy. And the emergency response capability is improved, so that a more intelligent solution is provided for urban traffic management.

Description

Technical Field

[0001] The present invention relates to the field of traffic data processing technology, and specifically to a smart traffic data processing method and system based on a 5G communication system. Background Art

[0002] With the continuous increase in urban traffic demand, traffic management faces increasingly complex and diverse challenges. Traditional traffic monitoring and management systems usually rely on offline processing and manual decision-making and cannot respond to sudden traffic conditions in real time, such as traffic accidents and road failures. In addition, with the increase in the number of vehicles and the complexity of traffic flow, traditional traffic management systems are difficult to accurately predict and optimize traffic flow, leading to traffic congestion, frequent traffic accidents and other problems.

[0003] In order to meet these challenges, the introduction of smart transportation systems has become particularly critical. Smart transportation systems achieve real-time monitoring and management of traffic flow by integrating advanced communication technologies, sensor networks and data analysis methods. However, traditional smart transportation systems are usually based on low-frequency data collection and transmission, and cannot achieve real-time response and decision-making on traffic data. With the development of 5G communication technology, low-latency, high-bandwidth, and large-connection 5G networks provide technical support for real-time data processing and intelligent decision-making in smart transportation. Edge computing, as a distributed computing architecture, can effectively reduce data transmission delays and improve real-time performance and system response speed by migrating data processing from the data source to a place closer to the data collection source. Combining the powerful computing power of cloud computing and the low-latency advantage of edge computing, traffic data can be efficiently processed, deeply analyzed, and optimized in real time. Therefore, the smart transportation system based on 5G communication and edge computing can achieve accurate processing and timely response to multi-dimensional information such as traffic flow, accident warning, and road condition analysis. Summary of the invention

[0004] In order to solve the above technical problems, a smart traffic data processing method and system based on a 5G communication system is provided. This technical solution solves the above problems.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for processing intelligent traffic data based on a 5G communication system, comprising:

[0007] Collect data from traffic sensors, surveillance cameras, vehicle terminals and roadside equipment based on 5G communication networks, and transmit data in real time;

[0008] Preprocess the collected traffic data through edge computing nodes, including data cleaning, feature extraction and preliminary analysis;

[0009] The pre-processed data is transmitted to the central cloud platform via the 5G network for in-depth analysis, and real-time traffic flow prediction and risk assessment are carried out based on the cloud platform;

[0010] Send real-time traffic information and optimization suggestions to the traffic management center and relevant vehicles;

[0011] In the event of an emergency, the 5G network can trigger a rapid response mechanism and dispatch traffic resources.

[0012] Preferably, the data collected from traffic sensors, surveillance cameras, vehicle terminals and roadside equipment based on the 5G communication network and the real-time transmission of the data specifically include:

[0013] Based on the collection of real-time data by traffic sensors and vehicle terminal equipment, traffic sensors obtain real-time information on roads, traffic flow, vehicle status and road conditions, surveillance cameras capture traffic video streams, vehicle terminals transmit real-time dynamic information on vehicle position, speed and direction, and roadside equipment collects environmental and traffic facility data through wireless sensor networks;

[0014] Use URLLC transmission protocol for real-time data transmission.

[0015] Preferably, the preprocessing of the collected traffic data by the edge computing node, including data cleaning, feature extraction and preliminary analysis, specifically includes:

[0016] Data transmitted through 5G networks, sensors, monitoring equipment, and vehicle terminals are sent to the nearest edge computing node for further processing. The edge node is accessed through the low-latency 5G network.

[0017] The edge node performs preliminary analysis, cleaning and aggregation of the transmitted data, removes abnormal data, and extracts data features, including traffic flow, accident warnings, and vehicle density;

[0018] After preliminary analysis at the edge computing node, the data is aggregated and uploaded to the cloud platform for in-depth analysis.

[0019] Preferably, the edge node performs preliminary analysis, cleaning and aggregation of the transmitted data, removes abnormal data, and extracts data features, including traffic flow, accident warning and vehicle density, specifically including:

[0020] Outliers are identified by calculating the interquartile range of the data, where the formula for the interquartile range is:

[0021] IQR=Q3-Q1

[0022] In the formula, IQR is the interquartile range, Q1 is the first quartile, and Q3 is the third quartile;

[0023] Based on the interquartile range calculation results, identify outliers in the data. If the data point is less than Q1-1.5×IQR, it is a lower bound outlier. If the data point is greater than Q3+1.5×IQR, it is an upper bound outlier.

[0024] For missing data, data is filled by mean filling, and the noise in the original data is filtered by sliding window smoothing data;

[0025] Aggregate the data based on spatial location, where the aggregation formula is:

[0026]

[0027] In the formula, u s is the weighted average flow rate of all sensors, w i represents the weight of the i-th sensor, w i represents the i-th data, x i is the value of the ith data point, and N is the total number of data points;

[0028] Through feature extraction, features are extracted from traffic data, including traffic flow, vehicle density, and accident warning.

[0029] Preferably, the pre-processed data is transmitted to the central cloud platform via the 5G network for in-depth analysis, and real-time prediction and risk assessment of traffic flow based on the cloud platform specifically include:

[0030] Based on historical data and real-time sensor data, real-time traffic prediction is performed through machine learning models, where the prediction formula is:

[0031] y(t)=w0+w1x1(t)+w2x2(t)+…+w n x n (t)+∈

[0032] Where y(t) is the traffic flow predicted at time t, x1(t)x2(t)x n (t) is the feature at time t, w1w2w n is the weight of the model, ∈ is the error term;

[0033] Predict potential traffic congestion areas based on traffic flow and other related factors, including traffic accidents, weather changes, and events. By analyzing historical data and integrating real-time sensor data, the cloud platform determines which areas are likely to be congested and issues early warnings.

[0034] Combine real-time traffic data, accident data and weather data to conduct traffic risk assessment;

[0035] Integrate road video surveillance streams, sensor data, and vehicle terminal information to identify and assess possible traffic accidents and emergencies, including car accidents and fires, and issue early warnings to the traffic management center and relevant personnel;

[0036] Based on traffic forecast and risk assessment results, the cloud platform generates traffic optimization strategies. Through real-time traffic forecast, it adjusts the timing of traffic lights, recommends vehicles to detour congested areas, and dispatches public transportation resources.

[0037] The cloud platform pushes the analysis results to the traffic management center and related vehicles in real time through the 5G network, providing real-time road conditions, traffic suggestions and risk warning information;

[0038] In the event of an emergency, including traffic accidents and road failures, the emergency response mechanism is triggered based on the analysis results of the cloud platform to dispatch traffic law enforcement vehicles, direct traffic flow, and adjust signal light timing. Through the collaboration of the 5G network and the central cloud platform, traffic resources are automatically dispatched, intelligent traffic lights are dispatched, traffic flow distribution is adjusted, and emergency vehicles are given priority.

[0039] Preferably, the information fusion of road video surveillance stream, sensor data and vehicle terminal information to identify and evaluate possible traffic accidents and emergencies specifically includes:

[0040] Based on the modal deep learning network, features from different data sources are integrated and input into the deep neural network for joint learning;

[0041] Obtain the latest data from sensors, video surveillance and vehicle terminal data sources in real time, including vehicle behavior, traffic flow and environmental conditions;

[0042] Based on the pre-trained model, the accident risk assessment is performed by inputting the current real-time data. The model calculates the probability of an accident based on the detected behavior patterns and traffic conditions. The probability calculation formula is:

[0043]

[0044] Where P represents the probability of an accident, x1 is the behavior feature, x2 is the traffic feature, x3 is the environment feature, β0 is the bias term, and β1β2β3 is the weight of x1x2x3;

[0045] When the model assesses that the probability of an accident exceeds the preset threshold, the system triggers an early warning and sends an alert to the traffic management center and relevant personnel. The early warning information includes the type of accident, the location of the accident, the severity of the accident and the timestamp of the accident.

[0046] A smart traffic data processing system based on a 5G communication system, comprising:

[0047] Data collection module: used to collect data from traffic sensors, surveillance cameras, vehicle terminals and roadside equipment through the 5G communication network;

[0048] Edge computing module: The edge computing module is electrically connected to the data acquisition module. The edge computing module is used to perform preliminary processing, cleaning and analysis on the collected data, and adjust the traffic lights in real time according to the road conditions and flow information;

[0049] Central cloud platform: The central cloud platform is electrically connected to the edge computing module. The central cloud platform is used to receive data transmitted from the edge computing node, conduct in-depth analysis and generate traffic flow prediction and optimization strategies;

[0050] Traffic information push module: The traffic information push module is electrically connected to the central cloud platform, and is used to push real-time traffic information and optimization suggestions to the traffic management center, related vehicles and other traffic equipment through the 5G communication network;

[0051] Quick response module: The quick response module is electrically connected to the traffic information push module. The quick response module is used to trigger the dispatch mechanism through the 5G network in an emergency to ensure that response measures are taken in a timely manner.

[0052] Preferably, the data acquisition module specifically includes:

[0053] Data acquisition unit: collects information on road vehicle flow, speed and lane occupancy, captures and transmits real-time video data based on surveillance cameras, performs traffic flow monitoring, license plate recognition and accident detection, and provides real-time vehicle location, speed, acceleration and driving behavior data based on vehicle terminals;

[0054] Communication unit: transmits the locally collected data to the central control platform via the 5G network;

[0055] Data storage unit: stores data from sensors and devices.

[0056] Preferably, the edge computing module specifically includes:

[0057] Data access unit: receives data, parses data from different devices, and performs protocol conversion;

[0058] Data processing unit: data cleaning, format conversion, missing value supplementation and denoising;

[0059] Data fusion unit: fuses data from different sensors, combines data from video surveillance and vehicle speed sensors, and generates comprehensive information about traffic density and road conditions;

[0060] Real-time analysis and decision-making unit: Based on the collected data on traffic flow, vehicle speed and traffic events, real-time analysis is performed, including traffic density analysis, traffic accident detection, road condition prediction and lane status assessment.

[0061] Preferably, the central cloud platform specifically includes:

[0062] Traffic decision and strategy generation unit: Generates corresponding traffic management strategies based on data analysis results, adjusts traffic light duration and switching strategies, optimizes traffic flow, dynamically adjusts lane usage based on traffic conditions, provides real-time route guidance for drivers, avoids congestion and accident-prone areas, and automatically generates control rules and strategies based on model predictions and historical data, and sends them to edge computing nodes for execution;

[0063] Decision Support and Visualization Unit: Provides decision support based on analysis results for traffic managers, including generating reports, charts and graphs to help users understand traffic conditions and make decisions, and providing real-time traffic flow monitoring panels.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] The present invention proposes a smart traffic data processing method and system based on the 5G communication system, which can give full play to the high bandwidth and low latency characteristics of the 5G communication network and the distributed processing capabilities of edge computing, collect, process and analyze traffic data in real time, and realize real-time prediction and management of traffic flow and accident risks. Through intelligent decision-making and optimized control strategies, this system can improve road utilization efficiency, reduce traffic accidents, and enhance emergency response capabilities, thereby providing a smarter, more efficient and safer solution for urban traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a step flow framework diagram of the present invention;

[0067] Figure 2 It is a system framework diagram of the present invention. DETAILED DESCRIPTION

[0068] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0069] Reference Figure 1 As shown, a smart traffic data processing method based on a 5G communication system includes:

[0070] Step 1:

[0071] Based on the collection of real-time data by traffic sensors and vehicle terminal equipment, traffic sensors obtain real-time information on roads, traffic flow, vehicle status and road conditions, surveillance cameras capture traffic video streams, vehicle terminals transmit real-time dynamic information on vehicle position, speed and direction, and roadside equipment collects environmental and traffic facility data through wireless sensor networks;

[0072] Use URLLC transmission protocol for real-time data transmission.

[0073] Step 2:

[0074] Data transmitted through 5G networks, sensors, monitoring equipment, and vehicle terminals are sent to the nearest edge computing node for further processing. The edge node is accessed through the low-latency 5G network.

[0075] The edge nodes perform preliminary analysis, cleaning and aggregation of the transmitted data, remove abnormal data, and extract data features, including traffic flow, accident warnings, and vehicle density.

[0076] After preliminary analysis at the edge computing node, the data is aggregated and uploaded to the cloud platform for in-depth analysis.

[0077] Outliers are identified by calculating the interquartile range of the data, where the formula for the interquartile range is:

[0078] IQR=Q3-Q1

[0079] In the formula, IQR is the interquartile range, Q1 is the first quartile, and Q3 is the third quartile;

[0080] Based on the interquartile range calculation results, identify outliers in the data. If the data point is less than Q1-1.5×IQR, it is a lower bound outlier. If the data point is greater than Q3+1.5×IQR, it is an upper bound outlier.

[0081] For missing data, data is filled by mean filling, and the noise in the original data is filtered by sliding window smoothing data;

[0082] Aggregate the data based on spatial location, where the aggregation formula is:

[0083]

[0084] In the formula, u s is the weighted average flow rate of all sensors, w i represents the weight of the i-th sensor, w i represents the i-th data, x i is the value of the ith data point, and N is the total number of data points;

[0085] Through feature extraction, features are extracted from traffic data, including traffic flow, vehicle density, and accident warning.

[0086] Step 3:

[0087] Based on historical data and real-time sensor data, real-time traffic prediction is performed through machine learning models, where the prediction formula is:

[0088] y(t)=w0+w1x1(t)+w2x2(t)+…+w n x n (t)+∈

[0089] Where y(t) is the traffic flow predicted at time t, x1(t)x2(t)x n (t) is the feature at time t, w1w2w n is the weight of the model, ∈ is the error term;

[0090] Predict potential traffic congestion areas based on traffic flow and other related factors, including traffic accidents, weather changes, and events. By analyzing historical data and integrating real-time sensor data, the cloud platform determines which areas are likely to be congested and issues early warnings.

[0091] Combine real-time traffic data, accident data and weather data to conduct traffic risk assessment;

[0092] Integrate road video surveillance streams, sensor data, and vehicle terminal information to identify and assess possible traffic accidents and emergencies, including car accidents and fires, and issue early warnings to the traffic management center and relevant personnel;

[0093] Based on the modal deep learning network, features from different data sources are integrated and input into the deep neural network for joint learning;

[0094] Obtain the latest data from sensors, video surveillance and vehicle terminal data sources in real time, including vehicle behavior, traffic flow and environmental conditions;

[0095] Based on the pre-trained model, the accident risk assessment is performed by inputting the current real-time data. The model calculates the probability of an accident based on the detected behavior patterns and traffic conditions. The probability calculation formula is:

[0096]

[0097] Where P represents the probability of an accident, x1 is the behavior feature, x2 is the traffic feature, x3 is the environment feature, β0 is the bias term, and β1β2β3 is the weight of x1x2x3;

[0098] When the model estimates that the probability of an accident exceeds the preset threshold, the system triggers an early warning and sends an alert to the traffic management center and relevant personnel. The early warning information includes the type of accident, the location of the accident, the severity of the accident, and the timestamp of the accident.

[0099] Based on traffic forecast and risk assessment results, the cloud platform generates traffic optimization strategies. Through real-time traffic forecast, it adjusts the timing of traffic lights, recommends vehicles to detour congested areas, and dispatches public transportation resources.

[0100] The cloud platform pushes the analysis results to the traffic management center and related vehicles in real time through the 5G network, providing real-time road conditions, traffic suggestions and risk warning information;

[0101] In the event of an emergency, including traffic accidents and road failures, the emergency response mechanism is triggered based on the analysis results of the cloud platform to dispatch traffic law enforcement vehicles, direct traffic flow, and adjust signal light timing. Through the collaboration of the 5G network and the central cloud platform, traffic resources are automatically dispatched, intelligent traffic lights are dispatched, traffic flow distribution is adjusted, and emergency vehicles are given priority.

[0102] Step 4:

[0103] Send real-time traffic information and optimization suggestions to the traffic management center and relevant vehicles.

[0104] Step 5:

[0105] In the event of an emergency, the 5G network can trigger a rapid response mechanism and dispatch traffic resources.

[0106] A smart traffic data processing system based on a 5G communication system, comprising:

[0107] Data acquisition module:

[0108] Data acquisition unit: collects information on road vehicle flow, speed and lane occupancy, captures and transmits real-time video data based on surveillance cameras, performs traffic flow monitoring, license plate recognition and accident detection, and provides real-time vehicle location, speed, acceleration and driving behavior data based on vehicle terminals;

[0109] Communication unit: transmits the locally collected data to the central control platform via the 5G network;

[0110] Data storage unit: stores data from sensors and devices.

[0111] Edge computing module:

[0112] Data access unit: receives data, parses data from different devices, and performs protocol conversion;

[0113] Data processing unit: data cleaning, format conversion, missing value supplementation and denoising;

[0114] Data fusion unit: fuses data from different sensors, combines data from video surveillance and vehicle speed sensors, and generates comprehensive information about traffic density and road conditions;

[0115] Real-time analysis and decision-making unit: Based on the collected data on traffic flow, vehicle speed and traffic events, real-time analysis is performed, including traffic density analysis, traffic accident detection, road condition prediction and lane status assessment.

[0116] Central cloud platform:

[0117] Traffic decision and strategy generation unit: Generates corresponding traffic management strategies based on data analysis results, adjusts traffic light duration and switching strategies, optimizes traffic flow, dynamically adjusts lane usage based on traffic conditions, provides real-time route guidance for drivers, avoids congestion and accident-prone areas, and automatically generates control rules and strategies based on model predictions and historical data, and sends them to edge computing nodes for execution;

[0118] Decision support and visualization unit: Provides decision support based on analysis results for traffic managers, including generating reports, charts and graphs to help users understand traffic conditions and make decisions, and providing a real-time traffic flow monitoring panel;

[0119] Traffic information push module: used to push real-time traffic information and optimization suggestions to the traffic management center, related vehicles and other traffic equipment through the 5G communication network;

[0120] Quick response module: used to trigger the dispatch mechanism through the 5G network in emergency situations to ensure timely response measures.

[0121] In summary, the advantages of the present invention are:

[0122] The real-time transmission of data from traffic sensors, surveillance cameras, vehicle terminals and other equipment through the 5G network can achieve full monitoring of traffic conditions. The high bandwidth and low latency characteristics of 5G ensure the real-time nature of traffic information and greatly enhance the system's ability to perceive traffic changes.

[0123] After data preprocessing, cleaning and preliminary analysis at the edge computing nodes, abnormal data is promptly eliminated and important features are extracted, reducing the computing burden of the central cloud platform and achieving rapid response through low-latency network access. This distributed processing architecture ensures that the system can still operate efficiently under conditions of dense traffic and huge data volumes.

[0124] Based on historical data and real-time sensor data, combined with machine learning models, the system can predict traffic flow changes in real time and assess potential traffic risks. For sudden traffic accidents, road failures and other events, the system can issue early warnings and optimize traffic flow through the cloud platform to reduce congestion and accidents.

[0125] Based on the traffic flow prediction and risk assessment of the cloud platform, the traffic management system can adjust the signal light timing, lane usage and traffic route suggestions in real time. This dynamic optimization strategy can effectively reduce traffic congestion, improve road utilization efficiency and improve traffic safety.

[0126] Through the integrated analysis of road video surveillance, sensor data and vehicle terminal information, traffic accidents, abnormal behaviors and emergencies can be accurately identified. Based on the modal fusion and real-time risk assessment model of deep learning technology, the system can automatically assess the probability of accidents and quickly trigger the emergency response mechanism when an early warning occurs.

[0127] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A smart traffic data processing method based on 5G communication system, characterized in that: include: Collect data from traffic sensors, surveillance cameras, vehicle terminals and roadside equipment based on 5G communication networks, and transmit data in real time; Preprocess the collected traffic data through edge computing nodes, including data cleaning, feature extraction and preliminary analysis; The pre-processed data is transmitted to the central cloud platform via the 5G network for in-depth analysis, and real-time traffic flow prediction and risk assessment are carried out based on the cloud platform; Send real-time traffic information and optimization suggestions to the traffic management center and relevant vehicles; In the event of an emergency, the 5G network can trigger a rapid response mechanism and dispatch traffic resources.

2. According to claim 1, a method for processing intelligent traffic data based on a 5G communication system is characterized in that: The data collected from traffic sensors, surveillance cameras, vehicle terminals and roadside equipment based on the 5G communication network and the real-time transmission of data specifically include: Based on the collection of real-time data by traffic sensors and vehicle terminal equipment, traffic sensors obtain real-time information on roads, traffic flow, vehicle status and road conditions, surveillance cameras capture traffic video streams, vehicle terminals transmit real-time dynamic information on vehicle position, speed and direction, and roadside equipment collects environmental and traffic facility data through wireless sensor networks; Use URLLC transmission protocol for real-time data transmission.

3. According to claim 2, a method for processing intelligent traffic data based on a 5G communication system is characterized in that: The preprocessing of the collected traffic data by the edge computing node, including data cleaning, feature extraction and preliminary analysis, specifically includes: Data transmitted through 5G networks, sensors, monitoring equipment, and vehicle terminals are sent to the nearest edge computing node for further processing. The edge node is accessed through the low-latency 5G network. The edge node performs preliminary analysis, cleaning and aggregation of the transmitted data, removes abnormal data, and extracts data features, including traffic flow, accident warnings, and vehicle density; After preliminary analysis at the edge computing node, the data is aggregated and uploaded to the cloud platform for in-depth analysis.

4. According to claim 3, a method for processing intelligent traffic data based on a 5G communication system is characterized in that: The edge node performs preliminary analysis, cleaning and aggregation of the transmitted data, removes abnormal data, and extracts data features, including traffic flow, accident warning and vehicle density. Specifically, it includes: Outliers are identified by calculating the interquartile range of the data, where the formula for the interquartile range is: IQR=Q3-Q1 In the formula, IQR is the interquartile range, Q1 is the first quartile, and Q3 is the third quartile; Based on the interquartile range calculation results, identify outliers in the data. If the data point is less than Q1-1.5×IQR, it is a lower bound outlier. If the data point is greater than Q3+1.5×IQR, it is an upper bound outlier. For missing data, data is filled by mean filling, and the noise in the original data is filtered by sliding window smoothing data; Aggregate the data based on spatial location, where the aggregation formula is: In the formula, u s is the weighted average flow rate of all sensors, w i represents the weight of the i-th sensor, w i represents the i-th data, x i is the value of the ith data point, and N is the total number of data points; Through feature extraction, features are extracted from traffic data, including traffic flow, vehicle density, and accident warning.

5. According to claim 4, a method for processing intelligent traffic data based on a 5G communication system is characterized in that: The pre-processed data is transmitted to the central cloud platform through the 5G network for in-depth analysis, and the real-time prediction and risk assessment of traffic flow based on the cloud platform specifically include: Based on historical data and real-time sensor data, real-time traffic prediction is performed through machine learning models, where the prediction formula is: y(t)=w0+w1x1(t)+w2x2(t)+…+w n x n (t)+∈ Where y(t) is the traffic flow predicted at time t, x1(t)x2(t)x n (t) is the feature at time t, w1w2w n is the weight of the model, ∈ is the error term; Predict potential traffic congestion areas based on traffic flow and other related factors, including traffic accidents, weather changes, and events. By analyzing historical data and integrating real-time sensor data, the cloud platform determines which areas are likely to be congested and issues early warnings. Combine real-time traffic data, accident data and weather data to conduct traffic risk assessment; Integrate road video surveillance streams, sensor data, and vehicle terminal information to identify and assess possible traffic accidents and emergencies, including car accidents and fires, and issue early warnings to the traffic management center and relevant personnel; Based on traffic forecast and risk assessment results, the cloud platform generates traffic optimization strategies. Through real-time traffic forecast, it adjusts the timing of traffic lights, recommends vehicles to detour congested areas, and dispatches public transportation resources. The cloud platform pushes the analysis results to the traffic management center and related vehicles in real time through the 5G network, providing real-time road conditions, traffic suggestions and risk warning information; In the event of an emergency, including traffic accidents and road failures, the emergency response mechanism is triggered based on the analysis results of the cloud platform to dispatch traffic law enforcement vehicles, direct traffic flow, and adjust signal light timing. Through the collaboration of the 5G network and the central cloud platform, traffic resources are automatically dispatched, intelligent traffic lights are dispatched, traffic flow distribution is adjusted, and emergency vehicles are given priority.

6. The method for processing intelligent traffic data based on a 5G communication system according to claim 5, characterized in that: The information fusion of road video surveillance stream, sensor data and vehicle terminal information to identify and evaluate possible traffic accidents and emergencies specifically includes: Based on the modal deep learning network, features from different data sources are integrated and input into the deep neural network for joint learning; Obtain the latest data from sensors, video surveillance and vehicle terminal data sources in real time, including vehicle behavior, traffic flow and environmental conditions; Based on the pre-trained model, the accident risk assessment is performed by inputting the current real-time data. The model calculates the probability of an accident based on the detected behavior patterns and traffic conditions. The probability calculation formula is: Where P represents the probability of an accident, x1 is the behavior feature, x2 is the traffic feature, x3 is the environment feature, β0 is the bias term, and β1β2β3 is the weight of x1x2x3; When the model assesses that the probability of an accident exceeds the preset threshold, the system triggers an early warning and sends an alert to the traffic management center and relevant personnel. The early warning information includes the type of accident, the location of the accident, the severity of the accident and the timestamp of the accident.

7. A smart traffic data processing system based on 5G communication system, characterized in that: include: Data collection module: used to collect data from traffic sensors, surveillance cameras, vehicle terminals and roadside equipment through the 5G communication network; Edge computing module: The edge computing module is electrically connected to the data acquisition module. The edge computing module is used to perform preliminary processing, cleaning and analysis on the collected data, and adjust the traffic lights in real time according to the road conditions and flow information; Central cloud platform: The central cloud platform is electrically connected to the edge computing module. The central cloud platform is used to receive data transmitted from the edge computing node, conduct in-depth analysis and generate traffic flow prediction and optimization strategies; Traffic information push module: The traffic information push module is electrically connected to the central cloud platform, and is used to push real-time traffic information and optimization suggestions to the traffic management center, related vehicles and other traffic equipment through the 5G communication network; Quick response module: The quick response module is electrically connected to the traffic information push module. The quick response module is used to trigger the dispatch mechanism through the 5G network in an emergency to ensure that response measures are taken in a timely manner.

8. The intelligent traffic data processing system based on the 5G communication system according to claim 7 is characterized in that: The data acquisition module specifically includes: Data acquisition unit: collects information on road vehicle flow, speed and lane occupancy, captures and transmits real-time video data based on surveillance cameras, performs traffic flow monitoring, license plate recognition and accident detection, and provides real-time vehicle location, speed, acceleration and driving behavior data based on vehicle terminals; Communication unit: transmits the locally collected data to the central control platform via the 5G network; Data storage unit: stores data from sensors and devices.

9. The intelligent traffic data processing system based on 5G communication system according to claim 8 is characterized in that: The edge computing module specifically includes: Data access unit: receives data, parses data from different devices, and performs protocol conversion; Data processing unit: data cleaning, format conversion, missing value supplementation and denoising; Data fusion unit: fuses data from different sensors, combines data from video surveillance and vehicle speed sensors, and generates comprehensive information about traffic density and road conditions; Real-time analysis and decision-making unit: Based on the collected data on traffic flow, vehicle speed and traffic events, real-time analysis is performed, including traffic density analysis, traffic accident detection, road condition prediction and lane status assessment.

10. The intelligent traffic data processing system based on 5G communication system according to claim 9 is characterized in that: The central cloud platform specifically includes: Traffic decision and strategy generation unit: Generates corresponding traffic management strategies based on data analysis results, adjusts traffic light duration and switching strategies, optimizes traffic flow, dynamically adjusts lane usage based on traffic conditions, provides real-time route guidance for drivers, avoids congestion and accident-prone areas, and automatically generates control rules and strategies based on model predictions and historical data, and sends them to edge computing nodes for execution; Decision Support and Visualization Unit: Provides decision support based on analysis results for traffic managers, including generating reports, charts and graphs to help users understand traffic conditions and make decisions, and providing real-time traffic flow monitoring panels.

Images