Urban traffic intelligent management method based on multi-source data

Abstract

The invention discloses an urban traffic intelligent management method based on multi-source data, and relates to the technical field of traffic data management, and the method comprises the steps: collecting multi-source traffic data, firstly carrying out the preprocessing, then carrying out the matching and integration, and building a unified traffic data warehouse; carrying out batch processing and stream processing on warehouse data by applying a distributed computing framework and a stream processing technology; on the basis of multi-source data, various traffic models are constructed and optimized, and a visual tool is developed to visually display an analysis result; by combining real-time traffic data, a model prediction result and historical data, traffic signals are dynamically adjusted, route planning and navigation services are provided for users, and routes and scheduling of public traffic are optimized; a traffic monitoring center is constructed, and real-time monitoring and timely early warning are carried out based on the traffic signal dynamic adjustment result and the real-time traffic data; establishing an emergency plan; and establishing a data sharing platform, and sharing the related traffic data. The system is used for monitoring, analyzing, managing and applying the traffic data.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic data management, in particular to an intelligent urban traffic management method based on multi-source data. Background Art

[0002] With the rapid advancement of urbanization, the urban population has increased dramatically, the number of motor vehicles has continued to rise, and urban traffic is facing unprecedented challenges. Traditional traffic management methods can no longer meet the increasingly complex traffic needs, which is specifically reflected in the following aspects:

[0003] 1. Traffic congestion is becoming increasingly serious

[0004] The speed of urban road construction is far behind the growth rate of vehicles, and traffic flow is concentrated during peak hours, resulting in road congestion becoming the norm. For example, during the morning and evening peak hours in many large cities, the average speed of vehicles on major roads has dropped significantly, and commuting time has been greatly extended. According to statistics, residents in first-tier cities such as Beijing and Shanghai spend an average of more than 2 hours commuting to and from work every day, which has seriously affected the quality of life of residents and the efficiency of urban operations.

[0005] The timing of traffic lights is often fixed and cannot be adjusted dynamically according to real-time traffic flow. This means that during certain periods of time, the green lights at some intersections are too long, leaving empty lights even when there are few vehicles, while other congested intersections have long waiting times, further exacerbating traffic congestion.

[0006] 2. Frequent traffic accidents

[0007] As traffic volume increases, the incidence of traffic accidents is also on the rise. Traditional traffic management methods are difficult to effectively prevent and quickly handle traffic accidents. For example, on some busy roads, due to the high speed of vehicles and large traffic volume, once a traffic accident occurs, it is easy to trigger a chain reaction and cause a larger range of traffic congestion.

[0008] The early warning and prediction capabilities for traffic accidents are insufficient, and measures cannot be taken in advance to reduce the risk of accidents. At the same time, after the accident, the coordination and response speed between departments is slow, and the deployment of rescue resources is not efficient, which affects the timeliness and effectiveness of accident handling.

[0009] 3. Public transportation is inefficient

[0010] Public transportation routes are not planned rationally, and some routes are duplicated or insufficiently covered, which has reduced the attractiveness of public transportation. Many citizens would rather choose private cars than public transportation, further increasing the pressure on road traffic.

[0011] The dispatch of public transportation vehicles is not flexible enough and cannot be adjusted dynamically according to real-time passenger flow. During peak hours, vehicles are crowded and passengers have to wait for a long time; while during off-peak hours, the vehicle idling rate is high, resulting in a waste of resources.

[0012] 4. Traffic data is fragmented and underutilized

[0013] Urban traffic data comes from a wide range of sources, including traffic management departments, bus companies, taxi companies, private car owners, etc., but these data are often scattered among various departments and institutions, lacking an effective integration and sharing mechanism. The data formats and standards of different departments are inconsistent, making it difficult to conduct unified analysis and processing.

[0014] Traditional traffic management methods mainly use traffic data at the level of simple statistics and reports, and are unable to deeply explore the laws and values ​​behind the data. For example, it is impossible to predict the changing trend of traffic flow through the analysis of traffic data and take measures to alleviate traffic congestion in advance.

[0015] 5. Lack of cross-departmental coordination mechanism

[0016] Urban traffic management involves multiple departments, such as traffic management, urban planning, and emergency management, but there is a lack of effective coordination mechanisms among departments. When formulating traffic policies and plans, they often act independently and lack overall consideration, resulting in contradictions or incoordination between policies.

[0017] When responding to emergencies, information communication between departments is not smooth, resource allocation is not timely, and effective synergy cannot be formed. For example, when encountering severe weather or major events, the cooperation between the traffic management department, emergency management department and public transportation department is not close enough, resulting in chaotic traffic order and serious impact on citizens' travel.

[0018] With the rapid development of information technology, the application of technologies such as big data, artificial intelligence, and the Internet of Things in the field of transportation has gradually become the key to solving urban traffic problems. By collecting and integrating multi-source traffic data and using advanced data analysis and processing technologies, we can achieve intelligent management of urban traffic, improve the efficiency and scientificity of traffic management, alleviate traffic congestion, reduce traffic accidents, improve the quality of public transportation services, and provide strong support for the sustainable development of cities. Summary of the invention

[0019] In view of the needs and shortcomings of current technological development, the present invention provides an urban traffic intelligent management method based on multi-source data.

[0020] The present invention provides an intelligent urban traffic management method based on multi-source data, and the technical solution adopted to solve the above technical problems is as follows:

[0021] An urban traffic intelligent management method based on multi-source data comprises the following steps:

[0022] S1. Collect multi-source traffic data, pre-process the collected data, and then use data fusion technology to match and integrate them to establish a unified traffic data warehouse;

[0023] S2. Use distributed computing frameworks and stream processing technologies to perform batch and stream processing on the massive traffic data in the traffic data warehouse; build and optimize various traffic models based on multi-source data with the help of machine learning and deep learning algorithms, and develop visualization tools to display the analysis results in a variety of intuitive and dynamic forms to assist in traffic management decision-making;

[0024] S3. Combine real-time traffic data, traffic model prediction results and historical data to dynamically adjust traffic signals, provide users with route planning and navigation services, and optimize public transportation routes and scheduling;

[0025] S4. Build a traffic monitoring center that integrates multi-source data, conduct real-time monitoring based on the dynamic adjustment results of traffic signals in step S3 and real-time traffic data, and issue timely warnings; at the same time, establish and improve emergency response plans that clarify processes and division of responsibilities, and use the intelligent dispatching system to coordinate various departments to quickly respond to abnormal events and restore traffic order;

[0026] S5. Establish an open data sharing platform and formulate unified interface standards to share the real-time traffic data, emergency plans and the aforementioned traffic data in step S4, and promote data sharing and collaboration among multiple departments.

[0027] Optionally, the step S1 involved specifically includes:

[0028] S1.1. Multi-source data collection:

[0029] Deploy monitoring equipment at key traffic nodes in the city, including traffic cameras, license plate recognition systems, traffic flow detectors, road detectors and environmental monitoring sensors to collect at least one type of traffic data, including vehicle flow, speed, density, license plate information, weather conditions and road status, in real time;

[0030] Install GPS devices on public transport vehicles and private cars to collect traffic data such as the real-time location, speed, driving route, number of stops and parking time of the vehicles;

[0031] Let citizens install and use traffic management mobile applications, which use the built-in GPS module and sensor module of the mobile phone to collect user travel information, obtain user real-time location information and traffic incident reports submitted by users through the application;

[0032] Cooperate with social media platforms to obtain traffic-related information posted by users on social media platforms, including traffic incidents, road conditions and weather information, and use natural language processing technology to analyze and mine text content to extract useful traffic data;

[0033] Collaborate with the transportation department to collect the real-time status, timing plan and signal adjustment records of traffic lights through the traffic signal control system, and upload them to the data processing center in real time by the signal controller;

[0034] S1.2, Multi-source data transmission and integration:

[0035] Using wireless communication technology, the collected multi-source data is transmitted to the data processing center in real time;

[0036] The data processing center is equipped with a preprocessing module to perform data cleaning, deduplication, formatting and standardization on the received data. Data cleaning includes processing missing values, outliers and erroneous data, data deduplication ensures that there are no duplicate records, and formatting and standardization convert data from different sources into a unified format.

[0037] The data processing center is equipped with a data fusion module. Based on time, space and content, the data fusion module uses data fusion technology to match and integrate data from different data sources, establish a unified traffic data warehouse, ensure the connection and consistency between different data sources, and form a comprehensive traffic data view.

[0038] Optionally, step S2 is performed to perform batch processing and stream processing on the massive traffic data in the traffic data warehouse using a distributed computing framework and stream processing technology. This process specifically includes:

[0039] Using the distributed computing framework of Hadoop and Spark, batch processing and stream processing tasks are performed on massive traffic data. Batch processing operations analyze traffic data according to preset cycles and generate corresponding reports to provide periodic summaries and analysis for traffic management. Stream processing operations monitor and respond to real-time traffic data in real time.

[0040] Apache Flink and Kafka Streams stream processing technologies are used to quickly process and analyze real-time traffic data.

[0041] Further optionally, step S2 is performed to construct and optimize various traffic models based on multi-source data using machine learning and deep learning algorithms. This process specifically includes:

[0042] Based on historical traffic data and real-time traffic data, machine learning algorithms and deep learning algorithms are used to build traffic flow prediction models, congestion detection models and accident prediction models. The machine learning algorithms involve time series analysis algorithms, regression analysis algorithms, and classification algorithms. The deep learning algorithms involve neural networks, convolutional neural networks, and recurrent neural networks.

[0043] The constructed traffic flow prediction model, congestion detection model and accident prediction model are trained through training data. The training data includes accumulated historical traffic data and real-time traffic data, as well as corresponding weather conditions, holiday arrangements and major event information. At the same time, cross-validation and hyperparameter optimization techniques are used to continuously optimize the traffic flow prediction model, congestion detection model and accident prediction model.

[0044] Machine learning algorithms such as isolation forest, support vector machine, and anomaly detection neural network are used to detect anomalies in traffic data and issue warnings and responses in a timely manner.

[0045] Further optionally, step S2 is performed to develop a visualization tool to intuitively and dynamically display the analysis results in various forms to assist in traffic management decision-making. This process specifically includes:

[0046] Develop data visualization tools that support multiple data display formats such as line charts, bar charts, pie charts, heat maps, and geographic information system maps;

[0047] Use data visualization tools to intuitively display the processed and analyzed traffic data results in at least one form of charts, maps and dashboards, realize the dynamic display function of traffic data, and generate real-time traffic flow maps, congestion maps, accident heat maps and traffic light status maps.

[0048] Optionally, the step S3 involved specifically includes:

[0049] S3.1 Traffic signal optimization:

[0050] Through the induction control technology of the dynamic signal control system, the arrival of vehicles at the intersection can be sensed in real time. Through the time period control algorithm of the dynamic signal control system, different signal light timing schemes can be set according to the traffic flow characteristics of different time periods. Through the timing optimization algorithm of the dynamic signal control system, the duration of the signal light can be accurately calculated and adjusted.

[0051] Introducing artificial intelligence algorithms of reinforcement learning and fuzzy logic control into dynamic signal control systems. The reinforcement learning algorithm allows the dynamic signal control system to learn the best signal timing strategy in a continuous trial and error process to adapt to the dynamic changes in traffic flow. Fuzzy logic control is based on fuzzy traffic flow and road condition information. It uses fuzzy reasoning and decision rules to adjust the signal timing plan in real time, so that traffic lights can adapt to different traffic conditions and needs more intelligently.

[0052] S3.2, Path Planning and Navigation:

[0053] Based on real-time traffic information and historical data, the system comprehensively considers distance, time, congestion and road grade, and uses path planning algorithms to provide optimal path planning and navigation services;

[0054] Based on the user's travel habits, preferences and real-time traffic conditions, collaborative filtering algorithms, content recommendation algorithms and hybrid recommendation algorithms are used to provide personalized route recommendations and traffic information;

[0055] S3.3. Public transportation optimization:

[0056] In-depth analysis of public transportation operation data, and optimization of bus routes and schedules through route optimization algorithms based on shortest path, linear programming, and network flow optimization;

[0057] The intelligent dispatching system combines public transportation vehicle location information obtained through real-time monitoring, passenger demand predicted through data analysis, and real-time vehicle operation status information to make real-time adjustments to the dispatching and operation plans of public transportation vehicles.

[0058] Optionally, the step S4 involved specifically includes:

[0059] S4.1. Build a traffic monitoring center:

[0060] Establish a traffic monitoring center, which includes a data monitoring module and a video analysis module. The data monitoring module monitors the city's traffic conditions in real time through the traffic data in the traffic data warehouse, and the video analysis module processes the real-time video, detects abnormal conditions and issues timely warnings;

[0061] S4.2. Establish and improve emergency response mechanism:

[0062] Develop detailed emergency plans, clarify the emergency response process and the division of responsibilities of each department when facing traffic accidents and natural disasters, and respond quickly to abnormal events;

[0063] When the traffic monitoring center discovers an abnormal situation and issues a timely warning, the intelligent dispatching system automatically generates an emergency dispatching plan based on real-time traffic data and the established emergency plan. Subsequently, the intelligent dispatching system executes the emergency dispatching plan and coordinates relevant departments to carry out emergency response and traffic diversion work.

[0064] Preferably, the emergency plan involves multiple links including event detection, information release, resource dispatch and on-site command, among which:

[0065] The event detection phase detects emergencies in a timely manner through monitoring systems and various sensors;

[0066] The information release phase ensures that event information is conveyed quickly and accurately to relevant departments and the public;

[0067] The resource dispatching link is responsible for deploying rescue vehicles and personnel;

[0068] The on-site command link provides unified command for on-site rescue and traffic diversion work, and all links work closely together to ensure the timeliness and effectiveness of the emergency response.

[0069] Optionally, the step S5 involved specifically includes:

[0070] S5.1. Data Sharing:

[0071] Establish an open data sharing platform with standardized API interfaces, support multiple data formats, and be compatible with different access methods;

[0072] Develop a unified set of data interface standards, including data format, data protocol and data interface documentation, to ensure the compatibility and ease of use of data sharing;

[0073] S5.2. Cross-departmental collaboration:

[0074] Actively promote data sharing and collaboration among multiple relevant departments such as transportation management departments, urban planning departments, and emergency management departments.

[0075] Build a multi-department collaboration platform with data sharing function, so that departments can exchange traffic-related data in real time; the collaboration platform also supports information exchange, facilitating communication and coordination among personnel of various departments; the collaboration platform also has joint decision-making function, providing a platform for various departments to jointly discuss traffic management strategies, thereby comprehensively improving the city's comprehensive management capabilities.

[0076] Through cross-departmental collaboration, the joint decision-making system uses integrated multi-source data and analysis results displayed by visualization tools to conduct a comprehensive assessment of traffic conditions, urban development needs and emergency response needs, providing scientific decision-making support for various departments.

[0077] Optionally, the urban traffic intelligent management method involved also includes:

[0078] In the process of executing steps S1-S5, data encryption technology is used to encrypt sensitive data, an access control mechanism is established to ensure data security, anonymization is used and laws and regulations are followed to ensure privacy protection.

[0079] Compared with the prior art, the urban traffic intelligent management method based on multi-source data of the present invention has the following beneficial effects:

[0080] 1. The present invention utilizes multi-source data to monitor and analyze traffic flow in real time, which can optimize traffic signal control, reduce traffic congestion, and improve road capacity and traffic efficiency. By analyzing traffic accident data, dangerous sections and accident-prone areas can be identified, and targeted traffic safety management measures can be implemented to reduce the accident rate and improve the level of traffic safety. By analyzing public transportation operation data, bus routes and schedules can be optimized to improve the quality of public transportation services and operational efficiency. In addition, personalized travel plans and real-time traffic information can be provided to citizens to enhance travel experience and reduce travel time and cost.

[0081] 2. The present invention reduces vehicle waiting time and congestion at intersections by real-time monitoring and adjusting the timing of traffic lights, thereby improving the smoothness of traffic flow. Through intelligent route planning, it provides optimal route recommendations for drivers and public transportation vehicles, avoids congested sections, disperses traffic pressure, and improves overall traffic fluidity. It uses big data and machine learning algorithms to accurately predict traffic flow trends, take optimization measures in advance, and improve road traffic efficiency. Through reasonable scheduling and route optimization, it improves the operating efficiency of public transportation vehicles such as buses and subways, and reduces passenger waiting time and travel time.

[0082] 3. Based on historical data and real-time data, the present invention analyzes high-incidence sections and time periods of traffic accidents, issues early warnings, and takes preventive measures; identifies potential dangerous driving behaviors, provides warnings and guidance through analysis of data such as vehicle speed, braking frequency, and driving trajectory; monitors road conditions in real time through video monitoring and sensor module data, quickly discovers traffic accidents, and promptly notifies relevant departments; uses an intelligent dispatching system to quickly coordinate relevant departments to arrive at the scene of the accident, conduct emergency treatment and traffic diversion, and reduce the impact of accidents on traffic flow;

[0083] 4. The present invention reduces air pollution by reducing traffic congestion and increasing vehicle speed, reducing vehicle idling time and exhaust emissions; by optimizing the public transportation system, citizens are encouraged to choose low-emission transportation tools such as buses and subways, reducing the frequency of private car use and reducing urban carbon emissions; by optimizing traffic flow and reducing congestion, travel time is shortened, work and life efficiency is improved, and time waste caused by traffic congestion is reduced; by reducing idling time and improving driving efficiency, vehicle fuel consumption is reduced and travel costs are saved; through intelligent path planning and real-time traffic information, logistics transportation routes are optimized, delivery time is reduced, and logistics efficiency is improved;

[0084] 5. The present invention helps citizens choose the best travel mode and improves travel experience by providing real-time traffic information and intelligent route planning; improves service quality and punctuality by optimizing the public transportation system and enhances citizens' satisfaction with public transportation; reduces the occurrence of traffic accidents and improves citizens' sense of travel safety through accident prevention and rapid response measures; and quickly handles traffic accidents and emergencies by establishing a complete emergency response mechanism, thereby enhancing citizens' sense of security and trust. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Attached Figure 1 It is a flow chart of the method of embodiment 1 of the present invention. DETAILED DESCRIPTION

[0086] In order to make the technical solution, the technical problem solved and the technical effect of the present invention more clearly understood, the technical solution of the present invention is clearly and completely described below in conjunction with specific embodiments.

[0087] Embodiment 1:

[0088] Combined with Figure 1 This embodiment proposes an intelligent urban traffic management method based on multi-source data, which includes the following steps:

[0089] S1. Collect multi-source traffic data, pre-process the collected data, and then use data fusion technology to match and integrate them to establish a unified traffic data warehouse, including:

[0090] S1.1. Multi-source data collection:

[0091] a) Deploy monitoring equipment at key traffic nodes in the city, such as major intersections, roundabouts, entrances and exits of main roads, including traffic cameras, license plate recognition systems, traffic flow detectors, road detectors and environmental monitoring sensors, to collect at least one type of traffic data in real time, including vehicle flow, speed, density, license plate information, weather conditions and road status;

[0092] b) Install GPS devices on public transportation vehicles (such as buses and taxis) and private cars to collect traffic data such as the real-time location, speed, driving route, number of stops and parking time of the vehicles through the GPS devices; the collection scope covers most public transportation routes in the city and private cars on some main roads;

[0093] c) Encourage citizens to install and use traffic management mobile applications, which use the built-in GPS module and accelerometer, gyroscope and other sensor modules in the mobile phone to collect users' travel information, such as departure point, destination, travel time, travel mode, etc., and obtain users' real-time location information and traffic incident reports submitted by users through the application, such as traffic accidents, road construction, road waterlogging, etc. The data collection scope of the application covers all areas of the city, making it convenient for citizens to feedback traffic information at any time;

[0094] d) Cooperate with social media platforms to obtain traffic-related information posted by users on social media platforms through web crawler technology, including traffic incidents, road conditions and weather information, and use natural language processing technology, such as lexical analysis, syntactic analysis, semantic analysis and other methods, to analyze and mine the text content of social media platforms and extract useful traffic data, such as traffic congestion locations, congestion levels, accident time and location, etc.;

[0095] e) Collaborate with the transportation department to collect the real-time status of traffic lights (red light, green light, yellow light), timing plan (duration setting of each phase of traffic lights) and traffic light adjustment records (time, reason and content of each adjustment) through the traffic signal control system; the signal controller uploads this data to the data processing center in real time through wired or wireless communication, providing key data for subsequent analysis of traffic light operation effects and optimization needs.

[0096] S1.2, Multi-source data transmission and integration:

[0097] Using 4G or 5G wireless communication technology, the collected multi-source data is transmitted to the data processing center in real time;

[0098] The data processing center is equipped with a preprocessing module, which uses tools such as Python's Pandas library to perform data cleaning, deduplication, formatting and standardization on the received data. For missing values, the mean filling method, K nearest neighbor algorithm and other methods are used for processing; for outliers, statistical methods (such as the 3σ principle) or machine learning algorithms (such as the isolation forest algorithm) are used for identification and correction; erroneous data are carefully checked and corrected to ensure data accuracy; data deduplication operations use hash algorithms and other technologies to ensure that there are no duplicate records in the data set; formatting and standardization processes convert data from different sources into a unified format, such as unifying the time format to the ISO 8601 standard, unifying the numerical unit (such as the speed unit to kilometers per hour), etc., to facilitate subsequent data fusion and analysis processing;

[0099] The data processing center is equipped with a data fusion module. According to time, space and content, the data fusion module adopts data fusion technology based on feature level and decision level to match and integrate data from different data sources, among which: data fusion based on feature level means fusing the features of different data sources after feature extraction of original data, such as associating and matching the vehicle features extracted by traffic cameras with the license plate features extracted by license plate recognition system; data fusion based on decision level means fusing the decision results after each data source makes independent decisions, such as combining the judgment results of traffic congestion by traffic flow detectors and traffic cameras to obtain a more accurate traffic congestion situation; through the aforementioned data fusion technology, a unified traffic data warehouse is established to ensure the association and consistency between different data sources, form a comprehensive traffic data view, and provide a high-quality data foundation for subsequent traffic analysis and decision-making.

[0100] S2. Use distributed computing frameworks and stream processing technologies to perform batch and stream processing on the massive traffic data in the traffic data warehouse; build and optimize various traffic models based on multi-source data with the help of machine learning and deep learning algorithms, and develop visualization tools to display the analysis results in a variety of intuitive and dynamic forms to assist in traffic management decision-making, including:

[0101] S2.1. Using the distributed computing framework of Hadoop and Spark, batch processing and stream processing tasks are performed on massive traffic data. Batch processing operations analyze traffic data according to preset cycles and generate corresponding reports to provide periodic summaries and analyses for traffic management. Stream processing operations monitor and respond to real-time traffic data in real time.

[0102] Apache Flink and Kafka Streams stream processing technologies are used to quickly process and analyze real-time traffic data. Kafka Streams, as a real-time data transmission pipeline, quickly transmits real-time collected traffic data to Flink. Flink has powerful stream processing capabilities and can perform complex analysis and calculations on these real-time data, such as real-time monitoring of traffic flow trends and timely issuance of warnings when traffic exceeds the set threshold.

[0103] S2.2. Based on historical traffic data and real-time traffic data, machine learning algorithms and deep learning algorithms are used to build traffic flow prediction models, congestion detection models and accident prediction models. The machine learning algorithms involve time series analysis algorithms, regression analysis algorithms, and classification algorithms. The deep learning algorithms involve neural networks, convolutional neural networks, and recurrent neural networks. For example, for traffic flow data with obvious time series characteristics, a time series analysis algorithm (such as an ARIMA model) is used for prediction. For congestion detection, a classification algorithm (such as a decision tree, random forest, etc.) is used to classify the road section status into congested or non-congested according to characteristics such as traffic flow and vehicle speed.

[0104] The constructed traffic flow prediction model, congestion detection model and accident prediction model are trained through training data. The training data is traffic data that has undergone preprocessing operations (including normalization, feature engineering, etc.), including accumulated historical traffic data and real-time traffic data, as well as corresponding weather conditions, holiday arrangements and major event information; at the same time, cross-validation and hyperparameter optimization techniques are used to continuously optimize the traffic flow prediction model, congestion detection model and accident prediction model;

[0105] Machine learning algorithms such as isolation forest, support vector machine and anomaly detection neural network are used to detect anomalies in traffic data and issue warnings and responses in a timely manner. Among them: the isolation forest algorithm evaluates the "degree of isolation" of data points by constructing a tree structure, and identifies abnormal situations such as sudden extremely high or extremely low traffic flow data; the support vector machine distinguishes between normal and abnormal data by finding the optimal classification hyperplane; the anomaly detection neural network learns the characteristic pattern of normal data and determines it as abnormal when the data deviates from the pattern.

[0106] S2.3. Develop data visualization tools. The data visualization tools support multiple data display forms such as line graphs, bar graphs, pie charts, heat maps and geographic information system maps. Among them: line graphs are used to show the trend of traffic flow over time; bar graphs are suitable for comparing traffic data of different sections or time periods; pie charts can be used to show the proportion of traffic data; heat maps intuitively show the distribution of urban traffic congestion; geographic information system maps combine traffic data with geographic location to facilitate viewing of traffic conditions in different areas;

[0107] Use data visualization tools to intuitively display the processed and analyzed traffic data results in at least one of the forms of charts, maps and dashboards, realize the dynamic display function of traffic data, and generate real-time traffic flow diagrams, congestion maps, accident heat maps and signal light status diagrams; among them: real-time traffic flow diagrams help traffic management personnel understand the traffic flow conditions of each section of the road in real time, and promptly discover sections with abnormal traffic flow; congestion maps intuitively display the scope and severity of congested areas in the city, providing a decision-making basis for traffic diversion; accident heat maps analyze the characteristics of accident-prone areas so as to take targeted safety measures; signal light status maps monitor the working status of signal lights in real time to ensure their normal operation.

[0108] These visual displays provide intuitive and accurate data support for traffic management decisions.

[0109] S3. Combine real-time traffic data, traffic model prediction results and historical data to dynamically adjust traffic signals, provide users with route planning and navigation services, and optimize public transportation routes and scheduling, including:

[0110] S3.1 Traffic signal optimization:

[0111] Through the induction control technology of the dynamic signal control system (such as geomagnetic sensors, video detectors and other equipment), the arrival of vehicles at the intersection is sensed in real time. Through the time period control algorithm of the dynamic signal control system, different signal light timing schemes are set according to the traffic flow characteristics of different time periods. Through the timing optimization algorithm of the dynamic signal control system (such as Webster algorithm, TRANSYT algorithm, etc.), the duration of the signal light is accurately calculated and adjusted.

[0112] Artificial intelligence algorithms of reinforcement learning and fuzzy logic control are introduced into dynamic signal control systems. The reinforcement learning algorithm allows the dynamic signal control system to learn the best signal timing strategy in a continuous trial and error process to adapt to the dynamic changes in traffic flow. Fuzzy logic control is based on fuzzy traffic flow and road condition information. It uses fuzzy reasoning and decision-making rules to adjust the signal timing plan in real time, so that traffic lights can adapt to different traffic conditions and needs more intelligently.

[0113] S3.2, Path Planning and Navigation:

[0114] Based on real-time traffic information and historical data, the system comprehensively considers distance, time, congestion and road grade, and uses path planning algorithms such as Dijkstra algorithm and A* algorithm to provide optimal path planning and navigation services. Among them: Dijkstra algorithm finds the optimal path by calculating the shortest distance from the starting point to each node; A* algorithm uses heuristic functions to estimate the distance to the target point while considering the distance, so it can find the optimal path faster.

[0115] Based on users' travel habits, preferences and real-time traffic conditions, collaborative filtering algorithms, content recommendation algorithms and hybrid recommendation algorithms are used to provide personalized route recommendations and traffic information.

[0116] S3.3. Public transportation optimization:

[0117] In-depth analysis of public transportation operation data, and optimization of bus routes and schedules through route optimization algorithms based on shortest path, linear programming, and network flow optimization;

[0118] The intelligent dispatching system combines public transportation vehicle location information obtained through real-time monitoring, passenger demand predicted through data analysis, and real-time vehicle operation status information to make real-time adjustments to the dispatching and operation plans of public transportation vehicles.

[0119] It should be added that the intelligent dispatching system architecture usually includes a data collection layer, a data processing layer, and a decision-making layer. The data collection layer obtains the location information of public transportation vehicles in real time through the on-board GPS device, predicts passenger demand through bus card swiping data and mobile application data, and collects real-time vehicle operation status information, such as vehicle failure, full load, etc. The data processing layer analyzes and processes the collected data, for example, predicting the passenger flow change trend in different time periods and different sections through data analysis. The decision-making layer makes real-time dispatching decisions based on the data processing results. When a vehicle on a certain line fails, the operation plan of other vehicles is adjusted in time to provide support; when the passenger demand in a certain area suddenly increases, the departure frequency of the area is temporarily increased to ensure the efficiency and stability of public transportation services.

[0120] S4. Build a traffic monitoring center that integrates multi-source data, conduct real-time monitoring based on the dynamic adjustment results of traffic signals in step S3 and real-time traffic data, and issue timely warnings; at the same time, establish and improve emergency response plans with clear processes and division of responsibilities, and use the intelligent dispatching system to coordinate various departments to quickly respond to abnormal events and restore traffic order, including:

[0121] S4.1. Build a traffic monitoring center:

[0122] Establish a traffic monitoring center, which includes a data monitoring module and a video analysis module. The data monitoring module monitors the city's traffic conditions in real time through the traffic data warehouse, and processes the real-time video through the video analysis module to detect abnormal situations and issue timely warnings; among them: the video analysis module ① has a vehicle identification function, which can accurately identify the type of vehicle, license plate number and other information; ② can perform traffic flow statistics and calculate the number of vehicles passing through a certain section of road in real time; ③ can monitor illegal behaviors, such as running red lights, speeding, illegal lane changes, etc. Through the analysis of this information by the video analysis module, abnormal situations can be discovered in a timely manner, such as abnormal vehicle driving trajectories, sudden and large fluctuations in traffic flow, etc., which may indicate the occurrence of traffic accidents or road congestion;

[0123] There can be many types of warnings, such as: through system pop-ups, text message notifications, etc., detailed information of abnormal situations (such as the location of the incident, type of incident, possible scope of impact, etc.) can be promptly conveyed to traffic management departments, emergency management departments, etc., so that they can respond quickly; at the same time, warning information is issued to drivers on surrounding roads through traffic broadcasts, reminding them to plan routes in advance and avoid areas where problems may occur; warnings can also be pushed to nearby vehicles through the on-board navigation system to guide drivers to detour.

[0124] S4.2. Establish and improve emergency response mechanism:

[0125] Formulate a detailed emergency plan, clarify the emergency response process and the division of responsibilities of each department when facing traffic accidents and natural disasters, and respond quickly to abnormal events; the emergency plan covers multiple links such as event detection, information release, resource dispatch and on-site command, among which: the event detection link uses the monitoring system and various sensors to timely detect emergencies; the information release link ensures that the event information is quickly and accurately conveyed to relevant departments and the public; the resource dispatch link is responsible for the deployment of rescue vehicles and personnel; the on-site command link conducts unified command of on-site rescue and traffic diversion work, and all links work closely together to ensure the timeliness and effectiveness of emergency response;

[0126] When the traffic monitoring center discovers an abnormal situation and issues a timely warning, the intelligent dispatching system automatically generates an emergency dispatching plan based on real-time traffic data and the established emergency plan. Subsequently, the intelligent dispatching system executes the emergency dispatching plan and coordinates relevant departments to carry out emergency response and traffic diversion work.

[0127] S5. Establish an open data sharing platform and formulate a unified interface standard to share the real-time traffic data, emergency plans and the aforementioned traffic data in step S4, and promote data sharing and collaboration among multiple departments, including:

[0128] S5.1. Data Sharing:

[0129] Establish an open data sharing platform equipped with standardized API interfaces, supporting multiple data formats and compatible with different access methods; data formats such as JSON (lightweight, easy to parse and generate, suitable for data exchange and storage), XML (good structure and extensibility, often used for data transmission and configuration files), CSV (a simple text format, convenient for data import and export), etc., access methods such as HTTP (Hypertext Transfer Protocol, used to transfer data between web browsers and servers), HTTPS (HTTP protocol based on SSL / TLS encryption, providing more secure data transmission), RESTful API (an API design that follows the REST architecture style, with the advantages of simplicity and easy extensibility, suitable for various web applications and mobile applications), etc., to meet the needs of different application scenarios and technical architectures;

[0130] Develop a set of unified data interface standards, including data format, data protocol and data interface documents, to ensure the compatibility and ease of use of data sharing; for example, the date format should uniformly adopt ISO8601 standard (such as "YYYY-MM-DDHH:MM:SS") to ensure the consistency of date representation; for numerical types, clearly specify the accuracy and range, such as the speed data is accurate to one decimal place, and the value range conforms to the actual traffic conditions; in terms of data protocol standards, use SSL / TLS encryption protocol to ensure the confidentiality and integrity of data during transmission and prevent data from being stolen or tampered with; the data interface document should contain detailed information about the interface. Function description, parameter description, request example, response example, etc. For example, for an interface for obtaining real-time traffic flow on a certain road section, the document should clearly state that the function of the interface is to return the current vehicle flow data of the specified road section, and the parameters include the road section ID, etc. At the same time, a request example (such as "GET / traffic-flow?roadId=123") and a response example (such as "{"roadId":123,"trafficFlow":500,"timestamp":"2024-10-0110:00:00"}") should be provided to facilitate developers to quickly understand and use the interface;

[0131] S5.2. Cross-departmental collaboration:

[0132] Actively promote data sharing and collaboration among multiple relevant departments such as transportation management departments, urban planning departments, and emergency management departments.

[0133] Build a multi-department collaboration platform with data sharing function, so that departments can exchange traffic-related data in real time; the collaboration platform also supports a variety of information exchange methods, which is convenient for personnel from various departments to communicate and coordinate; the collaboration platform also has a joint decision-making function, providing a platform for various departments to discuss traffic management strategies together, thereby comprehensively improving the city's comprehensive management capabilities. For example, when formulating urban traffic plans, the collaboration platform can comprehensively consider factors such as traffic flow forecast data, urban land use planning, and population distribution. Through data analysis and simulation, it provides evaluations and suggestions for different planning schemes to various departments, helping them make scientific decisions. When responding to major traffic incidents, such as large-scale events or natural disasters, the collaboration platform can quickly generate emergency response plans based on real-time traffic data, emergency plans and other information, and coordinate the actions of various departments. For example, during the construction of a new subway line in a certain city, the traffic management department, urban planning department and emergency management department shared data and information through a collaborative platform; the traffic management department provided real-time traffic flow data and traffic control plan recommendations; the urban planning department provided subway line planning and surrounding land use planning information; the emergency management department provided emergency plans and safety measures; through joint discussion and collaboration, detailed traffic diversion plans and emergency plans were formulated, which effectively reduced the impact on traffic during construction and improved the safety and efficiency of engineering construction; by comparing the changes in traffic congestion index before and after collaboration, the reduction in traffic accident rates and other indicators, the effectiveness of cross-departmental collaboration was quantitatively evaluated, providing a basis for further optimizing the collaboration mechanism;

[0134] Through cross-departmental collaboration, the joint decision-making system uses integrated multi-source data and analysis results displayed by visualization tools to conduct a comprehensive assessment of traffic conditions, urban development needs and emergency response needs, providing scientific decision-making support for various departments.

[0135] The joint decision-making system is an existing system used in the field of urban traffic management and integrated urban management. It mainly completes the following tasks: ① Collect and integrate real-time traffic data, emergency plan data and other relevant traffic data to break down data barriers and form a comprehensive and unified data set to provide a basis for subsequent analysis and decision-making; ② Use visualization tools to display these analysis results in intuitive charts, maps, etc., so that decision makers can understand and grasp the overall traffic conditions; ③ Based on the data analysis results, conduct a comprehensive assessment of the current traffic conditions, including road congestion, traffic smoothness, public transportation efficiency, etc., accurately judge the operating status of the transportation system, and identify existing problems and potential risks; Combined with the urban development plan and related data provided by the urban planning department, evaluate the degree of match between the current transportation system and urban development needs, analyze whether the transportation infrastructure can meet the needs of future urban development, and provide information for transportation planning and urban construction. ④ Provide a reference for the design; evaluate the emergency response capability of the transportation system in abnormal events or emergencies based on emergency plan data and real-time traffic data, such as the impact of road closures on traffic, the efficiency of rescue vehicles, the rationality of evacuation routes, etc., to provide a basis for optimizing emergency plans and improving emergency response capabilities; ④ Based on the evaluation results, provide a scientific and comprehensive decision-making basis for multiple departments such as transportation management departments, urban planning departments, and emergency management departments, and help various departments understand the current status and development trends of the transportation system, as well as the possible impacts of different decisions; through the joint decision-making function, provide a platform support for multiple departments to jointly discuss traffic management strategies, promote information sharing and collaborative work among departments, enable departments to communicate, coordinate and make decisions on a unified platform, and formulate more reasonable and effective traffic management measures, such as traffic congestion relief plans, transportation facility construction plans, emergency traffic control plans, etc., to improve the comprehensive management capabilities of the city.

[0136] It should be added that in the process of executing steps S1-S5, data encryption technology is used to encrypt sensitive data, an access control mechanism is established to ensure data security, anonymization is used and privacy protection is ensured in compliance with laws and regulations.

[0137] In summary, the use of an intelligent urban traffic management method based on multi-source data according to the present invention can improve traffic flow management efficiency, improve urban traffic safety, achieve accurate traffic forecasting and early warning, optimize public transportation systems, support personalized travel services, promote urban traffic planning and construction, and meet social development needs.

[0138] The above specific examples are used to explain the principles and implementation methods of the present invention in detail. These examples are only used to help understand the core technical content of the present invention. Based on the above specific embodiments of the present invention, any improvements and modifications made by technicians in this technical field without departing from the principles of the present invention should fall within the scope of patent protection of the present invention.

Claims

1. An intelligent urban traffic management method based on multi-source data, characterized in that: The steps include: S1. Collect multi-source traffic data, pre-process the collected data, and then use data fusion technology to match and integrate them to establish a unified traffic data warehouse; S2. Use distributed computing frameworks and stream processing technologies to perform batch and stream processing on the massive traffic data in the traffic data warehouse; build and optimize various traffic models based on multi-source data with the help of machine learning and deep learning algorithms, and develop visualization tools to display the analysis results in a variety of intuitive and dynamic forms to assist in traffic management decision-making; S3. Combine real-time traffic data, traffic model prediction results and historical data to dynamically adjust traffic signals, provide users with route planning and navigation services, and optimize public transportation routes and scheduling; S4. Build a traffic monitoring center that integrates multi-source data, conduct real-time monitoring and timely warning based on the dynamic adjustment results of traffic signals in step S3 and real-time traffic data; at the same time, establish and improve emergency response plans with clear processes and division of responsibilities, and use the intelligent dispatching system to coordinate various departments to quickly respond to abnormal events and restore traffic order; S5. Establish an open data sharing platform and formulate unified interface standards to share the real-time traffic data, emergency plans and the aforementioned traffic data in step S4, and promote data sharing and collaboration among multiple departments.

2. The method for intelligent urban traffic management based on multi-source data according to claim 1 is characterized in that: The step S1 specifically includes: S1.

1. Multi-source data collection: Deploy monitoring equipment at key traffic nodes in the city, including traffic cameras, license plate recognition systems, traffic flow detectors, road detectors and environmental monitoring sensors to collect at least one type of traffic data, including vehicle flow, speed, density, license plate information, weather conditions and road status, in real time; Install GPS devices on public transport vehicles and private cars to collect traffic data such as the real-time location, speed, driving route, number of stops and parking time of the vehicles; Let citizens install and use traffic management mobile applications, which use the built-in GPS module and sensor module of the mobile phone to collect user travel information, obtain user real-time location information and traffic incident reports submitted by users through the application; Cooperate with social media platforms to obtain traffic-related information posted by users on social media platforms, including traffic incidents, road conditions and weather information, and use natural language processing technology to analyze and mine text content to extract useful traffic data; Collaborate with the transportation department to collect the real-time status, timing plan and signal adjustment records of traffic lights through the traffic signal control system, and upload them to the data processing center in real time by the signal controller; S1.2, Multi-source data transmission and integration: Using wireless communication technology, the collected multi-source data is transmitted to the data processing center in real time; The data processing center is equipped with a preprocessing module to perform data cleaning, deduplication, formatting and standardization on the received data. Data cleaning includes processing missing values, outliers and erroneous data, data deduplication ensures that there are no duplicate records, and formatting and standardization convert data from different sources into a unified format. The data processing center is equipped with a data fusion module. Based on time, space and content, the data fusion module uses data fusion technology to match and integrate data from different data sources, establish a unified traffic data warehouse, ensure the connection and consistency between different data sources, and form a comprehensive traffic data view.

3. The method for intelligent urban traffic management based on multi-source data according to claim 1 is characterized in that: Execute step S2, use the distributed computing framework and stream processing technology to perform batch processing and stream processing on the massive traffic data in the traffic data warehouse. This process specifically includes: Using the distributed computing framework of Hadoop and Spark, batch processing and stream processing tasks are performed on massive traffic data. Batch processing operations analyze traffic data according to preset cycles and generate corresponding reports to provide periodic summaries and analysis for traffic management. Stream processing operations monitor and respond to real-time traffic data in real time. Apache Flink and Kafka Streams stream processing technologies are used to quickly process and analyze real-time traffic data.

4. The method for intelligent urban traffic management based on multi-source data according to claim 3 is characterized in that: Execute step S2 to build and optimize various traffic models based on multi-source data using machine learning and deep learning algorithms. This process specifically includes: Based on historical traffic data and real-time traffic data, machine learning algorithms and deep learning algorithms are used to build traffic flow prediction models, congestion detection models and accident prediction models. The machine learning algorithms involve time series analysis algorithms, regression analysis algorithms, and classification algorithms. The deep learning algorithms involve neural networks, convolutional neural networks, and recurrent neural networks. The constructed traffic flow prediction model, congestion detection model and accident prediction model are trained through training data. The training data includes accumulated historical traffic data and real-time traffic data, as well as corresponding weather conditions, holiday arrangements and major event information. At the same time, cross-validation and hyperparameter optimization techniques are used to continuously optimize the traffic flow prediction model, congestion detection model and accident prediction model. Machine learning algorithms such as isolation forest, support vector machine, and anomaly detection neural network are used to detect anomalies in traffic data and issue warnings and responses in a timely manner.

5. The method for intelligent urban traffic management based on multi-source data according to claim 4 is characterized in that: Execute step S2 to develop visualization tools to display the analysis results in a variety of forms to facilitate traffic management decision-making. This process specifically includes: Develop data visualization tools that support multiple data display formats such as line charts, bar charts, pie charts, heat maps, and geographic information system maps; Use data visualization tools to intuitively display the processed and analyzed traffic data results in at least one form of charts, maps and dashboards, realize the dynamic display function of traffic data, and generate real-time traffic flow maps, congestion maps, accident heat maps and traffic light status maps.

6. The method for intelligent urban traffic management based on multi-source data according to claim 4 is characterized in that: The step S3 specifically includes: S3.1 Traffic signal optimization: Through the induction control technology of the dynamic signal control system, the arrival of vehicles at the intersection can be sensed in real time. Through the time period control algorithm of the dynamic signal control system, different signal light timing schemes can be set according to the traffic flow characteristics of different time periods. Through the timing optimization algorithm of the dynamic signal control system, the duration of the signal light can be accurately calculated and adjusted. Introducing artificial intelligence algorithms of reinforcement learning and fuzzy logic control into dynamic signal control systems. The reinforcement learning algorithm allows the dynamic signal control system to learn the best signal timing strategy in a continuous trial and error process to adapt to the dynamic changes in traffic flow. Fuzzy logic control is based on fuzzy traffic flow and road condition information. It uses fuzzy reasoning and decision rules to adjust the signal timing plan in real time, so that traffic lights can adapt to different traffic conditions and needs more intelligently. S3.2, Path Planning and Navigation: Based on real-time traffic information and historical data, the system comprehensively considers distance, time, congestion and road grade, and uses path planning algorithms to provide optimal path planning and navigation services; Based on the user's travel habits, preferences and real-time traffic conditions, collaborative filtering algorithms, content recommendation algorithms and hybrid recommendation algorithms are used to provide personalized route recommendations and traffic information; S3.

3. Public transportation optimization: In-depth analysis of public transportation operation data, and optimization of bus routes and schedules through route optimization algorithms based on shortest path, linear programming, and network flow optimization; The intelligent dispatching system combines public transportation vehicle location information obtained through real-time monitoring, passenger demand predicted through data analysis, and real-time vehicle operation status information to make real-time adjustments to the dispatching and operation plans of public transportation vehicles.

7. The method for intelligent urban traffic management based on multi-source data according to claim 6 is characterized in that: The step S4 specifically includes: S4.

1. Build a traffic monitoring center: Establish a traffic monitoring center, which includes a data monitoring module and a video analysis module. The data monitoring module monitors the city's traffic conditions in real time through the traffic data in the traffic data warehouse, and the video analysis module processes the real-time video, detects abnormal conditions and issues timely warnings; S4.

2. Establish and improve emergency response mechanism: Develop detailed emergency plans, clarify the emergency response process and the division of responsibilities of each department when facing traffic accidents and natural disasters, and respond quickly to abnormal events; When the traffic monitoring center discovers an abnormal situation and issues a timely warning, the intelligent dispatching system automatically generates an emergency dispatching plan based on real-time traffic data and the established emergency plan. Subsequently, the intelligent dispatching system executes the emergency dispatching plan and coordinates relevant departments to carry out emergency response and traffic diversion work.

8. The method for intelligent urban traffic management based on multi-source data according to claim 7 is characterized in that: The emergency plan covers multiple aspects including event detection, information release, resource dispatch and on-site command, among which: The event detection phase detects emergencies in a timely manner through monitoring systems and various sensors; The information release phase ensures that event information is conveyed quickly and accurately to relevant departments and the public; The resource dispatching link is responsible for deploying rescue vehicles and personnel; The on-site command link provides unified command for on-site rescue and traffic diversion work, and all links work closely together to ensure the timeliness and effectiveness of the emergency response.

9. The method for intelligent urban traffic management based on multi-source data according to claim 1, characterized in that: The step S5 specifically includes: S5.

1. Data Sharing: Establish an open data sharing platform with standardized API interfaces, support multiple data formats, and be compatible with different access methods; Develop a unified set of data interface standards, including data format, data protocol and data interface documentation, to ensure the compatibility and ease of use of data sharing; S5.

2. Cross-departmental collaboration: Actively promote data sharing and collaboration among multiple relevant departments such as transportation management departments, urban planning departments, and emergency management departments. Build a multi-department collaboration platform with data sharing function, so that departments can exchange traffic-related data in real time; the collaboration platform also supports information exchange, facilitating communication and coordination among personnel of various departments; the collaboration platform also has joint decision-making function, providing a platform for various departments to jointly discuss traffic management strategies, thereby comprehensively improving the city's comprehensive management capabilities. Through cross-departmental collaboration, the joint decision-making system uses integrated multi-source data and analysis results displayed by visualization tools to conduct a comprehensive assessment of traffic conditions, urban development needs and emergency response needs, providing scientific decision-making support for various departments.

10. The method for intelligent urban traffic management based on multi-source data according to claim 1, characterized in that: The method further comprises: In the process of executing steps S1-S5, data encryption technology is used to encrypt sensitive data, an access control mechanism is established to ensure data security, anonymization is used and laws and regulations are followed to ensure privacy protection.

Images