Vehicle-road collaborative management method and system based on intelligent transportation
By building a road risk assessment model, combining traffic flow and weather interference index, early warning information is generated, and the problem of inaccurate road hazard judgment in the existing technology is solved, and traffic management efficiency and road safety are improved.
Patent Information
- Application Number
- CN202410971916.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-07-19
AI Technical Summary
The existing smart traffic vehicle-road collaboration system is difficult to accurately judge the direction of road hazard sources, resulting in inaccurate warning information or false alarms, and the inability to effectively analyze and determine the road warning level.
By collecting and preprocessing road environment data, building a road risk assessment model, obtaining traffic flow interference index and weather interference index, combining historical data and real-time data, setting early warning assessment thresholds, generating early warning information, and conducting coordinated management of road traffic.
Improve traffic management efficiency, enhance road safety, can respond quickly to traffic congestion and accidents, provide accurate navigation suggestions, reduce traffic delays and accident rates, and help formulate scientific traffic optimization strategies.
Smart Images

Figure CN118506583B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent transportation technology, and specifically to a vehicle-road collaborative management method and system based on intelligent transportation. Background Art
[0002] With the accelerated development of urbanization, the number of motor vehicles has increased dramatically, traffic pressure has increased, and problems such as traffic congestion and frequent accidents have become increasingly serious. Traditional traffic management methods can no longer meet the needs of modern urban traffic. With the rapid development of new generation information technologies such as big data, cloud computing, the Internet of Things, and artificial intelligence, it has provided strong technical support for the development of smart transportation and provided data and technical support for road-vehicle collaboration.
[0003] In the existing technology, due to the complex and changeable road environment, the vehicle-road cooperative system needs to collect multi-source data to comprehensively determine potential road hazards. Due to the complexity of the data, it is difficult to accurately determine the direction of the source of danger, and the warning information cannot give clear instructions, resulting in inaccurate information or false alarms. How to analyze the road data in smart transportation and determine the warning level is the problem we need to solve. To this end, a vehicle-road cooperative management method and system based on smart transportation are proposed. Summary of the invention
[0004] The purpose of the present invention is to provide a vehicle-road collaborative management method and system based on intelligent transportation to solve the problems raised in the above-mentioned background technology.
[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:
[0006] First, the vehicle-road collaborative management method based on intelligent transportation includes the following steps:
[0007] Step 1, collecting road environment data and transmitting the data to the traffic management center, wherein the collected road environment data includes historical data and real-time data;
[0008] Step 2, preprocessing the collected historical data and real-time data to extract road safety interference factors, wherein the road safety interference factors include traffic flow interference factors and weather interference factors;
[0009] Step 3: Analyze the preprocessed historical data and combine it with the extracted road safety interference factors to build a road risk assessment model, obtain the traffic flow interference index and weather interference index, and predict and analyze the vehicle driving trend and traffic flow trend;
[0010] Step 4, obtaining a road warning evaluation coefficient based on the traffic flow interference index and the weather interference index, and determining different warning levels of road danger conditions in combination with the preprocessed historical data, setting warning evaluation thresholds for different warning levels, and obtaining a warning evaluation sequence table;
[0011] Step 5: Input the preprocessed real-time data into the road risk assessment model for analysis to obtain the value of the road warning assessment coefficient, determine the warning level of the current road hazard situation, and generate corresponding warning information according to the corresponding warning level to conduct collaborative management of road traffic.
[0012] A further improvement of the technical solution of the present invention is that in step 1, the process of collecting and transmitting the road environment data is as follows:
[0013] Step 101, install sensor equipment in the road network to monitor and collect real-time data of the road environment in real time, and obtain historical data of the road environment from the public database of traffic management, wherein the historical data includes historical traffic flow and historical traffic accident record data. The sensor equipment is used to obtain real-time traffic flow, vehicle speed, weather conditions, road conditions, and vehicle location information. The acquisition of historical data of the road environment should be of sufficient length to analyze the long-term trend of road danger conditions, and the historical data of the road environment should have the same time and season span as the real-time data of the road environment to reduce the error of the historical data of the road environment for trend analysis; traffic flow, vehicle speed and weather condition data are obtained by traffic flow sensors, speed sensors and meteorological sensors respectively, road conditions are captured and obtained by high-definition cameras and image processing technology, and vehicle location information is obtained by radar equipment detection. It should be noted that the acquisition of historical data and real-time data requires authorization;
[0014] Step 102: The collected real-time data and historical data are transmitted to the traffic management center through the network, and the static information of the road network structure and the layout of traffic facilities is obtained in combination with the geographic information system (GIS), and the vehicle-road cooperative management sequence is obtained comprehensively. The static information generally includes the location and attribute information of the road geometric features, traffic signal control equipment, traffic monitoring equipment, and bus stops. The road geometric features are composed of road length, road width, and road curvature.
[0015] Step 103, construct a database in the traffic management center to store the road environment data and the vehicle-road collaborative management sequence, and back up the road environment data and the vehicle-road collaborative management sequence.
[0016] A further improvement of the technical solution of the present invention is that in step 2, the process of extracting the road safety interference factor is:
[0017] Step 201, data cleaning and preprocessing are performed on the collected historical data and real-time data to remove noise, outliers and redundant information. The specific process is as follows: first, the collected road environment data is cleaned to remove duplicate, erroneous, incomplete or abnormal data, including checking the rationality, range and missing values of the data, and integrating the data from different sensor devices, including data format conversion and time stamp alignment, and then normalizing the data;
[0018] Step 202, extracting features from the pre-processed historical data, performing feature extraction on traffic flow and weather conditions, respectively, to obtain road safety interference factors, specifically traffic flow interference factors and weather interference factors;
[0019] Step 203, based on the pre-processed historical data, obtain the associated data of the traffic flow interference factor, which are the vehicle flow data, vehicle speed data and vehicle density data; obtain the associated data of the weather interference factor, which are humidity data, wind speed data, rainfall data and visibility data. It should be noted that there is snowfall data in the associated data of the weather interference factor, but since the snowfall has a small period in regular traffic behavior, it is not considered.
[0020] A further improvement of the technical solution of the present invention is that in step 3, the construction of the road risk assessment model and the acquisition process of the traffic flow interference index and the weather interference index are as follows:
[0021] Step 301, integrating the associated data of traffic flow interference factors and weather interference factors in the pre-processed historical data to form a unified data set;
[0022] Step 302, feature encoding is performed on the associated data of the traffic flow interference factor and the weather interference factor in the data set, and a multivariate nonlinear regression model is defined as a road risk assessment model;
[0023] Step 303, dividing the integrated data set into a training set, a validation set and a test set, using the training set data to train the multivariate nonlinear regression model, building a road risk assessment model, and using the validation set and test set data to validate the trained road risk assessment model, and evaluating the performance of the road risk assessment model;
[0024] Step 304 , using the trained model and combining the pre-processed historical data to obtain the traffic flow interference index and the weather interference index, predicting and analyzing the vehicle driving trend and the traffic flow trend.
[0025] A further improvement of the technical solution of the present invention is that the calculation formula of the traffic flow interference index is:
[0026] ;
[0027] ;
[0028] in, is the traffic flow interference index, is the current traffic volume, is the minimum value of traffic flow in historical data, is the maximum value of traffic flow in historical data, is the standard deviation of vehicle speed, is the average vehicle speed in historical data, The calculation formula is: , For the The speed of the data point, is the number of data points, is the current vehicle density, is the average value of vehicle density in historical data, is the minimum value of vehicle density in historical data, is the maximum value of vehicle density in historical data, ;
[0029] The calculation formula of the weather interference index is:
[0030] ;
[0031] in, is the weather disturbance index, is the current humidity, is the maximum humidity in historical data, is the current wind speed, is the average wind speed in historical data, is the current rainfall, is the maximum rainfall in historical data. is the current visibility, is the minimum visibility in historical data, .
[0032] A further improvement of the technical solution of the present invention is that in step 4, the process of obtaining the road warning evaluation coefficient and the warning evaluation sequence table is as follows:
[0033] Step 401, traversing the pre-processed historical data, combining the traffic flow interference index and the weather interference index with the historical traffic accident record data, and analyzing the correlation between the road danger situation and the traffic flow interference index and the weather interference index;
[0034] Step 402, assigning different weights to the traffic flow interference index and the weather interference index, performing weighted calculation on the two indexes, and obtaining a road warning evaluation coefficient;
[0035] Step 403, according to the pre-processed historical data, the road hazard conditions in the historical traffic accident record data are matched to determine different warning levels, namely, the first warning level, the second warning level, the third warning level, and the fourth warning level, wherein the road hazard conditions of the warning levels increase step by step from the first warning level to the fourth warning level;
[0036] Step 404, matching the determined different warning levels with the results of the road warning evaluation coefficient, and setting corresponding warning evaluation thresholds for the different warning levels;
[0037] Step 405, all road warning evaluation coefficient values are arranged in descending order, and a corresponding warning level is assigned to each value to prepare a warning evaluation sequence table, listing the corresponding relationship between the road warning evaluation coefficient and the warning level.
[0038] A further improvement of the technical solution of the present invention is that the calculation formula of the road warning evaluation coefficient is:
[0039] ;
[0040] in, is the road warning evaluation coefficient, is the traffic flow interference index, is the weight of the traffic flow interference index, is the weather disturbance index, is the weight of the weather disturbance index, , The value range is .
[0041] A further improvement of the technical solution of the present invention is that: the multiple warning levels correspond to the multiple warning assessment thresholds, wherein the warning assessment thresholds include an upper threshold and a lower threshold;
[0042] The multiple warning levels and the multiple warning assessment thresholds satisfy the following relationship:
[0043] Level 1 warning The first-level warning measures include maintaining regular monitoring of traffic flow and weather conditions to ensure safe and smooth roads, continuing traffic safety publicity and education, enhancing the public's traffic safety awareness, setting up green warning signs on road screens to remind drivers, ensuring that drivers and pedestrians understand traffic rules, and conducting regular traffic safety publicity and reminders on car radios;
[0044] Level 2 warning The warning measures for the second-level warning level are to increase the monitoring of traffic flow and weather conditions, keep abreast of the latest situation, strengthen traffic safety publicity and reminders through radio, television, the Internet and other media, remind drivers to pay attention to road conditions and drive safely through car radio and mobile phone APP, set up yellow warning signs on the road screen to remind drivers to pay attention to traffic safety, increase traffic safety publicity and yellow warning information broadcasts in car radio, and push yellow warning information and road condition reminders to users through the mobile APP of the traffic management department;
[0045] Level 3 warning The warning measures for the third level are to increase the number of traffic police and patrol personnel, strengthen the monitoring of road and traffic conditions, implement speed limits and traffic restrictions according to weather or traffic conditions to reduce the risk of accidents, release orange warning information through multiple channels to remind drivers and pedestrians to pay attention to safety, set up orange warning signs on road screens to remind drivers to pay attention to road conditions and speed limits, increase traffic safety publicity in car radio and release orange warning information and road condition information in real time, and cooperate with the car navigation system to push orange warning information to vehicles in motion;
[0046] Four warning levels The warning measures for the fourth level are to limit the flow of traffic on roads or areas in the affected areas to prevent more vehicles and pedestrians from entering, display red warning information and road detour instructions on the road screen, broadcast red warning notifications in real time through car radio and mobile phone APP, and send text messages of traffic control notifications to drivers in the affected areas;
[0047] in, is the road warning evaluation coefficient, is the upper threshold corresponding to the first-level warning level and the lower threshold corresponding to the second-level warning level. is the upper threshold corresponding to the second-level warning level and the lower threshold corresponding to the third-level warning level. is the upper threshold corresponding to the third warning level and the lower threshold corresponding to the fourth warning level. , , .
[0048] A further improvement of the technical solution of the present invention is that in step 5, the process of road traffic collaborative management is:
[0049] Step 501, inputting the characteristic data of traffic flow and weather conditions in the pre-processed real-time data into the road risk assessment model, and calculating the traffic flow interference index and the weather interference index respectively;
[0050] Step 502, combining the calculated traffic flow interference index and weather interference index to obtain a road warning evaluation coefficient, and determining the warning level of the current road danger situation according to a preset warning evaluation threshold;
[0051] Step 503, generating corresponding warning information according to the warning level of the current road danger situation, and transmitting the warning information to the relevant personnel and departments of the road traffic collaborative management, wherein the relevant personnel and departments include the road management department, the traffic supervision center and the driver;
[0052] Step 504, monitor the development and execution of the early warning information, and record the feedback information.
[0053] In the second aspect, a vehicle-road collaborative management system based on smart transportation is used to implement a vehicle-road collaborative management method based on smart transportation, including a traffic management center, wherein the traffic management center is communicatively connected with a data acquisition module, a data analysis module, a model building module, a road warning assessment module, a warning module, and a traffic dispatching module, wherein electrical signals are connected between the modules;
[0054] The data acquisition module is used to collect real-time data of the road environment and obtain historical data of the road environment from the public database of traffic management, so as to ensure that the system can obtain comprehensive and accurate road environment data and provide data support for subsequent analysis and decision-making;
[0055] The data analysis module is used to pre-process the road environment data acquired by the data acquisition module and extract road safety interference factors;
[0056] The model building module is used to combine the pre-processed road environment historical data and road safety interference factors to build a road risk assessment model, obtain the traffic flow interference index and the weather interference index, and analyze the vehicle speed and traffic flow trend;
[0057] The road warning assessment module is used to combine the historical data of the road environment and the road risk assessment model to obtain the road warning assessment coefficient to assess the safety and risk of the road. By analyzing the road environment and combining the real-time data of the road environment to predict the real-time road danger situation, it provides decision support for vehicle driving and traffic management;
[0058] The warning module is used to determine the warning level of the current road danger situation based on the combination of the road warning evaluation coefficient and the real-time data of the road environment, and generate corresponding warning information based on the road warning evaluation result;
[0059] The traffic dispatching module is used to manage and dispatch road traffic according to early warning information and real-time traffic conditions.
[0060] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:
[0061] 1. The present invention provides a vehicle-road collaborative management method and system based on intelligent transportation. By collecting and processing road environment data in real time, monitoring road conditions in real time, and issuing early warnings for potential risks, it not only improves the efficiency of traffic management, but also greatly enhances the safety of road use. When traffic congestion, accidents or other abnormal situations occur, the system can respond quickly and provide drivers with accurate navigation and avoidance suggestions to reduce traffic delays and accident rates. At the same time, the system can also provide decision-making support for traffic management departments, enabling them to formulate traffic management strategies more accurately and optimize traffic flow.
[0062] 2. The present invention provides a vehicle-road collaborative management method and system based on intelligent transportation, which conducts in-depth mining of road environment data to provide a scientific basis for traffic decision-making, predicts future traffic conditions based on historical data and real-time data, and thus formulates traffic optimization strategies in advance. It provides drivers with rich driving assistance information to help them better plan their routes, and provides timely safety reminders to reduce the occurrence of traffic accidents. In severe weather or complex road conditions, it effectively reduces the driver's driving pressure and improves driving safety.
[0063] 3. The present invention provides a vehicle-road collaborative management method and system based on smart transportation. Based on real-time road data and warning information, the smart transportation system can realize dynamic traffic scheduling and navigation optimization, intelligently adjust traffic lights and speed limit measures according to traffic conditions, and provide real-time traffic navigation suggestions to drivers to help drivers choose the best driving route and time, thereby reducing traffic congestion and improving road traffic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0065] Figure 1 is a flow chart of the method of the present invention;
[0066] Figure 2 This is a flow chart of collecting and transmitting road environment data of the present invention;
[0067] Figure 3 The present invention is a flow chart for constructing a road risk assessment model and obtaining a traffic flow interference index and a weather interference index;
[0068] Figure 4The present invention is a flow chart for constructing a road risk assessment model and obtaining a traffic flow interference index and a weather interference index;
[0069] Figure 5 It is a module structure diagram of the present invention. DETAILED DESCRIPTION
[0070] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0071] Embodiment 1, as Figure 1-4 As shown, the present invention provides a vehicle-road collaborative management method based on intelligent transportation, comprising the following steps:
[0072] Step 1: Collect road environment data and transmit the data to the traffic management center. The collected road environment data includes historical data and real-time data. Sensor equipment is installed in the road network to monitor and collect real-time data of the road environment in real time, and obtain historical data of the road environment from the public database of traffic management. The historical data includes historical traffic flow and historical traffic accident record data. The sensor equipment is used to obtain real-time traffic flow, vehicle speed, weather conditions, road conditions, and vehicle location information. The acquisition of historical data of the road environment should be of sufficient length to analyze the long-term trend of road hazards, and the historical data of the road environment should have the same time and season span as the real-time data of the road environment to reduce the error of the historical data of the road environment for trend analysis; traffic flow, vehicle speed and weather condition data are obtained by traffic flow sensors, speed sensors and meteorological sensors respectively, road conditions are captured by high-definition cameras and image processing technology, and vehicle location information is obtained by radar equipment detection. It should be noted that the acquisition of historical data and real-time data requires authorization, and the collected real-time data and historical data are transmitted to the traffic management center through the network. The center is combined with the geographic information system (GIS) to obtain static information on the road network structure and the layout of traffic facilities, and the vehicle-road collaborative management sequence is obtained comprehensively. Among them, the static information usually includes the location and attribute information of road geometry, traffic signal control equipment, traffic monitoring equipment, and bus stops. The road geometry is composed of road length, road width, and road curvature. The GIS data is integrated into the database of the traffic management center and associated and matched with real-time and historical data. At the traffic management center, the real-time data, historical data, and GIS data are fused and analyzed to extract key information on traffic flow patterns, accident-prone sections, and traffic congestion areas. Combined with GIS data, the operating conditions of traffic facilities and the structural characteristics of the road network are analyzed to identify potential road hazards and traffic bottlenecks. Based on the results of data fusion and analysis, the vehicle-road collaborative management sequence is generated. The vehicle-road collaborative management sequence includes traffic signal control strategies, traffic flow induction plans, accident warnings, and emergency response measures. A database is built in the traffic management center to store road environment data and vehicle-road collaborative management sequences, and the road environment data and vehicle-road collaborative management sequences are backed up to ensure data reliability and security.
[0073] Step 2: Preprocess the collected historical data and real-time data to extract road safety interference factors, where road safety interference factors include traffic flow interference factors and weather interference factors. Clean and preprocess the collected historical data and real-time data to remove noise, outliers and redundant information. The specific process is as follows: first, clean the collected road environment data to remove duplicate, erroneous, incomplete or abnormal data, including checking the rationality, range and missing values of the data to ensure the accuracy of subsequent analysis, and integrate the data from different sensor devices to ensure the consistency and integrity of the data, including data format conversion and timestamp alignment, and then normalize the data. The preprocessed historical data are processed to better reveal the relationship and pattern between the data, and features are extracted from the preprocessed historical data. Feature extraction is performed for traffic flow and weather conditions respectively, and road safety interference factors are obtained, specifically traffic flow interference factors and weather interference factors. According to the preprocessed historical data, the associated data of traffic flow interference factors are obtained, which are vehicle flow data, vehicle speed data, and vehicle density data; the associated data of weather interference factors are obtained, which are humidity data, wind speed data, rainfall data, and visibility data. It should be noted that there is snowfall data in the associated data of weather interference factors, but since the snowfall has a small period in regular traffic behavior, it is not considered;
[0074] Step 3, analyze the preprocessed historical data and combine it with the extracted road safety interference factors to build a road risk assessment model, obtain the traffic flow interference index and the weather interference index to predict and analyze the vehicle driving trend and traffic flow trend, integrate the associated data of the traffic flow interference factors and the weather interference factors in the preprocessed historical data to form a unified data set, feature encode the associated data of the traffic flow interference factors and the weather interference factors in the data set, define a multivariate nonlinear regression model as a road risk assessment model, divide the integrated data set into a training set, a validation set and a test set, use the training set data to train the multivariate nonlinear regression model, build a road risk assessment model, and use the validation set and test set data to verify the trained road risk assessment model, evaluate the performance of the road risk assessment model, use the trained model to combine the preprocessed historical data to obtain the traffic flow interference index and the weather interference index, and predict and analyze the vehicle driving trend and traffic flow trend;
[0075] Furthermore, the calculation formula of the traffic flow interference index is:
[0076] ;
[0077] ;
[0078] ;
[0079] in, is the traffic flow interference index, is the current traffic volume, is the minimum value of traffic flow in historical data, is the maximum value of traffic flow in historical data, is the standard deviation of vehicle speed, is the average vehicle speed in historical data, For the The speed of the data point, is the number of data points, is the current vehicle density, is the average value of vehicle density in historical data, is the minimum value of vehicle density in historical data, is the maximum value of vehicle density in historical data, It should be noted that when Close to maximum When the first will increase, indicating that the traffic volume is high and may cause traffic congestion; when the standard deviation of vehicle speed When it increases, it means that the vehicle speed fluctuates greatly, which may be due to poor road conditions or unstable vehicle driving, which also increases traffic flow interference;
[0080] The calculation formula of weather interference index is:
[0081] ;
[0082] in, is the weather disturbance index, is the current humidity, is the maximum humidity in historical data, is the current wind speed, is the average wind speed in historical data, is the current rainfall, is the maximum rainfall in historical data. is the current visibility, is the minimum visibility in historical data, It should be noted that when When it increases, it means the road may be more slippery, affecting driving safety; when When it increases, it may be accompanied by unfavorable factors such as crosswind and dust. When it increases, the road conditions will become worse, such as water accumulation, slippery road surface, etc. When it decreases (i.e. the value decreases), it means that the driving conditions are deteriorating and the driver's field of vision is restricted;
[0083] Step 4, based on the traffic flow interference index and the weather interference index, a road warning evaluation coefficient is obtained, and different warning levels of road danger conditions are determined in combination with the pre-processed historical data, warning evaluation thresholds are set for different warning levels, and a warning evaluation sequence table is obtained. The pre-processed historical data is traversed, and the traffic flow interference index and the weather interference index are combined with the historical traffic accident record data, and the correlation between the road danger condition and the traffic flow interference index and the weather interference index is analyzed. Different weights are assigned to the traffic flow interference index and the weather interference index, and the two indexes are weightedly calculated to obtain the road warning evaluation coefficient. According to the pre-processed historical data, the road danger conditions in the historical traffic accident record data are matched, and different warning levels are determined, which are the first warning level, the second warning level, the third warning level, and the fourth warning level, respectively. Among them, the road danger conditions of the warning level increase step by step from the first warning level to the fourth warning level, and the determined different warning levels are matched with the results of the road warning evaluation coefficient, and corresponding warning evaluation thresholds are set for different warning levels, and all road warning evaluation coefficient values are arranged in order from high to low, and a corresponding warning level is assigned to each value, and a warning evaluation sequence table is made to list the corresponding relationship between the road warning evaluation coefficient and the warning level;
[0084] Furthermore, the calculation formula of the road warning evaluation coefficient is:
[0085] ;
[0086] in, is the road warning evaluation coefficient, is the traffic flow interference index, is the weight of the traffic flow interference index, is the weather disturbance index, is the weight of the weather disturbance index, , The value range is It should be noted that when When it is close to 0, it means the road condition is relatively safe; when When it is close to 1, it means the road condition is very dangerous; for example, The larger the value, the heavier the traffic flow or the more unstable the vehicle driving; The larger the value, the worse the weather conditions. It combines the values of traffic flow and weather interference factors to assess the dangerous conditions of roads; Indicates the degree of interference with traffic flow, Indicates the degree of impact of weather conditions on road traffic. and Indicates the importance of traffic flow disturbance index and weather disturbance index in assessing road hazard conditions;
[0087] Furthermore, the multiple warning levels correspond to multiple warning assessment thresholds, wherein the warning assessment thresholds include an upper threshold and a lower threshold;
[0088] Multiple warning levels and multiple warning assessment thresholds satisfy the following relationship:
[0089] Level 1 warning The first-level warning measures include maintaining regular monitoring of traffic flow and weather conditions to ensure safe and smooth roads, continuing traffic safety publicity and education, enhancing the public's traffic safety awareness, setting up green warning signs on road screens to remind drivers, ensuring that drivers and pedestrians understand traffic rules, and conducting regular traffic safety publicity and reminders on car radios;
[0090] Level 2 warning The warning measures for the second-level warning level are to increase the monitoring of traffic flow and weather conditions, keep abreast of the latest situation, strengthen traffic safety publicity and reminders through radio, television, the Internet and other media, remind drivers to pay attention to road conditions and drive safely through car radio and mobile phone APP, set up yellow warning signs on the road screen to remind drivers to pay attention to traffic safety, increase traffic safety publicity and yellow warning information broadcasts in car radio, and push yellow warning information and road condition reminders to users through the mobile APP of the traffic management department;
[0091] Level 3 warning The warning measures for the third level are to increase the number of traffic police and patrol personnel, strengthen the monitoring of road and traffic conditions, implement speed limits and traffic restrictions according to weather or traffic conditions to reduce the risk of accidents, release orange warning information through multiple channels to remind drivers and pedestrians to pay attention to safety, set up orange warning signs on road screens to remind drivers to pay attention to road conditions and speed limits, increase traffic safety publicity in car radio and release orange warning information and road condition information in real time, and cooperate with the car navigation system to push orange warning information to vehicles in motion;
[0092] Four warning levels The warning measures for the fourth level are to limit the flow of traffic on roads or areas in the affected areas to prevent more vehicles and pedestrians from entering, display red warning information and road detour instructions on the road screen, broadcast red warning notifications in real time through car radio and mobile phone APP, and send text messages of traffic control notifications to drivers in the affected areas;
[0093] in, is the road warning evaluation coefficient, is the upper threshold corresponding to the first-level warning level and the lower threshold corresponding to the second-level warning level. is the upper threshold corresponding to the second-level warning level and the lower threshold corresponding to the third-level warning level. is the upper threshold corresponding to the third warning level and the lower threshold corresponding to the fourth warning level. , , ;
[0094] Step 5, input the preprocessed real-time data into the road risk assessment model for analysis to obtain the value of the road warning assessment coefficient, determine the warning level of the current road hazard situation, and generate corresponding warning information according to the corresponding warning level to conduct collaborative management of road traffic, input the characteristic data of traffic flow and weather conditions in the preprocessed real-time data into the road risk assessment model, calculate the traffic flow interference index and weather interference index respectively, combine the calculated traffic flow interference index and weather interference index to obtain the road warning assessment coefficient, and determine the warning level of the current road hazard situation according to the preset warning assessment threshold, generate corresponding warning information according to the warning level of the current road hazard situation, and transmit the warning information to related personnel and departments of road traffic collaborative management, where the related personnel and departments include road management departments, traffic supervision centers and drivers, monitor the development and implementation of warning information, and record feedback information.
[0095] Embodiment 2, as Figure 5 As shown, on the basis of Example 1, the present invention further provides a vehicle-road collaborative management system based on smart transportation, which is used to implement a vehicle-road collaborative management method based on smart transportation, including a traffic management center, the traffic management center is communicatively connected with a data acquisition module, a data analysis module, a model building module, a road warning evaluation module, a warning module and a traffic dispatching module, wherein the modules are connected by electrical signals;
[0096] The data collection module is used to collect real-time data on the road environment and obtain historical data on the road environment from the public database of traffic management, ensuring that the system can obtain comprehensive and accurate road environment data and provide data support for subsequent analysis and decision-making;
[0097] A data analysis module is used to pre-process the road environment data acquired by the data acquisition module and extract road safety interference factors;
[0098] The model building module is used to combine the pre-processed road environment historical data and road safety interference factors to build a road risk assessment model, obtain the traffic flow interference index and weather interference index, and analyze the vehicle speed and traffic flow trend;
[0099] The road warning assessment module is used to combine the historical data of the road environment with the road risk assessment model to obtain the road warning assessment coefficient to evaluate the safety and risk of the road. By analyzing the road environment and combining the real-time data of the road environment to predict the real-time road danger situation, it provides decision support for vehicle driving and traffic management;
[0100] The warning module is used to determine the warning level of the current road danger situation based on the combination of the road warning evaluation coefficient and the real-time data of the road environment, and generate corresponding warning information based on the road warning evaluation results;
[0101] The traffic dispatch module is used to manage and dispatch road traffic based on early warning information and real-time traffic conditions.
[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. Vehicle-road collaborative management method based on intelligent transportation, Features: The following steps are involved: Step 1: Collect road environment data and transmit the data to the traffic management center, wherein the collected road environment data includes historical data and real-time data. In step 1, the collection and transmission process of the road environment data is as follows: Step 101, installing sensor equipment in the road network to monitor and collect real-time data of the road environment in real time, and obtaining historical data of the road environment from a public database of traffic management, wherein the historical data includes historical traffic flow and historical traffic accident record data, and the sensor equipment is used to obtain real-time traffic flow, vehicle speed, weather conditions, road conditions, and vehicle location information; Step 102, the collected real-time data and historical data are transmitted to the traffic management center through the network, and the static information of the road network structure and traffic facility layout is obtained in combination with the geographic information system to comprehensively obtain the vehicle-road collaborative management sequence; Step 103: construct a database in the traffic management center to store the road environment data and the vehicle-road collaborative management sequence, and back up the road environment data and the vehicle-road collaborative management sequence; Step 2, preprocessing the collected historical data and real-time data to extract road safety interference factors, wherein the road safety interference factors include traffic flow interference factors and weather interference factors. In step 2, the extraction process of the road safety interference factors is as follows: Step 201, cleaning and preprocessing the collected historical data and real-time data to remove noise, outliers and redundant information; Step 202, extracting features from the pre-processed historical data, performing feature extraction on traffic flow and weather conditions, respectively, to obtain road safety interference factors, specifically traffic flow interference factors and weather interference factors; Step 203, based on the pre-processed historical data, obtain the associated data of the traffic flow interference factor, which are the vehicle flow data, vehicle speed data and vehicle density data; obtain the associated data of the weather interference factor, which are the humidity data, wind speed data, rainfall data and visibility data; Step 3: Analyze the preprocessed historical data and combine it with the extracted road safety interference factors to build a road risk assessment model, obtain the traffic flow interference index and the weather interference index, so as to predict and analyze the vehicle driving trend and traffic flow trend. In step 3, the construction of the road risk assessment model and the acquisition process of the traffic flow interference index and the weather interference index are as follows: Step 301, integrating the associated data of traffic flow interference factors and weather interference factors in the pre-processed historical data to form a unified data set; Step 302, feature encoding is performed on the associated data of the traffic flow interference factor and the weather interference factor in the data set, and a multivariate nonlinear regression model is defined as a road risk assessment model; Step 303, dividing the integrated data set into a training set, a validation set and a test set, using the training set data to train the multivariate nonlinear regression model, building a road risk assessment model, and using the validation set and test set data to validate the trained road risk assessment model, and evaluating the performance of the road risk assessment model; Step 304: Use the trained model and the pre-processed historical data to obtain the traffic flow interference index and the weather interference index, and predict and analyze the vehicle driving trend and the traffic flow trend. The calculation formula of the traffic flow interference index is: Among them, JG is the traffic flow interference index, Q is the current traffic flow, and Q min is the minimum value of traffic flow in historical data, Q max is the maximum value of traffic flow in historical data, SV is the standard deviation of vehicle speed, is the average speed in historical data, V i is the speed of the i-th data point, n is the number of data points, D is the current vehicle density, is the average vehicle density in historical data, D min is the minimum value of vehicle density in historical data, D max is the maximum value of vehicle density in historical data, JG>0; The calculation formula of the weather interference index is: Among them, TG is the weather disturbance index, H is the current humidity, and H max is the maximum humidity in the historical data, W is the current wind speed, is the average wind speed in historical data, Y is the current rainfall, and Y max is the maximum rainfall in historical data, J is the current visibility, and J min is the minimum visibility in historical data, TG>0; Step 4: Obtain a road warning evaluation coefficient based on the traffic flow interference index and the weather interference index, determine different warning levels of road danger conditions in combination with preprocessed historical data, set warning evaluation thresholds for different warning levels, and obtain a warning evaluation sequence table. In step 4, the process of obtaining the road warning evaluation coefficient and the warning evaluation sequence table is as follows: Step 401, traversing the pre-processed historical data, combining the traffic flow interference index and the weather interference index with the historical traffic accident record data, and analyzing the correlation between the road danger situation and the traffic flow interference index and the weather interference index; Step 402, assigning different weights to the traffic flow interference index and the weather interference index, performing weighted calculation on the two indexes, and obtaining a road warning evaluation coefficient; Step 403, according to the pre-processed historical data, the road hazard conditions in the historical traffic accident record data are matched to determine different warning levels, namely, the first warning level, the second warning level, the third warning level, and the fourth warning level, wherein the road hazard conditions of the warning levels increase step by step from the first warning level to the fourth warning level; Step 404, matching the determined different warning levels with the results of the road warning evaluation coefficient, and setting corresponding warning evaluation thresholds for the different warning levels; Step 405, all road warning evaluation coefficient values are arranged in descending order, and a corresponding warning level is assigned to each value to form a warning evaluation sequence table, listing the corresponding relationship between the road warning evaluation coefficient and the warning level. The calculation formula of the road warning evaluation coefficient is: Among them, DP is the road warning evaluation coefficient, JG is the traffic flow interference index, and w 1 is the weight of the traffic flow interference index, TG is the weather interference index, and w 2 is the weight of the weather disturbance index, w 1 +w 2 =1, the value range of DP is 0,1; Step 5: Input the preprocessed real-time data into the road risk assessment model for analysis to obtain the value of the road warning assessment coefficient, determine the warning level of the current road hazard situation, and generate corresponding warning information according to the corresponding warning level to conduct collaborative management of road traffic.
2. According to the vehicle-road collaborative management method and system based on intelligent transportation according to claim 1, Features: A plurality of the warning levels correspond to a plurality of the warning assessment thresholds, wherein the warning assessment thresholds include an upper threshold and a lower threshold; The multiple warning levels and the multiple warning assessment thresholds satisfy the following relationship: Level 1 warning 0 <DP<DP A ; Level 2 warning level DP A ≤DP <DP W ; Level 3 warning level DP W ≤DP <DP Z ; Level 4 warning level DP Z ≤DP<1; Among them, DP is the road warning evaluation coefficient, DP A is the upper threshold corresponding to the first warning level and the lower threshold corresponding to the second warning level, DP W is the upper threshold corresponding to the second-level warning level and the lower threshold corresponding to the third-level warning level, DP Z is the upper threshold corresponding to the third warning level and the lower threshold corresponding to the fourth warning level, DP A =0.2,DP W =0.5,DP Z =0.
8.
3. According to the vehicle-road collaborative management method based on intelligent transportation according to claim 2, Features: In step 5, the process of road traffic collaborative management is: Step 501, inputting the characteristic data of traffic flow and weather conditions in the pre-processed real-time data into the road risk assessment model, and calculating the traffic flow interference index and the weather interference index respectively; Step 502, combining the calculated traffic flow interference index and weather interference index to obtain a road warning evaluation coefficient, and determining the warning level of the current road danger situation according to a preset warning evaluation threshold; Step 503, generating corresponding warning information according to the warning level of the current road danger situation, and transmitting the warning information to the relevant personnel and departments of the road traffic collaborative management, wherein the relevant personnel and departments include the road management department, the traffic supervision center and the driver; Step 504, monitor the development and execution of the early warning information, and record the feedback information.
4. A vehicle-road collaborative management system based on intelligent transportation, used to implement the vehicle-road collaborative management method based on intelligent transportation as described in any one of claims 1 to 3, comprising a traffic management center, Features: The traffic management center is communicatively connected with a data acquisition module, a data analysis module, a model building module, a road warning assessment module, a warning module and a traffic dispatch module, wherein the modules are connected by electrical signals; The data acquisition module is used to collect real-time data of the road environment and obtain historical data of the road environment from a public database of traffic management; The data analysis module is used to pre-process the road environment data acquired by the data acquisition module and extract road safety interference factors; The model building module is used to combine the pre-processed road environment historical data and road safety interference factors to build a road risk assessment model, obtain the traffic flow interference index and the weather interference index, and analyze the vehicle speed and traffic flow trend; The road warning assessment module is used to combine the historical data of the road environment and the road risk assessment model to obtain the road warning assessment coefficient to assess the safety and risk of the road; The warning module is used to determine the warning level of the current road danger situation based on the combination of the road warning evaluation coefficient and the real-time data of the road environment, and generate corresponding warning information based on the road warning evaluation result; The traffic dispatching module is used to manage and dispatch road traffic according to early warning information and real-time traffic conditions.
