Intelligent traffic management method and system based on traffic flow

Abstract

The application relates to the technical field of traffic management, and particularly discloses a smart traffic management method based on traffic flow, which comprises the following steps: firstly, collecting historical traffic flow data of a monitoring area in a specific time period; then, real-time calling road section vehicle information parameters monitored by historical monitoring images of a congestion road section, performing state prediction analysis on the road section vehicle information parameters, evaluating road condition change information, and obtaining a historical road condition evaluation coefficient; finally, inputting the historical traffic flow data into a traffic prediction model, obtaining a predicted road condition evaluation coefficient, comparing and analyzing the predicted road condition evaluation coefficient with the historical road condition evaluation coefficient, and performing early warning, early notification and adjustment of a traffic operation state according to an analysis result; the application combines traffic flow change analysis and the smart traffic management method to perform early prediction and analysis on a next road condition, thereby reducing the occurrence probability of traffic congestion and traffic accidents.

Description

Technical Field

[0001] This invention relates to the field of traffic management technology, specifically to a smart traffic management method and system based on traffic flow. Background Technology

[0002] With the development of high technologies such as big data, cloud computing, and the Internet of Things, some developed countries are actively carrying out research on intelligent transportation system projects, committed to creating a more intelligent and information-based traffic management system, improving the management level of transportation departments, and providing a better traffic environment for people's daily travel. Intelligent transportation systems have important application value in improving the intelligent management level of transportation departments and improving the road traffic environment.

[0003] The continuous growth in car ownership has exceeded the carrying capacity of most roads, leading to increasingly serious problems such as traffic congestion, traffic accidents, and environmental pollution. While existing intelligent traffic information management systems can improve the probability of traffic congestion and accidents as much as possible, they still cannot accurately predict changes in traffic flow based on errors, thus failing to provide advance forecasts and assessments of future road conditions. This results in an increase in congested road sections and a continuous increase in traffic pressure. Summary of the Invention

[0004] The purpose of this invention is to provide a smart traffic management method and system based on traffic flow, and to solve the following technical problems:

[0005] How can we combine traffic flow change analysis and intelligent traffic management methods to predict and analyze the next road conditions in advance, thereby reducing the probability of traffic congestion and traffic accidents?

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A smart traffic management method based on vehicle flow, the method comprising:

[0008] S1. Collect historical traffic flow data of the monitored area within a specific time period;

[0009] S2. Real-time retrieval of historical monitoring images of congested road sections to monitor road vehicle information parameters, conduct state prediction analysis of road vehicle information parameters, assess road condition change information, and obtain historical road condition assessment coefficients.

[0010] S3. Input historical traffic flow data into the traffic prediction model to obtain the predicted road condition assessment coefficient. Compare and analyze the predicted road condition assessment coefficient with the historical road condition assessment coefficient, and issue an early warning based on the analysis results.

[0011] Preferably, the state prediction analysis process in step S2 is as follows:

[0012] The time for acquiring surveillance image information is evenly divided into... Collect traffic flow data for congested road sections at any different time period. ,in, ;

[0013] Traffic flow data and the corresponding preset interval Compare them. , All are empirical constants;

[0014] like Greater than the preset range If the traffic flow exceeds the critical state, an early warning message will be generated.

[0015] like Less than the preset range If the traffic flow is below the critical state, the road conditions are relatively stable.

[0016] like Within the preset range If the traffic flow reaches a critical point, a road condition assessment and analysis will be conducted.

[0017] Preferably, the road condition assessment and analysis is as follows:

[0018] According to the formula: * * Obtain road condition assessment coefficient ,in The transformation function is monotonically increasing. To start from the total time period The selected time period, and >1; To complete the vehicle speed change within the selected time period from Down to The cumulative capacity of the road section during the process; To complete the vehicle speed change within the selected time period from Down to The standard value for the cumulative capacity of vehicles on the road section during the process; for arrive The arithmetic mean; This is the vehicle information deviation coefficient.

[0019] Preferably, the road condition assessment and analysis process includes:

[0020] Road condition assessment coefficient With preset interval [ , Compare sizes:

[0021] when If a significant change in road condition is detected, the current road condition evaluation coefficient is output as the historical road condition evaluation coefficient.

[0022] when < If the road condition changes are small, maintain the current operating status;

[0023] when > It can detect significant changes in road conditions and generate early warning information.

[0024] Preferably, the process of establishing the traffic prediction model in step S3 is as follows:

[0025] S31. Collect historical traffic flow data for several time periods in the monitored area, select traffic flow data for each congested road segment for the corresponding time period, and generate training and test sets.

[0026] S32. Build a model using a recurrent neural network, train the model using a traffic flow training set, test the trained model using a test set, and adjust the number of iterations based on the test error.

[0027] S33. Repeat step S32 and refit the training set to adjust the test error to a smaller combined model. When the test error is too large, go to step S32.

[0028] S34. Output the estimated predicted value.

[0029] Preferably, the formula for the predicted value is:

[0030]

[0031] Calculate and obtain traffic flow prediction coefficient ;in, , These represent the maximum and minimum values ​​of historical traffic flow within a certain time period, respectively. The parameter value representing the deviation of historical traffic flow over a certain period of time; is the prediction coefficient.

[0032] Preferably, based on traffic flow prediction coefficient The method for obtaining the predicted road condition assessment coefficient is as follows:

[0033] Through formula Calculate the predicted road condition assessment coefficient ,in, This is the road condition conversion coefficient.

[0034] Preferably, in step S3, the comparison and analysis process is as follows:

[0035] Predicted road condition assessment coefficient Historical road condition assessment coefficient Compare:

[0036] like ≥ If so, a warning signal will be issued; traffic flow will be adjusted.

[0037] Otherwise, continue running.

[0038] A smart traffic management system based on traffic flow, the system comprising:

[0039] The data acquisition module is used to collect historical traffic flow data of the monitored area within a specific time period;

[0040] The real-time monitoring module is used to retrieve historical monitoring images of congested road sections to monitor vehicle information parameters in real time.

[0041] The analysis module is used to perform state prediction analysis on road segment vehicle information parameters, evaluate road condition change information, and obtain historical road condition evaluation coefficients.

[0042] Traffic prediction models are used to obtain predicted road condition assessment coefficients based on historical traffic flow data;

[0043] The comparison module is used to compare and analyze the predicted road condition assessment coefficients and the historical road condition assessment coefficients;

[0044] The early warning module is used to issue early warning information when the monitored traffic flow status does not meet the requirements, when the road condition assessment and analysis results do not meet the requirements, and when the comparison and analysis results do not meet the requirements.

[0045] The information synchronization module is used to synchronize vehicle and road condition traffic information to the query platform in real time.

[0046] The beneficial effects of this invention are as follows: This invention monitors vehicle information parameters of congested road sections by retrieving historical monitoring images in real time and performing state prediction analysis to assess road condition changes and obtain historical road condition evaluation coefficients; it inputs historical traffic flow data into a traffic prediction model to calculate predicted road condition evaluation coefficients; by comparing the predicted road condition evaluation coefficients with the historical road condition evaluation coefficients, it adjusts the traffic critical capacity in a timely manner based on changes in road conditions under the current monitoring state, avoiding traffic accidents and reducing the significant impact of traffic congestion on the next traffic flow; and by providing advance traffic diversion guidance, speed reduction reminders, and traffic light timing adjustments, it reduces the occurrence of severe congestion, improves traffic operation efficiency, and lowers the probability of traffic accidents.

[0047] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating the steps of the intelligent traffic management method based on vehicle flow of the present invention.

[0050] Figure 2 This is a block diagram of the intelligent traffic management system based on traffic flow according to the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] While many mature software programs can monitor traffic conditions in real time, most of them rely on in-vehicle navigation or GPS positioning for data transmission. The instability of this transmission link can easily lead to data loss when using in-vehicle systems, resulting in inaccurate traffic monitoring information. Big data systems can improve prediction accuracy to some extent by extracting massive amounts of traffic flow data and discovering data patterns, which can help improve intelligent decision-making regarding the impact of traffic flow on traffic conditions. However, relying solely on big data systems for analysis and prediction still has a significant margin of error in grasping real-time traffic conditions, and its early warning function is not very effective. This can easily lead to severe traffic congestion and even traffic accidents, endangering the lives and property of travelers.

[0053] Please see Figure 1 As shown, this invention is a smart traffic management method based on traffic flow, and the specific method includes:

[0054] S1. Collect historical traffic flow data of the monitored area within a specific time period;

[0055] S2. Real-time retrieval of historical monitoring images of congested road sections to monitor road vehicle information parameters, conduct state prediction analysis of road vehicle information parameters, assess road condition change information, and obtain historical road condition assessment coefficients.

[0056] S3. Input historical traffic flow data into the traffic prediction model to obtain the predicted road condition assessment coefficient. Compare and analyze the predicted road condition assessment coefficient with the historical road condition assessment coefficient, and issue an early warning based on the analysis results.

[0057] To address the aforementioned technical problems, this embodiment designs a smart traffic management method based on traffic flow: First, historical traffic flow data of the monitored area within a specific time period is collected. Massive amounts of traffic information data are obtained using big data technology, and the traffic flow data of the monitored area within a specific time period is locked. Then, the vehicle information parameters of the congested road sections are retrieved in real-time from historical monitoring images. State prediction analysis is performed on these parameters to assess road condition changes and obtain historical road condition evaluation coefficients. Since road condition changes are assessed through image detection and state prediction analysis, as traffic flow, primarily vehicle flow, continuously increases, leading to congestion and increasing the probability of traffic accidents, reasonable monitoring and prediction of traffic flow can effectively prevent traffic accidents. Scientific and rational arrangement and scheduling of traffic flow to reduce congestion is a powerful measure to prevent traffic accidents.

[0058] It should be noted that the road condition information here includes four levels: smooth traffic, slow traffic, congested traffic, and severe congestion. A congestion index is obtained by fitting the congestion level. The road condition is predicted based on the congestion index. Historical road condition assessment coefficients are obtained by evaluating changes in road conditions. Finally, historical traffic flow data is input into the traffic prediction model to obtain predicted road condition assessment coefficients. The predicted road condition assessment coefficients are compared and analyzed with historical road condition assessment coefficients. Early warnings are issued based on the analysis results. Timely early warnings ensure timely adjustment of road condition assessment coefficients and timely prediction and updating of real-time road condition status.

[0059] As one embodiment of the present invention, the state prediction analysis process in step S2 is as follows:

[0060] The time for acquiring surveillance image information is evenly divided into... Collect traffic flow data for congested road sections at any different time period. ,in, ;

[0061] Traffic flow data and the corresponding preset interval Compare them. , All are empirical constants;

[0062] like Greater than the preset range If the traffic flow exceeds the critical state, an early warning message will be generated.

[0063] like Less than the preset range If the traffic flow is below the critical state, the road conditions are relatively stable.

[0064] like Within the preset range If the traffic flow reaches a critical point, a road condition assessment and analysis will be conducted.

[0065] Through the above technical solution, this embodiment performs state prediction analysis in step S2. Specifically, firstly, the acquisition time of the monitoring image information is evenly divided into... Collect traffic flow data for congested road sections at any different time period. ,in, Then, the traffic flow data and the corresponding preset interval Compare them. , All are empirical constants; judgment if Greater than the preset range If the traffic flow exceeds the critical state, a warning message is generated; if... Less than the preset range If the traffic flow is below the critical state, the road conditions are relatively stable; if... Within the preset range If the traffic flow reaches a critical point, a road condition assessment and analysis will be conducted.

[0066] It should be noted that the preset interval It is a range obtained by analyzing and judging different road surface information, vehicle information, traffic rules, and past experience; the critical state is the degree of severe congestion when judging the number of vehicles. It can also be directly judged based on the set congestion index.

[0067] As one embodiment of the present invention, the road condition assessment and analysis is as follows:

[0068] According to the formula: * * Obtain road condition assessment coefficient ,in The transformation function is monotonically increasing. To start from the total time period The selected time period, and >1; To complete the vehicle speed change within the selected time period from Down to The cumulative capacity of the road section during the process; To complete the vehicle speed change within the selected time period from Down to The standard value for the cumulative capacity of vehicles on the road section during the process; for arrive The arithmetic mean; This is the vehicle information deviation coefficient.

[0069] Based on the above technical solution, in this embodiment, the road condition assessment and analysis is performed using the following formula: * * Obtain road condition assessment coefficient Specifically, the analysis is based on road condition assessment coefficients. The size of the road surface will be further adjusted to improve its operational status and facilitate the accurate selection of historical road condition assessment coefficients; among which, The transformation function is monotonically increasing, and its value belongs to the threshold range. ; To start from the total time period The selected time period; for arrive The arithmetic mean; for arrive The standard deviation reflects arrive The degree of data dispersion, that is, ensuring accuracy when the standard deviation is small. Adjust or maintain within the threshold range; for The vehicle speed was completed within a time period from The cumulative capacity of vehicles on the road section during the process of reducing speed to near zero; To complete the vehicle speed change within the selected time period from Down to The standard value of the cumulative capacity of the road section during the process; when The larger the value, the greater the impact on traffic congestion. for arrive The arithmetic mean; The deviation coefficient for vehicle information at the selected time.

[0070] As one embodiment of the present invention, the road condition assessment and analysis process includes:

[0071] Road condition assessment coefficient With preset interval [ , Compare sizes:

[0072] when If a significant change in road condition is detected, the current road condition evaluation coefficient is output as the historical road condition evaluation coefficient.

[0073] when < If the road condition changes are small, maintain the current operating status;

[0074] when > It can detect significant changes in road conditions and generate early warning information.

[0075] Through the above technical solution, the road condition assessment and analysis process in this embodiment includes: converting the road condition assessment coefficients... With preset interval [ , Compare sizes: when When a significant change in road condition is detected, the current road condition evaluation coefficient is output as the historical road condition evaluation coefficient; when < If the road condition changes little, maintain the current operating state; when > It can detect significant changes in road conditions and generate early warning information.

[0076] As one embodiment of the present invention, the process of establishing the traffic prediction model in step S3 is as follows:

[0077] S31. Collect historical traffic flow data for several time periods in the monitored area, select traffic flow data for each congested road segment for the corresponding time period, and generate training and test sets.

[0078] S32. Build a model using a recurrent neural network, train the model using a traffic flow training set, test the trained model using a test set, and adjust the number of iterations based on the test error.

[0079] S33. Repeat step S32 and refit the training set to adjust the test error to a smaller combined model. When the test error is too large, go to step S32.

[0080] S34. Output the estimated predicted value.

[0081] Through the above technical solution, this embodiment analyzes the specific process of establishing the traffic prediction model in step S3. For most cities, traffic flow is mainly affected by various factors such as congested locations, external weather, and modes of transportation. Many factors influence the prediction of traffic flow changes. This embodiment particularly emphasizes the continuous traffic congestion within a certain time frame. This state continuously affects the speed of the next wave of vehicles and the continuous increase in traffic flow on road sections. By constructing a traffic prediction model, the error in traffic flow prediction caused by this influence can be mitigated to a certain extent. The specific steps are as follows: First, collect historical traffic flow data for several time periods in the monitored area, select traffic flow data for each congested road section corresponding to the time period, and generate training and testing sets. Then, build a model using a recurrent neural network, train the model using the traffic flow training set, and test the trained model using the testing set, adjusting the iteration number based on the test error. Next, repeat step S32 and refit the training set, adjusting the test error to a smaller combined model. When the test error result is too large, return to step S32. Finally, output the estimated prediction value.

[0082] As one embodiment of the present invention, the formula for the predicted value is:

[0083]

[0084] Calculate and obtain traffic flow prediction coefficient ;in, , These represent the maximum and minimum values ​​of historical traffic flow within a certain time period, respectively. The parameter value representing the deviation of historical traffic flow over a certain period of time; is the prediction coefficient.

[0085] Based on the above technical solution, the predicted value in this embodiment is the traffic flow prediction coefficient, obtained through the formula... Calculate and obtain traffic flow prediction coefficient Traffic flow prediction coefficient It can largely reflect the impact of predicted traffic flow on road conditions, ensuring advance prediction of congestion on the next road segment and improving prediction efficiency; among them, , These represent the maximum and minimum values ​​of historical traffic flow within a certain time period, respectively. The parameter value representing the deviation of historical traffic flow over a certain period of time; is the prediction coefficient.

[0086] Note: Prediction coefficient It is obtained by fitting the predicted regression calculation and is closely related to the accuracy of the prediction; the deviation parameter value It is obtained through real-time analysis using an intelligent algorithm system.

[0087] As one embodiment of the present invention, based on traffic flow prediction coefficient The method for obtaining the predicted road condition assessment coefficient is as follows:

[0088] Through formula Calculate the predicted road condition assessment coefficient ,in, This is the road condition conversion coefficient.

[0089] Through the above technical solution, this embodiment uses a traffic flow prediction coefficient. The predicted road condition assessment coefficient is obtained using the formula. Calculate the predicted road condition assessment coefficient By predicting road condition evaluation coefficients It can largely analyze predicted road conditions in advance and determine whether the current assessment status matches the historical assessment coefficient status. This is the road condition conversion factor. It is derived from the correlation between traffic flow prediction coefficient and road condition assessment, which will not be elaborated here.

[0090] In one embodiment of the present invention, the comparison and analysis process in step S3 is as follows:

[0091] Predicted road condition assessment coefficient Historical road condition assessment coefficient Compare:

[0092] like ≥ If so, a warning signal will be issued; traffic flow will be adjusted.

[0093] Otherwise, continue running.

[0094] Through the above technical solution, this embodiment uses the predicted road condition evaluation coefficient. Historical road condition assessment coefficient Adjusting traffic conditions under current monitoring to promptly adjust the critical capacity of traffic flow can prevent traffic accidents and reduce the significant impact of traffic congestion on the next flow of vehicles. By diverting and guiding traffic flow in advance, providing speed reduction reminders, and adjusting traffic light timings, it can reduce the occurrence of severe congestion, improve traffic efficiency, and decrease the probability of traffic accidents.

[0095] A smart traffic management system based on traffic flow was also designed; please refer to [link / reference]. Figure 2 As shown, the system includes:

[0096] The data acquisition module is used to collect historical traffic flow data of the monitored area within a specific time period;

[0097] The real-time monitoring module is used to retrieve historical monitoring images of congested road sections to monitor vehicle information parameters in real time.

[0098] The analysis module is used to perform state prediction analysis on road segment vehicle information parameters, evaluate road condition change information, and obtain historical road condition evaluation coefficients.

[0099] Traffic prediction models are used to obtain predicted road condition assessment coefficients based on historical traffic flow data;

[0100] The comparison module is used to compare and analyze the predicted road condition assessment coefficients and the historical road condition assessment coefficients;

[0101] The early warning module is used to issue early warning information when the monitored traffic flow status does not meet the requirements, when the road condition assessment and analysis results do not meet the requirements, and when the comparison and analysis results do not meet the requirements.

[0102] The information synchronization module is used to synchronize vehicle and road condition traffic information to the query platform in real time.

[0103] Through the above technical solution, this embodiment establishes a traffic flow-based intelligent traffic management system. Specifically, it includes a data acquisition module for collecting historical traffic flow data of the monitored area within a specific time period; a real-time monitoring module for retrieving vehicle information parameters from historical monitoring images of congested road sections in real time; an analysis module for performing state prediction analysis on the vehicle information parameters, assessing road condition changes, and obtaining historical road condition assessment coefficients; a traffic prediction model for obtaining predicted road condition assessment coefficients based on historical traffic flow data; a comparison module for comparing and analyzing the predicted road condition assessment coefficients with historical road condition assessment coefficients; an early warning module for issuing warnings when the monitored traffic flow status, road condition assessment results, and comparison analysis results do not meet requirements; and an information synchronization module for synchronizing vehicle and road condition traffic information to the query platform in real time.

[0104] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in the claims, they should all fall within the protection scope of the present invention.

Claims

1. A smart traffic management method based on traffic flow, characterized in that, The method includes: S1. Collect historical traffic flow data of the monitored area within a specific time period; S2. Real-time retrieval of historical monitoring images of congested road sections to monitor road vehicle information parameters, conduct state prediction analysis of road vehicle information parameters, assess road condition change information, and obtain historical road condition assessment coefficients. S3. Input historical traffic flow data into the traffic prediction model to obtain the predicted road condition evaluation coefficient. Compare and analyze the predicted road condition evaluation coefficient with the historical road condition evaluation coefficient, and issue warnings based on the analysis results. The state prediction and analysis process in step S2 is as follows: The time for acquiring surveillance image information is evenly divided into... Collect traffic flow data for congested road sections at any different time period. ,in, ; Traffic flow data and the corresponding preset interval Compare them. , All are empirical constants; like Greater than the preset range If the traffic flow exceeds the critical state, an early warning message will be generated. like Less than the preset range If the traffic flow is below the critical state, the road conditions are relatively stable. like Within the preset range If the traffic flow reaches a critical point, a road condition assessment and analysis will be conducted. The road condition assessment and analysis includes: According to the formula: * * Obtain road condition assessment coefficient ,in The transformation function is monotonically increasing. To start from the total time period The selected time period, and >1; To complete the vehicle speed change within the selected time period from Down to The cumulative capacity of the road section during the process; To complete the vehicle speed change within the selected time period from Down to The standard value for the cumulative capacity of vehicles on the road section during the process; Traffic flow data for congested road sections at different time periods; for arrive The arithmetic mean; This is the vehicle information deviation coefficient; The road condition assessment and analysis process includes: Road condition assessment coefficient With preset interval [ , Compare sizes: when If a significant change in road condition is detected, the current road condition evaluation coefficient is output as the historical road condition evaluation coefficient. when < If the road condition changes are small, maintain the current operating status; when > It can detect significant changes in road conditions and generate early warning information.

2. The intelligent traffic management method based on traffic flow according to claim 1, characterized in that, The process of establishing the traffic prediction model in step S3 is as follows: S31. Collect historical traffic flow data for several time periods in the monitored area, select traffic flow data for each congested road segment for the corresponding time period, and generate training and test sets. S32. Build a model using a recurrent neural network, train the model using a traffic flow training set, test the trained model using a test set, and adjust the number of iterations based on the test error. S33. Repeat step S32 and refit the training set to adjust the test error to a smaller combined model. When the test error is too large, go to step S32. S34, Output estimated traffic flow prediction coefficients.

3. The intelligent traffic management method based on traffic flow according to claim 2, characterized in that, The formula for the traffic flow prediction coefficient is: ； Calculate and obtain traffic flow prediction coefficient ;in, , These represent the maximum and minimum values ​​of historical traffic flow within a certain time period, respectively. The parameter value representing the deviation of historical traffic flow over a certain period of time; is the prediction coefficient.

4. The intelligent traffic management method based on traffic flow according to claim 3, characterized in that, Based on traffic flow prediction coefficient The method for obtaining the predicted road condition assessment coefficient is as follows: Through formula Calculate the predicted road condition assessment coefficient ,in, This is the road condition conversion coefficient.

5. The intelligent traffic management method based on traffic flow according to claim 1, characterized in that, In step S3, the comparison and analysis process is as follows: Predicted road condition assessment coefficient Historical road condition assessment coefficient Compare: like ≥ If so, a warning signal will be issued; traffic flow will be adjusted. Otherwise, continue running.

6. A traffic flow-based intelligent traffic management system, used to implement the traffic flow-based intelligent traffic management method as described in claim 1, characterized in that, The system includes: The data acquisition module is used to collect historical traffic flow data of the monitored area within a specific time period; The real-time monitoring module is used to retrieve historical monitoring images of congested road sections to monitor vehicle information parameters in real time. The analysis module is used to perform state prediction analysis on road segment vehicle information parameters, evaluate road condition change information, and obtain historical road condition evaluation coefficients. Traffic prediction models are used to obtain predicted road condition assessment coefficients based on historical traffic flow data; The comparison module is used to compare and analyze the predicted road condition assessment coefficients and the historical road condition assessment coefficients; The early warning module is used to issue early warning information when the monitored traffic flow status does not meet the requirements, when the road condition assessment and analysis results do not meet the requirements, and when the comparison and analysis results do not meet the requirements. The information synchronization module is used to synchronize vehicle and road condition traffic information to the query platform in real time.

Images