C-V2X-based traffic monitoring management method and system

Abstract

The invention discloses a C-V2X-based traffic monitoring management method and a C-V2X-based traffic monitoring management system, relates to the technical field of path planning, and solves the problems of relatively single influence factor and insufficient individuation degree of path planning in the prior art. Various data including vehicle driving data and traffic flow data are collected, a traffic flow model is constructed based on the traffic flow data to predict the traffic flow, then a clustering algorithm is adopted to construct a vehicle driving behavior model, vehicles are classified based on the vehicle driving data, and finally a target function is established to predict the traffic flow. And calculating an optimal driving route for each vehicle based on the traffic flow model and the vehicle driving behavior model. According to the method, data of more dimensions, such as driving behaviors, driving habits and vehicle types of vehicles, can be introduced into path planning, so that more personalized and accurate path planning is realized, the requirements of different drivers are met, and the overall efficiency and safety of a traffic system are improved.

Description

Technical Field

[0001] This invention relates to the field of route planning technology, and in particular to a traffic monitoring and management method and system based on C-V2X. Background Technology

[0002] With the rapid development of intelligent transportation technology, traffic monitoring and management systems based on C-V2X (Cellular Vehicle-to-Everything) are gradually becoming a key means to improve urban traffic efficiency and safety. C-V2X technology connects vehicles to vehicles (V2V), vehicles to infrastructure (V2I), vehicles to networks (V2N), and vehicles to pedestrians (V2P), enabling real-time sharing and interaction of traffic information. The core advantage of this technology lies in its ability to monitor traffic flow in real time and provide dynamic route planning for each vehicle based on traffic flow data. By deploying a large number of sensing devices and roadside communication units (RSUs), the system can collect real-time traffic flow information for road segments, including vehicle density, speed distribution, and congestion levels. Based on this data, the traffic management system uses advanced algorithm models to predict traffic flow trends and generate optimal routes for vehicles, thereby effectively alleviating traffic congestion and improving road capacity. For example, during peak hours, the system can guide vehicles to avoid congested sections and choose alternative routes with lower traffic volume, ensuring smooth traffic flow. This traffic flow-based route planning method not only improves traffic efficiency but also reduces vehicle fuel consumption and exhaust emissions, thus having a positive impact on environmental protection.

[0003] While C-V2X-based traffic monitoring and management has made significant progress in utilizing traffic flow data for route planning, existing systems still have some shortcomings. First, current route planning methods rely primarily on traffic flow as a single factor, neglecting personalized characteristics such as vehicle driving behavior and habits. In real-world traffic environments, different drivers have significantly different driving styles; some prefer smooth driving, while others may favor aggressive driving. These differences in driving behavior have a substantial impact on vehicle safety and traffic efficiency. However, existing route planning systems fail to adequately consider these personalized factors, resulting in planned routes that may not fully meet the driver's actual needs. For example, for vehicles with aggressive driving, the system may guide them to road sections unsuitable for their driving style, increasing the risk of traffic accidents; while for vehicles with smooth driving, the system may not fully utilize the advantages of their driving habits, leading to suboptimal route planning. Route planning methods that solely rely on traffic flow may not provide sufficiently flexible and accurate solutions when facing complex traffic scenarios.

[0004] Therefore, a traffic monitoring and management method and system based on C-V2X is needed. Summary of the Invention

[0005] To address the issue that existing route planning technologies often rely on only one factor—traffic flow—and fail to consider individual vehicle driving behavior and habits, resulting in insufficient personalization, this invention provides a C-V2X-based traffic monitoring and management method and system. This method incorporates more dimensions of data into route planning, such as vehicle driving behavior, habits, and vehicle type, to achieve more personalized and accurate route planning, meeting the needs of different drivers and improving the overall efficiency and safety of the traffic system. The specific technical solution is as follows: A traffic monitoring and management method based on C-V2X includes the following steps: Data is collected, including vehicle driving data and traffic flow data; Traffic flow models are built based on traffic flow data to predict traffic flow. A clustering algorithm is used to construct a vehicle driving behavior model, and vehicles are classified based on vehicle driving data; An objective function is established, and based on the traffic flow model and vehicle driving behavior model, the optimal driving route is calculated for each vehicle. The objective function is expressed as follows: In the formula, N is the total number of vehicles, and i is the index of the vehicle. and These represent the start and end points of time, respectively. Indicates basic operating costs. These are the weighting coefficients. Indicates traffic flow cost, Indicates stability cost, Indicates the cost of complex road sections. Indicates peak-hour costs; The objective function is solved to obtain the optimal driving route, which is then transmitted via C-V2X.

[0006] Preferably, vehicle driving data includes speed, acceleration, position, lane change frequency, and braking frequency; traffic flow data includes road segment traffic flow and road segment congestion.

[0007] Preferred, The calculations include driving time, fuel consumption, and distance, as detailed below: In the formula, Indicates the weighting coefficient. Indicates travel time. Indicates fuel consumption. Indicates the distance traveled.

[0008] Preferred, traffic flow cost The formula for calculating the cost of driving a vehicle on a high-traffic road is as follows: In the formula, It is the traffic flow predicted by the traffic flow model for road segment (i,j) at time t. It is an indicator function, which is 1 when vehicle i is on road segment (i,j) and 0 otherwise.

[0009] Preferred weighting coefficient To balance the relationship between different costs, adjustments are made based on the output of the vehicle's driving behavior model, which includes smooth driving and aggressive driving, as detailed below: Smooth driving: Increase The weight, reduce and The weights; Aggressive driving vehicles: Increase and The weight, reduce The weight.

[0010] Preferably, the process of constructing the traffic flow model is as follows: S201: Data collection: Collect the traffic flow of each road segment (i,j) at time t, the congestion of each road segment (i,j) at time t, as well as weather conditions, holiday information, special events, and record the time point of each data collection. S202: Data preprocessing: including data cleaning and data normalization; S203: Feature Extraction: Extract at least the following features, including time features, traffic features, and other features, to form a feature vector. The feature vector is represented as follows: In the formula, Indicates the number of hours in a day. It indicates a day of the week. Does Best Express operate on holidays? This indicates the traffic flow in the previous time period. This indicates the congestion situation in the previous time period. Indicates weather conditions. This indicates a special event, which includes at least road construction and accidents.

[0011] S204: A Long Short-Term Memory (LSTM) network model is used. During model training, the data is divided into training and validation sets. Mean squared error is used as the loss function, and backpropagation and optimization algorithms are used for training. The loss function is expressed as follows: In the formula, is the weighting coefficient, and MSE() is the mean squared error.

[0012] Preferably, the process for obtaining the vehicle driving behavior model is as follows: S301: Acquire speed, acceleration, position, lane change frequency, and braking frequency, and acquire the time point of each data acquisition; S302: Data preprocessing: including data cleaning and data normalization; S303: Obtain the feature vector after feature extraction. , means as follows: In the formula, This represents the average speed of the vehicle over the statistical period. The standard deviation of vehicle acceleration reflects the degree of acceleration and deceleration. This indicates the number of lane changes a vehicle made within the statistical period. The number of times the vehicle braked within the statistical time period. This indicates the number of times the vehicle accelerated rapidly within the statistical time period. This indicates the number of times the vehicle braked suddenly within the statistical period.

[0013] S304: Using the K-means clustering algorithm, data points are divided into K categories, making the data points in each category as similar as possible. A suitable number of categories K is selected, and K data points are randomly selected as the initial cluster centers. Then, each data point is assigned to the nearest cluster center, and the cluster center is updated to the mean of all data points assigned to that category. Finally, the process is repeated until the cluster centers no longer change or the maximum number of iterations is reached.

[0014] A C-V2X-based traffic monitoring and management system, applied to the method described above, includes: Roadside units: Deployed in key traffic areas to communicate with vehicles and broadcast traffic light status, road conditions, and traffic flow; Sensing devices include high-definition cameras, radar, and weather sensors, used to collect real-time traffic flow, vehicle speed, road conditions, and weather information; Edge computing nodes: Deployed at the edge of the road, they perform real-time processing and preliminary analysis of data collected by sensing devices, reducing data transmission latency; Communication network: 5G network or other high-speed communication network to ensure stable and reliable communication between vehicles, between vehicles and roads, and between vehicles and the network; Cloud Platform: Through onboard units, the system collects real-time data on vehicle speed, acceleration, location, direction of travel, and driving habits, and uploads it to the cloud platform. The cloud platform analyzes the collected traffic flow data in real time, combines it with historical data to predict traffic flow trends, identify congested areas and time periods, and analyzes data such as vehicle speed, acceleration, and driving habits to establish vehicle driving behavior models, providing a basis for route planning.

[0015] A computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the C-V2X-based traffic monitoring and management method as described above.

[0016] A processor for running a program, wherein the program executes the C-V2X-based traffic monitoring and management method as described above.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention collects various data, including vehicle driving data and traffic flow data. Based on the traffic flow data, it constructs a traffic flow model to predict traffic flow. Subsequently, it employs a clustering algorithm to build a vehicle driving behavior model, classifying vehicles based on their driving data. Finally, it establishes an objective function and calculates the optimal route for each vehicle based on the traffic flow model and the vehicle driving behavior model. This allows for the incorporation of more dimensions of data into route planning, such as vehicle driving behavior, driving habits, and vehicle type, to achieve more personalized and accurate route planning, meeting the needs of different drivers and improving the overall efficiency and safety of the transportation system. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0019] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0020] 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, not all, of the embodiments of the present invention. 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.

[0021] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0022] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] In one embodiment of the present invention, a traffic monitoring and management method based on C-V2X is provided, such as... Figure 1 As shown, it includes the following steps: Step 1: Collect data, including vehicle driving data and traffic flow data. In addition, each data item records the time point of data collection, and the vehicle driving data is marked with a unique vehicle identifier to distinguish the data of different vehicles.

[0025] For example, vehicle driving data includes speed, acceleration, position, lane change frequency, and braking frequency; traffic flow data includes road segment traffic flow and road segment congestion.

[0026] For example, traffic flow data for different time periods is collected through RSUs and sensing devices, including vehicle speed, location, and direction of travel; and missing, duplicate, and outlier values ​​are processed. For example, missing trajectory point data is supplemented using front-to-back average interpolation.

[0027] Step 2: Construct a traffic flow model to predict traffic flow, as detailed below: S201: Data Collection: Collect the traffic flow (unit: vehicles / hour) of each road segment (i,j) at time t, and the congestion status of each road segment (i,j) at time t (for example, 0 indicates no congestion, 1 indicates severe congestion), and record the time point of each data collection. In addition, collect weather conditions, holiday information, and special events (such as road construction, accidents).

[0028] S202: Data preprocessing: including data cleaning and data normalization.

[0029] For example, data cleaning specifically involves removing missing and outlier values; interpolating missing values ​​(e.g., linear interpolation); smoothing outliers (e.g., moving average filtering); and data normalization specifically involves normalizing traffic flow and congestion to the range of [0, 1] and standardizing timestamps (e.g., converting time into hours of the day).

[0030] S203: Feature Extraction: Extract at least the features including time features, traffic features and other features to form a feature vector.

[0031] For example, the feature vector is represented as follows: In the formula, Indicates the number of hours in a day. It indicates a day of the week. Does Best Express operate on holidays? This indicates the traffic flow in the previous time period. This indicates the congestion situation in the previous time period. Indicates weather conditions. This indicates a special event, which includes at least road construction and accidents.

[0032] S204: Uses a Long Short-Term Memory (LSTM) network model, where the input layer of the model receives feature vectors. The model's LSTM layer processes time-series data and captures temporal dependencies; the model's output layer outputs the predicted traffic flow. and congestion situation During model training, the data is divided into training and validation sets. Mean squared error (MSE) is used as the loss function, and backpropagation and optimization algorithms (such as Adam) are employed for training. The loss function is expressed as follows: In the formula, is the weighting coefficient, and MSE() is the mean squared error.

[0033] S205: Model Validation. Based on the validation dataset, the model performance is evaluated using metrics such as mean squared error (MSE) and mean absolute error (MAE). A comparison chart of predicted and actual values ​​is plotted to intuitively evaluate the model's effectiveness. The model parameters (such as the number of units in the LSTM layer and the learning rate) are adjusted according to the validation results, and the model is retrained and validated until the model performance reaches a satisfactory level.

[0034] Step 3: Construct a vehicle driving behavior model and classify vehicles based on driving data; the specific steps are as follows: S301: Acquire speed, acceleration, position, lane change frequency, and braking frequency, and acquire the time point of each data acquisition.

[0035] S302: Data preprocessing: including data cleaning and data normalization.

[0036] For example, data cleaning specifically involves removing missing and outlier values; interpolating missing values ​​(e.g., linear interpolation); smoothing outliers (e.g., moving average filtering); and data normalization specifically involves normalizing traffic flow and congestion to the range of [0, 1] and standardizing timestamps (e.g., converting time into hours of the day).

[0037] S303: Obtain the feature vector after feature extraction. , means as follows: In the formula, This represents the average speed of the vehicle over the statistical period (a set time period, the same below). The standard deviation of vehicle acceleration reflects the degree of acceleration and deceleration. This indicates the number of lane changes a vehicle made within the statistical period. The number of times the vehicle braked within the statistical time period. This indicates the number of times the vehicle accelerates rapidly within a statistical period (acceleration exceeding a certain threshold). θ accelerate), This indicates the number of times the vehicle braked suddenly within the statistical period (deceleration exceeding a certain threshold). θ brake).

[0038] S304: Use the K-means clustering algorithm to divide data points into K categories, making the data points in each category as similar as possible. Choose an appropriate number of categories K (e.g., 2, representing smooth driving and aggressive driving), and randomly select K data points as initial cluster centers. Then, assign each data point to the nearest cluster center, update the cluster center to the mean of all data points assigned to that category, and finally repeat the loop until the cluster centers no longer change or the maximum number of iterations is reached.

[0039] S305: Use the silhouette coefficient to evaluate the quality of the clustering results, plot the clustering results, visually assess the rationality of the category division, adjust the number of categories K or other parameters based on the validation results, and retrain and validate until the clustering results reach a satisfactory level.

[0040] Step 4: Establish the objective function and calculate the optimal route for each vehicle based on the traffic flow model and vehicle driving behavior model.

[0041] In this embodiment, weights or constraints related to driving behavior are introduced into the objective function to construct an objective function that can satisfy different driving preferences, and then route planning is optimized according to the driver's preferences (such as smooth driving or aggressive driving).

[0042] The objective function is expressed as follows: In the formula, N is the total number of vehicles, and i is the index of the vehicle, representing the i-th vehicle. and These represent the start and end points of time, respectively, indicating the time interval from the start to the end of the journey. Indicates basic operating costs. These are the weighting coefficients. This indicates the position of the i-th car at time t. This represents the speed of the i-th vehicle at time t. Indicates traffic flow cost, Indicates stability cost, Indicates the cost of complex road sections. This indicates the cost during peak hours.

[0043] in, The calculations include driving time, fuel consumption, and distance, as detailed below: In the formula, Indicates the weighting coefficient. Indicates travel time. Indicates fuel consumption. Indicates the distance traveled.

[0044] Traffic flow cost The formula for calculating the cost of driving a vehicle on a high-traffic road is as follows: In the formula, It is the traffic flow predicted by the traffic flow model for road segment (i,j) at time t. It is an indicator function, which is 1 when vehicle i is on road segment (i,j) and 0 otherwise.

[0045] Stability Costs The formula used to measure the change in acceleration during vehicle movement is as follows: In the formula, This represents the change in acceleration of the vehicle on road segment (i,j).

[0046] Cost of complex road sections The formula for measuring the cost of driving a vehicle on complex road sections is as follows: In the formula, It is a complexity index of road segment (i,j), which is set in advance by humans.

[0047] Peak period costs The formula for measuring the cost of driving a vehicle during peak hours is as follows: In the formula, It is the peak hour weight of road segment (i,j) at time t, which is set in advance by humans.

[0048] It should be understood that, apart from data that can be obtained through models or sensors, all other data can be set and adjusted by those skilled in the art based on actual conditions, and this application does not impose any restrictions.

[0049] Among them, the weighting coefficient These weights are used to balance the relationships between different costs. These weights can be adjusted based on the vehicle's driving behavior (e.g., smooth driving or aggressive driving). That is, the output of the vehicle driving behavior model. (e.g., smooth driving or aggressive driving) is weighted by coefficients. This is manifested in the following ways: Drive the vehicle smoothly: Increase The weighting is adjusted to reduce road sections with large acceleration changes.

[0050] Decrease and The weighting allows vehicles to travel on complex road sections and during peak hours.

[0051] Aggressive driving: Increase and The weighting should be adjusted to avoid complex road sections and peak hours.

[0052] Decrease The weighting allows vehicles to travel on road sections with large changes in acceleration.

[0053] For example, when hour, ; ; ;when hour, ; ; .

[0054] By adjusting the weighting coefficients The objective function can dynamically adjust the route planning results based on the vehicle's driving behavior. The output of the vehicle driving behavior model... These weighting coefficients are reflected in the objective function, thereby enabling personalized route planning for vehicles with different driving behaviors.

[0055] In one embodiment of the present invention, a C-V2X-based traffic monitoring and management system is provided, comprising: Roadside Units (RSUs): Deployed in key traffic areas, such as intersections, highway entrances and exits, and congested road sections, they communicate with vehicles and broadcast information such as traffic light status, road conditions, and traffic flow. RSUs and sensing devices collect data such as traffic flow, road conditions, and weather information, and after preliminary processing by MEC, they are uploaded to the cloud platform.

[0056] Sensing devices include high-definition cameras, radar, and weather sensors, used to collect data such as traffic flow, vehicle speed, road conditions, and weather information in real time.

[0057] Edge computing nodes (MECs): Deployed at the edge of the road, they perform real-time processing and preliminary analysis of data collected by sensing devices, reducing data transmission latency.

[0058] Communication network: 5G network or other high-speed communication network to ensure stable and reliable communication between vehicles (V2V), vehicles and roads (V2I), and vehicles and networks (V2N).

[0059] Cloud Platform: The platform collects real-time data on vehicle speed, acceleration, location, direction of travel, and driving habits (such as frequent lane changes, rapid acceleration / deceleration) via on-board units (OBUs) and uploads this information to the cloud platform. The cloud platform analyzes the collected traffic flow data in real time, combines it with historical data to predict traffic flow trends, identify congested areas and time periods, and analyzes vehicle speed, acceleration, and driving habits to build vehicle behavior models, providing a basis for route planning.

[0060] In summary, this invention collects various data, including vehicle driving data and traffic flow data, and constructs a traffic flow model based on the traffic flow data to predict traffic flow. Subsequently, a clustering algorithm is used to construct a vehicle driving behavior model, classifying vehicles based on driving data. Finally, an objective function is established, and the optimal driving route is calculated for each vehicle based on the traffic flow model and the vehicle driving behavior model. This allows for the incorporation of more dimensional data into route planning, such as vehicle driving behavior, driving habits, and vehicle type, to achieve more personalized and accurate route planning, meeting the needs of different drivers and improving the overall efficiency and safety of the transportation system.

[0061] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0062] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0063] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0064] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A traffic monitoring and management method based on C-V2X, characterized in that, Includes the following steps: Data is collected, including vehicle driving data and traffic flow data; Traffic flow models are built based on traffic flow data to predict traffic flow. A clustering algorithm is used to construct a vehicle driving behavior model, and vehicles are classified based on vehicle driving data; An objective function is established, and based on the traffic flow model and vehicle driving behavior model, the optimal driving route is calculated for each vehicle. The objective function is expressed as follows: In the formula, N is the total number of vehicles, and i is the index of the vehicle. and These represent the start and end points of time, respectively. Indicates basic operating costs. These are the weighting coefficients. Indicates traffic flow cost, Indicates stability cost, Indicates the cost of complex road sections. Indicates peak-hour costs; The objective function is solved to obtain the optimal driving route, which is then transmitted via C-V2X.

2. The traffic monitoring and management method based on C-V2X according to claim 1, characterized in that, Vehicle driving data includes speed, acceleration, position, lane change frequency, and braking frequency; traffic flow data includes road segment traffic flow and road segment congestion.

3. The traffic monitoring and management method based on C-V2X according to claim 1, characterized in that, The calculations include driving time, fuel consumption, and distance, as detailed below: In the formula, Indicates the weighting coefficient. Indicates travel time. Indicates fuel consumption. Indicates the distance traveled.

4. The traffic monitoring and management method based on C-V2X according to claim 1, characterized in that, Traffic flow cost The formula for calculating the cost of driving a vehicle on a high-traffic road is as follows: In the formula, It is the traffic flow predicted by the traffic flow model for road segment (i,j) at time t. It is an indicator function, which is 1 when vehicle i is on road segment (i,j) and 0 otherwise.

5. A traffic monitoring and management method based on C-V2X according to claim 4, characterized in that, Weighting coefficient To balance the relationship between different costs, adjustments are made based on the output of the vehicle's driving behavior model, which includes smooth driving and aggressive driving, as detailed below: Smooth driving: Increase The weight, reduce and The weights; Aggressive driving vehicles: Increase and The weight, reduce The weight.

6. A traffic monitoring and management method based on C-V2X according to claim 1, characterized in that, The process of constructing the traffic flow model is as follows: S201: Data collection: Collect the traffic flow of each road segment (i,j) at time t, the congestion of each road segment (i,j) at time t, as well as weather conditions, holiday information, special events, and record the time point of each data collection. S202: Data preprocessing: including data cleaning and data normalization; S203: Feature Extraction: Extract at least the following features, including time features, traffic features, and other features, to form a feature vector. The feature vector is represented as follows: In the formula, Indicates the number of hours in a day. It indicates a day of the week. Does Best Express operate on holidays? This indicates the traffic flow in the previous time period. This indicates the congestion situation in the previous time period. Indicates weather conditions. This indicates a special event, which includes at least road construction and accidents. S204: A Long Short-Term Memory (LSTM) network model is used. During model training, the data is divided into training and validation sets. Mean squared error is used as the loss function, and backpropagation and optimization algorithms are used for training. The loss function is expressed as follows: In the formula, is the weighting coefficient, and MSE() is the mean squared error.

7. A traffic monitoring and management method based on C-V2X according to claim 1, characterized in that, The process of obtaining the vehicle driving behavior model is as follows: S301: Acquire speed, acceleration, position, lane change frequency, and braking frequency, and acquire the time point of each data acquisition; S302: Data preprocessing: including data cleaning and data normalization; S303: Obtain the feature vector after feature extraction. , means as follows: In the formula, This represents the average speed of the vehicle over the statistical period. The standard deviation of vehicle acceleration reflects the degree of acceleration and deceleration. This indicates the number of lane changes a vehicle made within the statistical period. The number of times the vehicle braked within the statistical time period. This indicates the number of times the vehicle accelerated rapidly within the statistical time period. This indicates the number of times the vehicle braked suddenly within the statistical period. S304: Using the K-means clustering algorithm, data points are divided into K categories, making the data points in each category as similar as possible. A suitable number of categories K is selected, and K data points are randomly selected as the initial cluster centers. Then, each data point is assigned to the nearest cluster center, and the cluster center is updated to the mean of all data points assigned to that category. Finally, the process is repeated until the cluster centers no longer change or the maximum number of iterations is reached.

8. A traffic monitoring and management system based on C-V2X, characterized in that, The method applied to any one of claims 1 to 7 includes: Roadside units: Deployed in key traffic areas to communicate with vehicles and broadcast traffic light status, road conditions, and traffic flow; Sensing devices include high-definition cameras, radar, and weather sensors, used to collect real-time traffic flow, vehicle speed, road conditions, and weather information; Edge computing nodes: Deployed at the edge of the road, they perform real-time processing and preliminary analysis of data collected by sensing devices, reducing data transmission latency; Communication network: 5G network or other high-speed communication network to ensure stable and reliable communication between vehicles, between vehicles and roads, and between vehicles and the network; Cloud Platform: Through onboard units, the system collects real-time data on vehicle speed, acceleration, location, direction of travel, and driving habits, and uploads it to the cloud platform. The cloud platform analyzes the collected traffic flow data in real time, combines it with historical data to predict traffic flow trends, identify congested areas and time periods, and analyzes data such as vehicle speed, acceleration, and driving habits to establish vehicle driving behavior models, providing a basis for route planning.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the C-V2X-based traffic monitoring and management method according to any one of claims 1 to 7.

10. A processor, characterized in that, The processor is used to run a program, wherein the program executes the C-V2X-based traffic monitoring and management method according to any one of claims 1 to 7.

Images