Vehicle driving intelligent control method and device

Abstract

The embodiments of the present application provide a method and device for intelligent vehicle driving control, which realizes multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle's driving trajectory, and the traffic flow prediction and risk assessment model is trained at the edge. The cloud platform integrates data from multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a method and device for intelligent vehicle driving control. Background Art

[0002] Existing intelligent vehicle control methods have significant shortcomings. Traditional systems often rely on a single onboard device for road condition perception, lacking coordination with roadside equipment, making it difficult to achieve comprehensive traffic scene perception.

[0003] Furthermore, existing technologies face bottlenecks in data processing and early warning. Most systems fail to establish effective regional linkage mechanisms and lack the ability to intelligently predict and assess risks based on multi-source data, resulting in delayed or inaccurate early warning information.

[0004] Existing systems have technical shortcomings in traffic flow prediction and road condition analysis. They lack comprehensive consideration of environmental factors and struggle to provide timely and accurate driving recommendations for complex road conditions. Addressing these issues is crucial for improving the intelligence and practicality of assisted driving systems. Summary of the Invention

[0005] In response to the problems in the existing technology, this application provides a method and device for intelligent vehicle driving control, which can effectively solve the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improve the intelligence level and service quality of the assisted driving system.

[0006] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a vehicle driving intelligent control method, comprising:

[0008] Analysis and identification units are set up along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. On-board modules are deployed on the vehicle side. The on-board modules establish a connection with and register with the cloud platform via the Internet of Things communication module. The on-board modules call the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks.

[0009] The license plate capture camera obtains the vehicle's license plate number, license plate color and vehicle model information, the wide-angle camera obtains real-time road images, the environmental detection equipment obtains road visibility and road surface state parameters, the edge box extracts vehicle driving characteristics based on the real-time road images, the edge box trains a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and sends the vehicle driving characteristics, traffic flow prediction results, risk assessment values ​​and environmental parameters collected by each analysis and recognition unit to the cloud platform;

[0010] The cloud platform receives data uploaded by multiple analysis and identification units, and determines whether to trigger regional linkage based on a preset road traffic strategy and the risk assessment value. When regional linkage is triggered, a linkage instruction is issued to the relevant analysis and identification units according to the regional linkage network and a communication link is established. The cloud platform receives the traffic flow prediction results uploaded by the relevant analysis and identification units, and generates warning information including real-time road conditions, recommended detour routes and safe vehicle speeds based on the traffic flow prediction results, and sends it to the vehicle-mounted module corresponding to the license plate number for broadcast.

[0011] Furthermore, the method further includes: selecting a key location on the road to deploy the analysis and identification unit, initializing parameters of the edge box, the edge box obtaining a unique identification code through an IoT communication module, sending a registration request to the cloud platform based on the unique identification code, the cloud platform returning registration authorization information, and the edge box establishing a secure communication link with the cloud platform based on the registration authorization information;

[0012] The edge box establishes a communication connection with the smart camera and the environmental detection device, calibrates the angle and focal length of the smart camera, sets the license plate capture camera to point in the direction of vehicle traffic, and sets the wide-angle camera to a panoramic road monitoring angle. A sub-device management group is established with the edge box as the center, and the sampling period and trigger threshold of the environmental detection device are configured. The edge box obtains environmental parameters including visibility, temperature, humidity and light intensity from the environmental detection device at preset time intervals.

[0013] Furthermore, the method further includes: the vehicle-mounted module obtains a unique device identifier through the Internet of Things communication module, sends a registration request including the vehicle VIN code to the cloud platform based on the unique device identifier, the cloud platform returns a device authorization code, the vehicle-mounted module establishes a data transmission channel with the cloud platform based on the device authorization code, and the vehicle-mounted module calls the vehicle computer CAN bus interface to collect the vehicle's real-time position coordinates, driving speed and direction angle data;

[0014] The on-board module uploads the position coordinates, driving speed and direction angle data to the cloud platform at preset time intervals. The cloud platform maps the vehicle position coordinates to an electronic map based on a geographic information system, determines a forward predicted path according to the vehicle's driving direction, extracts the analysis and identification units within the coverage of the predicted path, constructs the extracted analysis and identification units into a regional linkage network, and assigns a network priority to each of the analysis and identification units.

[0015] Furthermore, the method further includes: the license plate capture camera collects image data of a vehicle passing by; the edge box processes the image data based on a convolutional neural network model, extracts license plate area features and performs character segmentation, recognizes the license plate number and color information, analyzes vehicle body contour features through a deep learning model to obtain a vehicle model classification result, and stores the license plate number, color information, and vehicle model classification result in a cache database of the edge box;

[0016] The wide-angle camera collects road traffic video streams at a preset frame rate. The environmental detection equipment obtains visibility values ​​based on the laser ranging principle and detects road surface state parameters through surface temperature sensors and humidity sensors. The edge box performs target detection and tracking processing on the video stream, extracts driving characteristic parameters such as vehicle traffic trajectory, vehicle speed, and vehicle spacing, and establishes a mapping relationship between the driving characteristic parameters and license plate information.

[0017] Furthermore, the method further includes: the edge box divides the vehicle driving characteristic parameters into a training data set according to a time series, uses a long short-term memory neural network to construct a network structure of a traffic flow prediction model, uses vehicle speed, vehicle density, and travel time as input features, iteratively trains the network structure to obtain a traffic flow prediction model, constructs a risk assessment model based on a decision tree algorithm, and uses vehicle spacing, relative speed, and road surface state parameters as input variables to calculate a collision risk assessment value;

[0018] The edge box organizes the vehicle driving characteristics, environmental parameters and timestamp information into a data packet, which contains the future traffic flow state prediction results output by the traffic flow prediction model and the risk assessment value calculated by the risk assessment model. The edge box sends the data packet to the cloud platform through a secure communication link according to a preset data upload cycle, and the cloud platform performs time synchronization and data verification on the received data packet.

[0019] Furthermore, the method further includes: the cloud platform receiving data packets uploaded by a plurality of the analysis and identification units, extracting the risk assessment value, traffic flow, speed and other index parameters from the data packets, comparing the index parameters with thresholds in a road traffic strategy, wherein the road traffic strategy includes a traffic flow density threshold, an average speed threshold, and a unit mileage accident risk threshold; when the index parameters of any of the analysis and identification units exceed the corresponding threshold, a regional linkage judgment is triggered, and the cloud platform determines the affected range according to the position of the analysis and identification unit that triggered the linkage;

[0020] The cloud platform selects the analysis and identification unit located within the affected range from the regional linkage network as a linkage object, generates a linkage session including a linkage object identification code, creates a data sharing channel based on the linkage session, sends a linkage instruction including sharing channel configuration information to the linkage object, receives a confirmation response returned by the linkage object through the data sharing channel, and completes the establishment of a communication link between the linkage objects.

[0021] Furthermore, the method further includes: the cloud platform receiving the traffic flow prediction result uploaded by the linkage object, mapping the traffic flow prediction result to a road section based on the real-time location coordinates, calculating the congestion index of each road section, the cloud platform calling a path planning engine to calculate the shortest path and the optimal detour path, inputting lane-level traffic condition information, road section congestion index, average travel speed, and travel time into a warning information generation model, calculating a recommended safe speed based on vehicle type and road conditions, and generating warning text content;

[0022] The cloud platform extracts the license plate information from the cache database of the linkage object, establishes a correspondence between the warning text content and the license plate information, and generates a warning message containing an addressing identifier. The cloud platform queries the communication address of the on-board module and sends the warning message to the corresponding on-board module through the message queue. After receiving the warning message, the on-board module calls the speech synthesis engine to broadcast it and displays the warning content on the vehicle screen.

[0023] In a second aspect, the present application provides a vehicle driving intelligent control device, comprising:

[0024] The system construction module is used to set up analysis and identification units along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. The vehicle-mounted module is deployed on the vehicle side. The vehicle-mounted module establishes a connection with and registers with the cloud platform via the Internet of Things communication module. The vehicle-mounted module calls the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks.

[0025] A traffic prediction module is configured to use the license plate capture camera to capture the vehicle's license plate number, license plate color, and vehicle model information, the wide-angle camera to capture real-time road images, the environmental detection equipment to capture road visibility and road surface state parameters, the edge box to extract vehicle driving characteristics based on the real-time road images, the edge box to train a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and to send the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform;

[0026] The assisted driving module is used for the cloud platform to receive data uploaded by multiple analysis and identification units, determine whether to trigger regional linkage based on the preset road traffic strategy and the risk assessment value, and when regional linkage is triggered, issue linkage instructions to the relevant analysis and identification units according to the regional linkage network and establish a communication link, receive the traffic flow prediction results uploaded by the relevant analysis and identification units, and the cloud platform generates early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds based on the traffic flow prediction results, and sends it to the vehicle-mounted module corresponding to the license plate number for broadcast.

[0027] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the vehicle driving intelligent control method when executing the program.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle driving intelligent control method.

[0029] In a fifth aspect, the present application provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the vehicle driving intelligent control method.

[0030] It can be seen from the above technical solution that the present application provides a method and device for intelligent vehicle driving control, which realizes multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle driving trajectory, and the traffic flow prediction and risk assessment models are trained at the edge. The cloud platform integrates the data of multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0032] Figure 1 Schematic diagram of the process of the vehicle driving intelligent control method in the embodiment of the present application;

[0033] Figure 2 This is a structural diagram of the vehicle driving intelligent control device in an embodiment of the present application;

[0034] Figure 3 Schematic diagram of the structure of the electronic device in the embodiment of the present application.

[0035] Reference numerals:

[0036] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver program storage unit 9144, antenna 9111, speaker 9131, microphone 9132. DETAILED DESCRIPTION

[0037] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0038] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0039] Taking into account the problems existing in the prior art, the present application provides a method and device for intelligent vehicle driving control, which realizes multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle's driving trajectory, and the traffic flow prediction and risk assessment models are trained at the edge. The cloud platform integrates data from multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system.

[0040] In order to effectively solve the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improve the intelligence level and service quality of the assisted driving system, this application provides an embodiment of a vehicle driving intelligent control method, see Figure 1 The vehicle driving intelligent control method specifically includes the following contents:

[0041] Step S101: Setting up analysis and identification units along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. Deploying an on-board module on the vehicle side. The on-board module establishes a connection with and registers with the cloud platform via an IoT communication module. The on-board module calls the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks.

[0042] Optionally, this embodiment deploys analysis and identification units at key road nodes along major thoroughfares, such as highways and urban expressways. Representative monitoring points are selected by analyzing road geometry and historical traffic data at locations such as accident-prone sections, elevated bridges, and tunnel entrances and exits. A standardized pole structure is constructed at each monitoring point, with the equipment mounted using adjustable cantilever brackets to ensure that the height and angle of the equipment meet monitoring requirements.

[0043] The edge box in this embodiment uses an industrial-grade embedded computing platform equipped with a high-performance ARM processor and AI accelerator chip, supporting edge computing and deep learning algorithms. The edge box connects to the Internet of Things via a 4G / 5G dual-mode communication module, generates a registration key based on the unique device serial number, and establishes a secure communication link with the cloud platform using the TLS encryption protocol. During the registration process, the edge box reports information such as the device's location coordinates and coverage range to the cloud platform, which assigns it a unique identifier and returns an authorization certificate.

[0044] The smart camera in this embodiment consists of two independent imaging units. The license plate capture camera uses a high-definition CCD sensor, equipped with an auto-iris lens and a fill light, enabling clear license plate image capture in all lighting conditions. The wide-angle camera uses a fisheye lens with a 180-degree field of view, enabling panoramic road monitoring. The two cameras undergo angle calibration and spatial mapping to establish an image coordinate system, enabling multi-target tracking and spatial positioning.

[0045] The environmental monitoring device in this embodiment integrates multiple sensors, including a laser visibility meter, a surface temperature sensor, a humidity sensor, and a light sensor. The laser visibility meter measures atmospheric transmittance based on the scattering principle and calculates visibility values. A surface sensor array is embedded in the road surface to monitor road surface temperature distribution and water accumulation in real time. All sensor data is connected to the edge box via an industrial bus, enabling unified management and data fusion.

[0046] This embodiment deploys a standardized onboard module on the vehicle side, using a plug-and-play design and connecting to the vehicle's CAN bus via the OBD interface. The onboard module incorporates a high-precision positioning chip and inertial measurement unit, integrating multi-mode positioning signals such as GPS and Beidou to achieve sub-meter positioning accuracy. An IoT communication module establishes a data channel with the cloud platform, using the lightweight MQTT protocol to transmit vehicle status data.

[0047] The on-board module in this embodiment uses a standardized interface to call the vehicle computer system to obtain vehicle status data such as engine speed, vehicle speed, and steering wheel angle. Combined with high-precision positioning information, it constructs a vehicle motion model and generates an accurate driving trajectory. The on-board module uploads this trajectory data to a cloud platform at regular intervals. The cloud platform maps the trajectory points onto the road network using an electronic map to predict the vehicle's future driving path.

[0048] This embodiment innovatively proposes a method for dynamically constructing a regional linkage network. Based on the predicted vehicle path, the cloud platform extracts analysis and identification units along the route and constructs a directed graph structure based on geospatial relationships. Nodes in the graph represent analysis and identification units, and edges represent the relationships between units. By assigning network priorities and establishing a cascading trigger mechanism, when a node detects an anomaly, it can quickly notify downstream nodes for a coordinated response.

[0049] This embodiment utilizes a distributed edge computing architecture, offloading computational tasks like data collection and feature extraction to edge nodes, reducing the load on the cloud platform. Both the edge box and the onboard module possess local computing capabilities, enabling data preprocessing and preliminary analysis. Furthermore, through unified cloud platform scheduling, device collaboration is achieved, building an intelligent perception network covering the entire road area.

[0050] This embodiment addresses the issues of dispersed equipment, data silos, and delayed response times found in traditional road monitoring systems. Through edge computing and regional linkage mechanisms, it enables real-time perception of road conditions and rapid early warnings. In practical applications, this solution can significantly improve traffic safety in scenarios such as inclement weather and frequent accidents. Particularly in closed road environments such as highways, the system can provide drivers with accurate road condition information and safety warnings, effectively reducing the risk of traffic accidents.

[0051] Step S102: The license plate capture camera acquires the vehicle's license plate number, license plate color, and vehicle model information, the wide-angle camera acquires real-time road images, the environmental detection equipment acquires road visibility and road surface state parameters, the edge box extracts vehicle driving characteristics based on the real-time road images, the edge box trains a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and sends the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform;

[0052] Optionally, this embodiment adopts a multi-stage processing strategy for license plate capture. The license plate capture camera triggers capture based on vehicle front-end detection and uses adaptive exposure technology to ensure image quality. The edge box runs an improved YOLOv5 object detection algorithm to locate the license plate area and combines morphological processing to achieve license plate character segmentation. Character recognition is performed using a deep convolutional neural network. The model is trained using a noisy synthetic dataset to improve recognition accuracy in complex environments. Vehicle type classification is also performed based on vehicle body contour features, supporting accurate recognition of various vehicle types such as sedans, buses, and trucks.

[0053] The wide-angle camera in this embodiment captures real-time road images at a sampling rate of 25 frames per second. The edge box processes the video stream in real time and uses an improved DeepSORT algorithm to track multiple targets. The algorithm integrates appearance and motion features during the feature extraction phase to improve vehicle tracking stability. Vehicle motion parameters, including instantaneous speed, acceleration, and lane change frequency, are calculated by tracking trajectories. Furthermore, the relative distance and speed between vehicles are calculated based on spatial mapping relationships to construct vehicle interaction behavior profiles.

[0054] The environmental monitoring equipment in this embodiment uses a multi-sensor collaborative sensing solution. A laser visibility meter calculates visibility by measuring the atmospheric attenuation coefficient, with a sampling period of one minute. A surface sensor array monitors road surface temperature distribution in real time and, combined with humidity data, determines road surface conditions, such as dryness, dampness, waterlogging, or ice. A light sensor monitors changes in ambient brightness and is used to adjust camera parameters and fill-light strategies. All environmental parameters undergo data filtering and smoothing to ensure data quality.

[0055] This embodiment innovatively designs a traffic flow prediction model. The model utilizes a long short-term memory (LSTM) network architecture, and its input features include time-series data such as historical traffic volume, average speed, and vehicle type composition. An attention mechanism captures traffic flow patterns at different time scales, improving prediction accuracy. The model is trained using a sliding window strategy, with the window size dynamically adjusted based on the prediction time span. The prediction results include traffic flow status at multiple future time points, providing a basis for traffic control decisions.

[0056] This example constructs a risk assessment model based on multidimensional features. It uses the Gradient Boosting Decision Tree (GBDT) algorithm. Input features include behavioral characteristics such as vehicle spacing, relative speed, acceleration, and lane changes, as well as environmental characteristics such as visibility and road conditions. The model analyzes historical accident data to establish a mapping between these features and risk levels. The assessment results are output as probabilities, providing a direct reflection of the safety risk level of the current road section.

[0057] This embodiment designs an efficient data transmission mechanism. The edge box packages vehicle characteristics, prediction results, and risk assessment values ​​into structured data, using the protobuf encoding format to reduce transmission overhead. Data packets are uploaded to the cloud platform at a fixed interval, which can be dynamically adjusted based on network conditions. For emergencies, a real-time push mechanism is used to ensure the timely delivery of critical information. The cloud platform synchronizes and analyzes data using timestamps.

[0058] This embodiment implements a computing architecture that integrates edge intelligence and the cloud. Real-time-critical tasks such as feature extraction and target tracking are deployed on edge boxes to reduce network transmission latency. Model training and optimization are performed in the cloud, with updated model parameters regularly distributed to edge nodes. This layered architecture ensures the system's real-time responsiveness while supporting continuous model optimization and evolution.

[0059] This embodiment addresses the challenges of traditional traffic monitoring systems, such as insufficient perception and low prediction accuracy, through multi-source data fusion and intelligent analysis. In practical applications, this solution accurately identifies vehicle characteristics, predicts traffic flow trends, and promptly identifies safety hazards. Especially in scenarios such as inclement weather and complex road conditions, the system can comprehensively analyze multi-dimensional data to provide reliable decision-making support for traffic management and vehicle warnings, effectively improving road efficiency and safety.

[0060] Step S103: The cloud platform receives data uploaded by a plurality of the analysis and identification units, determines whether to trigger regional linkage based on a preset road traffic strategy and the risk assessment value, and when regional linkage is triggered, issues linkage instructions to the relevant analysis and identification units according to the regional linkage network and establishes a communication link, receives the traffic flow prediction results uploaded by the relevant analysis and identification units, and generates warning information including real-time road conditions, recommended detour routes and safe vehicle speeds based on the traffic flow prediction results, and sends the warning information to the vehicle-mounted module corresponding to the license plate number for broadcast.

[0061] Optionally, this embodiment innovatively implements intelligent data collection and processing at the edge. The license plate capture camera uses a two-stage detection mechanism based on a combination of image processing and deep learning to locate license plates. The first stage uses an improved YOLOv5 model for rough positioning, while the second stage employs a high-precision license plate character segmentation network for accurate character-level recognition. This maintains a high recognition accuracy even in complex lighting and occlusion conditions.

[0062] The wide-angle camera in this embodiment uses a multi-scale object detection algorithm to detect and track key targets such as vehicle outlines, pedestrians, and road markings in real time. It calculates driving characteristics such as the vehicle's instantaneous speed, acceleration, and lane departure through spatiotemporal feature analysis. The edge box utilizes a stream processing architecture to establish a feature extraction pipeline, enabling real-time processing of video streams with millisecond latency.

[0063] This example builds a traffic flow prediction model based on a long short-term memory (LSTM) network. The model input features include time-series data such as historical traffic flow, average speed, and vehicle density, while also incorporating environmental factors such as weather conditions and road surface conditions. An attention mechanism captures the correlation between different features, improving prediction accuracy. The prediction results include traffic flow status at multiple future time points, providing a basis for predictive decision-making in traffic management.

[0064] This embodiment designs a risk assessment model based on random forests. The model input variables include multi-dimensional features such as vehicle spacing, relative speed, weather visibility, and road friction coefficient. Feature importance analysis identifies key factors that significantly impact traffic safety. The model outputs a risk assessment value that reflects the probability of a traffic accident occurring on the current road section and is used to trigger an early warning mechanism. In practical applications, the model is continuously optimized through online learning to adapt to the safety characteristics of different scenarios.

[0065] This embodiment optimizes the data transmission strategy. The edge box uses a hierarchical caching mechanism to store raw data, feature data, and model prediction results separately. Data upload uses batch processing, dynamically adjusting the batch size based on data priority and network conditions. Data compression and incremental update mechanisms reduce transmission bandwidth usage.

[0066] This embodiment implements an intelligent regional linkage mechanism based on road traffic strategies. After receiving data uploaded by each analysis and recognition unit, the cloud platform first performs data quality assessment and outlier detection. When the risk assessment value of a road section exceeds a threshold, a regional linkage decision is triggered. The linkage range is determined based on a traffic flow propagation model, taking into account factors such as traffic flow direction and traffic saturation.

[0067] This embodiment builds a warning information generation engine that calculates the congestion index for each road section based on traffic flow predictions. A route planning algorithm comprehensively considers factors such as distance, time, and safety to generate personalized detour suggestions for different vehicle types. Recommended safe speeds are calculated based on current road conditions, weather conditions, and vehicle characteristics to ensure safe driving.

[0068] This embodiment implements a precise information push mechanism. Warning information is distributed to the onboard module via a message queue system, supporting message priority management and reliable transmission. After receiving the warning information, the onboard module selects the appropriate broadcast timing based on the vehicle's driving status and converts the text information into clear voice prompts using speech synthesis technology.

[0069] Through the above technological innovations, this embodiment effectively addresses the problems of traditional traffic warning systems, such as blind spots, delayed predictions, and untimely linkage. In practical applications, this solution accurately identifies traffic risks, predicts traffic flow changes in advance, and enables rapid response through a regional linkage mechanism. Especially in scenarios such as inclement weather and frequent accidents, the system can provide drivers with precise warning information and safety recommendations, significantly improving road safety and efficiency.

[0070] As can be seen from the above description, the vehicle driving intelligent control method provided by the embodiment of the present application can realize multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle driving trajectory, and the traffic flow prediction and risk assessment model is trained at the edge. The cloud platform integrates the data of multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system.

[0071] In one embodiment of the vehicle driving intelligent control method of the present application, the following contents may also be specifically included:

[0072] Step S201: Deploy the analysis and identification unit at a key location on the road, initialize and configure parameters of the edge box, obtain a unique identification code through the IoT communication module, send a registration request to the cloud platform based on the unique identification code, and the cloud platform returns registration authorization information. The edge box then establishes a secure communication link with the cloud platform based on the registration authorization information.

[0073] Step S202: The edge box establishes a communication connection with the smart camera and the environmental detection device, calibrates the angle and focal length of the smart camera, sets the license plate capture camera to point in the direction of vehicle traffic, and sets the wide-angle camera to a panoramic road monitoring angle. A sub-device management group is established with the edge box as the center, and the sampling period and trigger threshold of the environmental detection device are configured. The edge box obtains environmental parameters including visibility, temperature, humidity and light intensity from the environmental detection device at preset time intervals.

[0074] Optionally, this embodiment identifies key monitoring locations by analyzing historical traffic accident data and road network structural characteristics. This prioritizes accident-prone sections, sharp bends and steep slopes, tunnel entrances and exits, and overpasses. Traffic flow distribution characteristics are then combined to determine the optimal deployment locations for analysis and identification units. A standardized pole structure is established at each monitoring point, using adjustable brackets for mounting equipment to ensure complete coverage of the target area.

[0075] This embodiment performs comprehensive parameter initialization and configuration for the edge box. First, basic device parameters are set, including processor frequency, memory allocation, and storage policy. The network configuration uses a dual-link redundant design, supporting both wired and 4G / 5G wireless networks to ensure communication reliability. The edge box obtains a unique hardware-based identification code through the IoT communication module. This identification code is combined with geographic location information and device type to generate a globally unique device ID.

[0076] This embodiment designs a secure device registration mechanism. The edge box generates a registration request message based on a unique identification code and signs the request content using an asymmetric encryption algorithm. After receiving the registration request, the cloud platform verifies the legitimacy of the device identity and allocates resource quotas. Registration authorization information includes access tokens, encryption keys, service configuration, and other information. Based on this authorization information, the edge box establishes a TLS encrypted channel for secure communication with the cloud platform.

[0077] This embodiment achieves precise calibration of smart cameras. The license plate capture camera uses a two-axis pan-tilt mount, automatically adjusting the shooting angle and focal length through an image quality assessment algorithm. The calibration process uses standard test license plates, collects image samples under different lighting conditions, and optimizes image processing parameters. The wide-angle camera uses a specialized calibration plate, establishing an image coordinate system through corner detection and spatial mapping.

[0078] This embodiment builds a device management system based on edge boxes. The edge boxes serve as local control centers, connecting to smart cameras and environmental monitoring equipment via industrial Ethernet. Devices use a master-slave communication architecture, with the edge boxes periodically sending heartbeat packets to sub-devices to check their online status. If a device anomaly is detected, the system automatically switches to a backup communication link to ensure continuous data collection.

[0079] This embodiment optimizes the configuration strategy for environmental monitoring equipment. The visibility sensor's sampling period dynamically adjusts based on the rate of weather change, increasing the sampling frequency in adverse weather conditions such as fog. The temperature and humidity sensors use a threshold trigger mechanism, immediately reporting data when parameter changes exceed preset thresholds. The light sensor is linked to camera parameters to adjust image gain and exposure time in real time.

[0080] This embodiment designs an intelligent data collection and scheduling mechanism. The edge box sets differentiated sampling strategies for different types of environmental parameters based on business needs and device characteristics. For example, visibility data is sampled once a minute, temperature and humidity data every five minutes, and light intensity sampling frequency is dynamically adjusted based on sunrise and sunset times. Collected environmental parameters undergo data filtering and outlier detection to ensure data quality.

[0081] This embodiment enables remote management of device configurations. The cloud platform can dynamically adjust the configuration parameters of edge boxes and sub-devices based on actual needs. Configuration updates are incremental, distributing only changed configuration items to reduce network transmission overhead. After receiving configuration updates, the edge box uses a transaction mechanism to ensure atomic configuration updates and avoid configuration inconsistencies.

[0082] This embodiment, through the above technological innovations, addresses the challenges inherent in the deployment and management of traditional road monitoring equipment. In practical applications, this solution enables plug-and-play and intelligent management of equipment, significantly improving system reliability and maintenance efficiency. The system maintains stable operation, particularly under complex road conditions and inclement weather, providing reliable data support for traffic monitoring and early warning.

[0083] In one embodiment of the vehicle driving intelligent control method of the present application, the following contents may also be specifically included:

[0084] Step S301: The vehicle-mounted module obtains a unique device identifier through the IoT communication module, and sends a registration request including the vehicle VIN code to the cloud platform based on the unique device identifier. The cloud platform returns a device authorization code, and the vehicle-mounted module establishes a data transmission channel with the cloud platform based on the device authorization code. The vehicle-mounted module uses the vehicle-mounted CAN bus interface to collect the vehicle's real-time position coordinates, driving speed, and direction angle data;

[0085] Step S302: The on-board module uploads the position coordinates, driving speed and direction angle data to the cloud platform at preset time intervals. The cloud platform maps the vehicle position coordinates to an electronic map based on a geographic information system, determines a forward predicted path according to the vehicle's driving direction, extracts the analysis and identification units within the coverage of the predicted path, constructs the extracted analysis and identification units into a regional linkage network, and assigns a network priority to each of the analysis and identification units.

[0086] Optionally, this embodiment implements intelligent deployment and automatic registration of the vehicle-mounted module. The vehicle-mounted module utilizes a plug-and-play design, connecting to the vehicle's CAN bus via the OBD interface, automatically identifying the vehicle model and loading the corresponding protocol stack. The IoT communication module generates a unique device identifier based on the built-in security chip. This identifier is bound to the hardware characteristics, ensuring uniqueness and immutability of the device's identity.

[0087] This embodiment designs a secure device registration mechanism. The onboard module scans the vehicle's electronic control unit to obtain the VIN code and combines it with the device's unique identifier to generate a registration credential. Registration requests are signed using an asymmetric encryption algorithm to ensure authenticity. After verifying the registration information, the cloud platform generates a device authorization code containing permission information and an encryption key, enabling secure device access.

[0088] This embodiment establishes a reliable data transmission channel. The onboard module establishes TLS encrypted communication based on the device authorization code, supporting data compression and resumable transmission. The channel uses a two-way authentication mechanism, ensuring data transmission security through session key negotiation. It also implements a network switching function, automatically switching to a backup network when the 4G signal is unstable, ensuring communication continuity.

[0089] This embodiment optimizes the vehicle data collection strategy. The onboard module acquires vehicle status information in real time via the CAN bus interface, employing a multi-threaded parallel processing mechanism to ensure real-time data collection. Position coordinates are acquired using a dual-mode GPS and Beidou positioning module, and data fusion is performed with an inertial measurement unit to improve positioning accuracy. Vehicle speed and azimuth data are directly acquired from vehicle sensors to ensure data accuracy.

[0090] This embodiment implements an intelligent data upload mechanism. The onboard module dynamically adjusts the data upload frequency based on the vehicle's motion state, increasing the sampling rate when the vehicle is turning, accelerating, or decelerating, and appropriately reducing the sampling rate when stationary or traveling at a constant speed. Data is packaged using incremental encoding, transmitting only the changed data items, reducing bandwidth usage. A local caching mechanism is also implemented, temporarily storing data during network interruptions and automatically retransmitting it upon network recovery.

[0091] This embodiment innovatively designs a location mapping algorithm. The cloud platform utilizes high-precision electronic maps and a multi-level indexing structure to rapidly locate the vehicle's current road section. This location mapping takes into account road geometry and traffic regulations, accurately identifying the vehicle's lane. Based on historical trajectory data and current heading angle, a Kalman filter algorithm is used to predict the vehicle's future path, with the prediction range dynamically adjusted based on vehicle speed.

[0092] This embodiment builds an adaptive regional linkage network. The cloud platform extracts relevant analysis and identification units based on the predicted path and constructs a directed acyclic graph using graph theory algorithms. Nodes in the graph represent analysis and identification units, and edges represent the relationships between units. Network priority assignment takes into account multiple factors, including distance from the predicted path, road grade, and historical accident frequency. Priority values ​​are calculated through weighted calculations and used for subsequent linkage triggering decisions.

[0093] This embodiment implements dynamic updates to the network topology. As vehicle locations change, the cloud platform adjusts the coverage of the regional linkage network in real time. Using a sliding window mechanism, analysis and identification units that are about to enter the predicted path are added to the network in advance, while units that have already left the path are removed. This dynamic adjustment mechanism ensures that the network structure always stays synchronized with the vehicle's travel path.

[0094] Through the above technological innovations, this embodiment effectively addresses the challenges of traditional on-board device management and path prediction. In practical applications, this solution enables intelligent access to on-board devices and reliable data transmission, providing an accurate location basis for subsequent traffic warnings. Especially in complex road networks, the system can accurately predict vehicle paths and establish an efficient regional linkage mechanism, providing strong support for proactive safety warnings.

[0095] In one embodiment of the vehicle driving intelligent control method of the present application, the following contents may also be specifically included:

[0096] Step S401: The license plate capture camera collects image data of a vehicle passing by. The edge box processes the image data based on a convolutional neural network model, extracts license plate area features and performs character segmentation, identifies the license plate number and color information, analyzes the vehicle body contour features through a deep learning model to obtain a vehicle model classification result, and stores the license plate number, color information, and vehicle model classification result in a cache database of the edge box.

[0097] Step S402: The wide-angle camera collects road traffic video streams at a preset frame rate. The environmental detection equipment obtains visibility values ​​based on the laser ranging principle and detects road surface state parameters through surface temperature sensors and humidity sensors. The edge box performs target detection and tracking processing on the video stream, extracts driving characteristic parameters such as vehicle trajectory, vehicle speed, and vehicle spacing, and establishes a mapping relationship between the driving characteristic parameters and license plate information.

[0098] Optionally, this embodiment employs a multi-stage processing strategy for license plate recognition. First, the license plate capture camera uses adaptive exposure technology, dynamically adjusting exposure parameters based on ambient lighting conditions to ensure image quality. When a vehicle enters the field of view, high-speed capture is triggered, capturing multiple frames of image data. A motion compensation algorithm is then used to select the clearest image for processing.

[0099] This embodiment designs an improved license plate detection network. The convolutional neural network model, built on the YOLOv5 framework, employs a multi-scale feature fusion strategy to enhance detection capabilities for license plates at varying distances. A spatial pyramid pooling module is incorporated into the network structure to enhance adaptability to license plate deformation and tilt. The model is trained using a dataset of license plate images under various lighting and weather conditions to improve generalization.

[0100] This embodiment implements a precise character segmentation algorithm. It uses an improved FCN semantic segmentation network to achieve pixel-level segmentation at the character level. By introducing an attention mechanism, the ability to distinguish similar characters is improved. During the character recognition stage, a deep residual network is used in conjunction with the CTC loss function to improve recognition accuracy. Furthermore, color histogram analysis is used to determine the base color of the license plate, enabling accurate classification of the license plate type.

[0101] This embodiment innovatively designs a vehicle classification method. A deep learning model extracts vehicle body contour features, including key features such as aspect ratio, front shape, and window layout. A multi-task learning framework is employed to simultaneously predict vehicle type, make, and model, improving classification accuracy. The model also employs a transfer learning strategy, leveraging pre-trained models to accelerate training convergence.

[0102] This embodiment builds an efficient cache database. It uses a key-value storage structure, with the license plate number as the primary key, to store vehicle-related feature information. The database supports concurrent access and transaction processing to ensure data consistency. It manages in-memory data using a least-repeated (LRU) cache strategy, automatically clearing the least recently accessed records when capacity is exceeded.

[0103] This embodiment optimizes the video stream processing process. The wide-angle camera uses a 25 frames per second sampling rate and implements video compression through a hardware encoder. The edge box utilizes a multi-threaded parallel processing architecture to simultaneously process multiple video streams. Object detection utilizes an improved DeepSORT algorithm to achieve stable vehicle tracking. A projection transformation establishes a mapping between pixel coordinates and actual distances to calculate the vehicle's actual position and speed.

[0104] This embodiment implements intelligent collection of environmental parameters. A laser ranging device calculates visibility by measuring the attenuation of the laser signal, with the sampling period dynamically adjusted based on the rate of weather change. A surface sensor array uses thermocouples to measure road surface temperature distribution and, combined with humidity data, determines road surface conditions, such as dryness, dampness, waterlogging, and icing.

[0105] This embodiment innovatively establishes a feature mapping mechanism. Using a spatiotemporal correlation algorithm, a correspondence is established between vehicle tracking trajectories and license plate information. This algorithm considers the continuity of vehicle motion and physical constraints, effectively addressing correlation issues in situations with occlusion and dense traffic. For vehicles that temporarily lose their license plate information, trajectory prediction is used to maintain tracking.

[0106] This embodiment designs a feature parameter extraction method. Based on the tracked trajectory, it calculates vehicle kinematic characteristics, including instantaneous velocity, acceleration, and steering angular velocity. It also calculates the distance between vehicles and their relative speeds based on the positional relationships of adjacent vehicles to assess potential collision risks. All feature parameters undergo data smoothing and outlier filtering to ensure data quality.

[0107] Through the above technological innovations, this embodiment overcomes the limitations of traditional traffic monitoring systems in vehicle identification and behavior analysis. In practical applications, this solution accurately identifies vehicle characteristics and tracks vehicle movement in real time, providing reliable data support for traffic flow prediction and risk assessment. The system maintains stable identification and tracking performance, particularly under complex road conditions and inclement weather, significantly improving the accuracy and reliability of traffic monitoring.

[0108] In one embodiment of the vehicle driving intelligent control method of the present application, the following contents may also be specifically included:

[0109] Step S501: The edge box divides the vehicle driving characteristic parameters into a training data set according to the time series, uses a long short-term memory neural network to construct a network structure of a traffic flow prediction model, uses vehicle speed, vehicle density, and travel time as input features, iteratively trains the network structure to obtain a traffic flow prediction model, and constructs a risk assessment model based on a decision tree algorithm, using vehicle spacing, relative speed, and road surface state parameters as input variables to calculate a collision risk assessment value;

[0110] Step S502: The edge box organizes the vehicle driving characteristics, environmental parameters and timestamp information into a data packet, which contains the future traffic flow state prediction results output by the traffic flow prediction model and the risk assessment value calculated by the risk assessment model. The edge box sends the data packet to the cloud platform through a secure communication link according to a preset data upload cycle, and the cloud platform performs time synchronization and data verification on the received data packet.

[0111] Optionally, this embodiment innovatively designs a data preprocessing process. The edge box uses a sliding window mechanism to organize continuously collected vehicle driving features into training samples in chronological order. The window size is dynamically adjusted based on the prediction time span, for example, using a 5-minute window for short-term predictions and a 15-minute window for medium-term predictions. During the data preprocessing phase, feature scaling is unified using maximum and minimum normalization, and median filtering is used to remove outliers.

[0112] This example builds a traffic flow prediction model based on a long short-term memory (LSTM) network. The network structure consists of an input layer, an LSTM layer, a fully connected layer, and an output layer. Input features include three key indicators: vehicle speed, vehicle density, and travel time. These indicators comprehensively reflect road traffic conditions. The LSTM layer uses a gating mechanism to capture long-term dependencies in time series data. The forget gate filters out irrelevant information, and the input and output gates control information updates and outputs.

[0113] This embodiment optimizes the model training strategy. Batch gradient descent is used for parameter optimization, and the learning rate is adaptively adjusted. A higher learning rate is used for rapid convergence in the early stages of training, and a gradually reduced learning rate is used for fine-tuning. To prevent overfitting, a dropout layer is introduced to randomly discard some neurons, and L2 regularization is used to constrain model parameters. The loss function uses mean squared error, and the backpropagation algorithm is used to calculate gradients and update parameters.

[0114] This embodiment implements a risk assessment model based on a decision tree. A binary decision tree is constructed using the CART algorithm, with input variables including vehicle spacing, relative speed, and road surface condition parameters. The decision tree's splitting criterion uses the Gini index, recursively selecting the optimal splitting feature and threshold. The predicted value of a leaf node represents the collision risk probability, ranging from 0 to 1. The model is trained using labeled historical accident data, and the optimal tree depth is determined through cross-validation.

[0115] This embodiment innovatively designs a risk assessment method. The risk assessment value R is calculated using the following formula:

[0116] R = w1 D + w2 V + w3 S

[0117] Where D is the normalized vehicle spacing, V is the relative speed, S is the road surface condition coefficient, and w1, w2, and w3 are weighting factors. The weighting factors are determined through historical data analysis and reflect the impact of each factor on safety risk. A risk warning is triggered when the R value exceeds a preset threshold.

[0118] This embodiment optimizes the data packet structure. It employs a layered design: the bottom layer contains basic data fields, including device ID, timestamp, and location coordinates; the middle layer contains feature data fields, including vehicle driving characteristics and environmental parameters; and the top layer contains analysis result fields, including traffic flow prediction results and risk assessment values. Data packets are encoded in a compact binary format to reduce transmission overhead.

[0119] This embodiment implements an intelligent data upload strategy. Under normal circumstances, data packets are uploaded at a fixed interval, which can be dynamically adjusted based on network conditions. When an abnormality is detected, such as a sudden increase in risk assessment values ​​or a dramatic change in traffic flow as indicated by forecast results, a real-time upload mechanism is triggered. Data transmission utilizes the TLS encryption protocol to ensure data security.

[0120] This embodiment designs a data synchronization and verification mechanism. After receiving a data packet, the cloud platform first checks the timestamp consistency and reorders packets that arrive out of order. Data integrity is verified using a CRC checksum, and packets that fail verification are requested to be retransmitted. A clock synchronization mechanism is also implemented to ensure time consistency between the edge box and the cloud platform.

[0121] Through the above technological innovations, this embodiment addresses the problems of low prediction accuracy and inaccurate risk assessments that plague traditional traffic prediction systems. In practical applications, this solution can accurately predict traffic flow trends and promptly identify potential safety risks. Especially in complex road conditions, the system can comprehensively analyze multi-dimensional data, providing a reliable basis for traffic management decisions and effectively improving road safety and efficiency.

[0122] In one embodiment of the vehicle driving intelligent control method of the present application, the following contents may also be specifically included:

[0123] Step S601: The cloud platform receives data packets uploaded by multiple analysis and identification units, extracts the risk assessment value, traffic flow, speed and other indicator parameters from the data packets, and compares the indicator parameters with thresholds in the road traffic strategy, which includes a traffic flow density threshold, an average speed threshold, and a unit mileage accident risk threshold. When the indicator parameters of any analysis and identification unit exceed the corresponding threshold, a regional linkage judgment is triggered, and the cloud platform determines the affected range based on the location of the analysis and identification unit that triggered the linkage;

[0124] Step S602: The cloud platform selects the analysis and identification unit located within the affected range from the regional linkage network as a linkage object, generates a linkage session including a linkage object identification code, creates a data sharing channel based on the linkage session, sends a linkage instruction including sharing channel configuration information to the linkage object, receives a confirmation response returned by the linkage object through the data sharing channel, and completes the establishment of a communication link between the linkage objects.

[0125] Optionally, this embodiment implements an intelligent data processing process. The cloud platform uses a distributed message queue to receive data packets uploaded by multiple analysis and recognition units, and uses message middleware to achieve reliable data transmission and load balancing. Upon arrival, the data packets are first parsed and verified, extracting key indicator parameters such as risk assessment value, traffic volume, and average speed. These parameters are then cleaned and standardized to ensure data consistency.

[0126] This embodiment designs an adaptive threshold judgment mechanism. The threshold in the road traffic strategy is not fixed, but is dynamically adjusted based on road grade, time characteristics and historical data. The traffic flow density threshold D is calculated by the following formula:

[0127] D = Dbase (1 + k1 T + k2 W)

[0128] Where Dbase is the base density threshold, T is the time period coefficient, W is the weather impact coefficient, and k1 and k2 are adjustment factors. This dynamic threshold mechanism can better adapt to the needs of different scenarios.

[0129] This embodiment innovatively implements a regional linkage judgment algorithm. When an indicator parameter of a specific analysis and identification unit exceeds a threshold, the system calculates the impact range based on a traffic flow propagation model. This propagation model considers factors such as road network topology, traffic flow direction, and propagation speed. A graph theory algorithm analyzes road network connectivity and identifies potentially affected associated road sections. The impact range is calculated using a spatiotemporal diffusion model, with the size of the range positively correlated with the degree and duration of the violation.

[0130] This embodiment establishes an efficient linkage target selection mechanism. The cloud platform extracts analysis and identification units within the affected area from a pre-established regional linkage network and screens them based on priority and location. The selection process considers multiple dimensions, including device performance, network status, and historical reliability, to ensure the most appropriate linkage targets. A backup mechanism is also implemented, configuring backup devices for key nodes to improve system reliability.

[0131] This embodiment optimizes the linkage session management process. Each linkage session is assigned a globally unique session ID, which contains information such as trigger conditions, participants, and validity period. Session management utilizes a distributed architecture, supporting parallel processing of multiple sessions. A state machine mechanism manages the session lifecycle, ensuring controllable and traceable session creation, maintenance, and release processes.

[0132] This embodiment designs a reliable data sharing channel. A full-duplex communication link is established based on the WebSocket protocol, supporting real-time data push and command issuance. Channel configuration adopts a hierarchical design, including basic and extended configurations. The basic configuration ensures basic channel connectivity, while the extended configuration is dynamically loaded based on business needs. Channel creation uses a handshake mechanism to ensure that all participants reach consensus on communication parameters.

[0133] This embodiment implements an intelligent command issuance strategy. Linked commands are processed according to priority, with urgent commands prioritized. The command format utilizes a unified protocol specification, including fields such as command type, parameter configuration, and execution time. Reliable command transmission is achieved through a message queue mechanism, supporting command confirmation and retransmission. Real-time monitoring of command execution status is also implemented, enabling timely detection and resolution of anomalies.

[0134] This embodiment establishes a complete confirmation and response mechanism. After receiving a command, the linked object first verifies its legitimacy and integrity. It then evaluates the command's feasibility based on local resource availability and generates a response message containing an execution plan. This response message is returned to the cloud platform via a data sharing channel, which confirms the establishment of the linkage relationship. For devices that fail to respond in a timely manner, a timeout mechanism is triggered.

[0135] Through the above technological innovations, this embodiment addresses the issues of delayed regional coordination and low coordination efficiency in traditional traffic management systems. In practical applications, this solution enables rapid response to traffic anomalies and establishes an efficient device coordination mechanism. Especially in emergencies such as traffic accidents and severe weather, the system can quickly coordinate the response of relevant devices, providing strong support for traffic diversion and safety warnings, significantly enhancing the level of intelligent road traffic management.

[0136] In one embodiment of the vehicle driving intelligent control method of the present application, the following contents may also be specifically included:

[0137] Step S701: The cloud platform receives the traffic flow prediction results uploaded by the linkage object, maps the traffic flow prediction results to road sections based on real-time location coordinates, calculates the congestion index of each road section, and calls the path planning engine to calculate the shortest path and the optimal detour path. The cloud platform inputs the lane-level traffic condition information, the road section congestion index, the average travel speed, and the travel time into the warning information generation model, calculates the recommended safe speed based on the vehicle type and road conditions, and generates warning text content.

[0138] Step S702: The cloud platform extracts the license plate information from the cache database of the linkage object, establishes a corresponding relationship between the warning text content and the license plate information, and generates a warning message containing an addressing identifier. The cloud platform queries the communication address of the on-board module and sends the warning message to the corresponding on-board module through the message queue. After receiving the warning message, the on-board module calls the speech synthesis engine to broadcast it and displays the warning content on the car screen.

[0139] Optionally, this embodiment implements an intelligent traffic flow analysis mechanism. After receiving the prediction results uploaded by the linked objects, the cloud platform first performs a spatiotemporal consistency check to ensure the validity of the data. The prediction results are mapped to specific road sections using a high-precision electronic map, establishing a correlation between the prediction data and the road network topology. The congestion index CI is calculated using the following formula:

[0140] CI = (V0 - V) / V0 (ρ / ρmax)

[0141] Where V0 is the free flow speed, V is the current average speed, ρ is the current traffic density, and ρmax is the maximum traffic density. This index comprehensively reflects the road traffic status.

[0142] This embodiment optimizes the path planning algorithm. The algorithm searches for the shortest path, using the congestion index as a weighting factor for road sections and dynamically adjusting path evaluation criteria. When calculating the optimal detour, it comprehensively considers factors such as distance increment, time increment, and road reliability. Using a multi-objective optimization approach, it selects the optimal solution from multiple candidate paths, ensuring the practicality of the detour recommendations.

[0143] This embodiment innovatively designs a warning information generation model. The model utilizes a deep neural network architecture, with input features including multi-dimensional data such as lane-level road conditions, congestion index, and average speed. An attention mechanism identifies key information and generates warning text that aligns with human cognitive habits. The model is trained using a large amount of real-world scenario data to ensure the accuracy and comprehensibility of the generated content.

[0144] This embodiment implements an intelligent safe speed calculation method. A baseline speed is set based on vehicle type and dynamically adjusted based on environmental factors such as road curvature, slope, and weather conditions. Additional speed constraints are introduced in special sections of road, such as construction zones and school areas. The system also considers safety factors such as following distance and braking distance to ensure the recommended speed meets safety requirements.

[0145] This embodiment establishes an efficient vehicle information management mechanism. The cloud platform maintains a distributed cache database that stores the mapping between license plate information and onboard modules. A multi-level caching strategy keeps hot data in memory, improving query efficiency. The database supports real-time updates, ensuring the timeliness of vehicle information. A data synchronization mechanism ensures data consistency across all nodes.

[0146] This embodiment optimizes the organizational structure of warning messages. Warning messages consist of multiple layers: a metadata layer containing basic information such as the message ID, timestamp, and priority; a content layer containing specific information such as road conditions, detour suggestions, and recommended speeds; and a control layer containing presentation parameters such as broadcast strategies and display styles. A compact serialization format is used to reduce transmission overhead.

[0147] This embodiment designs a reliable message delivery mechanism. The cloud platform implements asynchronous transmission of warning messages through a message queue system, supporting message priority management and retry upon failure. A push-pull approach is employed, with urgent messages proactively pushed and common messages allowed to be periodically retrieved by the onboard module. A heartbeat mechanism monitors communication status to ensure message delivery.

[0148] This embodiment implements an intelligent broadcast control strategy. Upon receiving a warning message, the onboard module first analyzes the message's priority and timeliness. Urgent warnings are immediately interrupted for an interruption, while standard warnings are broadcast at an appropriate time. Speech synthesis utilizes a deep learning model to generate natural and fluent voice prompts. Key information is also prominently displayed on the vehicle's screen.

[0149] This embodiment optimizes information presentation through a dynamic display strategy. The screen uses a partitioned layout, placing important information prominently. Key prompts are enhanced through animation, such as dynamic arrows for detours. The display automatically adjusts information density based on vehicle speed, ensuring the driver can quickly access critical information.

[0150] Through the above technological innovations, this embodiment addresses the issues of limited information targeting and low transmission efficiency in traditional warning systems. In practical applications, this solution can provide personalized warning information for different vehicles, helping drivers to promptly understand road conditions and make informed decisions. Especially in complex road conditions and emergency situations, the system delivers warning information promptly through multiple channels, effectively improving road safety and efficiency and significantly enhancing the driver's travel experience.

[0151] In order to effectively solve the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improve the intelligence level and service quality of the assisted driving system, the present application provides an embodiment of a vehicle driving intelligent control device for implementing all or part of the content of the vehicle driving intelligent control method, see Figure 2 The vehicle driving intelligent control device specifically includes the following contents:

[0152] The system construction module 10 is used to set up analysis and identification units along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. An on-board module is deployed on the vehicle side. The on-board module establishes a connection with and registers with the cloud platform via an Internet of Things communication module. The on-board module calls the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks.

[0153] Traffic prediction module 20, configured to use the license plate capture camera to capture the vehicle's license plate number, license plate color, and vehicle model information, the wide-angle camera to capture real-time road images, the environmental detection equipment to capture road visibility and road surface state parameters, the edge box to extract vehicle driving characteristics based on the real-time road images, the edge box to train a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and to send the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform;

[0154] The assisted driving module 30 is used for the cloud platform to receive data uploaded by multiple analysis and identification units, determine whether to trigger regional linkage based on the preset road traffic strategy and the risk assessment value, and when regional linkage is triggered, issue linkage instructions to the relevant analysis and identification units according to the regional linkage network and establish a communication link, receive the traffic flow prediction results uploaded by the relevant analysis and identification units, and the cloud platform generates early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds based on the traffic flow prediction results, and sends it to the vehicle-mounted module corresponding to the license plate number for broadcast.

[0155] From the above description, it can be seen that the vehicle driving intelligent control device provided in the embodiment of the present application can realize multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle driving trajectory, and the traffic flow prediction and risk assessment model is trained at the edge. The cloud platform integrates the data of multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system.

[0156] From a hardware perspective, in order to effectively address the shortcomings of traditional technologies in scene perception, data collaboration, and early warning decision-making, and significantly improve the intelligence level and service quality of assisted driving systems, this application provides an embodiment of an electronic device for implementing all or part of the content of the vehicle driving intelligent control method. The electronic device specifically includes the following content:

[0157] A processor, memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to transmit information between the vehicle driving intelligent control device and related devices such as core business systems, user terminals, and related databases; the logic controller can be a desktop computer, a tablet computer, a mobile terminal, etc., but this embodiment is not limited thereto. In this embodiment, the logic controller can be implemented with reference to the embodiments of the vehicle driving intelligent control method and the vehicle driving intelligent control device in the embodiments, the contents of which are incorporated herein and repeated parts are not repeated.

[0158] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0159] In practical applications, portions of the vehicle driving intelligent control method may be executed on the electronic device side as described above, or all operations may be performed on the client device. The specific selection may depend on the processing capabilities of the client device and the limitations of the user's usage scenario. This application does not impose any restrictions on this. If all operations are performed on the client device, the client device may also include a processor.

[0160] The aforementioned client device may include a communication module (i.e., a communication unit) capable of establishing a communication connection with a remote server to facilitate data transmission with the server. The server may include a server at the task scheduling center or, in other implementation scenarios, a server on an intermediate platform, such as a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may comprise a single computer device, a server cluster consisting of multiple servers, or a distributed server configuration.

[0161] Figure 3 Schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 3 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that the Figure 3 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0162] In one embodiment, the vehicle driving intelligent control method function may be integrated into the central processing unit 9100. The central processing unit 9100 may be configured to perform the following control:

[0163] Step S101: Setting up analysis and identification units along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. Deploying an on-board module on the vehicle side. The on-board module establishes a connection with and registers with the cloud platform via an IoT communication module. The on-board module calls the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks.

[0164] Step S102: The license plate capture camera acquires the vehicle's license plate number, license plate color, and vehicle model information, the wide-angle camera acquires real-time road images, the environmental detection equipment acquires road visibility and road surface state parameters, the edge box extracts vehicle driving characteristics based on the real-time road images, the edge box trains a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and sends the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform;

[0165] Step S103: The cloud platform receives data uploaded by a plurality of the analysis and identification units, determines whether to trigger regional linkage based on a preset road traffic strategy and the risk assessment value, and when regional linkage is triggered, issues linkage instructions to the relevant analysis and identification units according to the regional linkage network and establishes a communication link, receives the traffic flow prediction results uploaded by the relevant analysis and identification units, and generates warning information including real-time road conditions, recommended detour routes and safe vehicle speeds based on the traffic flow prediction results, and sends the warning information to the vehicle-mounted module corresponding to the license plate number for broadcast.

[0166] As can be seen from the above description, the electronic device provided in the embodiment of the present application realizes multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle's driving trajectory, and the traffic flow prediction and risk assessment model is trained at the edge. The cloud platform integrates the data of multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system.

[0167] In another embodiment, the vehicle driving intelligent control device can be configured separately from the central processing unit 9100. For example, the vehicle driving intelligent control device can be configured as a chip connected to the central processing unit 9100, and the vehicle driving intelligent control method function can be realized through the control of the central processing unit.

[0168] like Figure 3 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 3 In addition, the electronic device 9600 may also include all components shown in Figure 3 For components not shown, reference may be made to the prior art.

[0169] like Figure 3As shown, the central processing unit 9100 is sometimes also referred to as a controller or operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0170] Memory 9140 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and also store programs that execute the relevant information. The CPU 9100 can execute the programs stored in memory 9140 to implement information storage or processing.

[0171] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 may be, for example, a keypad or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0172] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), or SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is capable of storing additional data. Examples of such memory are sometimes referred to as EPROMs. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs, or processes used by the central processing unit 9100 to execute operations of the electronic device 9600.

[0173] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, images, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various driver programs for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0174] The communication module 9110 is a transmitter / receiver that transmits and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0175] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless local area network modules. The communication module 9110 (transmitter / receiver) is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130, providing audio output via the speaker 9131 and receiving audio input from the microphone 9132, thereby implementing common telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 9130 is coupled to the central processing unit 9100, enabling local recording via the microphone 9132 and playback of stored audio via the speaker 9131.

[0176] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the vehicle driving intelligent control method in the above-mentioned embodiments, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements all steps of the vehicle driving intelligent control method in the above-mentioned embodiments, where the execution subject is a server or a client. For example, when the processor executes the computer program, the following steps are implemented:

[0177] Step S101: Setting up analysis and identification units along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. Deploying an on-board module on the vehicle side. The on-board module establishes a connection with and registers with the cloud platform via an IoT communication module. The on-board module calls the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks.

[0178] Step S102: The license plate capture camera acquires the vehicle's license plate number, license plate color, and vehicle model information, the wide-angle camera acquires real-time road images, the environmental detection equipment acquires road visibility and road surface state parameters, the edge box extracts vehicle driving characteristics based on the real-time road images, the edge box trains a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and sends the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform;

[0179] Step S103: The cloud platform receives data uploaded by a plurality of the analysis and identification units, determines whether to trigger regional linkage based on a preset road traffic strategy and the risk assessment value, and when regional linkage is triggered, issues linkage instructions to the relevant analysis and identification units according to the regional linkage network and establishes a communication link, receives the traffic flow prediction results uploaded by the relevant analysis and identification units, and generates warning information including real-time road conditions, recommended detour routes and safe vehicle speeds based on the traffic flow prediction results, and sends the warning information to the vehicle-mounted module corresponding to the license plate number for broadcast.

[0180] As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application realizes multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle's driving trajectory, and the traffic flow prediction and risk assessment model is trained at the edge. The cloud platform integrates the data of multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system.

[0181] The embodiments of the present application also provide a computer program product capable of implementing all steps of the vehicle driving intelligent control method in the above-mentioned embodiments, where the execution subject is a server or a client. When the computer program / instructions are executed by a processor, the computer program / instructions implement the steps of the vehicle driving intelligent control method. For example, the computer program / instructions implement the following steps:

[0182] Step S101: Setting up analysis and identification units along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. Deploying an on-board module on the vehicle side. The on-board module establishes a connection with and registers with the cloud platform via an IoT communication module. The on-board module calls the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks.

[0183] Step S102: The license plate capture camera acquires the vehicle's license plate number, license plate color, and vehicle model information, the wide-angle camera acquires real-time road images, the environmental detection equipment acquires road visibility and road surface state parameters, the edge box extracts vehicle driving characteristics based on the real-time road images, the edge box trains a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and sends the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform;

[0184] Step S103: The cloud platform receives data uploaded by a plurality of the analysis and identification units, determines whether to trigger regional linkage based on a preset road traffic strategy and the risk assessment value, and when regional linkage is triggered, issues linkage instructions to the relevant analysis and identification units according to the regional linkage network and establishes a communication link, receives the traffic flow prediction results uploaded by the relevant analysis and identification units, and generates warning information including real-time road conditions, recommended detour routes and safe vehicle speeds based on the traffic flow prediction results, and sends the warning information to the vehicle-mounted module corresponding to the license plate number for broadcast.

[0185] As can be seen from the above description, the computer program product provided in the embodiment of the present application realizes multi-dimensional data collection through edge boxes, smart cameras and environmental detection equipment. The regional linkage network is dynamically divided based on the vehicle's driving trajectory, and the traffic flow prediction and risk assessment model is trained at the edge. The cloud platform integrates the data of multiple analysis and recognition units, triggers the regional linkage mechanism according to the road traffic strategy and risk assessment value, and generates accurate early warning information including real-time road conditions, recommended detour routes and safe vehicle speeds. This method effectively solves the shortcomings of traditional technologies in scene perception, data collaboration and early warning decision-making, and significantly improves the intelligence level and service quality of the assisted driving system.

[0186] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatuses, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0187] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0188] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0189] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0190] Specific embodiments are used in the present invention to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A vehicle driving intelligent control method, characterized in that: The method comprises: Analysis and identification units are set up along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. On-board modules are deployed on the vehicle side. The on-board modules establish a connection with and register with the cloud platform via the Internet of Things communication module. The on-board modules call the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks. The license plate capture camera obtains the vehicle's license plate number, license plate color and vehicle model information, the wide-angle camera obtains real-time road images, the environmental detection equipment obtains road visibility and road surface state parameters, the edge box extracts vehicle driving characteristics based on the real-time road images, the edge box trains a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and sends the vehicle driving characteristics, traffic flow prediction results, risk assessment values ​​and environmental parameters collected by each analysis and recognition unit to the cloud platform; The cloud platform receives data packets uploaded by the plurality of analysis and identification units, extracts the risk assessment value, traffic flow, and speed index parameters from the data packets, and compares the index parameters with thresholds in a road traffic strategy, which includes a traffic flow density threshold, an average speed threshold, and a unit mileage accident risk threshold. When the index parameters of any of the analysis and identification units exceed the corresponding thresholds, a regional linkage judgment is triggered. The cloud platform determines an affected range based on the location of the analysis and identification unit that triggered the linkage. The cloud platform selects the analysis and identification units within the affected range from the regional linkage network as linkage targets, generates a linkage session including a linkage target identification code, creates a data sharing channel based on the linkage session, issues a linkage instruction including sharing channel configuration information to the linkage target, receives a confirmation response returned by the linkage target via the data sharing channel, establishes a communication link between the linkage targets, and receives the traffic flow prediction results uploaded by the linkage targets. Based on the traffic flow prediction results, the cloud platform generates warning information including real-time road conditions, recommended detour routes, and safe vehicle speed, and transmits it to the vehicle-mounted module corresponding to the license plate number for broadcast.

2. The vehicle driving intelligent control method according to claim 1, characterized in that: The analysis and identification unit is set up along the road. The analysis and identification unit includes an edge box, a smart camera and an environmental detection device. The edge box establishes a communication connection with the cloud platform and registers. The smart camera includes a license plate capture camera and a wide-angle camera. The environmental detection device collects road environment parameters, including: Deploy the analysis and identification unit at a key location on the road, initialize and configure parameters of the edge box, obtain a unique identification code through the IoT communication module, send a registration request to the cloud platform based on the unique identification code, and the cloud platform returns registration authorization information. The edge box then establishes a secure communication link with the cloud platform based on the registration authorization information. The edge box establishes a communication connection with the smart camera and the environmental detection device, calibrates the angle and focal length of the smart camera, sets the license plate capture camera to point in the direction of vehicle traffic, and sets the wide-angle camera to a panoramic road monitoring angle. A sub-device management group is established with the edge box as the center, and the sampling period and trigger threshold of the environmental detection device are configured. The edge box obtains environmental parameters including visibility, temperature, humidity and light intensity from the environmental detection device at preset time intervals.

3. The vehicle driving intelligent control method according to claim 1, characterized in that: The vehicle-mounted module is deployed on the vehicle side, the vehicle-mounted module establishes a connection with the cloud platform through the Internet of Things communication module and registers, the vehicle-mounted module calls the vehicle-machine interface to obtain the vehicle's driving trajectory, and divides the multiple analysis and identification units into a regional linkage network based on the driving trajectory, including: The on-board module obtains a unique device identifier through the Internet of Things communication module, and sends a registration request including the vehicle VIN code to the cloud platform based on the unique device identifier. The cloud platform returns a device authorization code, and the on-board module establishes a data transmission channel with the cloud platform based on the device authorization code. The on-board module calls the vehicle computer CAN bus interface to collect the vehicle's real-time position coordinates, driving speed, and direction angle data; The on-board module uploads the position coordinates, driving speed and direction angle data to the cloud platform at preset time intervals. The cloud platform maps the vehicle position coordinates to an electronic map based on a geographic information system, determines a forward predicted path according to the vehicle's driving direction, extracts the analysis and identification units within the coverage of the forward predicted path, constructs the extracted analysis and identification units into a regional linkage network, and assigns a network priority to each of the analysis and identification units.

4. The vehicle driving intelligent control method according to claim 1, characterized in that: The license plate capture camera obtains the vehicle's license plate number, license plate color, and vehicle model information; the wide-angle camera obtains real-time road images; the environmental detection equipment obtains road visibility and road surface state parameters; and the edge box extracts vehicle driving characteristics based on the real-time road images, including: The license plate capture camera collects image data of vehicles passing by, and the edge box processes the image data based on a convolutional neural network model, extracts license plate area features and performs character segmentation, recognizes license plate numbers and color information, analyzes vehicle body contour features through a deep learning model to obtain vehicle model classification results, and stores the license plate number, color information, and vehicle model classification results in a cache database of the edge box; The wide-angle camera collects road traffic video streams at a preset frame rate. The environmental detection equipment obtains visibility values ​​based on the laser ranging principle and detects road surface state parameters through surface temperature sensors and humidity sensors. The edge box performs target detection and tracking processing on the video stream, extracts vehicle traffic trajectory, vehicle speed, and vehicle spacing driving characteristic parameters, and the edge box establishes a mapping relationship between the driving characteristic parameters and license plate information.

5. The vehicle driving intelligent control method according to claim 1, characterized in that: The edge box trains a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and sends the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform, including: The edge box divides vehicle driving characteristic parameters into training data sets according to time series, uses a long short-term memory neural network to build a network structure of a traffic flow prediction model, uses vehicle speed, vehicle density, and travel time as input features, iteratively trains the network structure to obtain a traffic flow prediction model, and builds a risk assessment model based on a decision tree algorithm, using vehicle spacing, relative speed, and road surface state parameters as input variables to calculate a collision risk assessment value; The edge box organizes the vehicle driving characteristics, environmental parameters and timestamp information into a data packet, which contains the future traffic flow state prediction results output by the traffic flow prediction model and the risk assessment value calculated by the risk assessment model. The edge box sends the data packet to the cloud platform through a secure communication link according to a preset data upload cycle, and the cloud platform performs time synchronization and data verification on the received data packet.

6. The vehicle driving intelligent control method according to claim 1, characterized in that: The receiving of the traffic flow prediction result uploaded by the linkage object, the cloud platform generating warning information including real-time road conditions, recommended detour routes and safe vehicle speed based on the traffic flow prediction result, and sending the warning information to the vehicle-mounted module corresponding to the license plate number for broadcasting, including: The cloud platform receives the traffic flow prediction results uploaded by the linkage object, maps the traffic flow prediction results to road sections based on real-time location coordinates, calculates the congestion index of each road section, and calls the path planning engine to calculate the shortest path and the optimal detour path. The cloud platform inputs the lane-level traffic condition information, the road section congestion index, the average travel speed, and the travel time into the warning information generation model, calculates the recommended safe speed based on the vehicle type and road conditions, and generates warning text content; The cloud platform extracts the license plate information from the cache database of the linkage object, establishes a correspondence between the warning text content and the license plate information, and generates a warning message containing an addressing identifier. The cloud platform queries the communication address of the on-board module and sends the warning message to the corresponding on-board module through the message queue. After receiving the warning message, the on-board module calls the speech synthesis engine to broadcast it and displays the warning content on the vehicle screen.

7. A vehicle driving intelligent control device, characterized in that: The device comprises: The system construction module is used to set up analysis and identification units along the road. The analysis and identification units include edge boxes, smart cameras, and environmental detection equipment. The edge boxes establish a communication connection with and register with the cloud platform. The smart cameras include license plate capture cameras and wide-angle cameras. The environmental detection equipment collects road environment parameters. The vehicle-mounted module is deployed on the vehicle side. The vehicle-mounted module establishes a connection with and registers with the cloud platform via the Internet of Things communication module. The vehicle-mounted module calls the vehicle-machine interface to obtain the vehicle's driving trajectory. Based on the driving trajectory, multiple analysis and identification units are divided into regional linkage networks. A traffic prediction module is configured to use the license plate capture camera to capture the vehicle's license plate number, license plate color, and vehicle model information, the wide-angle camera to capture real-time road images, the environmental detection equipment to capture road visibility and road surface state parameters, the edge box to extract vehicle driving characteristics based on the real-time road images, the edge box to train a traffic flow prediction model and a risk assessment model based on the vehicle driving characteristics, and to send the vehicle driving characteristics, traffic flow prediction results, risk assessment values, and environmental parameters collected by each analysis and recognition unit to the cloud platform; The assisted driving module is configured to receive data packets uploaded by the plurality of analysis and identification units on the cloud platform, extract the risk assessment value, traffic flow, and speed index parameters from the data packets, and compare the index parameters with thresholds in a road traffic policy, wherein the road traffic policy includes a traffic flow density threshold, an average speed threshold, and a unit mileage accident risk threshold. When the index parameter of any of the analysis and identification units exceeds the corresponding threshold, a regional linkage judgment is triggered, and the cloud platform determines the affected range based on the location of the analysis and identification unit that triggered the linkage. The cloud platform selects the analysis and identification units within the affected range from the regional linkage network as linkage targets, generates a linkage session including a linkage target identification code, creates a data sharing channel based on the linkage session, issues a linkage instruction including sharing channel configuration information to the linkage target, receives a confirmation response returned by the linkage target via the data sharing channel, completes the establishment of a communication link between the linkage targets, and receives the traffic flow prediction results uploaded by the linkage targets. The cloud platform generates warning information including real-time road conditions, recommended detour routes, and safe vehicle speed based on the traffic flow prediction results, and transmits the warning information to the vehicle-mounted module corresponding to the license plate number for broadcast.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the vehicle driving intelligent control method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle driving intelligent control method according to any one of claims 1 to 6 are implemented.

Images