Vehicle-road cooperation speed control method and system based on multivariate data perception

Abstract

The invention provides a vehicle-road cooperation speed control method based on multivariate data perception, and relates to the field of intelligent traffic, and the method comprises the steps: building a distributed vehicle-road cooperation network of a vehicle with the speed to be controlled, collecting the multivariate data of the vehicle with the speed to be controlled through the distributed vehicle-road cooperation network, carrying out the data synchronization of the multivariate data, and obtaining the synchronous multivariate data; constructing a graph neural network of the synchronous multivariate data to extract multivariate vehicle driving characteristics of the synchronous multivariate data, and analyzing the vehicle driving scene state of the vehicle with the speed to be controlled by using the trained vehicle scene analysis model; and constructing an adaptive speed decision model of the vehicle with the to-be-controlled speed, identifying the optimal speed parameter of the vehicle with the to-be-controlled speed by using the adaptive speed decision model, and executing vehicle-road cooperative speed control of the vehicle with the to-be-controlled speed based on the optimal speed parameter. The method has the beneficial effects that the optimal speed parameter is provided for the vehicle with the to-be-controlled speed in the vehicle-road cooperative control, so that the driving safety of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to a vehicle-road cooperative speed control method and system based on multivariate data perception, and belongs to the field of intelligent transportation. Background Art

[0002] Vehicle-road cooperative speed control refers to the use of communication technology between vehicles and between vehicles and roadside infrastructure, as well as information collected by on-board sensors and roadside sensors, to dynamically manage and control vehicle speeds through intelligent algorithms. The purpose is to improve road traffic efficiency, reduce traffic accidents, improve traffic smoothness, and reduce environmental pollution.

[0003] At present, vehicle-road cooperative speed control mainly relies on fixed rules and preset parameters. The vehicle speed is statically managed through communication between the vehicle and the roadside infrastructure. This method has the disadvantages of slow response, lack of flexibility and inability to adapt to complex and changing traffic conditions, thereby reducing road traffic efficiency and driving safety. Summary of the invention

[0004] The present invention provides a vehicle-road cooperative speed control method and system based on multivariate data perception, the main purpose of which is to improve the safety of traveling vehicles.

[0005] To achieve the above object, the present invention provides a vehicle-road cooperative speed control method based on multivariate data perception, comprising:

[0006] Acquire a vehicle driving path and vehicle information of a vehicle to be speed-controlled, acquire historical vehicle driving data of the vehicle driving path, and analyze vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data;

[0007] According to the vehicle driving path characteristics, construct a multi-path monitoring device for the vehicle driving path, configure a multi-vehicle monitoring device for the vehicle to be controlled based on the vehicle information, and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device;

[0008] Based on the network slicing algorithm and the distributed network architecture, a distributed vehicle-road cooperative network of the vehicle to be controlled is established, multivariate data of the vehicle to be controlled is collected by using the distributed vehicle-road cooperative network, and the multivariate data is synchronized by using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data;

[0009] Constructing a graph neural network of the synchronized multivariate data, extracting multivariate vehicle driving features of the synchronized multivariate data based on the graph neural network, and analyzing the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving features;

[0010] Based on the vehicle driving path characteristics, the vehicle information and preset vehicle driving constraints, an adaptive speed decision model of the vehicle to be speed controlled is constructed; based on the vehicle driving scene state, the adaptive speed decision model is used to identify the optimal speed parameters of the vehicle to be speed controlled; and based on the optimal speed parameters, vehicle-road cooperative speed control of the vehicle to be speed controlled is performed.

[0011] Optionally, analyzing the vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data includes:

[0012] Preprocessing the historical vehicle driving data to obtain preprocessed driving data;

[0013] Dividing the pre-processed driving data into path environment data and historical vehicle data;

[0014] Extracting path environment features and historical vehicle driving features of the path environment data and historical vehicle data respectively;

[0015] Analyzing the characteristic correlation coefficients of the path environment characteristics and the historical vehicle driving characteristics;

[0016] Based on the feature association coefficient, a preset feature mining algorithm is used to mine the vehicle driving path features of the vehicle driving path.

[0017] Optionally, the analyzing the characteristic correlation coefficient of the path environment characteristics and the historical vehicle driving characteristics includes:

[0018] The path environment features and the historical vehicle driving features are integrated to obtain integrated features;

[0019] Calculating the multidimensional support and multidimensional confidence of the fusion feature;

[0020] Based on the multidimensional support and multidimensional confidence, the multidimensional lift of the fusion feature is calculated using the following formula:

[0021] Multilife(A→B,C)=MultiCon(A→B,C) / MultiSupport(B,C)

[0022] Among them, Multilife(A→B, C) represents the multidimensional improvement between fusion features A, fusion features B and fusion features C, MultiCon(A→B, C) represents the multidimensional confidence between fusion features A, fusion features B and fusion features C, and MultiSupport(B, C) represents the multidimensional support between fusion features B and fusion features C;

[0023] According to the multi-dimensional lift, a feature correlation coefficient of the fused feature is determined.

[0024] Optionally, the multi-path monitoring device for constructing the vehicle driving path according to the vehicle driving path characteristics includes:

[0025] Marking the path nodes of the vehicle's travel path;

[0026] Based on the vehicle driving path characteristics, identifying the risk level and risk description of the path node;

[0027] Calculating the value to be monitored of the path node according to the risk degree;

[0028] Based on the value to be monitored, marking the node to be monitored of the path node;

[0029] Analyzing the monitoring requirements of the nodes to be monitored through the risk description;

[0030] According to the monitoring requirements, a multi-path monitoring device of the node to be monitored is determined.

[0031] Optionally, the establishing of a distributed vehicle-road cooperative network of the vehicle to be controlled in terms of speed based on the network slicing algorithm and the distributed network architecture includes:

[0032] Determining the vehicle-road cooperative network requirements and network physical resources of the vehicle to be controlled in terms of speed;

[0033] Based on the distributed network architecture, the network physical resources are divided into network slices, and the quality of service parameters of the network slices are configured;

[0034] Analyzing the network status of the network slice by using the quality of service parameter;

[0035] According to the vehicle-road cooperative network requirements and the network status, using the network slicing algorithm to configure the dynamic slice resources of the network slice;

[0036] Analyzing the slice performance of the network slice based on the slice dynamic resources;

[0037] When the slice performance meets the preset slice performance threshold, the multi-path monitoring device and the multi-vehicle monitoring device corresponding to the speed-controlled vehicle are connected to the network slice to obtain a distributed vehicle-road cooperative network for the speed-controlled vehicle.

[0038] Optionally, analyzing the network status of the network slice by using the quality of service parameter includes:

[0039] Based on the quality of service parameter, analyzing the status influencing factor of the network slice;

[0040] Analyze the network impact relationship between the state impact factor and the network slice;

[0041] According to the network influence relationship, construct a dynamic weight allocation algorithm for the state influence factor;

[0042] Based on the dynamic weight allocation algorithm, the network quality of the network slice is calculated using the following formula:

[0043]

[0044] Among them, τ represents the network quality of the network slice, G represents the weight normalization function, σ represents the dynamic weight allocation algorithm, and r α represents the αth state impact factor, R α represents the real-time network influence coefficient of the αth state influence factor, and m represents the number of state influence factors;

[0045] The network status of the network slice is determined through the network quality.

[0046] Optionally, the using a preset high-precision time synchronization algorithm to synchronize the multivariate data to obtain synchronized multivariate data includes:

[0047] extracting a timestamp of the multivariate data;

[0048] calculating a timestamp difference of said timestamps;

[0049] determining a time source for the multivariate data;

[0050] According to the time source and the timestamp difference, configuring synchronization algorithm parameters of the high-precision time synchronization algorithm;

[0051] The multivariate data is synchronized according to the synchronization algorithm parameters to obtain synchronized multivariate data.

[0052] Optionally, constructing the graph neural network for synchronizing multivariate data includes:

[0053] The multivariate path monitoring device and the multivariate vehicle monitoring device corresponding to the synchronized multivariate data are used as graph nodes;

[0054] Analyzing the device connection relationship between the multi-path monitoring device and the multi-vehicle monitoring device;

[0055] Constructing a graph structure of the synchronized multivariate data according to the graph nodes and the device connection relationship;

[0056] Analyzing computational efficiency requirements of the synchronized multivariate data;

[0057] Determine the graph neural attention network architecture for synchronizing multivariate data based on the computational efficiency requirement, and configure network architecture parameters of the graph neural attention network architecture;

[0058] The graph neural network for synchronized multivariate data is constructed according to the graph structure, the graph neural attention network architecture and the network architecture parameters.

[0059] Optionally, constructing the graph neural network for synchronizing multivariate data according to the graph structure, the graph neural attention network architecture, and the network architecture parameters includes:

[0060] Based on the graph structure, the graph neural attention network architecture and the network architecture parameters, construct an initial graph neural network for the synchronized multivariate data;

[0061] Initializing the original features of the graph nodes corresponding to the initial graph neural network to obtain the initial features of the nodes;

[0062] Calculating the attention energy of the graph node according to the initial features of the node;

[0063] Calculating the attention coefficient of the graph node by using the attention energy;

[0064] Based on the attention coefficient, the updated features of the graph nodes corresponding to the initial graph neural network are calculated using the following formula:

[0065]

[0066] Among them, S ‘ e represents the updated features of graph node e, ω represents the nonlinear activation function, l ev represents the attention coefficient between graph node e and graph node v, θ represents the weight matrix of the initial graph neural network, S v Represents the initial node features of graph node v, C e Represents the set of neighbor nodes of graph node e;

[0067] Analyzing the feature extraction performance of the initial graph neural network through the updated features;

[0068] When the feature extraction performance meets a preset feature extraction performance standard, the initial graph neural network is used as the graph neural network for synchronized multivariate data.

[0069] In order to solve the above problems, the present invention further provides a vehicle-road cooperative speed control system based on multivariate data perception, the system comprising:

[0070] A driving path characteristic analysis module, used to obtain a vehicle driving path and vehicle information of a vehicle to be speed-controlled, obtain historical vehicle driving data of the vehicle driving path, and analyze vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data;

[0071] A distributed network construction module, used to construct a multi-path monitoring device for the vehicle's driving path according to the vehicle's driving path characteristics, configure a multi-vehicle monitoring device for the vehicle to be controlled based on the vehicle information, and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device;

[0072] A synchronous multivariate data acquisition module is used to establish a distributed vehicle-road cooperative network of the vehicle to be controlled in terms of speed based on the network slicing algorithm and the distributed network architecture, collect multivariate data of the vehicle to be controlled in terms of speed using the distributed vehicle-road cooperative network, and synchronize the multivariate data using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data;

[0073] A driving scene state analysis module, used to construct a graph neural network of the synchronized multivariate data, extract multivariate vehicle driving features of the synchronized multivariate data based on the graph neural network, and analyze the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving features;

[0074] The vehicle-road cooperative speed control module is used to construct an adaptive speed decision model of the vehicle to be speed controlled based on the vehicle driving path characteristics, the vehicle information and preset vehicle driving constraints; based on the vehicle driving scene state, the adaptive speed decision model is used to identify the optimal speed parameters of the vehicle to be speed controlled; and based on the optimal speed parameters, the vehicle-road cooperative speed control of the vehicle to be speed controlled is performed.

[0075] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0076] at least one processor; and,

[0077] a memory communicatively connected to the at least one processor; wherein,

[0078] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the above-mentioned vehicle-road cooperative speed control method based on multivariate data perception.

[0079] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned vehicle-road collaborative speed control method based on multivariate data perception.

[0080] Compared with the problems described in the background technology, the present invention analyzes the vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data, which can comprehensively analyze the historical vehicle driving data, understand the vehicle driving characteristics, and provide a basis for subsequent vehicle speed control; further, the present invention constructs a multi-path monitoring device for the vehicle driving path according to the vehicle driving path characteristics to realize real-time monitoring and management of the vehicle driving path, further, the present invention constructs the network slicing algorithm and distributed network architecture of the multi-path monitoring device and the multi-vehicle monitoring device to provide a basis for subsequent data transmission and processing requirements, further, the present invention establishes a distributed vehicle-road cooperative network of the vehicle to be controlled based on the network slicing algorithm and distributed network architecture, which can establish an efficient and flexible distributed vehicle-road cooperative network to support the data transmission and processing requirements of the vehicle-road cooperative speed control system, and then The present invention constructs a graph neural network of the synchronized multivariate data to construct an effective graph neural network to provide support for vehicle driving state analysis and vehicle-road cooperative speed control. The present invention extracts the multivariate vehicle driving characteristics of the synchronized multivariate data based on the graph neural network. Based on the multivariate vehicle driving characteristics, the vehicle driving scene state of the speed-controlled vehicle is analyzed using a trained vehicle scene analysis model, which can provide a basis for the subsequent vehicle speed control. Finally, the present invention constructs an adaptive speed decision model of the speed-controlled vehicle based on the vehicle driving path characteristics, the vehicle information and the preset vehicle driving constraints to provide the vehicle with the best speed parameters to improve the safety of the driving vehicle and use the adaptive speed decision model to identify the optimal speed parameters of the speed-controlled vehicle, which helps to guide the vehicle to adjust the speed under different traffic and environmental conditions to achieve safer, more efficient and environmentally friendly driving. Therefore, the present invention can improve the safety of driving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 A schematic flow chart of a vehicle-road cooperative speed control method based on multivariate data perception provided by an embodiment of the present invention;

[0082] Figure 2 A functional module diagram of a vehicle-road cooperative speed control system based on multivariate data perception provided by an embodiment of the present invention;

[0083] Figure 3A schematic diagram of the structure of an electronic device of a vehicle-road cooperative speed control system based on multivariate data perception provided by an embodiment of the present invention;

[0084] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0085] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0086] The embodiment of the present application provides a vehicle-road cooperative speed control method based on multivariate data perception. The execution subject of the vehicle-road cooperative speed control method based on multivariate data perception includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the vehicle-road cooperative speed control method based on multivariate data perception can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0087] Embodiment 1:

[0088] Reference Figure 1 FIG. 1 is a flow chart of a vehicle-road cooperative speed control method based on multivariate data perception provided by an embodiment of the present invention. In this embodiment, the vehicle-road cooperative speed control method based on multivariate data perception includes:

[0089] S1. Acquire a vehicle driving path and vehicle information of a vehicle to be speed-controlled, acquire historical vehicle driving data of the vehicle driving path, and analyze vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data.

[0090] It should be explained that the vehicle driving path refers to the actual trajectory of the vehicle on the road, including the starting point, the end point and the various road sections passed along the way; the vehicle information refers to the basic attributes of the vehicle, such as vehicle model, license plate number, vehicle color, etc., as well as possible other vehicle characteristics, such as vehicle performance parameters, on-board equipment configuration, etc.; the historical vehicle driving data refers to the data records left by the vehicle during its past driving process, including the vehicle's speed, location, driving time, driving route, traffic light status, road conditions, weather conditions and other data.

[0091] The present invention analyzes the vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data, which can comprehensively analyze the historical vehicle driving data, understand the vehicle driving characteristics, and provide a basis for subsequent vehicle speed control.

[0092] In detail, the analyzing the vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data includes:

[0093] Preprocessing the historical vehicle driving data to obtain preprocessed driving data;

[0094] Dividing the pre-processed driving data into path environment data and historical vehicle data;

[0095] Extracting path environment features and historical vehicle driving features of the path environment data and historical vehicle data respectively;

[0096] Analyzing the characteristic correlation coefficients of the path environment characteristics and the historical vehicle driving characteristics;

[0097] Based on the feature association coefficient, a preset feature mining algorithm is used to mine the vehicle driving path features of the vehicle driving path.

[0098] Among them, the pre-processed driving data refers to the pre-processed historical vehicle driving data, including speed, position, timestamp, driving route and other data; the path environment data refers to the environmental factor data that affects vehicle driving, such as weather, road conditions, traffic flow, signal light status and other data; the historical vehicle data refers to the driving data of the vehicle itself, such as speed, position, acceleration, etc.; the path environment characteristics refer to the key features extracted from the path environment data, such as road type, weather conditions, etc.; the historical vehicle driving characteristics refer to the key features extracted from the historical vehicle data, such as average speed, acceleration mode, driving mode, etc.; the feature correlation coefficient refers to the analysis of the correlation between the path environment characteristics and the historical vehicle driving characteristics; the feature mining algorithm refers to the algorithm used to mine the vehicle driving path characteristics, such as association rule mining, cluster analysis and other algorithms; the vehicle driving path characteristics refer to the key features of the vehicle driving path obtained through the above analysis, such as the typical driving mode or behavior of the vehicle in a specific environment.

[0099] Furthermore, the analysis of the characteristic correlation coefficient of the path environment characteristics and the historical vehicle driving characteristics includes:

[0100] The path environment features and the historical vehicle driving features are integrated to obtain integrated features;

[0101] Calculating the multidimensional support and multidimensional confidence of the fusion feature;

[0102] Based on the multidimensional support and multidimensional confidence, the multidimensional lift of the fusion feature is calculated using the following formula:

[0103] Multilife(A→B,C)=MultiCon(A→B,C) / MultiSupport(B,C)

[0104] Among them, Multilife(A→B, C) represents the multidimensional improvement between fusion features A, fusion features B and fusion features C, MultiCon(A→B, C) represents the multidimensional confidence between fusion features A, fusion features B and fusion features C, and MultiSupport(B, C) represents the multidimensional support between fusion features B and fusion features C;

[0105] According to the multi-dimensional lift, a feature correlation coefficient of the fused feature is determined.

[0106] Among them, the fusion feature refers to a new feature set formed by combining path environment features and historical vehicle driving features, the multidimensional support refers to the frequency of the combination of fusion features A, fusion features B and fusion features C in all transactions, the multidimensional confidence refers to the proportion of transactions containing fusion features B and fusion features C in transactions containing fusion feature A, and the multidimensional lift refers to an indicator to measure the correlation between fusion features, which reflects the ratio of the proportion of transactions containing fusion features B and fusion features C in transactions containing fusion feature A to the frequency of simultaneous occurrence of these fusion features in all transactions.

[0107] S2. According to the vehicle driving path characteristics, construct a multi-path monitoring device for the vehicle driving path; based on the vehicle information, configure a multi-vehicle monitoring device for the vehicle to be controlled in terms of speed; and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device.

[0108] The present invention constructs a multi-path monitoring device for the vehicle driving path according to the vehicle driving path characteristics to achieve real-time monitoring and management of the vehicle driving path.

[0109] In detail, the multi-path monitoring device for constructing the vehicle driving path according to the vehicle driving path characteristics includes:

[0110] Marking the path nodes of the vehicle's travel path;

[0111] Based on the vehicle driving path characteristics, identifying the risk level and risk description of the path node;

[0112] Calculating the value to be monitored of the path node according to the risk degree;

[0113] Based on the value to be monitored, marking the node to be monitored of the path node;

[0114] Analyzing the monitoring requirements of the nodes to be monitored through the risk description;

[0115] According to the monitoring requirements, a multi-path monitoring device of the node to be monitored is determined.

[0116] Among them, the path node refers to the key location point on the vehicle's driving path, such as intersections, curves, traffic lights, etc., the risk degree refers to an indicator for measuring the risk of the path node, the risk description refers to the specific description of the risk of the path node, including descriptions of possible risk factors, accident types and consequences, etc., the monitored value refers to the value calculated based on the risk degree, which is used to indicate the degree to which the path node needs to be monitored, the node to be monitored refers to the path node that is marked as requiring additional monitoring according to the value to be monitored, the monitoring requirement is determined according to the risk description of the node to be monitored, which defines what types of monitoring are required for these nodes, as well as the frequency and accuracy requirements of the monitoring, and the multi-path monitoring device refers to a combination of multiple devices used to monitor the vehicle's driving path. These devices can cover different types of monitoring requirements, such as cameras, radars, sensors, etc.

[0117] Optionally, the risk degree and risk description of the path node identified based on the vehicle driving path characteristics may be analyzed by statistical analysis technology.

[0118] It should be explained that the multi-vehicle monitoring equipment refers to equipment for monitoring vehicles whose speed is to be controlled, including speed sensors, position locators and other equipment.

[0119] The present invention constructs the network slicing algorithm and distributed network architecture of the multi-path monitoring device and the multi-vehicle monitoring device to provide a basis for subsequent data transmission and processing requirements. Among them, the network slicing algorithm refers to an algorithm for managing and optimizing network resources and the distributed network architecture refers to a decentralized network design that distributes network functions across multiple network nodes.

[0120] S3. Based on the network slicing algorithm and distributed network architecture, a distributed vehicle-road cooperative network for the vehicle to be controlled in terms of speed is established. Multivariate data of the vehicle to be controlled is collected using the distributed vehicle-road cooperative network. The multivariate data is synchronized using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data.

[0121] Based on the network slicing algorithm and distributed network architecture, the present invention establishes a distributed vehicle-road cooperative network for the vehicle to be speed controlled, and can establish an efficient and flexible distributed vehicle-road cooperative network to support the data transmission and processing requirements of the vehicle-road cooperative speed control system.

[0122] In detail, the distributed vehicle-road cooperative network of the vehicle to be controlled in speed is established based on the network slicing algorithm and the distributed network architecture, including:

[0123] Determining the vehicle-road cooperative network requirements and network physical resources of the vehicle to be controlled in terms of speed;

[0124] Based on the distributed network architecture, the network physical resources are divided into network slices, and the quality of service parameters of the network slices are configured;

[0125] Analyzing the network status of the network slice by using the quality of service parameter;

[0126] According to the vehicle-road cooperative network requirements and the network status, using the network slicing algorithm to configure the dynamic slice resources of the network slice;

[0127] Analyzing the slice performance of the network slice based on the slice dynamic resources;

[0128] When the slice performance meets the preset slice performance threshold, the multi-path monitoring device and the multi-vehicle monitoring device corresponding to the speed-controlled vehicle are connected to the network slice to obtain a distributed vehicle-road cooperative network for the speed-controlled vehicle.

[0129] Among them, the vehicle-road cooperative network requirements refer to a series of performance indicators and functional requirements that the network must meet in the vehicle-road cooperative system. These requirements may include real-time data transmission, low latency, high bandwidth, high reliability, security and other requirements. The network physical resources refer to the resources that actually exist in the network infrastructure, such as optical fiber, radio frequency, computing power, storage space and other resources. The network slice refers to the division of network physical resources into multiple logically independent virtual networks. The network status refers to the current operating status of the network, such as excellent, good, medium, poor and very poor status. The service quality parameters refer to a series of parameters used to define the performance of network slices, such as bandwidth, latency, packet loss rate, jitter, availability and other parameters. The slice performance refers to the service quality level achieved by the network slice in actual operation. The slice performance threshold refers to the threshold of the preset quality of service (QoS) parameter, which is used to determine whether the network slice reaches or exceeds the predetermined performance standard. The distributed vehicle-road cooperative network refers to a network established based on the network slicing algorithm and distributed network architecture, which is used to support the vehicle-road cooperative speed control system.

[0130] Further, analyzing the network status of the network slice by using the quality of service parameter includes:

[0131] Based on the quality of service parameter, analyzing the status influencing factor of the network slice;

[0132] Analyze the network impact relationship between the state impact factor and the network slice;

[0133] According to the network influence relationship, construct a dynamic weight allocation algorithm for the state influence factor;

[0134] Based on the dynamic weight allocation algorithm, the network quality of the network slice is calculated using the following formula:

[0135]

[0136] Among them, τ represents the network quality of the network slice, G represents the weight normalization function, σ represents the dynamic weight allocation algorithm, and r α represents the αth state impact factor, R α represents the real-time network influence coefficient of the αth state influence factor, and m represents the number of state influence factors;

[0137] The network status of the network slice is determined through the network quality.

[0138] Among them, the network impact relationship refers to the correlation between the state impact factor and the network slice performance, the dynamic weight allocation algorithm refers to an algorithm for dynamically allocating weights based on the state impact factor and network impact relationship of the network slice, and the weight normalization function refers to a function used to normalize the weights obtained by the dynamic weight allocation algorithm. The normalized weights can ensure that the sum of the weights of each state impact factor is 1, which is convenient for subsequent calculations. The real-time network impact coefficient refers to the degree of influence of the state impact factor calculated based on real-time data and network conditions on the performance of the network slice, and the network quality refers to the comprehensive performance of the network slice on all considered state impact factors.

[0139] It should be explained that the multivariate data refers to data collected by various sensors, including vehicle status data, environmental data, sensor data, communication data and other data.

[0140] The present invention utilizes a preset high-precision time synchronization algorithm to synchronize the multivariate data, thereby obtaining accurate and consistent synchronized multivariate data, thereby providing reliable data support for the vehicle-road cooperative speed control system.

[0141] In detail, the using a preset high-precision time synchronization algorithm to synchronize the multivariate data to obtain synchronized multivariate data includes:

[0142] extracting a timestamp of the multivariate data;

[0143] calculating a timestamp difference of said timestamps;

[0144] determining a time source for the multivariate data;

[0145] According to the time source and the timestamp difference, configuring synchronization algorithm parameters of the high-precision time synchronization algorithm;

[0146] The multivariate data is synchronized according to the synchronization algorithm parameters to obtain synchronized multivariate data.

[0147] Among them, the timestamp refers to a mark that records the data collection time, usually including information such as year, month, day, hour, minute, second and millisecond; the timestamp difference refers to the difference between the timestamps of data collected by different sensors; the time source refers to the reference time for determining the time base of multivariate data; the synchronization algorithm parameters refer to a set of parameters used to adjust the timestamp to achieve synchronization; and the synchronized multivariate data refers to the multivariate data adjusted by a high-precision time synchronization algorithm.

[0148] Optionally, the calculating of the timestamp difference of the timestamp may be implemented by calculating the difference between the timestamp of each data point and a reference timestamp.

[0149] S4. Construct a graph neural network for the synchronized multivariate data, extract multivariate vehicle driving characteristics of the synchronized multivariate data based on the graph neural network, and analyze the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving characteristics.

[0150] The present invention constructs the graph neural network of synchronized multivariate data to construct an effective graph neural network to provide support for vehicle driving status analysis and vehicle-road collaborative speed control.

[0151] In detail, the step of constructing the graph neural network for synchronizing multivariate data includes:

[0152] The multivariate path monitoring device and the multivariate vehicle monitoring device corresponding to the synchronized multivariate data are used as graph nodes;

[0153] Analyzing the device connection relationship between the multi-path monitoring device and the multi-vehicle monitoring device;

[0154] Constructing a graph structure of the synchronized multivariate data according to the graph nodes and the device connection relationship;

[0155] Analyzing computational efficiency requirements of the synchronized multivariate data;

[0156] Determine the graph neural attention network architecture for synchronizing multivariate data based on the computational efficiency requirement, and configure network architecture parameters of the graph neural attention network architecture;

[0157] The graph neural network for synchronized multivariate data is constructed according to the graph structure, the graph neural attention network architecture and the network architecture parameters.

[0158] Among them, the graph node refers to the entity represented in the graph structure, such as a multi-path monitoring device and a multi-vehicle monitoring device, and the device connection relationship refers to the connection method between the multi-path monitoring device and the multi-vehicle monitoring device. These relationships may be based on physical connections, data associations or other dependencies. The graph structure refers to a network composed of graph nodes and edges connecting these nodes. The computational efficiency requirement refers to the demand for computing resources when building a graph neural network. This includes requirements for data processing speed, real-time performance, etc. The graph neural attention network architecture is a graph neural network that uses an attention mechanism to learn dependencies between nodes. The network architecture parameters refer to parameters used to configure the graph neural attention network, such as the number of layers, the number of hidden units, attention weights, etc. These parameters determine the performance and computational efficiency of the network. The graph neural network refers to a deep learning model specifically used to process graph data. It is able to learn the features of nodes from a graph.

[0159] Furthermore, constructing the graph neural network for synchronizing multivariate data according to the graph structure, the graph neural attention network architecture, and the network architecture parameters includes:

[0160] Based on the graph structure, the graph neural attention network architecture and the network architecture parameters, construct an initial graph neural network for the synchronized multivariate data;

[0161] Initializing the original features of the graph nodes corresponding to the initial graph neural network to obtain the initial features of the nodes;

[0162] Calculating the attention energy of the graph node according to the initial features of the node;

[0163] Calculating the attention coefficient of the graph node by using the attention energy;

[0164] Based on the attention coefficient, the updated features of the graph nodes corresponding to the initial graph neural network are calculated using the following formula:

[0165]

[0166] Among them, S ‘ e represents the updated features of graph node e, ω represents the nonlinear activation function, l ev represents the attention coefficient between graph node e and graph node v, θ represents the weight matrix of the initial graph neural network, S v Represents the initial node features of graph node v, C eRepresents the set of neighbor nodes of graph node e;

[0167] Analyzing the feature extraction performance of the initial graph neural network through the updated features;

[0168] When the feature extraction performance meets a preset feature extraction performance standard, the initial graph neural network is used as the graph neural network for synchronized multivariate data.

[0169] Among them, the initial graph neural network refers to the first graph neural network model used in the construction process, the node initial feature refers to the feature vector initialized for each node (such as multi-path monitoring equipment and multi-vehicle monitoring equipment) before building the graph neural network, the attention energy refers to a measure used to calculate the attention coefficient in the graph neural network, the attention coefficient refers to a weight used to weighted aggregate neighbor node features in the graph neural network, the updated feature graph neural network generates a feature vector during the feature update process, the feature extraction performance refers to the performance of the graph neural network in extracting features, and the feature extraction performance standard refers to a preset threshold or requirement for measuring feature extraction performance.

[0170] The present invention extracts the multivariate vehicle driving characteristics of the synchronized multivariate data based on the graph neural network, and based on the multivariate vehicle driving characteristics, uses a trained vehicle scene analysis model to analyze the vehicle driving scene state of the vehicle to be controlled in terms of speed, which can provide a basis for subsequent vehicle speed control.

[0171] It should be explained that the multivariate vehicle driving features refer to a collection of multiple features related to vehicle driving extracted from synchronized multivariate data, and the vehicle scene analysis model refers to a machine learning model or a deep learning model used to analyze vehicle driving scenes. The model learns how to identify and classify different vehicle driving scenes through training, such as uniform speed driving, accelerated driving, decelerated driving, collision ahead, heavy rain, heavy fog and other scenes. In detail, the vehicle scene analysis model can be trained through a large number of historical multivariate vehicle driving features. The vehicle driving scene state refers to the driving environment or driving state of the vehicle at a specific moment or in a specific time period, including road state, environmental state, normal driving, emergency braking, emergency avoidance, congestion state, traffic light state and other states.

[0172] S5. Based on the vehicle driving path characteristics, the vehicle information and the preset vehicle driving constraints, an adaptive speed decision model of the speed-to-be-controlled vehicle is constructed; based on the vehicle driving scene state, the adaptive speed decision model is used to identify the optimal speed parameters of the speed-to-be-controlled vehicle; and based on the optimal speed parameters, vehicle-road cooperative speed control of the speed-to-be-controlled vehicle is performed.

[0173] The present invention constructs an adaptive speed decision model of the vehicle to be controlled based on the vehicle driving path characteristics, the vehicle information and the preset vehicle driving constraints to provide the vehicle with the best speed parameters to improve the safety of the driving vehicle. The adaptive speed decision model refers to a model that automatically generates vehicle speed parameters based on factors such as the current driving scene, environment, and state of the vehicle to be controlled. In detail, the adaptive speed decision model of the vehicle to be controlled includes: configuring the speed parameter optimization target and the speed decision model architecture of the vehicle to be controlled, analyzing the performance parameters of the vehicle to be controlled based on the vehicle information and the preset vehicle driving constraints; based on the performance parameters and the speed parameter optimization target, constructing the simulated driving scene state of the vehicle to be controlled using the vehicle driving path characteristics, training the speed decision model architecture based on the simulated driving scene state, and obtaining the adaptive speed decision model of the vehicle to be controlled.

[0174] Among them, the simulated driving scene state refers to simulating various states of the vehicle on the path through the vehicle driving path characteristics, such as high-speed driving in heavy rain; the speed parameter optimization target refers to the goal pursued when constructing the speed decision model; the speed decision model architecture refers to the structure used to train and optimize the speed decision model, including the input layer, hidden layer and output layer, and the connection method and parameters between them; the performance parameters refer to the key performance indicators of the vehicle to be controlled, such as speed threshold, minimum turning radius, grip and other parameters.

[0175] The present invention utilizes the adaptive speed decision model to identify the optimal speed parameter of the vehicle to be controlled, which helps guide the vehicle to adjust its speed under different traffic and environmental conditions to achieve safer, more efficient and environmentally friendly driving. The optimal speed parameter refers to the best speed setting that can maximize vehicle performance or meet specific goals under specific driving conditions.

[0176] Compared with the problems described in the background technology, the present invention analyzes the vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data, which can comprehensively analyze the historical vehicle driving data, understand the vehicle driving characteristics, and provide a basis for subsequent vehicle speed control; further, the present invention constructs a multi-path monitoring device for the vehicle driving path according to the vehicle driving path characteristics to realize real-time monitoring and management of the vehicle driving path, further, the present invention constructs the network slicing algorithm and distributed network architecture of the multi-path monitoring device and the multi-vehicle monitoring device to provide a basis for subsequent data transmission and processing requirements, further, the present invention establishes a distributed vehicle-road cooperative network of the vehicle to be controlled based on the network slicing algorithm and distributed network architecture, which can establish an efficient and flexible distributed vehicle-road cooperative network to support the data transmission and processing requirements of the vehicle-road cooperative speed control system, and then The present invention constructs a graph neural network of the synchronized multivariate data to construct an effective graph neural network to provide support for vehicle driving state analysis and vehicle-road cooperative speed control. The present invention extracts the multivariate vehicle driving characteristics of the synchronized multivariate data based on the graph neural network. Based on the multivariate vehicle driving characteristics, the vehicle driving scene state of the speed-controlled vehicle is analyzed using a trained vehicle scene analysis model, which can provide a basis for the subsequent vehicle speed control. Finally, the present invention constructs an adaptive speed decision model of the speed-controlled vehicle based on the vehicle driving path characteristics, the vehicle information and the preset vehicle driving constraints to provide the vehicle with the best speed parameters to improve the safety of the driving vehicle and use the adaptive speed decision model to identify the optimal speed parameters of the speed-controlled vehicle, which helps to guide the vehicle to adjust the speed under different traffic and environmental conditions to achieve safer, more efficient and environmentally friendly driving. Therefore, the present invention can improve the safety of driving vehicles.

[0177] Embodiment 2:

[0178] like Figure 2 As shown, it is a functional module diagram of a vehicle-road cooperative speed control system based on multivariate data perception provided by one embodiment of the present invention.

[0179] The vehicle-road cooperative speed control system 200 based on multivariate data perception described in the present invention can be installed in an electronic device. According to the functions implemented, the vehicle-road cooperative speed control system 200 based on multivariate data perception can include a driving path feature analysis module 201, a distributed network construction module 202, a synchronous multivariate data acquisition module 203, a driving scene state analysis module 204 and a vehicle-road cooperative speed control module 205. The module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0180] In this embodiment, the functions of each module / unit are as follows:

[0181] The driving path feature analysis module 201 is used to obtain the vehicle driving path and vehicle information of the vehicle whose speed is to be controlled, obtain the historical vehicle driving data of the vehicle driving path, and analyze the vehicle driving path features of the vehicle driving path based on the historical vehicle driving data;

[0182] The distributed network construction module 202 is used to construct a multi-path monitoring device for the vehicle's driving path according to the vehicle's driving path characteristics, configure a multi-vehicle monitoring device for the vehicle to be controlled based on the vehicle information, and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device;

[0183] The synchronous multivariate data acquisition module 203 is used to establish a distributed vehicle-road cooperative network of the vehicle to be controlled based on the network slicing algorithm and the distributed network architecture, collect multivariate data of the vehicle to be controlled by using the distributed vehicle-road cooperative network, and synchronize the multivariate data by using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data;

[0184] The driving scene state analysis module 204 is used to construct a graph neural network of the synchronized multivariate data, extract multivariate vehicle driving features of the synchronized multivariate data based on the graph neural network, and analyze the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving features;

[0185] The vehicle-road cooperative speed control module 205 is used to construct an adaptive speed decision model of the vehicle to be speed controlled based on the vehicle driving path characteristics, the vehicle information and preset vehicle driving constraints, and based on the vehicle driving scene state, use the adaptive speed decision model to identify the optimal speed parameters of the vehicle to be speed controlled, and perform vehicle-road cooperative speed control of the vehicle to be speed controlled based on the optimal speed parameters.

[0186] In detail, the modules described in the vehicle-road cooperative speed control system 200 based on multivariate data perception in the embodiment of the present invention adopt the same technical means as the vehicle-road cooperative speed control method based on multivariate data perception described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0187] An embodiment of the present invention provides an electronic device for implementing a vehicle-road cooperative speed control method based on multivariate data perception.

[0188] See also Figure 3As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a vehicle-road collaborative speed control method program based on multivariate data perception.

[0189] Among them, the processor can be composed of an integrated circuit in some embodiments, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors and various control chips. The processor is the control core (Control Unit) of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes programs or modules stored in the memory (for example, executing a vehicle-road cooperative speed control program based on multivariate data perception, etc.), and calls the data stored in the memory to execute various functions of the electronic device and process data.

[0190] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the memory may also include both an internal storage unit and an external storage device of the electronic device. The memory can be used not only to store application software and various types of data installed in the electronic device, such as the code of a vehicle-road cooperative speed control program based on multivariate data perception, but also to temporarily store data that has been output or is to be output.

[0191] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0192] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0193] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0194] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0195] The vehicle-road cooperative speed control program based on multivariate data perception stored in the memory of the electronic device is a combination of multiple instructions, and when running in the processor, it can achieve:

[0196] Acquire a vehicle driving path and vehicle information of a vehicle to be speed-controlled, acquire historical vehicle driving data of the vehicle driving path, and analyze vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data;

[0197] According to the vehicle driving path characteristics, construct a multi-path monitoring device for the vehicle driving path, configure a multi-vehicle monitoring device for the vehicle to be controlled based on the vehicle information, and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device;

[0198] Based on the network slicing algorithm and the distributed network architecture, a distributed vehicle-road cooperative network of the vehicle to be controlled is established, multivariate data of the vehicle to be controlled is collected by using the distributed vehicle-road cooperative network, and the multivariate data is synchronized by using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data;

[0199] Constructing a graph neural network of the synchronized multivariate data, extracting multivariate vehicle driving features of the synchronized multivariate data based on the graph neural network, and analyzing the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving features;

[0200] Based on the vehicle driving path characteristics, the vehicle information and preset vehicle driving constraints, an adaptive speed decision model of the vehicle to be speed controlled is constructed; based on the vehicle driving scene state, the adaptive speed decision model is used to identify the optimal speed parameters of the vehicle to be speed controlled; and based on the optimal speed parameters, vehicle-road cooperative speed control of the vehicle to be speed controlled is performed.

[0201] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0202] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0203] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0204] Acquire a vehicle driving path and vehicle information of a vehicle to be speed-controlled, acquire historical vehicle driving data of the vehicle driving path, and analyze vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data;

[0205] According to the vehicle driving path characteristics, construct a multi-path monitoring device for the vehicle driving path, configure a multi-vehicle monitoring device for the vehicle to be controlled based on the vehicle information, and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device;

[0206] Based on the network slicing algorithm and the distributed network architecture, a distributed vehicle-road cooperative network of the vehicle to be controlled is established, multivariate data of the vehicle to be controlled is collected by using the distributed vehicle-road cooperative network, and the multivariate data is synchronized by using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data;

[0207] Constructing a graph neural network of the synchronized multivariate data, extracting multivariate vehicle driving features of the synchronized multivariate data based on the graph neural network, and analyzing the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving features;

[0208] Based on the vehicle driving path characteristics, the vehicle information and preset vehicle driving constraints, an adaptive speed decision model of the vehicle to be speed controlled is constructed; based on the vehicle driving scene state, the adaptive speed decision model is used to identify the optimal speed parameters of the vehicle to be speed controlled; and based on the optimal speed parameters, vehicle-road cooperative speed control of the vehicle to be speed controlled is performed.

[0209] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0210] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0212] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0213] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0214] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0215] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A vehicle-road cooperative speed control method based on multivariate data perception, characterized in that: The method comprises: Acquire a vehicle driving path and vehicle information of a vehicle to be speed-controlled, acquire historical vehicle driving data of the vehicle driving path, and analyze vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data; According to the vehicle driving path characteristics, construct a multi-path monitoring device for the vehicle driving path, configure a multi-vehicle monitoring device for the vehicle to be controlled based on the vehicle information, and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device; Based on the network slicing algorithm and the distributed network architecture, a distributed vehicle-road cooperative network of the vehicle to be controlled is established, multivariate data of the vehicle to be controlled is collected by using the distributed vehicle-road cooperative network, and the multivariate data is synchronized by using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data; Constructing a graph neural network of the synchronized multivariate data, extracting multivariate vehicle driving features of the synchronized multivariate data based on the graph neural network, and analyzing the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving features; Based on the vehicle driving path characteristics, the vehicle information and preset vehicle driving constraints, an adaptive speed decision model of the vehicle to be speed controlled is constructed; based on the vehicle driving scene state, the adaptive speed decision model is used to identify the optimal speed parameters of the vehicle to be speed controlled; and based on the optimal speed parameters, vehicle-road cooperative speed control of the vehicle to be speed controlled is performed.

2. The vehicle-road cooperative speed control method based on multivariate data perception according to claim 1, characterized in that: The analyzing the vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data includes: Preprocessing the historical vehicle driving data to obtain preprocessed driving data; Dividing the pre-processed driving data into path environment data and historical vehicle data; Extracting path environment features and historical vehicle driving features of the path environment data and historical vehicle data respectively; Analyzing the characteristic correlation coefficients of the path environment characteristics and the historical vehicle driving characteristics; Based on the feature association coefficient, a preset feature mining algorithm is used to mine the vehicle driving path features of the vehicle driving path.

3. The vehicle-road cooperative speed control method based on multivariate data perception as claimed in claim 2, characterized in that: The analysis of the characteristic correlation coefficient of the path environment characteristics and the historical vehicle driving characteristics includes: The path environment features and the historical vehicle driving features are integrated to obtain integrated features; Calculating the multidimensional support and multidimensional confidence of the fusion feature; Based on the multidimensional support and multidimensional confidence, the multidimensional lift of the fusion feature is calculated using the following formula: Multilife(A→B,C)=MultiCon(A→B,C) / MultiSupport(B,C) Among them, Multilife(A→B, C) represents the multidimensional improvement between fusion features A, fusion features B and fusion features C, MultiCon(A→B, C) represents the multidimensional confidence between fusion features A, fusion features B and fusion features C, and MultiSupport(B, C) represents the multidimensional support between fusion features B and fusion features C; According to the multi-dimensional lift, a feature correlation coefficient of the fused feature is determined.

4. The vehicle-road cooperative speed control method based on multivariate data perception as claimed in claim 3, characterized in that: The multi-path monitoring device for constructing the vehicle driving path according to the vehicle driving path characteristics comprises: Marking the path nodes of the vehicle's travel path; Based on the vehicle driving path characteristics, identifying the risk level and risk description of the path node; Calculating the value to be monitored of the path node according to the risk degree; Based on the value to be monitored, marking the node to be monitored of the path node; Analyzing the monitoring requirements of the nodes to be monitored through the risk description; According to the monitoring requirements, a multi-path monitoring device of the node to be monitored is determined.

5. The vehicle-road cooperative speed control method based on multivariate data perception according to claim 4, characterized in that: The method of establishing a distributed vehicle-road cooperative network of the vehicle to be controlled in terms of speed based on the network slicing algorithm and the distributed network architecture includes: Determining the vehicle-road cooperative network requirements and network physical resources of the vehicle to be controlled in terms of speed; Based on the distributed network architecture, the network physical resources are divided into network slices, and the quality of service parameters of the network slices are configured; Analyzing the network status of the network slice by using the quality of service parameter; According to the vehicle-road cooperative network requirements and the network status, using the network slicing algorithm to configure the dynamic slice resources of the network slice; Analyzing the slice performance of the network slice based on the slice dynamic resources; When the slice performance meets the preset slice performance threshold, the multi-path monitoring device and the multi-vehicle monitoring device corresponding to the speed-controlled vehicle are connected to the network slice to obtain a distributed vehicle-road cooperative network for the speed-controlled vehicle.

6. The vehicle-road cooperative speed control method based on multivariate data perception as claimed in claim 5, characterized in that: The analyzing the network status of the network slice by using the quality of service parameter includes: Based on the quality of service parameter, analyzing the status influencing factor of the network slice; Analyze the network impact relationship between the state impact factor and the network slice; According to the network influence relationship, construct a dynamic weight allocation algorithm for the state influence factor; Based on the dynamic weight allocation algorithm, the network quality of the network slice is calculated using the following formula: Among them, τ represents the network quality of the network slice, G represents the weight normalization function, σ represents the dynamic weight allocation algorithm, and r α represents the αth state impact factor, R α represents the real-time network influence coefficient of the αth state influence factor, and m represents the number of state influence factors; The network status of the network slice is determined through the network quality.

7. The vehicle-road cooperative speed control method based on multivariate data perception as claimed in claim 6, characterized in that: The method of synchronizing the multivariate data using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data includes: extracting a timestamp of the multivariate data; calculating a timestamp difference of said timestamps; determining a time source for the multivariate data; According to the time source and the timestamp difference, configuring synchronization algorithm parameters of the high-precision time synchronization algorithm; The multivariate data is synchronized according to the synchronization algorithm parameters to obtain synchronized multivariate data.

8. The vehicle-road cooperative speed control method based on multivariate data perception according to claim 7, characterized in that: The step of constructing the graph neural network for synchronizing multivariate data includes: The multivariate path monitoring device and the multivariate vehicle monitoring device corresponding to the synchronized multivariate data are used as graph nodes; Analyzing the device connection relationship between the multi-path monitoring device and the multi-vehicle monitoring device; Constructing a graph structure of the synchronized multivariate data according to the graph nodes and the device connection relationship; Analyzing computational efficiency requirements of the synchronized multivariate data; Determine the graph neural attention network architecture for synchronizing multivariate data based on the computational efficiency requirement, and configure network architecture parameters of the graph neural attention network architecture; The graph neural network for synchronized multivariate data is constructed according to the graph structure, the graph neural attention network architecture and the network architecture parameters.

9. The vehicle-road cooperative speed control method based on multivariate data perception as claimed in claim 8, characterized in that: The step of constructing the graph neural network for synchronizing multivariate data according to the graph structure, the graph neural attention network architecture, and the network architecture parameters includes: Based on the graph structure, the graph neural attention network architecture and the network architecture parameters, construct an initial graph neural network for the synchronized multivariate data; Initializing the original features of the graph nodes corresponding to the initial graph neural network to obtain the initial features of the nodes; Calculating the attention energy of the graph node according to the initial features of the node; Calculating the attention coefficient of the graph node by using the attention energy; Based on the attention coefficient, the updated features of the graph nodes corresponding to the initial graph neural network are calculated using the following formula: Among them, S ‘ e represents the updated features of graph node e, ω represents the nonlinear activation function, l ev represents the attention coefficient between graph node e and graph node v, θ represents the weight matrix of the initial graph neural network, S v Represents the initial node features of graph node v, C e Represents the set of neighbor nodes of graph node e; Analyzing the feature extraction performance of the initial graph neural network through the updated features; When the feature extraction performance meets a preset feature extraction performance standard, the initial graph neural network is used as the graph neural network for synchronized multivariate data.

10. A vehicle-road cooperative speed control system based on multivariate data perception, characterized in that: The system is used to execute the vehicle-road cooperative speed control method based on multivariate data perception as claimed in any one of claims 1 to 9, and comprises: A driving path characteristic analysis module, used to obtain a vehicle driving path and vehicle information of a vehicle to be speed-controlled, obtain historical vehicle driving data of the vehicle driving path, and analyze vehicle driving path characteristics of the vehicle driving path based on the historical vehicle driving data; A distributed network construction module, used to construct a multi-path monitoring device for the vehicle's driving path according to the vehicle's driving path characteristics, configure a multi-vehicle monitoring device for the vehicle to be controlled based on the vehicle information, and construct a network slicing algorithm and a distributed network architecture for the multi-path monitoring device and the multi-vehicle monitoring device; A synchronous multivariate data acquisition module is used to establish a distributed vehicle-road cooperative network of the vehicle to be controlled in terms of speed based on the network slicing algorithm and the distributed network architecture, collect multivariate data of the vehicle to be controlled in terms of speed using the distributed vehicle-road cooperative network, and synchronize the multivariate data using a preset high-precision time synchronization algorithm to obtain synchronized multivariate data; A driving scene state analysis module, used to construct a graph neural network of the synchronized multivariate data, extract multivariate vehicle driving features of the synchronized multivariate data based on the graph neural network, and analyze the vehicle driving scene state of the vehicle to be controlled by using a trained vehicle scene analysis model based on the multivariate vehicle driving features; The vehicle-road cooperative speed control module is used to construct an adaptive speed decision model of the vehicle to be speed controlled based on the vehicle driving path characteristics, the vehicle information and preset vehicle driving constraints; based on the vehicle driving scene state, the adaptive speed decision model is used to identify the optimal speed parameters of the vehicle to be speed controlled; and based on the optimal speed parameters, the vehicle-road cooperative speed control of the vehicle to be speed controlled is performed.

Images