578 results about "Smart transportation" patented technology

The invention discloses an intelligent traffic control system and method based on multi-agent near-end strategy optimization, and belongs to the field of intelligent traffic, Internet of Vehicles and deep reinforcement learning. The method comprises the following steps: firstly, constructing a fog-cloud collaborative three-layer architecture, and realizing real-time monitoring and dynamic regulation and control of traffic flow through cloud global decision and local sensing collaboration of a road side unit (RSU); secondly, designing indexes of'road section overlap ratio 'and'road section time overlap ratio', and solving the problem of secondary congestion caused by rerouting; then, a multi-agent near-end strategy optimization (MAPPO) algorithm is adopted, so that the traffic signal lamp is used as an autonomous agent to dynamically adjust the phase, and the limitation of single-point control is broken; and finally, through integrated optimization of rerouting and adaptive signal control, an original multi-objective optimization problem is converted into a layered multi-agent reinforcement learning problem. According to the invention, vehicle driving time and system energy consumption can be effectively reduced, road traffic efficiency is improved, and active avoidance and dynamic alleviation of urban traffic congestion are realized.

The invention discloses an intelligent traffic control method and system in a low-altitude economic environment, and relates to the technical field of intelligent traffic systems, and the method comprises the steps: collecting low-altitude aircraft and ground traffic spatio-temporal data through a multi-modal sensor network, and generating a multi-source heterogeneous data set; constructing a dynamic traffic situation map through spatio-temporal feature fusion; performing three-dimensional path planning to generate a three-dimensional guiding strategy; detecting conflicts and correcting strategies according to a preset rule base, and outputting an instruction set to distribute real-time traffic flow. The technical problem that in the low-altitude economic environment, a traditional traffic management and control method is difficult to meet the cross-domain cooperation requirement of the low-altitude aircraft and the ground traffic is solved, and the technical effects of three-dimensional cooperative management and control of the low-altitude aircraft and the ground traffic and further guaranteeing safe and efficient operation of the traffic in the low-altitude economic environment are achieved.

The invention relates to a multi-distribution-center open type vehicle path intelligent optimization method and system, and belongs to the technical field of logistics distribution optimization and intelligent transportation, and the method comprises the steps: firstly obtaining the input data of a multi-distribution-center vehicle path optimization problem, selecting a multi-distribution-center processing strategy according to the problem scale and constraint conditions, and carrying out the optimization of the multi-distribution-center vehicle path; a vehicle path optimization model is constructed, the vehicle path optimization model comprises a single-target model and a multi-target model, a multi-algorithm collaborative optimization framework is adopted for solving, and the multi-algorithm collaborative optimization framework comprises an ant colony algorithm, a variable neighborhood search optimization ant colony algorithm and a non-dominated sorting genetic algorithm; and outputting an optimal vehicle path scheme, wherein the optimal vehicle path scheme comprises a distribution route, a distribution sequence and a corresponding objective function value of each vehicle. According to the method, strategy adaptive selection and algorithm collaborative optimization are carried out, global exploration, local optimization and multi-target equalization are carried out by combining the advantages of the ant colony algorithm, the variable neighborhood search algorithm and the non-dominated sorting genetic algorithm, and the method is good in reproducibility, high in scene adaptability and high in decision support capability.

The invention belongs to the technical field of intelligent traffic and new energy power supply, particularly relates to a traffic equipment solar power supply fault diagnosis system, and aims to solve the problems that a solar power supply system is not timely in fault diagnosis, low in precision and difficult to distinguish instantaneous interference and continuous faults. The system collects multi-source data through an environment sensing and electrical parameter monitoring module, generates a power deviation sequence and extracts time sequence characteristics by combining dynamic expected power modeling with actual output comparison; the fault identification module adopts a multi-level logic discrimination and 12-hour continuous verification mechanism, accurately identifies photovoltaic panel pollution, storage battery aging, poor line contact and controller faults, and distinguishes instantaneous interference; and the decision alarm module generates graded alarms according to fault types and grades, and realizes accurate positioning and operation and maintenance scheduling in linkage with geographic information. The system also has the functions of internal resistance pulse detection, dual-channel redundancy sampling, adaptive threshold adjustment and model self-learning, and the diagnosis accuracy and the operation and maintenance efficiency are significantly improved.

The invention relates to a multi-type emergency vehicle signal dynamic priority control method based on vehicle-road cloud cooperation, and belongs to the technical field of intelligent traffic control. The method comprises the following steps: acquiring an emergency vehicle state and traffic environment data in real time through cooperation of a vehicle-mounted terminal, roadside equipment and a cloud control platform; the cloud control platform dynamically calculates priority scores based on vehicle types, task emergency degrees, predicted arrival time, real-time traffic influences and path complexity multi-dimensional factors; when multiple vehicles have conflicts, collaborative decision making is carried out based on scores; and finally, an optimized signal control strategy is generated and executed. The system effectively solves the problems that a traditional priority control mode is extensive, and traffic jam and multi-vehicle conflicts are easily caused, achieves the purpose that interference to social traffic is minimized while efficient passing of emergency vehicles is guaranteed, and improves the overall efficiency and safety of an urban traffic system.

The invention discloses a vehicle collision detection, description and early warning system and method based on a driving video, and belongs to the technical field of artificial intelligence and intelligent traffic safety. According to the system, on the basis of a vision-language model, vehicle-mounted videos such as an automobile data recorder are automatically analyzed, and detection, severity grading, natural language description generation and real-time early warning of vehicle collision events are achieved. The system extracts high-dimensional semantic features of video frames through a CLIP model, focuses key information through an attention weighting network, inputs the key information into a deep classification network composed of a plurality of full connection layers, a batch normalization layer and an activation function, and outputs a multi-level accident severity classification result. Integrating target detection and environment information, and generating a structured accident description text by using a fine tuning BART model; a sliding window and time sequence modeling mechanism is adopted, and recognition and early warning of the pre-collision state are achieved. The method effectively solves the technical problems of lack of semantic understanding, inaccurate severity judgment, incapability of early warning and the like of a traditional method, has high accuracy, high interpretability and real-time response capability, and is suitable for intelligent driving assistance and traffic safety monitoring scenes.

The invention relates to the technical field of intelligent traffic control, and discloses a road traffic AI adaptive edge computing server. The server comprises a traffic situation sensing module, a traffic flow intention analysis module, a control strategy construction module, a control scheme generation module and an efficiency rolling optimization module. The server synchronously receives the original data flow of the heterogeneous traffic sensor, and extracts and generates a microscopic traffic behavior sequence after timestamp alignment and cleaning. A behavior sequence is matched with a historical scheme library, a control strategy knowledge graph based on a traffic entity relationship is constructed, and a candidate control scheme set is reasoned according to the control strategy knowledge graph. And performing conflict detection and rolling optimization on the candidate schemes based on a short-time traffic flow prediction result, and outputting a final adaptive control instruction set. According to the invention, deep understanding and foresight control of a complex traffic scene are realized, and the intersection passing efficiency and the control adaptive capability are improved.

The invention belongs to the field of intelligent transportation, and relates to a future feature enhanced vehicle trajectory prediction generative adversarial method, which comprises the following steps: a conditional information learning step: completing joint modeling of historical and future features; a generative adversarial training step: performing multi-modal trajectory prediction by adopting a CVAE-GAN hybrid architecture; wherein the CVAE-GAN hybrid architecture comprises an encoder, a generator and a discriminator; the encoder comprises a regression encoder and a prior encoder, and the regression encoder is responsible for mapping a real track to a submerged space, learning compact representation of the track and only being used during model training; the priori encoder performs network sampling to obtain a latent variable; the generator reconstructs a multi-modal future trajectory according to latent variables and condition information; the discriminator receives the trajectory and the condition information, and evaluates the authenticity of the trajectory and the consistency of the trajectory and the condition information. By designing a double-stage strategy, stable generation and optimization of multi-modal trajectory distribution are realized, and the problems that traditional GAN training is unstable and CVAE output is too smooth are solved.

The invention relates to an ice and snow disaster variable speed limit control method and system based on a friction coefficient, and belongs to the field of intelligent traffic. According to the method, a set of variable speed limit control units are arranged on a road at intervals, and all the variable speed limit control units are in communication connection with a centralized decision-making unit through communication modules; each set of variable speed-limiting control unit detects traffic flow data, meteorological environment data and road condition data of a lane level in real time, uploads the data to the centralized decision-making unit, determines an optimal lane-level variable speed-limiting control scheme and an optimal deicing and snow-removing scheme through a decision-making optimization algorithm, and issues the optimal lane-level variable speed-limiting control scheme and the optimal deicing and snow-removing scheme to the variable speed release module; and the variable speed release module releases a lane level variable speed limit control scheme of a corresponding section, namely the lowest speed limit value, the highest speed limit value, the suggested speed and the like of each lane, and performs deicing and snow removal operation according to the deicing and snow removal scheme so as to ensure road traffic safety in ice and snow weather. The road traffic safety guarantee level is improved through variable speed limiting.

The invention provides a parking lot intelligent path optimization system and method based on a GA-SMA algorithm, and belongs to the technical field of intelligent traffic management. The system comprises an intersection point conflict detection module, a GA-SMA path optimization module, an intelligent speed scheduling module, a conflict resolution module and a visualization module. The system analyzes vehicle track data, adopts a unified detection framework based on intersection point time overlapping and coming vehicle direction analysis, automatically identifies two conflict types of road section occupation conflict and confluence conflict, and calculates the conflict severity. According to the method, a self-adaptive stage scheduling mechanism and path awareness genetic manipulation are creatively combined, the GA-SMA algorithm is provided, advantage complementation of GA exploration capability and SMA convergence capability is realized, a search strategy can be dynamically adjusted according to an evolution process, and a high-quality multi-vehicle cooperative path is generated. The system adopts an intelligent speed scheduling strategy to implement preventive deceleration at an intersection point in front of a conflict point so as to avoid parking waiting.

The invention discloses a highway accident scene sensing system based on AI identification and unmanned aerial vehicle cooperation, and relates to the technical field of intelligent traffic. Comprising a central planning node for fusing geographic information, meteorological information and road obstacle information of a target site with the real-time state of an unmanned aerial vehicle, constructing a digital twin scene model, generating an initial four-dimensional collaborative awareness route plan, and dividing sub-airspaces; the distributed airborne intelligent agent obtains peripheral multi-source data of the unmanned aerial vehicle, constructs a surrounding environment real-time situation map through an AI recognition algorithm, and determines a flight instruction of the unmanned aerial vehicle according to the surrounding environment real-time situation map and the divided sub-airspace; and the reconfigurable intelligent metasurface is used for adjusting surface electromagnetic characteristics according to the divided sub-airspaces and sending directional beams to the unmanned aerial vehicle. Therefore, the problems of cooperative scheduling, obstacle avoidance and communication guarantee of multiple unmanned aerial vehicles in a complex accident scene are effectively solved, and the efficiency and safety of emergency disposal are remarkably improved.

The invention relates to the technical field of intelligent traffic and Internet of Vehicles, in particular to a traffic and air pollution bidirectional coupling flow prediction method based on double-path dynamic fusion. Comprising the following steps: collecting traffic flow and air pollutant concentration data, and carrying out space-time alignment and reversible instance normalization; the data is divided into two branches, the first branch extracts time-dependent features through gated convolution and probability sparse self-attention, and the second branch obtains variable interaction features through dimension remodeling, context extraction and reversible coupling transformation; bidirectional feature interaction is carried out through cross attention, weights are dynamically generated based on channel attention, and residual connection is carried out after weighted fusion; and performing linear mapping and inverse normalization on the fused features to obtain a traffic flow predicted value. According to the method, the prediction precision and robustness in a pollution sensitive scene are remarkably improved.

The invention discloses a vehicle-mounted and mobile platform ground disaster multi-mode sensing, alarming and risk avoiding method and system, and belongs to the technical field of intelligent traffic and geological disaster monitoring. According to the technical scheme, multiple types of sensors such as vision, laser radar, millimeter wave radar, a positioning navigation device and an inertial measurement unit are fused, a multi-modal sensing data matrix under a unified space-time coordinate system is constructed, and timely and dynamic sensing and intelligent analysis of multiple types of geological disasters are achieved; the problems of coverage blind area, perception deficiency and information isolated island of the traditional monitoring means are solved; the system comprises functional modules of environment perception, disaster identification, risk assessment and collaborative early warning, active risk avoidance and the like, and is used for collecting multi-source environment data, identifying disaster types and positions, assessing risk levels and executing risk avoidance strategies. The method has the advantages of real-time sensing, high-precision recognition, dynamic risk judgment and active risk avoiding, and is suitable for various mobile platforms in road and non-road scenes of geological disaster high-incidence areas.

The invention relates to the technical field of intelligent traffic. The driver state recognition and vehicle control method comprises the steps that driver monitoring information comprises eye movement information, voice information and steering wheel operation information, and the eye movement information, the voice information and the steering wheel operation information are input into a multi-modal fusion judgment model; the multi-modal fusion judgment model dynamically adjusts the weight of each modal feature based on the attention mechanism and in combination with preset driver modal preference parameters to obtain fusion feature representation data, determines driver state information based on the fusion feature representation data, matches a preset composite event recognition rule according to the driver state information, and judges whether the driver state information is abnormal or not. And if the driver state information represents any one of a fatigue state, a distraction state or an emotional stress state, determining a corresponding event triggering level, and generating corresponding vehicle control information based on the event triggering level. The method has the effect of improving the driving safety.

The present application relates to the technical field of intelligent traffic control, and particularly relates to a rescue emergency light linkage control method combined with a vehicle system, comprising: S1: environment perception, collecting road topological structure, potential congestion obstacle distribution, visibility level and vehicle density value in real time through the vehicle system of a rescue vehicle; S2: dynamic decision, generating an emergency light control instruction based on the output of S1; S3: multi-vehicle linkage, predicting a future path based on the position and historical trajectory of the rescue vehicle, and broadcasting a V2X instruction containing real-time coordinates, path vector and avoidance direction identifier to vehicles within a preset radius; S4: closed-loop execution, issuing the instruction of S2 to a light control unit, and capturing an actual flashing sequence through a camera for time domain matching verification, and triggering instruction retransmission when the matching degree is lower than a reliability threshold. The method not only improves traffic safety and rescue efficiency, but also enhances the intelligence and reliability of the system, and adapts to modern rescue needs.

The invention belongs to the technical field of intelligent traffic and deep learning modeling, and particularly relates to a cross-layer low-rank fusion space-time traffic flow prediction modeling method. The method comprises the following steps: firstly, carrying out standardization, complementation and coding processing on historical traffic data, time labels and road topology, and constructing a space-time embedding representation; then, through node aggregation and agent number adaptive estimation, a double-stage attention modeling structure is established so as to reduce the calculation complexity; efficient fusion of cross-layer information is realized through output pairing and feature splicing of adjacent layers in combination with low-rank bottleneck compression and gating residual fusion; and a robust prediction result is generated by adopting a hybrid expert decoding structure and combining time dimension aggregation, routing weight initialization and multi-target constraint. According to the method, the problems of high-dimensional redundancy, calculation bottleneck and distribution drift in large-scale traffic flow prediction are effectively solved, and the prediction precision and the model efficiency are improved.

The invention provides an intelligent network connection device remote cluster control method and system based on vehicle-road cooperation, and relates to the technical field of intelligent traffic, and the method comprises the steps: obtaining vehicle end state information and road side sensing information, carrying out the cross-domain fusion based on a vehicle-road space-time alignment rule to obtain a global view, grouping vehicle end devices according to the road segment attribution and task association degree, and carrying out the clustering of the vehicle end devices; and generating a hierarchical control instruction according to the grouping structure and the global view, executing remote control, and adaptively adjusting an alignment rule by using feedback information. According to the invention, the accurate control of the equipment cluster in the vehicle-road cooperation environment is realized, and the operation efficiency and safety of the vehicle-road cooperation system are improved.

The invention provides a traffic accident emergency response method and system based on vehicle state perception, and relates to the technical field of intelligent traffic, and the method comprises the steps: deploying a vehicle-mounted sensor and roadside perception equipment, and collecting and obtaining vehicle state data and traffic environment data; constructing a traffic accident analysis index set, and analyzing the vehicle state data and the traffic environment data; building a traffic accident risk assessment model, assessing the traffic accident index parameter set, and outputting a traffic accident risk coefficient; triggering a target emergency response strategy; and analyzing the traffic accident index parameter set to obtain a target emergency strategy parameter, and carrying out accident emergency response processing. According to the method and the device, the technical problem of emergency response delay caused by inaccurate risk assessment of the traffic accident in a complex traffic situation in the prior art is solved, and the processing efficiency of the traffic accident is improved by comprehensively considering the multi-dimensional data, accurately assessing the risk of the traffic accident and automatically triggering the emergency strategy.

The invention provides a ramp traffic signal adaptive control method and system based on unmanned aerial vehicle cooperation, and belongs to the technical field of intelligent traffic control, and the method comprises the steps: collecting traffic data in real time based on an unmanned aerial vehicle cluster dynamically deployed over a ramp, constructing a global traffic state matrix, and carrying out the initial processing through edge calculation; carrying out edge calculation on the primarily processed data by utilizing an edge node to generate a local optimal signal timing suggestion in real time; the local optimal signal timing suggestions uploaded by the multiple unmanned aerial vehicles are integrated at the cloud, and a global optimal signal timing strategy is generated through unified training; signal lamp parameters are adjusted in real time on the basis of a global optimal signal timing strategy, the direct intervention capability on site traffic is enhanced through an air guiding function, and a high-reliability solution is provided for an intelligent traffic system.

The invention discloses a traffic state prediction method and device based on surface domain spatial semantics, and belongs to the field of intelligent traffic and space-time big data analysis. Comprising the steps of fusing traffic flow, time embedding and remote sensing semantics to obtain uniform node features; a road short-distance graph is constructed according to the actual distance between the sensors, a semantic long-distance graph is constructed according to the functional area proportion similarity, and a global static adjacency matrix is subjected to weighted synthesis; a dynamic adjacency matrix updated along with time is generated through a self-attention mechanism, and multi-order diffusion and time localization are combined; performing multi-order graph convolution by using the static and dynamic adjacency matrixes to capture spatial dependence; extracting a short-term change, mining a long-term period, and capturing time dependence; and finally, dynamically balancing the contribution of space and time dependence through a space-time decoupling module, and outputting a prediction result. According to the method, the functional area difference is described through the surface domain space semantics, and the prediction precision and adaptability in the non-stable traffic scene are improved by combining static and dynamic graph modeling and layered time modeling.

The invention discloses a cross-device multi-target tracking method and system. The method comprises the following steps: converting vehicle driving data collected by a camera and a radar into trajectory data under a global coordinate system; dividing all the sensing devices into a plurality of adjacent device pairs; checking the time dimension and the space dimension of the upstream track and the downstream track which are respectively formed by the adjacent equipment pair in sequence; and if the upstream track and the downstream track meet verification, splicing the track sequence according to a timestamp sequence to perform fusion of the global track, otherwise, temporarily storing the track as an isolated track independent of the global track. The system is used for implementing the method. The method has the advantages that feature extraction is not needed, the calculation complexity is low, and the real-time processing requirement of a large-scale sensing network can be met. Spatial similarity calculation methods are respectively designed for devices of the same type and different types, the cooperation requirements of mainstream sensing devices in an intelligent traffic scene are covered, and the compatibility is high.

The invention relates to the technical field of intelligent traffic and auxiliary travel, and discloses a multi-modal space-time fusion intelligent vehicle danger pre-judgment method and system, and the method comprises the steps: obtaining multi-modal sensing data around an intelligent vehicle, constructing a deep learning-based danger pre-judgment model which comprises a space-time fusion module and a risk evolution module; the space-time fusion module carries out space-time alignment and fusion on multi-modal sensing data to obtain unified space-time voxel features, and the space-time alignment and fusion processing process is focused on a high-uncertainty region through the risk attention gating module. The risk evolution module identifies objects around the intelligent vehicle according to the space-time voxel features, and predicts the motion trails and potential collision risks of the objects; and performing real-time danger judgment on the intelligent vehicle by using the world model distillation danger pre-judgment model and the post-distillation danger pre-judgment model. According to the invention, various sensing data can be effectively fused to carry out danger judgment in the vehicle driving process, and the judgment accuracy is improved.

The invention provides an urban road network traffic congestion state prediction method and system based on deep learning, and relates to the technical field of intelligent traffic control, and the method comprises the steps: obtaining congestion state image data of an urban road network, and carrying out the preprocessing to extract structured road congestion information; constructing a road network topological graph based on the road congestion information, and performing structure sensing state coding on the road network topological graph to generate a structure sensing state vector fusing local congestion features and global topological position information; and inputting the structure perception state vector into an improved deep learning prediction model, performing feature deepening and enhancement through a graph neural network which dynamically adjusts a graph structure and aggregates node information, and finally outputting road network congestion state prediction results of a plurality of time scales in the future. According to the method, accurate prediction of the urban road network congestion state can be realized, and reliable technical support is provided for intelligent traffic management, resource scheduling optimization, travel path planning and the like.

The invention belongs to the technical field of intelligent transportation and unmanned aerial vehicles, and particularly discloses an expressway disease inspection system and method based on an intelligent unmanned aerial vehicle with a body, and the method comprises the steps: collecting the multi-dimensional data of an expressway and the pose information of the unmanned aerial vehicle through the unmanned aerial vehicle carrying a multi-source sensor; an edge calculation module is used for adjusting the subsequent flight path of the unmanned aerial vehicle and multi-mode disease recognition, local real-time recognition and decision making of highway disease inspection are achieved, and a highway disease recognition result is output; the communication subsystem is used for receiving the expressway disease recognition result and transmitting the expressway disease recognition result to the rear-end intelligent management platform; and receiving an expressway disease identification result through a back-end intelligent management platform, carrying out visual display, and maintaining decision support and data evidence storage. According to the invention, the problems of insufficient automation level, low multi-source data fusion efficiency and weak real-time response capability in the prior art are solved.

The invention relates to the technical field of intelligent traffic and smart city waste management, and discloses a path planning method and system for a garbage transport vehicle based on multi-source data, and the method comprises the steps: generating a reference path based on historical collection and transportation data, the method comprises the following steps: performing data cleaning on pre-acquired garbage quantity data, vehicle state data, real-time traffic data, hydroelectric data and fuel consumption data, performing multi-source time sequence feature fusion anomaly detection on a cleaned data set, performing trajectory inversion on the cleaned data set, performing target constraint through a mixed integer programming model, and performing multi-source time sequence feature fusion anomaly detection on the cleaned data set. Then gradient descent parameter optimization is carried out on the initial optimization model, elastic resource scheduling is carried out on an optimized path scheme based on a large event plan library, a path instruction set is generated, dynamic re-optimization evaluation is carried out on the path instruction set based on garbage amount change and traffic condition data fed back in real time, and an updated path is generated; according to the invention, the path planning efficiency of the garbage transport vehicle based on the multi-source data can be improved.

The invention discloses a vehicle fine granularity detection method based on a three-dimensional grid and YOLOv11 transfer learning. The method mainly comprises three components: a source domain prediction network structure, a target domain prediction network structure and a transfer learning module. Wherein the source domain prediction network and the target domain prediction network are dual-channel deep networks fusing two-dimensional images and three-dimensional grids, and efficient migration of source domain knowledge in a target domain is realized by aligning feature distribution of the source domain and the target domain. Through deep fusion of three-dimensional grid information and two-dimensional image features, the method can maintain robust detection performance under adverse conditions of vehicle attitude change, illumination interference, shielding and the like, can effectively reduce large-scale data annotation and training cost, improves the rapid adaptation capability of the model in a new scene or a new vehicle type, and improves the robustness of the model. And a high-precision, extensible and rapid-iteration fine-grained identification and detection solution is provided for intelligent traffic monitoring, unmanned driving perception, military equipment identification and digital twin systems.

The invention provides a fault repair and task unloading optimization method under a space-air-ground fusion vehicle-mounted network framework, and belongs to the technical field of Internet of Vehicles. According to the first stage, the optimal deployment point location of the unmanned aerial vehicle is searched globally based on the wolf pack algorithm, the flight path is planned dynamically in combination with the near-end strategy optimization algorithm, and network connectivity repair of a fault area is achieved; and in the second stage, a task unloading decision initial population is generated through multiple deep reinforcement learning agents, and a Pareto optimal solution set is obtained through optimization of a non-dominated sorting genetic algorithm II, so that multi-target balance of energy consumption, cost and time delay is realized. According to the method, the fault self-healing capability and task processing efficiency of the SAGVN can be remarkably improved, and the method adapts to the high-dynamic and high-reliability requirements of intelligent traffic.

The invention discloses a device and a system for risk identification and early warning of an expressway operation area. The system comprises a portable pressure-sensitive deceleration strip, an integrated intelligent traffic cone and an engineering early warning vehicle, the two portable pressure-sensitive deceleration strips are arranged at the first-level early warning boundary and the second-level early warning boundary in front of the integrated intelligent traffic cone on the upstream of the operation area respectively and used for sending alarm signals to other associated equipment when it is detected that a vehicle on the high-speed early warning lane enters the early warning area; the integrated intelligent traffic cone is used for configuring integrated modules such as a monitoring camera, an audible and visual alarm and a character notice board according to an early warning effect when the traffic cone is automatically placed at a set position so as to identify risks inside and outside an operation area and perform early warning; and the engineering early warning vehicle is used for assisting in identifying risks inside and outside the operation area, processing early warning information and slowing down collision. By constructing the device and the system for identifying and early warning the risks of people, vehicles and equipment in the expressway operation area, the external vehicle intrusion risk and the internal personnel and equipment risk in the operation area can be actively found, an alarm prompt is given before the risks come, workers in the operation area are guided to rapidly evacuate, and casualties caused by accidents are reduced.

The invention discloses a traffic scene training data generation method and device, electronic equipment and a medium, and relates to the technical field of intelligent traffic, and the method comprises the steps: obtaining multi-modal traffic data, building a dynamic semantic interaction network according to the multi-modal traffic data, and enabling the dynamic semantic interaction network to comprise a plurality of traffic entities, the dynamic attribute of each traffic entity and the space-time relationship between the traffic entities are determined; in the dynamic semantic interaction network, labeling the target event and a core node of the target event according to a preset event specific sub-graph; performing causal chain backtracking on the labeled target event and the core node of the target event to obtain structured causal chain data corresponding to the target event; and performing question and answer pair generation processing on the structured causal chain data corresponding to the target event to obtain an instruction fine tuning data set for training the traffic large model. Therefore, automatic and high-quality generation of the traffic scene training data is realized, and the logical reasoning ability and interpretability of the model are improved.

The invention discloses a federated learning semantic communication method for an unmanned aerial vehicle cluster, and the method comprises the steps: firstly, designing a multi-scale joint information source channel encoder through combining the characteristics of a traffic aerial image, and achieving the efficient extraction and compression of semantic features; then, locally training a convolutional neural network with a low-bit quantization weight at each unmanned aerial vehicle, and only uploading a quantization value of a variable quantity of a parameter, thereby reducing energy consumption and protecting privacy; the edge server carries out aggregation and global synchronization on the parameters uploaded by the unmanned aerial vehicles, and the system cooperation efficiency is improved; finally, through energy consumption modeling and experimental verification, it is proved that the method can effectively improve the reconstruction quality and greatly reduce the overall energy consumption, and has excellent robustness. According to the method, efficient semantic communication in a multi-unmanned aerial vehicle traffic scene can be realized with low energy consumption and high privacy protection, and technical support is provided for design and optimization of a future AI-assisted 6G intelligent traffic communication system.