137 results about "Road congestion" patented technology

Provided are a method and an apparatus for constructing a road congestion prediction model, a device, a medium, and a product. A road traffic network is defined as a directed weighted graph. Historical dynamic traffic features of each road segment in the road traffic network are obtained as sample data, including recent dynamic traffic features and periodic dynamic traffic features. The sample data is input into a mixture of adaptive graph learners (MAGL) model for learning, and a probability prediction vector is output. The sample data is input into a trend expert model, and a trend distribution vector of a predicted probability of future traffic conditions is output. The periodic dynamic traffic features are fused to determine a periodicity prediction vector. An aggregated logit vector is obtained. An objective function is determined based on the aggregated logit vector. Congestion prediction training is performed to obtain a road congestion prediction model.

The invention discloses a road congestion prediction system and method based on spatial-temporal feature extraction, and belongs to the field of intelligent traffic. The system adopts a layered distributed architecture, and comprises a multi-source data acquisition module, a data preprocessing unit, a double-flow spatio-temporal feature extraction network, a two-stage spatio-temporal attention mechanism module, a congestion prediction model and a result feedback interface. Multi-modal data such as a vehicle-mounted GPS track, checkpoint flow, video monitoring and meteorological data are integrated, a double-flow feature extraction network is constructed by adopting a graph convolutional network and a bidirectional gating circulation unit, and a key space-time region is dynamically focused in combination with a multi-head self-attention and time weighted dot product attention mechanism; and finally, optimizing the generalization ability of the model through a composite loss function. According to the method, a dynamic adaptive learning framework and multi-source data combined modeling mode is adopted for urban road traffic flow characteristics, the space-time precision and the real-time response capability of road network congestion prediction are remarkably improved, and reliable decision support is provided for intelligent traffic control.

This invention discloses a method, system, and storage medium for electric vehicle charging scheduling based on dynamic data fusion, relating to the field of data processing technology. The method includes the following steps: acquiring the status monitoring parameters of all standby charging interfaces and filtering out available charging piles that meet the requirements; classifying vehicles into charging-priority vehicles and cost-priority vehicles based on the real-time status data and environmental parameters of the electric vehicles requesting charging; for charging-priority vehicles, adjusting the charging pile search range, introducing output power to determine the target charging pile and performing a locking operation; for cost-priority vehicles, calculating the cost optimization coefficient based on arrival time prediction and electricity price fluctuations within the time period, and generating a preferred charging pile sequence. The user finally selects and locks the charging pile, while dynamically adjusting the locking time according to road congestion. This method achieves efficient allocation of charging pile resources, optimizing user experience and economic costs.

The invention belongs to the field of urban traffic management, and provides a hierarchical dynamic routing system and method for a computing power-energy fusion network, and the method comprises the steps: dividing a fusion network graph into a plurality of region sub-graphs, and dividing a path table and a connection point path table based on each region sub-graph; monitoring the running states of the road, the edge computing node and the charging station in real time, and predicting the road congestion intensity, the edge computing node queuing estimation information and the charging constraint; and determining a candidate path set in the partition path table and the connection point path table according to an online request of the vehicle, screening each candidate path in the candidate path set based on the road congestion intensity, the edge computing node queuing estimation information and the charging constraint, and determining an optimal path. According to the method, online retrieval is converted into rapid combination and evaluation of small candidate sets from full-graph traversal; traffic, energy and computing power are incorporated into the same decision framework, and systematicness deviation caused by evaluation of the future at present is avoided.

The invention relates to the technical field of traffic management, in particular to a school entrance and exit pedestrian traffic management system and method based on the Internet of Things, and the method comprises the steps: obtaining the road traffic monitoring data of a school entrance and exit in a school leaving period; the road congestion degree is evaluated by extracting vehicle distribution data; evaluating the traffic interference degree by identifying the vehicle driving direction and the mixed driving behavior of the vehicle and the pedestrian; and evaluating the school leaving speed of the students according to the road congestion degree and the traffic interference degree, and adjusting the school leaving strategy according to the school leaving speed of the students. The school leaving speed of the students is evaluated by quantifying the road congestion degree and the traffic interference degree of the school entrances and exits, the school leaving efficiency of the students is improved, and meanwhile the road traffic safety risk of the school entrances and exits is reduced.

The invention discloses an intelligent highway abnormal event identification method based on multi-mode perception, and relates to the field of congestion identification, and the method comprises the steps: collecting the dynamic data of a highway in real time through a sensor network; feature extraction is carried out based on historical and real-time traffic flow data of each road section of the expressway, the road congestion condition is judged through feature fusion, and a congestion index is generated; based on the congestion event, triggering traceability analysis, and generating a feature vector of the source area; carrying out model training through a deep reinforcement learning model, obtaining a trained congestion reason identification and classification model, and obtaining a congestion reason label; and generating early warning information based on an identification result, and updating a navigation route through the linkage navigation platform. The method has the advantages that abnormal events on the expressway are accurately recognized by fusing video monitoring, radar, weather and toll station data, real-time traffic early warning is provided through the deep learning and prediction model, and road safety and traffic efficiency are 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 discloses a traffic signal scheduling system and method based on road section congestion information, and relates to the technical field of traffic management and control. Comprising the following steps: S1, data acquisition and preprocessing: acquiring original traffic data of a road section in real time through a multi-source data acquisition unit, the original traffic data comprising traffic flow, vehicle speed, queuing length, occupancy and travel time; meanwhile, external environment data are obtained, wherein the external environment data comprise weather information, holiday and festival information and traffic event information; traffic data and external environment data are acquired in real time through the multi-source data acquisition unit, data quality is guaranteed through cleaning, denoising and standardized preprocessing, and the problem that data fusion of an existing system is insufficient is solved; by means of an adaptive weight learning model, historical traffic data, real-time data and environmental data are combined to dynamically adjust a congestion evaluation index weight, and the defect that a fixed or empirical weight is difficult to adapt to traffic dynamic changes is overcome.

The invention discloses a road congestion prediction system and method based on spatial-temporal feature extraction, and belongs to the field of intelligent traffic. The system adopts a layered distributed architecture, and comprises a multi-source data acquisition module, a data preprocessing unit, a double-flow spatio-temporal feature extraction network, a two-stage spatio-temporal attention mechanism module, a congestion prediction model and a result feedback interface. Multi-modal data such as a vehicle-mounted GPS track, checkpoint flow, video monitoring and meteorological data are integrated, a double-flow feature extraction network is constructed by adopting a graph convolutional network and a bidirectional gating circulation unit, and a key space-time region is dynamically focused in combination with a multi-head self-attention and time weighted dot product attention mechanism; and finally, optimizing the generalization ability of the model through a composite loss function. According to the method, a dynamic adaptive learning framework and multi-source data combined modeling mode is adopted for urban road traffic flow characteristics, the space-time precision and the real-time response capability of road network congestion prediction are remarkably improved, and reliable decision support is provided for intelligent traffic control.

The embodiment of the invention discloses a vehicle driving monitoring method and device, electronic equipment and a medium. The method comprises the following steps: monitoring vehicle data and road data on a target road through a congestion monitoring camera, and calculating a road traffic jam index of the target road; if the road traffic jam index of the target section on the target road exceeds the preset traffic jam index, scheduling a target number of violation monitoring cameras to move to a target position range on the moving track; wherein the laying direction of the moving track is consistent with the direction of the target road; the violation monitoring camera moves on the moving track; the target position range corresponds to the actual position of the target interval; and monitoring whether the vehicle in the target interval runs illegally or not through the violation monitoring camera. According to the scheme, under the condition of road congestion, the traffic violation monitoring camera on the mobile track is dispatched to monitor the congested road section in a targeted manner, the vehicle traffic violation behavior is determined in time, and the road traffic safety is improved.

The invention relates to a road congestion detection method and device, a vehicle and a medium. The method comprises the following steps: acquiring a current frame image of a road scene around the vehicle and inertial data of the vehicle; and obtaining congestion degree information of the road according to the current frame image and the inertial data.

This invention provides a method, apparatus, and electronic device for road congestion analysis from the perspective of a low-altitude unmanned aerial vehicle (UAV). The method includes: determining a pixel offset height; determining a target road inspection image based on an initial road inspection image to be identified; determining vehicle detection results of the target road inspection image based on the pixel offset height and the target road inspection image; determining vehicle target feature extraction results of a corresponding reference road inspection image for the target road inspection image, and determining target road congestion discrimination data based on the vehicle detection results of the target road inspection image and the vehicle target feature extraction results of the reference road inspection image; acquiring road congestion analysis data when the target road congestion discrimination data indicates road congestion; and determining the road congestion analysis result based on the road congestion analysis data. This invention can improve the accuracy of road congestion analysis.

The invention provides an expressway streaming media pre-pushing method and system based on multi-dimensional pre-judgment, and belongs to the crossing field of intelligent traffic and streaming media technologies, and the method comprises the steps: carrying out the parallel pre-judgment and triggering of three dimensions of traffic events, high-risk road sections and high-attention resources, and achieving the active scheduling of streaming media resources. Specifically, the method comprises the following steps: firstly, identifying suspected events in real-time traffic data, performing multi-source confidence verification, and marking effective events with high confidence; secondly, predicting the congestion and accident probability of future road sections based on historical data, and marking high-risk road sections; meanwhile, the resource access probability and the access amount are predicted through user behavior analysis, and high-attention resources are marked. When a mark is triggered in any dimension, the system starts a pre-pushing flow mechanism, and the video flow is pre-cached to an edge node after being coded and packaged. According to the invention, the first frame response speed of the expressway streaming media service is improved, and the utilization efficiency of streaming media resources and the real-time performance of the system are improved.

The invention relates to a real-time risk monitoring method for safe lane changing of an automatic driving vehicle, and belongs to the technical field of intelligent networked automobiles. The invention provides an independent three-layer security architecture (a lane changing function layer, a lane changing function monitoring layer and a basic security monitoring layer) to solve the problems that in the prior art, a lane changing security monitoring module is coupled with a decision system, the lane changing process is insufficient in intervention and depends on a high-precision map, and the like. Real-time weather, pavement state and traffic jam information are fused, a lane changing safety boundary is dynamically calculated, a lane changing risk is evaluated in real time, and intervention is triggered. The technical scheme comprises core modules of road congestion estimation, moving target behavior prediction, lane changing maximum time estimation, safety time interval calculation, lane changing safety evaluation, safety boundary control and the like. The method has the advantages that the lane changing safety independence is improved, the dependence on a high-precision map is reduced, real-time risk monitoring and emergency intervention in an all-weather environment are realized, and the risk of wrong lane changing and traffic accidents is effectively reduced.

The invention relates to the technical field of safety detection for traffic while construction, in particular to an informatization safety monitoring method for traffic while construction, which comprises the following steps: preparing for construction; selecting a monitoring site; installing a monitoring radar system and laying anti-intrusion equipment; establishing a wireless data gateway; monitoring radar software installation and opening anti-intrusion equipment; debugging and running. According to the invention, dual systems of the radar congestion monitoring system and the infrared anti-intrusion alarm system are adopted for monitoring and early warning, road congestion and social vehicle intrusion in a construction section are monitored in real time, and dual insurance of safety management of equipment and operators in the construction section is realized. The safety monitoring and early warning timeliness of the road section with traffic and construction is effectively improved, and the emergency capability of avoiding safety risks is effectively improved.

A method for lane-level road congestion identification and forecasting includes identifying lane-level road congestion using Gaussian mixture modeling, predicting lane-level road congestion using a 2D Markov chain, and identifying routes and route changes for a host vehicle and applying the route and route changes to improve a host vehicle estimated time of arrival (ETA) at a predetermined finish location such that the ETA is shorter than a predetermined threshold.

The application relates to the technical field of urban traffic, and provides a vehicle networking big data driven urban traffic congestion relieving method and system.The method comprises the following steps: collecting target area road network distribution, performing road congestion correlation identification based on historical congestion records, and establishing a congestion correlation network; monitoring road traffic data of each road through vehicle networking, identifying congestion lanes and generating congestion degree identification; extracting correlation lanes in the congestion correlation network, identifying signal lights and tidal lane distribution thereof; establishing a traffic flow guiding network, combining the congestion degree, the signal light and the tidal lane distribution, and performing control optimization.The application solves the technical problem that a traditional urban traffic management method cannot effectively identify congestion correlation between roads, leading to congestion diffusion and low relieving efficiency, achieves the technical effect that a congestion correlation network is driven by vehicle networking big data, dynamic control is combined with signal lights and tidal lanes, accurate identification and efficient relief of urban road network congestion are realized, and road passing efficiency is improved.

The embodiment of the invention discloses a traffic signal lamp control method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the steps of obtaining real-time traffic data and regional point cloud data in a target traffic region; constructing a graph neural network according to the traffic data and the regional point cloud data; generating future movement track information corresponding to the target traffic object information by using a graph neural network; inputting the future movement track information and the historical traffic data into a pre-trained traffic flow prediction model to obtain flow prediction data of the target future time period; according to the flow prediction data, the future motion trail information and the adjacent intersection information, using a traffic signal lamp motion prediction method of reinforcement learning to generate prediction motion information; and performing light control on the target traffic signal lamp according to the predicted action information. According to the embodiment, the signal lamp can be controlled in real time according to the traffic congestion condition, the road congestion degree is relieved, and the traffic efficiency is improved.

The invention discloses a method, device and equipment for recognizing a road congestion state in real time and a storage medium. Comprising the steps of obtaining track data corresponding to an idling vehicle provided with front image equipment, and screening target vehicles running on a road based on the track data; extracting a vehicle-mounted front view image of the target vehicle, inputting the vehicle-mounted front view image into a pre-trained traffic object recognition model, and outputting a traffic object recognition result in the image; screening an initial congestion image based on the traffic object recognition result, and automatically marking a traffic light category corresponding to the initial congestion image; and inputting the initial congestion image into a corresponding congestion identification model based on the traffic light category, and outputting a congestion level determination result of the current vehicle. According to the method, the congestion level is accurately judged through image data identification and congestion level identification, the accuracy and the real-time performance of congestion identification are improved, powerful support is provided for traffic management and optimization, and the road traffic efficiency is improved.

The application discloses a public transport line generation method and system based on road congestion avoidance, comprising the following steps: constructing a public transport search graph; obtaining a pickup point input by a user, obtaining a congestion index of the input pickup point, a first-order neighbor of the input pickup point or a second-order neighbor of the input pickup point based on the public transport search graph, and generating a recommended pickup point according to the congestion index; obtaining a starting point and a terminal point input by the user, constructing a candidate line set based on the public transport search graph, screening the candidate line set, and generating a recommended line. The application can provide a road congestion avoidance travel line for the user, save the travel time of the user, intelligently guide the user to go to a suitable station to take a bus during a peak period, enhance the willingness of the user to use public transport for travel, and realize green travel.

The invention relates to a control method and a regulation and control agent for coordinated regulation of traffic volume of parallel arterial roads, which are based on a relative saturation difference as a trigger condition of flow regulation between the parallel arterial roads. And synchronously determining a first signal control strategy for increasing the passing delay of the vehicle on the high-saturation trunk road and a first signal control strategy for increasing the passing delay of the vehicle on the high-saturation trunk road based on the target transfer flow, so as to realize balanced adjustment between the two parallel trunk roads. When the saturation degree of the parallel main road reaches the steady flow upper limit, vehicles not entering the congested main road can enter the parallel road with high admission ability and low traffic pressure, so that the traffic flow is uniformly distributed, and the utilization rate of the parallel road is improved while the congestion of the main road is relieved. According to the method, the path selection of the vehicle can be actively adjusted before the congestion is formed or after the congestion occurs, the bottleneck suppression is realized, and the road network traffic efficiency is improved.

The invention discloses an automobile travel road condition congestion prompting method, device and equipment, and the method comprises the steps: querying a matched travel taking a current position as a departure place in a preset fixed travel and a common travel when an automobile enters a driving mode and does not move; according to the average speed of all vehicles at the current moment in each matched journey, determining a congestion condition corresponding to each matched journey; sequentially carrying out voice broadcasting on the congestion matching journeys, and when each congestion journey is broadcasted, inquiring whether a user needs to recommend and display an alternative route of the same destination; when a positive voice signal of the user is detected, a navigation route is displayed through a vehicle display screen, voice broadcasting is stopped, and when a negative voice signal of the user is detected, voice broadcasting is conducted on the next congested travel. According to the invention, under the condition that the user does not actively start the vehicle-mounted guide during driving, the congestion condition of the travel which the user may pass through can be timely notified to the user through voice broadcast, and the travel efficiency and the driving experience of the user are improved.

The present application relates to a kind of wisdom public transport combined scheduling method, device and storage medium, it is related to scheduling optimization field, call bus card record establishes card site feature set, establishes navigation site trigger and carries out navigation record matching analysis, establishes space-time heat forecast graph;Multi-source traffic flow data set is constructed to carry out road congestion state prediction and construct regional level road congestion state graph;According to space-time heat forecast graph, regional level road congestion state graph, establish site passenger flow demand, line travel time and congestion state;Configure multi-objective scheduling channel, and site passenger flow demand, line travel time and congestion state are used as input data, by passenger waiting time target, scheduling cost target, vehicle utilization rate target, congestion influence target, line bus scheduling optimization is carried out, the technical problem that the present application solves is that there is data utilization insufficient, prediction precision is limited and scheduling strategy lacks flexibility in bus scheduling.

The invention discloses an intelligent traffic road condition real-time monitoring device, and relates to the technical field of road condition real-time monitoring. The problem that the road congestion processing efficiency is low due to the fact that congestion sources cannot be quickly checked is solved. The device specifically comprises a set of mounting columns fixed to the outer wall of the top of the road surface, a mounting plate is fixed to the outer walls of the tops of the mounting columns, a second stepping motor is fixed to the inner wall of one end of the mounting plate, a connecting block is fixed to an output shaft of the second stepping motor, a rotating rod is fixed to the outer wall of one side of the connecting block, and a guide groove is formed in the outer wall of one side of the rotating rod. When road congestion occurs, the shooting angle and the height of the monitoring probe can be adjusted, the lens of the monitoring probe can shoot the congestion part in front of the road, and traffic control personnel can know the reason of the road congestion in advance through the picture shot by the monitoring probe, so that corresponding processing can be quickly performed; and the processing efficiency of road congestion and accidents is improved.

The invention belongs to the technical field of post-earthquake building falling object accumulation range probability prediction models and urban road network blocking vulnerability estimation, and discloses a post-earthquake building ruin distribution range probability prediction model and an urban road network blocking vulnerability estimation method. The building falling object accumulation range prediction model proposed based on the Bayesian theory considers multiple damage states of the building under the earthquake action, including building complete collapse and non-structural member damage; posterior probability distribution of unknown parameters of a prediction model can be obtained based on the Bayesian theory, and accordingly cognitive uncertainty from the model parameters is quantified in post-earthquake road blocking vulnerability evaluation. The method not only helps to improve the accuracy of post-earthquake road congestion risk assessment, but also helps to reasonably plan a post-disaster rescue evacuation path.

The application discloses a kind of tire dust micro plastic emission estimation method, spatial distribution simulation method and system. Including: first, the vehicle population of simulation area, vehicle average mileage, road congestion level, road surface material and heavy vehicle quantity proportion are obtained.Then according to road congestion level, road surface material and heavy vehicle quantity proportion, correction coefficient and correction coefficient are set.Fusion vehicle population, vehicle average mileage, correction coefficient and correction coefficient are then estimated tire dust micro plastic emission.Afterwards, the simulation area is spatially discretized, and the road length proportion of grid is counted.Finally, combined with road length proportion and tire dust micro plastic emission, the grid tire dust micro plastic emission of grid is calculated, and the spatial distribution of tire dust micro plastic in simulation area under grid scale is determined.No need for field sampling and test analysis, improve the efficiency of micro plastic spatial distribution simulation, reduce monitoring cost and monitoring time.

The invention discloses an electric vehicle charging scheduling method and system based on dynamic data fusion and a storage medium, and relates to the technical field of data processing. Comprising the following steps that state monitoring parameters of all standby state charging interfaces are obtained, and available charging piles meeting requirements are screened out; according to the real-time state data and the environment parameters of the charging request electric vehicle, the vehicle is divided into a charging priority vehicle and a cost priority vehicle. For the charging priority vehicle, adjusting a charging pile search range, introducing output power to determine a target charging pile, and performing locking operation; and for the cost-first vehicle, calculating a cost optimization coefficient in combination with arrival time prediction and electricity price fluctuation in a time period, and generating an optimization charging pile sequence. And the user finally selects and locks the charging pile, and dynamically adjusts the locking time according to the road congestion condition. According to the method, efficient distribution of charging pile resources is realized, and user experience and economic cost are optimized.

An accident early warning method, apparatus and system. The method comprises: a server receives road anomaly information indicating a position where an accident occurs, and on the basis of the road anomaly information, determines a first broadcast area to which the accident belongs and a first early warning area, wherein the first early warning area is an area where a vehicle is instructed to report vehicle state information, and the vehicle state information comprises a vehicle speed and is used for determining the degree of road congestion caused by the accident; the server broadcasts, to a vehicle in the first broadcast area, accident indication information that indicates the first early warning area. The vehicle in the first broadcast area performs, at least on the basis of a positional relationship between the first early warning area and the ego vehicle, at least one of the following: sending the vehicle state information to the server, controlling an alert apparatus of the ego vehicle to provide accident information, or controlling the ego vehicle to avoid the accident.

The invention discloses wearable interaction hardware equipment, and relates to the technical field of man-machine interaction. S1, equipment wearing and setting; s2, reporting contact information; s3, automatically replying the voice message; s4, performing voice reply by the user; and S5, traffic light pause state notification. According to the wearable interaction hardware equipment, a user does not need to hold a mobile phone to check or edit messages, distracted driving is avoided through voice interaction of a Bluetooth headset, the traffic accident risk is reduced, meanwhile, road congestion caused by distraction of a driver is reduced, and timely transmission of emergency messages and delayed processing of non-emergency messages are ensured through emergency feature word recognition; not only are important cooperation or help information not missed, but also normal driving is not interfered, the non-emergency message is automatically replied and the optimal contact time is informed, the communication cost of a user is reduced, and the non-emergency message is broadcasted and replied on the premise of ensuring sufficient time in combination with a traffic light pause state, so that the message processing efficiency is improved, and message accumulation is avoided.

The invention discloses a mine transportation scheduling method and system based on a hybrid genetic algorithm, and belongs to the technical field of intelligent optimization scheduling. The method comprises the following steps: S100, inputting mine tunnel network, facility and equipment parameters; s200, a Dijkstra algorithm and breadth-first search are combined, and an optimal path set containing a shortest path and a secondary short path is generated for each pair of ore unloading fields and mining sites so as to disperse traffic flows; s300, establishing a multi-objective optimization model for minimizing waste time and fuel consumption and maximizing transportation volume; s400, a non-dominated sorting genetic algorithm is adopted for solving, the core of the non-dominated sorting genetic algorithm is that a special triple coding mode is adopted, an execution vehicle is allocated for each transportation task, a going route is selected for each transportation task, a return route is selected for each transportation task, and complex constraints are fused into a chromosome structure; s500, performing dynamic simulation on each scheduling scheme, updating the vehicle state and speed based on the real-time road congestion degree, and accurately evaluating the performance of the scheme; s600, selecting a final scheme from the Pareto optimal solution set by using a multi-attribute decision-making method; and S700, when a fault occurs, automatically re-evaluating and allocating tasks. According to the method, the problems of single path, inaccurate model and uncomfortable coding of a traditional method are effectively solved, and high efficiency, energy conservation and high robustness of vehicle scheduling in a complex mine tunnel network are realized.