103 results about "Transportation forecasting" patented technology

The invention belongs to the technical field of intelligent traffic systems, and particularly relates to an intersection signal timing dynamic coordination system and method based on real-time traffic prediction.The method comprises the steps of collecting multi-source traffic data, generating a space-time prediction digital twin model, dynamically defining an intersection coordination cluster and executing cluster coordination optimization control. And signal timing and closed loop feedback are carried out. By adopting the technical scheme, the cooperative operation efficiency and the intelligent management level of the urban intersection group can be effectively improved, and the fundamental conversion from local and reactive active cooperative control to global and predictive active cooperative control is realized.

The invention discloses a traffic prediction method and device based on multi-modal feature fusion, and a medium, and relates to the technical field of traffic prediction. The method comprises the following steps: performing unmanned aerial vehicle video acquisition and preprocessing on an interleaving area to obtain a target area video; traffic flow parameters are extracted from the target area video based on a multi-target detection and tracking algorithm, wherein the traffic flow parameters comprise a space average speed, a space occupancy rate and a vehicle interleaving conflict index; a deep learning model is adopted to process the image sequence of the target area video, potential semantic features are extracted, and the deep learning model comprises a variational auto-encoder; carrying out weighting processing on the potential semantic features by adopting a double attention mechanism; and splicing the weighted potential semantic features and the traffic flow parameters into a multi-modal feature vector, and carrying out traffic state prediction. According to the method, the accuracy and robustness of traffic state prediction of the interlaced area are improved, and more accurate data support and decision basis are provided for dynamic traffic management of complex road sections.

The invention relates to the field of intelligent traffic, and provides a cross-domain-oriented urban traffic road network toughness pre-judgment and evaluation method, which comprises the following three steps: step 1, based on input source domain and target domain urban traffic data, constructing a space-time cross-domain traffic prediction model, realizing traffic state transfer learning and generalization prediction among different cities, and establishing a space-time cross-domain traffic prediction model; generating traffic prediction in a cross-domain scene and a corresponding traffic map structure; 2, designing a hysteretic toughness index in combination with a prediction result and a traffic map structure, and fusing structure-function toughness and a hysteretic toughness factor to form a toughness index capable of reflecting a road network performance evolution mechanism; and step 3, based on the hysteretic toughness index, establishing a space-time fine-grained toughness quantization algorithm for quantizing node-level toughness of the road network. According to the method, the three major problems of lack of pre-judgment and cross-domain generalization ability, single toughness index representation and rough toughness quantification of an existing evaluation method are effectively solved, and the perspectiveness, the adaptability and the accuracy of road network toughness evaluation are remarkably improved.

The invention discloses an inland waterway congestion dredging method and device, and relates to the field of traffic control, and the method comprises the steps: obtaining multi-source traffic data and waterway meteorological and hydrological data of each ship in a waterway; performing space-time registration and fusion processing on the multi-source traffic data, generating comprehensive traffic situation information of the whole section of the channel, and extracting traffic flow characteristic parameters and channel congestion indexes; inputting the traffic flow characteristic parameters, the channel congestion index and the channel meteorological and hydrological data into a trained traffic flow prediction model to obtain traffic prediction information of key nodes in the channel in a future preset time window; based on the comprehensive traffic situation information and the traffic prediction information, generating preventive control parameters for channel key node signal lamps; and according to the traffic prediction information and the preventive control parameters, traffic guidance information is generated and sent to the corresponding ship terminals, and the preventive control parameters are sent to the corresponding signal lamp control machines. The overall passing efficiency of the channel can be improved.

The invention discloses an abnormal traffic situation generation method based on a large language model and a diffusion model, and relates to the field of computer machine learning, and the method comprises the steps: obtaining a traffic event text description and a historical traffic state, aligning the time stamps of the text description and the historical traffic state, and dividing a training set, a verification set and a test set; acquiring a traffic network structure, and making the traffic network structure into an adjacent matrix for spatial relationship modeling of a subsequent model; constructing an abnormal traffic situation generation model, training by adopting a training set, adjusting parameters by adopting a verification set, and evaluating a generation effect by using a test set; and finally, optimizing the model by adopting a weighted mixed objective function combining noise prediction loss and potential reconstruction loss. According to the method, the abnormal traffic situation with semantic consistency and spatial rationality can be effectively generated, and support is provided for traffic prediction, emergency management and intelligent traffic scheduling.

The invention discloses a tunnel ventilation system and a control method thereof, and relates to the technical field of tunnel ventilation energy-saving control. According to the method, traffic data, environment data and equipment starting data in a tunnel are preprocessed and divided into data sets, a traffic prediction model based on LSTM and an environment prediction model based on full connection are constructed, and training is carried out through a root-mean-square error and an average absolute percentage error; and sequentially predicting traffic and environment data by using the model, and solving an optimal ventilation equipment combination through a sequential quadratic programming algorithm by taking energy consumption minimization as a target and environmental standard reaching as a constraint, and adjusting operation. The method has the advantages that advanced regulation and control are achieved through the two-stage prediction model, pollutants are prevented from exceeding the standard, and the air quality is guaranteed; dynamic training, multi-parameter optimization and a fault tolerance mechanism are combined, energy conservation and environment regulation and control are accurately balanced, meanwhile, the operation reliability and the intelligent level of the system are improved, and manual intervention is reduced.

This invention discloses a multimodal traffic flow prediction method based on multi-source data feature fusion, comprising: acquiring traffic data; dividing the traffic data into training and testing sets; constructing a traffic prediction model and training the traffic prediction model using the training set; and validating the traffic prediction model using the testing set. The traffic prediction model includes: a cloud map encoder for extracting features from cloud map data to obtain cloud map features; a spatiotemporal encoder for extracting features from spatiotemporal data to obtain spatiotemporal features; a fusion module for fusing cloud map features and spatiotemporal features to obtain fused features; and adding the cloud map features, spatiotemporal features, and fused features, inputting the sum to the spatiotemporal decoder for prediction to obtain the final prediction result. This invention integrates multi-dimensional and multi-faceted information, simplifies redundant information in the spatiotemporal feature extraction process, and achieves efficient and high-precision prediction, which can be widely applied in the field of traffic flow prediction technology.

The invention discloses a traffic flow prediction method based on cross-modal interactive geographic image coding, and relates to the technical field of intelligent traffic systems and data processing. The method comprises the following steps: firstly, acquiring historical traffic data and a road network geographic image, and respectively constructing an embedded representation containing space-time periodicity and extracting node-level visual features; secondly, through a hybrid cross attention mechanism, utilizing a learnable global visual token as an abstract agent, compressing visual features and performing cross-modal alignment with the dynamic space-time representation to generate an enhanced space-time representation; meanwhile, a visual relation mode is constructed based on local visual patches between the nodes, and refining is carried out through a general relation matrix; and finally, dynamically fusing time, space and visual relation characteristics by using an adaptive gating mechanism, and predicting future traffic flow. Visual modes such as road geometry can be effectively captured, the problem of dynamic and static heterogeneous mode alignment is solved, and the accuracy of traffic prediction is remarkably improved while the calculation efficiency is guaranteed.

The invention discloses a scenic spot traffic flow prediction-oriented multi-source heterogeneous data driven space-time modeling method. The method comprises the following steps: acquiring traffic historical data, a road network topological structure and scenic spot related auxiliary factors, and constructing multi-dimensional tensor and graph structure representation; spatio-temporal feature learning is realized through time slice embedding and spectrogram position coding, and a tourism enhancement tensor is constructed in combination with scenic spot auxiliary semantic factors and serves as node regulation and control guide input; and introducing a cross attention mechanism which is jointly regulated and controlled by a tourism regulation factor and a propagation delay factor into the encoder, and fusing multi-source embedded information to generate a traffic flow prediction result. The method is suitable for scenes with severe flow change such as holidays, holidays and hot scenic spots, the dynamic regulation and control relation of tourism activities to traffic states can be accurately reflected, and the response capability, interpretability and robustness of a traffic prediction model to high-association nodes are improved.

The invention discloses a multi-traffic-mode prediction method based on a hybrid expert model and space-time attention, and relates to the technical field of traffic prediction, and the method comprises the steps: dividing historical passenger flow sequences of multiple traffic modes according to tasks through employing a multi-gating hybrid expert model, and outputting a weighted expert feature corresponding to each task; wherein different tasks correspond to different traffic modes; performing feature structuring on the weighted expert features of each task in a traffic mode by using a space-time double-patch architecture to obtain space-time structural features; performing multi-scale feature extraction in a traffic mode and inter-modal feature fusion on the space-time structure features by using a space-time multi-attention convolutional neural network to obtain fused features; and traffic flow data of the multiple traffic modes are obtained through prediction according to the fusion features. According to the invention, through combined prediction of multiple traffic modes, flexible and steady multi-task learning is realized, different prediction tasks are adaptively balanced, and traffic flow data of different traffic modes can be accurately predicted.

The invention discloses a traffic flow prediction method based on a large language model, and the method comprises the steps: data preparation, construction of a road network diagram structure, collection of traffic sensor data, construction of a traffic prediction model, formatting of the data into a mixed format in which a natural language and a structure are combined, spatial feature extraction through LLM, formatting of time series data, and reprogramming. And then fusing the spatial features with the spatial-temporal features of the reprogrammed time series data, performing lightweight fine tuning on the language model by using LoRA, then performing forward propagation, abandoning a suffix part and obtaining an output representation, performing a flattening operation on the output representation, and obtaining a prediction result through a linear projection layer. According to the method, the LLM is conveniently used for traffic flow prediction under the condition that the backbone language model is kept complete, and the complexity and parameter quantity of model training are remarkably reduced while the prediction accuracy is improved.

The invention discloses a cross-city traffic prediction method and system based on multi-modal fusion and spatial expert routing, relates to the technical field of traffic prediction, and provides an adaptive modal selection mechanism based on a signal-to-noise ratio for the problems of missing, noise and uneven quality of multi-modal data in different cities. And a low-quality mode is dynamically suppressed in combination with comparative learning, and robust multi-mode fusion is realized. In order to solve the problems of large space structure difference and weak generalization ability among cities, a multi-modal guided space expert routing architecture is designed: modal sharing experts and routing experts are activated by using a multi-modal context, and local space dependence is adaptively modeled for different functional regions. The method supports any modal combination input, city specific fine tuning is not needed, and the zero sample cross-city prediction performance is significantly improved.

The invention relates to the technical field of intelligent traffic control, particularly discloses a traffic flow dynamic prediction and scheduling method based on artificial intelligence, and aims to solve the problems that the traffic prediction precision is insufficient and the scheduling strategy lacks adaptability. According to the method, continuous optimization is realized through multi-source traffic data fusion, spatial-temporal feature depth extraction, multi-scale dynamic prediction and adaptive scheduling strategy generation in combination with closed-loop feedback. A deep convolutional network and a graph attention network are adopted to extract spatial-temporal features, and a signal control and lane management strategy is dynamically generated through multi-target reinforcement learning, so that the road network traffic efficiency and the system adaptive ability are effectively improved.

A traffic information providing method and a system thereof are provided. The traffic information providing method according to an embodiment of the present disclosure is executed by a computing system, and may comprise the steps of: inputting a plurality of traffic mode data and real-time traffic information, which are generated in advance, into a traffic prediction model; outputting an error of each piece of traffic mode data in the plurality of pieces of traffic mode data at the first time point as an input result; and generating traffic information from a departure place to a destination using first traffic mode data with the smallest error among the plurality of traffic mode data, where the traffic mode data is a combination of mode speeds for each road segment, which is a smallest unit of a road.

This invention discloses a traffic prediction method and system based on a spatiotemporal hierarchical network. The method includes: acquiring traffic data and preprocessing the data to construct a hierarchical regional augmentation network and a traffic feature matrix; using the hierarchical regional augmentation network and the traffic feature matrix as input to a prediction model, learning spatial and temporal correlations, and outputting prediction results; the prediction model includes a region-aware spatial correlation model and a region-aware temporal correlation model. The system includes a preprocessing module and a prediction module. By using this invention, the spatiotemporal correlations in traffic data are effectively captured, improving the accuracy of traffic flow prediction. This invention, as a traffic prediction method and system based on a spatiotemporal hierarchical network, can be widely applied in the field of traffic prediction.

The invention discloses a coating intelligent control system and control method for a self-luminous road marking, relates to the technical field of road engineering, and aims to construct a road marking, environment and traffic digital twinborn model, operate a deep reinforcement learning algorithm at an edge end, and construct a coating intelligent control system for a self-luminous road marking based on key characterization parameters and traffic prediction data. An optimal light-emitting parameter decision is output through a digital twinborn model, and a preliminary flexible controllable light-emitting unit control instruction is formed; a vehicle-road cloud integrated collaborative interaction mechanism is constructed, vehicles, a traffic platform and a cross-department system are linked, real-time interaction data is supplemented for algorithm decision, and a flexible controllable light-emitting unit control instruction is optimized and output. According to the invention, multi-dimensional regulation and control of light-emitting parameters are realized, and environment and traffic adaptability is enhanced; the digital twin-driven adaptive algorithm gives consideration to the visual distance and energy consumption optimization, and ensures that the visual distance is greater than or equal to a set threshold value while the energy consumption is greatly reduced; the vehicle-road cloud integrated cooperation mechanism greatly reduces the response delay of the emergency scene, and improves the road safety.

The invention is applicable to the technical field of intelligent traffic systems, and provides a universal path representation learning method based on multi-modal spatial-temporal feature fusion, which comprises the following steps: firstly, carrying out multi-modal data preprocessing on a road network, a historical traffic speed and a remote sensing image, and constructing basic features; thirdly, through speed-road network fusion modeling, a road topological structure and periodic traffic speed dynamic characteristics are combined, and road path representation is generated; the road path representation and the image path representation are then subjected to fine-grained, medium-grained and coarse-grained semantic alignment at a node level, a sub-path level and a full-path level. And finally, through cross-modal residual fusion based on graph semantic information, integrating roads, images and environment semantic information thereof by using a graph neural network to obtain final path representation with enhanced semantics and stronger discrimination. According to the method, space-time dynamic and visual semantics are effectively fused, and more robust and universal path representation can be provided for downstream tasks such as path planning and traffic prediction.

The application discloses a traffic robust knowledge distillation training prediction method and device, equipment and a storage medium, the method comprises the following steps: acquiring traffic flow historical observation data, dividing the traffic flow historical observation data into source domain training data and out-of-distribution verification data, and constructing a knowledge distillation architecture comprising a teacher model and a student model; according to the source domain training data and the out-of-distribution verification data, performing meta-learning double-layer optimization training on the knowledge distillation architecture, using the source domain training data in the inner loop to guide the student model to imitate the teacher model, using the out-of-distribution verification data in the outer loop to evaluate the generalization performance of the student model and correct the parameters of the teacher model in reverse, until a robust target student model is obtained; according to the target student model, receiving real-time input traffic flow data and performing forward reasoning, and outputting a prediction result of future traffic conditions, which can significantly improve the generalization ability and accuracy of traffic prediction, and realize efficient and robust prediction in complex traffic environment.

The application provides a traffic prediction system and method based on a space-time gating hypergraph convolution network. The method constructs a traffic hypergraph to model high-order spatial correlation; a plurality of historical time road node traffic flows are divided into a plurality of groups of road node traffic flow samples and real traffic flows through a sliding window division method; a space-time gating hypergraph convolution network traffic prediction model is constructed in combination with the traffic hypergraph, each group of samples is input into the prediction model for prediction to obtain predicted traffic flow, a loss function is constructed in combination with the real traffic flow, and an optimized space-time gating hypergraph convolution network traffic prediction model is obtained through Adam optimization training; a central server collects a plurality of time road node traffic flows through a plurality of traffic flow sensors, and the collected traffic flow is predicted through the optimized space-time gating hypergraph convolution network traffic prediction model to obtain future plurality of time road node traffic flows. The application fully excavates the correlation between high-order spatial correlation and different types of traffic data.

The application discloses a traffic flow prediction method based on a graph attention mechanism and a bidirectional gated recurrent unit, and is realized through four steps of capturing spatial dependence features, capturing time dependence features, full connection operation and result prediction.The application is superior to other benchmark models in the extraction of space-time features and achieves good results in long-time traffic flow prediction.The traffic prediction results of the application model at different nodes in the real road network are good, the space-time dependence features of the traffic road network can be fully captured, the effectiveness of the application model in long-time traffic flow prediction is better reflected, and the real vehicle speed change trend can be reflected.

The present application relates to the field of intelligent transportation, and proposes a cross-domain-oriented urban traffic network resilience prediction and evaluation method, which contains three steps: step 1: based on the input source domain and target domain urban traffic data, a time-space cross-domain traffic prediction model is constructed, the traffic state migration learning and generalization prediction between different cities are realized, and the traffic prediction and the corresponding traffic graph structure under the cross-domain scene are generated; step 2: combining the prediction result and the traffic graph structure, a hysteresis resilience index is designed, the structure-function resilience and hysteresis resilience factors are fused, and the resilience index reflecting the performance evolution mechanism of the road network is formed; step 3: based on the hysteresis resilience index, a time-space fine-grained resilience quantification algorithm is established, which is used for quantifying the node-level resilience of the road network. The present application effectively solves the three major problems of the existing evaluation method: lack of predictability and cross-domain generalization ability, single resilience index representation and rough resilience quantification, and significantly improves the forward-looking, adaptability and accuracy of the road network resilience evaluation.

The embodiment of the invention provides an urban traffic prediction method and device and electronic equipment, and relates to the field of traffic prediction.The method comprises the steps that first original data are received, the first original data comprise roadside data and vehicle end data, space-time alignment is conducted on the first original data through edge cloud, and the aligned first original data are obtained; and generating a street-level short-term prediction result based on the aligned first original data, processing the aligned first original data and the street-level short-term prediction result through the regional cloud, generating a regional-level medium-term prediction result, and processing the regional-level medium-term prediction result through the central cloud to obtain a city-level long-term prediction result. Through the urban traffic prediction method provided by the invention, the problems of single information source, poor architecture timeliness, difficulty in heterogeneous information fusion and insufficient prediction levels in the prior art are solved, and the accuracy of traffic prediction is further improved.

The invention discloses a road charging station dynamic constant volume method based on deep reinforcement learning, and belongs to the technical field of traffic prediction. The method comprises the steps that a charging station constant volume model is constructed, the charging station constant volume model is a D3QN-PER-2s network model, and a state space, an action space, a reward function and a target function are defined based on the charging station constant volume model; acquiring annual average day-based charging demand data of the target service area; and inputting the annual average day-based charging demand data of the target service area into the trained charging station constant volume model to obtain the target charging station capacity required by the target service area. According to the method, the accuracy and reliability of highway service area charging station capacity prediction are improved.

The application relates to the technical field of intelligent traffic prediction, and discloses a traffic prediction method and system based on spatiotemporal graph convolution, wherein the traffic prediction method based on spatiotemporal graph convolution comprises the following steps: acquiring traffic data and establishing a safety rule knowledge base, encoding traffic safety specifications into structured safety rules; processing historical traffic data and designing an adversarial sample generator; training a safety boundary detector; performing adversarial safety detection; implementing progressive safety stress testing; deploying a real-time safety protection layer according to the results of the adversarial safety detection and the progressive safety stress testing; constructing an adaptive safety constraint mechanism, dynamically adjusting a safety threshold and a correction strategy; and generating a prediction result with safety verification reinforcement; the traffic prediction method fuses safety rule knowledge and adversarial safety detection, improves the safety reliability of a prediction result while maintaining prediction accuracy.

The invention discloses a path query method, which comprises the following steps: acquiring graph data of a time-varying road network, the graph data comprising a vertex set, an edge set, a time-varying transit time function set and a current time window; constructing a time-varying H2H index based on the vertex set, the edge set and the time-varying passing time function set; setting a sliding time window taking the current time window as a reference; sliding the sliding time window along the positive direction of the time axis at a preset time interval, and obtaining corresponding updated traffic prediction data; according to the updated traffic prediction data, performing incremental expansion and updating on the time-varying H2H index to obtain an updated time-varying H2H index; obtaining a query request of a user; and according to the query request, outputting the path with the shortest required passing time corresponding to the query request and the corresponding passing time by using the updated time-varying H2H index.

The technology described herein is directed towards accurate low-complexity decision tree-based traffic predictor models, such as decision tree regressor models for use by base stations. Each model is rapidly retrained per base station using data relevant to the base station. To improve accuracy, statistically significant feature data is selected by performing hypothesis testing on candidate features to filter out features that cannot satisfy a statistical significance threshold (e.g., p-value). The decision tree regressor model is recursively grown based on the selected features' feature values and their traffic level labels. Predicted traffic level data is determined by traversing the trained decision tree to reach a leaf node associated with the prediction data. Resource allocation can be based on the prediction. In addition to time-series training data, spatial training data can be used. Real time traffic monitoring by a radio unit for operating in an autonomous management mode is also facilitated.

The invention discloses a smart traffic adaptive regulation and control system and method based on social perception, and belongs to the technical field of traffic Internet of Things. Comprising a multi-modal social perception layer module, an edge intelligent preprocessing node module, a dynamic social flow modeling engine module, a space-time social prediction engine module, an adaptive signal lamp optimization module, an Internet of Vehicles collaborative pushing module and a traffic closed-loop feedback module. A social event factor is dynamically injected through an LSTM-Transform hybrid model, and self-adaptive adjustment of space-time prediction is achieved; the accuracy and robustness of traffic prediction are remarkably improved, and the congestion risk can be accurately recognized in advance in the social event high-incidence period; and prediction misjudgment caused by neglecting social behaviors is avoided, so that the system can dynamically respond to traffic flow changes, the congestion pressure is effectively relieved, and the road traffic efficiency and the overall traffic smoothness are improved.

The application relates to an intelligent networked vehicle trajectory planning method based on a space-time dynamic coupling graph in the technical field of intelligent traffic and automatic driving, and comprises the following steps: S1, collecting and fusing multi-source traffic data, constructing a double-level dynamic coupling graph comprising a physical topology layer and a variable interaction layer, generating a traffic network dynamic model reflecting the evolution of a traffic state in real time, and outputting a traffic state tensor E, a physical topology matrix and a variable interaction matrix; S2, inputting the traffic state tensor E, the physical topology matrix and the variable interaction matrix into a prediction network, extracting space-time features of speed, flow and density through independent channels, capturing dynamic coupling relationships among variables by combining a cross-variable attention mechanism, generating a multi-step traffic prediction result Y, and performing vehicle trajectory planning; the method can effectively fuse multi-source traffic data, depict multi-variable dynamic coupling relationships and be beneficial to dynamic optimization of vehicle trajectories.

The application discloses a coating film intelligent control system and control method for self-luminous road marking, relates to the technical field of road engineering, constructs a road marking, environment and traffic digital twin model, runs a deep reinforcement learning algorithm on an edge side, outputs optimal luminous parameter decisions through the digital twin model based on key characteristic parameters and traffic prediction data, forms a preliminary flexible controllable luminous unit control instruction, constructs a vehicle-road cloud integrated collaborative interaction mechanism, links vehicles, traffic platforms and cross-department systems, supplements real-time interaction data for algorithm decisions, optimizes flexible controllable luminous unit control instructions and outputs them. The application realizes multi-dimensional regulation and control of luminous parameters, enhances environmental and traffic adaptability, and an adaptive algorithm driven by a digital twin considers visible distance and energy consumption optimization, so that the energy consumption is greatly reduced while ensuring that the visible distance is greater than or equal to a set threshold value; the vehicle-road cloud integrated collaborative interaction mechanism greatly reduces response delay in emergency scenarios and improves road safety.

An example operation includes one or more of receiving a current geographic location of a vehicle traveling along a travel route from at least one hardware sensor installed on the vehicle, predicting an upcoming geographic location of the vehicle based on the current geographic location of the vehicle, selecting an artificial intelligence (AI) model from among a plurality of AI models in a mixture-of-experts (MoE) based on the upcoming geographic location of the vehicle, forecasting traffic parameters at the upcoming geographic location based on execution of the selected AI model on sensor data from the upcoming geographic location, and rerouting the vehicle to a different travel route based on the forecasted traffic parameters at the upcoming geographic location.