166 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 provides a non-stationary traffic prediction method based on wave flow decomposition and time delay perception. The method mainly comprises the following steps: constructing a traffic network diagram and inputting historical traffic flow data; constructing a decoupling flow layer, and decoupling the original flow into a wave component and a flow component; constructing a time gating convolution module, and capturing short-time dependency; constructing a space-time causal chain of time-delay perception directed graph attention and processing wave components; constructing an adaptive graph convolutional network, and processing global steady-state features of flow components; constructing a time gating convolution module, and capturing long-term time dependence; constructing an adaptive event fusion module; constructing a full connection layer; and outputting the predicted traffic flow data. The method overcomes the limitation of a traditional method in the aspects of prediction accuracy and coping with a complex traffic network, and effectively solves the problems that a traditional traffic flow prediction method is insufficient in prediction accuracy in an intelligent traffic system, cannot reflect the influence of the traffic network and the like.

The invention relates to a gated multi-graph convolution perception modeling method for traffic flow prediction. The method integrates multi-graph structure construction, gating graph convolution and time feature extraction, and aims to solve the problems of strong time fluctuation and heterogeneous spatial relationship in traffic data. The method comprises the following steps of: firstly, respectively constructing a geographic map and a semantic map according to the maximum mutual information measurement between the spatial distribution information of a sensor and historical traffic data; and then, designing a dual-adaptive gating graph convolution module, and dynamically adjusting an information propagation path of a multi-graph structure by introducing an attention mechanism and a gating factor, thereby improving the modeling performance of the model on spatial isomerism dependence. On the time dimension, a time sequence interactive sensing module is constructed in combination with multi-scale causal convolution and an attention mechanism, time dependence characteristics of a short period and a long period are captured, and fusion and expression of time characteristics are completed. According to the method, the modeling precision and stability of the traffic prediction model in a complex traffic scene can be effectively enhanced, and the method has relatively high practical application value.

The invention discloses a traffic flow prediction method based on multi-view fusion and diffusion diagram convolution. The traffic flow prediction method is suitable for dynamic modeling and space-time dependence extraction in a complex traffic scene. The method comprises the following steps: firstly, extracting short-term fluctuation and long-term periodic characteristics through double-path time slice convolution, and modeling multi-scale time dependence; in the aspect of spatial modeling, three types of graph structures including a static physical graph, a historical semantic graph and a current feature graph are fused, a sparse dynamic graph is generated through a Top-K mechanism, multi-order diffusion graph convolution is executed in combination with a static graph, and local and global spatial features are extracted. Furthermore, a space-time fusion strategy of bidirectional cross gating is provided, the information circulation direction between short-term and long-term features is dynamically adjusted, and coordinated fusion of multi-scale features is realized. And finally, the traffic state of multiple time steps in the future is output through a gating structure and a non-regression prediction module. According to the method, the modeling capability of the model for the complex traffic dependency relationship is effectively enhanced, and the prediction precision and robustness are remarkably improved.

The invention relates to the technical field of traffic prediction, in particular to a multi-layer space-time structure correlation perception traffic flow prediction model, which comprises a space-time structure decomposition layer for decomposing original traffic flow data into a road hierarchical structure feature matrix, a dynamic time period feature matrix and a hidden space topology feature matrix; the dynamic adjacency matrix generation layer is used for constructing a self-adaptive adjacency weight matrix based on the hidden space topological feature matrix; the cross-level correlation perception layer performs bidirectional feature modulation on the road hierarchical structure feature matrix and the dynamic time period feature matrix to generate a space-time coupling feature tensor; and the prediction layer inputs the space-time coupling feature tensor into a space-time diagram convolution prediction network and outputs a traffic flow prediction value in a future time period. According to the method, the expression ability of the model on potential heterogeneous association between the nodes is improved, and the generalization ability across regions and time periods is effectively improved.

The invention provides a traffic control strategy self-adaption method and system based on simulation feedback, and belongs to the technical field of traffic prediction and control, and the method comprises the steps: firstly obtaining traffic control scene data containing traffic flow data and road condition information, then constructing a simulation evaluation environment, configuring scene parameters based on the traffic control scene data, and carrying out the simulation evaluation environment; the method comprises the following steps: simulating traffic operation states under different traffic control strategies, calling a pre-trained reinforcement learning model to perform simulation evaluation on each strategy in a traffic control strategy set, generating a strategy effect feedback set comprising a traffic operation efficiency index and a traffic order stability index, and according to the strategy effect feedback set, calculating the traffic order stability of the traffic control strategy. And performing parameter adjustment on the strategy in consideration of the index association relationship to obtain an adjusted strategy, and finally outputting the adjusted strategy to the traffic control system to realize strategy updating, thereby effectively improving traffic operation efficiency, ensuring traffic order stability, and realizing adaptive optimization of the traffic control strategy.

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 discloses a federal space-time attention adaptive graph learning method and system, and the method comprises the steps: constructing a traffic prediction problem, constructing a space-time attention enhancement dynamic graph convolutional network model composed of a feature enhancement layer, a dynamic graph convolutional recursive network, a multi-head time attention module, a graph attention module and a space-time attention fusion module according to the traffic prediction problem; placing a traffic prediction problem in a federated learning scene, and setting privacy constraints of the model; on the basis of privacy constraints, an activation decomposition strategy is implemented on the model, and the activation decomposition strategy is that a transfer function is applied to a dynamic graph convolutional recursive network in the model; and performing traffic prediction on the traffic data acquired by the sensor by using the model which implements the activation decomposition strategy in a federated learning scene. According to the method, the problems of privacy leakage risk, high communication cost, limited model flexibility and the like in a traditional federal space-time attention adaptive graph learning framework are solved.

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 adaptive and interpretable traffic situation prediction method and system based on a large language model, and the method comprises the following steps: obtaining historical traffic data related to a prediction task, inputting a trained time sequence prediction basic model, and generating candidate traffic state tracks of a plurality of prediction periods based on the prediction task; acquiring context information related to a prediction time period, and evaluating the candidate traffic state trajectory based on a configured large language reasoning model to obtain an optimal trajectory conforming to the context information of the prediction time period; and based on the optimal track and the context information, generating a text report by utilizing the configured large language interpretation model. Probability prediction is carried out through the time sequence prediction basic model, context reasoning and text generation are carried out through the large language model, the accuracy, adaptability and interpretability of traffic prediction under abnormal events are remarkably improved, and powerful support is provided for intelligent traffic.

The invention discloses a vehicle cruise control method and system based on traffic prediction, and relates to the technical field of vehicle intelligent control. The method comprises the following steps: preprocessing vehicle state data and driving environment data by utilizing edge calculation; performing information fusion and mapping on the preprocessed data by using a cloud control platform to obtain a road traffic condition simulation result, and generating an optimal vehicle driving strategy according to the road traffic condition simulation result by using reinforcement learning; a hierarchical control strategy is constructed by considering traffic constraints and economic vehicle speed factors, and the vehicle is dynamically regulated and controlled; and the real-time driving state of the vehicle is fed back to the cloud control platform, and parameter optimization is carried out on the optimal driving strategy of the vehicle. According to the invention, traffic information is efficiently mined and fused by using the powerful information processing and fusion capability of the cloud control platform, predictive cruise control of the vehicle is realized in combination with a vehicle control optimization algorithm, and the energy-saving effect and the driving efficiency of the vehicle in a complex traffic environment are improved.

The invention discloses an intelligent electric vehicle queue optimization method based on congestion prediction and DRL. The method comprises the following steps: (1) modeling a queue position optimization problem of an electric vehicle queue into a mathematical model which takes energy balance as a target and is constrained by a traffic environment; and (2) solving the mathematical model in the step (1) by adopting a DRL method based on a TRPO algorithm to obtain an optimal queue adjustment strategy of the electric vehicle queue. In the step (2), congestion state information in an external traffic environment is obtained through an LSTM traffic prediction and FCM method, and the congestion state information, the remaining electric quantity of each vehicle in the motorcade and the accumulated driving distance are jointly used as state input of a TRPO algorithm; according to the TRPO algorithm, a strategy network and a value network are adopted to respectively obtain a strategy for adjusting the queue position, and the return expectation in the current state is evaluated. The TRPO algorithm dynamically adjusts the updating step length of the strategy through the KL divergence updated by the constraint strategy, and guarantees the stability and convergence in the strategy updating process.

The invention relates to an intelligent traffic signal control method and system based on traffic flow prediction, and belongs to the technical field of intelligent traffic. Traffic vehicle video streams and traffic flow data are collected through a high-definition camera and a traffic flow sensor group, different vehicles and speeds, directions and movement tracks thereof are identified through the traffic vehicle video streams, special vehicles are judged, traffic violation behaviors and road abnormal conditions are monitored according to the traffic vehicle video streams and the traffic flow data, and the traffic violation behaviors and the road abnormal conditions are monitored. A traffic prediction model is established according to traffic vehicle video streams and traffic flow historical record data, and traffic flow, vehicle positions, vehicle categories, lane line information, vehicle movement tracks, traffic violation, road abnormal conditions, and traffic flow values and vehicle speeds in future time periods of all lanes at all intersections are obtained from a server in real time. And different signal lamp control schemes are generated according to different vehicles. According to the invention, a signal control scheme is designed in combination with vehicle types, traffic violation, road abnormity and other conditions, and accurate traffic congestion dispersion is realized.

The invention provides a short-term traffic flow prediction method and device, equipment and a storage medium, and belongs to the technical field of road traffic prediction. The scheme comprises the following steps: collecting historical road index data, wherein the index data comprises time characteristics, weather characteristics, road section characteristics and holiday and festival characteristics; carrying out one-hot coding processing on the weather features, respectively carrying out normalization processing on the time features and the road segment features, and carrying out binarization processing on holiday and festival features; a decision-making tree and a corresponding prediction function are constructed through a gradient boosting decision-making model according to the processed multiple groups of index data, multiple decision-making trees are generated through multi-round iteration, and the decision-making tree enabling the loss function of the current iteration to be minimum is obtained through each round of iteration on the basis of the previous round of iteration; calculating the weight of each decision tree in the prediction function based on the loss function of each round; accumulating the decision-making trees constructed in each step through the weights to obtain a final decision-making tree; and inputting the latest collected index data into the final decision tree, and outputting a prediction result of the traffic flow of the current road in the next time period. According to the scheme, the problem that the traffic flow prediction precision is not accurate enough due to the fact that the number of researched data dimensions is relatively small in the existing short-time traffic flow prediction technology is solved.

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 relates to the technical field of traffic prediction, and discloses a road traffic flow prediction method and system based on big data, and the system comprises a data fusion processing module, a prediction algorithm matching module and a dynamic prediction execution module. The method solves the time-space sampling frequency difference between meteorological environment data and dynamic traffic flow data, achieves the refined quantitative characterization of impact factors of sudden traffic events, enhances the prediction stability under severe meteorological conditions, fuses road network adjacency relation characteristics through a time-space grid matrix, captures the cascading congestion propagation effect caused by upstream accidents, and improves the prediction accuracy. The prediction reliability of complex road network structures such as interchange junctions is improved, the congestion false alarm rate is reduced, deviation accumulation in the continuous prediction process is continuously corrected through linkage of dynamic prediction model training and a real-time feedback optimization module, the model robustness in a special traffic scene is improved, and the stability of long-term operation of a prediction system is kept.

The embodiment of the invention discloses a multi-source big data traffic control management method and system based on a distributed architecture, and belongs to the technical field of intelligent traffic. The problem that in the prior art, traffic situation prediction precision is insufficient, and consequently traffic regulation and control are not accurate is solved. Comprising the following steps: constructing a dynamic traffic flow model based on extracted feature data and a dynamic space-time diagram corresponding to a traffic network; deducing the traffic situation through a central node in a traffic road network to obtain a plurality of traffic prediction scenes, and matching corresponding traffic regulation and control strategies; after the abnormal traffic event is detected, an affected area is delimited according to the corresponding propagation influence trend of the abnormal traffic event on the space axis; dynamically combining a plurality of operation units corresponding to the traffic regulation and control strategy through the central node, and generating a customized regulation and control scheme; and each edge node performs joint optimization on the customized regulation and control scheme by using a distributed optimization algorithm based on local traffic flow data so as to realize traffic control management.

The invention discloses an urban circle traffic demand prediction method and system, and belongs to the technical field of traffic data processing, and the method comprises the steps: taking a four-stage theory as a basis, efficiently obtaining a travel demand OD matrix of urban circle global traffic middle area granularity in the future, and mastering the overall traffic demand pattern of an urban circle from a macroscopic level; on the basis of a trip chain theory, a city traffic cell granularity trip demand OD matrix with higher time-space precision in the future year is accurately obtained, and the method can adapt to more application scenes and reflect traffic prediction and evaluation analysis of traffic demand details; through a traffic distribution algorithm of motor vehicles and public traffic, traffic flow indexes borne by urban circle traffic supply facilities are obtained, and continuity and consistency of spatial and temporal distribution of the current situation and indexes such as traffic supply facilities, travel demands, road flow and bus passenger volume in the future are achieved. And therefore, the traffic demand prediction and evaluation index result of the urban circle in the future year can scientifically meet the needs of users.

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.

The invention discloses a heterogeneous perception traffic prediction method based on federated learning, and the method employs federated learning to design a unified heterogeneous perception framework, and supports an existing centralized traffic prediction model. Clients with similar traffic flow data distribution are gathered together by utilizing multi-dimensional positive sample comparative learning, so that the clients of the same kind can cooperatively train a model, and the influence of data isomerism between different clients is avoided; the model of each stage is trained in sequence based on a time window by using data partition, so that the influence of data missing on traffic prediction is reduced; noise detection is used for global detection and local denoising, so that the quality of client data is ensured.

The invention discloses a traffic prediction method based on an adaptive semantic enhancement space-time diagram network, and the method comprises the steps: firstly constructing an initial space diagram through traffic sensor data, and carrying out the standardization processing; secondly, introducing an adaptive node embedding method to dynamically learn a spatial dependency relationship among nodes in the traffic network; a double-branch structure is further adopted, a parallel gating network (PGN) is used for capturing a long-term traffic mode, and linear hierarchical aggregation is adopted for capturing a short-term local mode; and finally, fusing space and time features to perform end-to-end training to optimize the prediction model. The method can effectively improve the accuracy and robustness of traffic prediction, and is suitable for intelligent management and decision optimization of a complex urban traffic environment.

The application provides a traffic control strategy adaptive method and system based on simulation feedback, belonging to the technical field of traffic prediction and control. First, traffic control scene data containing traffic flow data and road condition information is obtained, then a simulation evaluation environment is constructed, scene parameters are configured based on the above traffic control scene data, the traffic running state under different traffic control strategies is simulated, then a pre-trained reinforcement learning model is called to simulate and evaluate each strategy in the traffic control strategy set, generating a strategy effect feedback set containing traffic operation efficiency indicators and traffic order stability indicators, according to the strategy effect feedback set, the parameters of the strategy are adjusted considering the index correlation, obtaining the adjusted strategy, finally the adjusted strategy is output to the traffic control system, realizing strategy updating, thereby effectively improving traffic operation efficiency, guaranteeing traffic order stability, and realizing adaptive optimization of traffic control strategy.

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 belongs to the technical field of traffic prediction, and discloses a subway passenger flow prediction method and system based on a multi-view space-time neural network. And a plurality of spatial correlation diagrams are constructed based on the physical topological structure of the metro, the station traffic similarity and the traffic interaction relationship. These graph structures provide abundant information for capturing spatial dependencies in a metro network. Thirdly, processing the spatial diagrams by adopting a multi-hop graph convolution network (R-GAT), and updating node features step by step through multi-layer graph convolution so as to capture the spatial relationship among different sites; meanwhile, in combination with a multi-view attention mechanism, contributions of different spatial views to passenger flow prediction are dynamically evaluated, so that the learning process of spatial features is optimized. The subway passenger flow volume prediction method based on the multi-view space-time neural network provided by the invention has relatively high theoretical value and application prospect.

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.