61 results about "Traffic forecast" patented technology

The invention discloses a traffic flow prediction method and device, a storage medium and electronic equipment. The method relates to the technical field of traffic flow analysis, and comprises the following steps: constructing a multi-source traffic data pool, and preprocessing historical traffic data in the multi-source traffic data pool to obtain a target multi-source traffic data pool; performing data enhancement processing on the historical traffic data in the target multi-source traffic data pool by adopting a pre-trained GANs model to obtain an enhanced sample set for training a target traffic flow prediction model; performing model training on an initial traffic flow prediction model by adopting a Dropout method based on the enhanced sample set to obtain a target traffic flow prediction model meeting a preset condition; and performing traffic flow prediction on multi-source traffic data acquired in real time by using the target traffic flow prediction model to obtain a traffic flow prediction result. According to the method, the accuracy of urban traffic flow prediction can be improved.

The invention belongs to the technical field of traffic flow green wave control, and particularly relates to a green wave control method based on traffic flow prediction driving. The method comprises the following steps: acquiring multi-dimensional real-time data in a distributed manner; performing abnormal value detection and data interpolation based on space-time neighborhood analysis to generate high-quality time sequence traffic flow data; modeling a road network into a dynamic graph fusing static connectivity and real-time traffic flow coupling degree, and constructing a double-time-scale time sequence diagram sequence; inputting an improved space-time diagram neural network, extracting time features by optimizing Bi-GRU, capturing spatial association by a multi-head attention mechanism, and outputting an accurate road section-level traffic flow prediction result through residual fusion; and finally, constructing a multi-objective optimization model based on prediction, solving by using an improved multi-objective particle swarm algorithm, obtaining a signal timing scheme, and issuing and executing the signal timing scheme. The method can dynamically adapt to traffic changes, improves the traffic efficiency, and avoids green wave failure and congestion.

The invention discloses an urban traffic flow prediction method fusing a graph attention network and a Transform, and belongs to the field of traffic flow prediction. The method comprises the following steps: (1) constructing an urban refined characteristic traffic flow high-quality data set based on actual license plate recognition (LPR) probe data; (2) building an efficient space-time traffic flow prediction model of a fusion graph attention network GAT and a Transform model; and (3) traffic flow prediction model training based on time-space fusion. According to the method, the traffic flow prediction model fusing the graph attention mechanism and the Transform is established, the space-time dependency relationship of the traffic flow in the urban complex road network is accurately described, the traffic flow prediction level under the urban complex road network is improved, and efficient data support is provided for intelligent traffic management, signal control optimization and urban congestion management.

The present application relates to the technical field of smart tourism and passenger flow management, and particularly relates to a smart tourism destination tourist carrying capacity dynamic evaluation method and system, the method comprising: collecting entrance ticket scanning data, device signal density data and video passenger flow statistical data to form multi-source passenger flow data through ticket scanning gate, wireless network probe and video passenger flow camera respectively; reconstructing a node real-time tourist density distribution map through a spatial interpolation algorithm; obtaining a node engineering carrying threshold parameter and performing upstream and downstream coupling conduction modulation on the node engineering carrying threshold parameter based on an upstream node congestion index to obtain a node dynamic carrying threshold; performing a three-hour passenger flow prediction based on historical passenger flow time series data and external passenger flow influence factors, comparing the node predicted passenger flow with the node dynamic carrying threshold to trigger a shunt early warning; and generating a low-density tour route suggestion based on the node real-time tourist density distribution map and the shunt early warning and pushing the low-density tour route suggestion to a tourist terminal.

The invention provides an operation optimization scheduling method of an expressway tunnel micro-storage system. The system is composed of a photovoltaic power generation unit, a wind power generation unit, a diesel power generation unit, a storage battery, a super-capacitor energy storage unit and a power grid interaction interface. The method comprises the following steps: acquiring system inherent parameters, sun position, weather and traffic flow prediction data; calculating wind power and ideal photovoltaic output; aiming at shadow influence of a mountain in a tunnel environment, dynamically calculating a tunnel shading loss coefficient based on a geometric projection principle, and correcting photovoltaic output; calculating tunnel dynamic electrical load according to traffic flow prediction; establishing a multi-objective optimization model and solving by taking system power balance and equipment constraint as conditions and taking operation cost, expected power shortage and carbon emission minimization as objectives to obtain a day-ahead optimization scheduling scheme of each unit and energy storage; according to the invention, the photovoltaic output prediction precision in the tunnel environment and the reliability, economy and environmental protection of the scheduling scheme are improved.

The invention discloses a motor vehicle charging pile management optimization method and system based on artificial intelligence, and the method comprises the following steps: collecting operation data, and generating an original flow data set; mapping the original traffic data set to a double-layer graph structure, and constructing a space-time traffic feature matrix; inputting the space-time traffic characteristic matrix into a traffic prediction module to obtain a prediction result; inputting a prediction result into a scheduling strategy optimization module, and initializing a state space and a constraint condition; calculating an initial control action based on the state space and the constraint condition; substituting the initial control action into an obstacle constraint optimization process, and carrying out iterative solution to obtain an optimal scheduling action; inputting the optimal scheduling action into a system execution module to obtain a feedback data set; and carrying out decomposition operation on flow and power flow change data, updating gradient flow, rotation flow and harmonic flow components, and realizing online closed-loop optimization of the obstacle Lyapunov constraint strategy model. According to the invention, artificial intelligence motor vehicle charging pile management optimization is realized.

The invention discloses a railway hub large passenger flow intelligent prediction method based on a space-time attention mechanism, and belongs to the technical field of intelligent traffic and traffic transportation prediction. The method comprises the following steps: collecting and preprocessing multi-source data; based on an LSTM network and a random forest algorithm, constructing a fusion model, and using the trained fusion model to obtain a third passenger flow prediction result; performing cross-model residual error correction on the third passenger flow volume prediction result to obtain a final fusion prediction result; and according to the fusion prediction result and the early warning threshold, carrying out early warning grade division, and carrying out corresponding dynamic response and scheduling output. According to the invention, based on multi-source decision fusion of a deep learning prediction result and a nonlinear feature model result, intelligent early warning and dynamic management and control output of railway hub large passenger flow are realized; a multi-model decision confidence fusion mechanism is established through a D-S evidence theory, and credibility enhancement and early warning grading response of a prediction result are realized in combination with a passenger flow threshold grading strategy.

The invention discloses an aero-engine air inlet passage secondary flow prediction method based on a neural network. The method comprises the steps that an air inlet passage physical model containing suction holes is established, and grids are divided; setting boundary conditions required for solving; performing numerical simulation to obtain flow field data under different working conditions, calculating mass flow under a suction hole blocking condition and a corresponding surface dimensionless sound velocity flow coefficient, and constructing a training data set; training and constructing a traffic prediction model based on a neural network; re-establishing a simplified air inlet channel physical model without suction holes and dividing grids; and calling a flow prediction model to predict a dimensionless sound velocity flow coefficient of the simplified air inlet physical model, and reversely calculating actual suction mass flow, and applying the actual suction mass flow as a boundary condition to a suction hole area corresponding to the simplified air inlet physical model to realize equivalent numerical simulation of the suction effect. According to the method, calculation efficiency and prediction precision are both considered, and integration can be carried out in a CFD solver to support air inlet parameterization design and rapid performance evaluation.

The invention discloses a TCN-LSTM-Attention prediction model construction method and a highway toll station dynamic lane configuration method, and the method comprises the steps: obtaining traffic data in a time period M, and the traffic flow of each lane, the traffic flow of an ETC lane and the traffic flow of an MTC lane in a time period M + 1, and carrying out the preprocessing of the traffic data, the traffic flow of each lane, the traffic flow of the ETC lane and the traffic flow of the MTC lane; through a TCN-LSTM-Attention prediction model composed of a TCN layer, an LSTM layer, an Attention layer and a full-connection layer, spatial-temporal feature extraction is performed on historical traffic flow data, accurate prediction of traffic flow is realized, and traffic passing efficiency is improved. Meanwhile, based on the predicted traffic flow condition, an expressway toll station dynamic lane configuration strategy with toll station traffic capacity maximization and lane switching cost minimization as objective functions is constructed, dynamic configuration of lanes is achieved according to a real-time traffic flow prediction result, the problems of resource waste and congestion caused by fixed lane configuration are avoided, and the traffic flow prediction efficiency is improved. The technical problem that a lane configuration method in the prior art cannot perform lane configuration according to the traffic flow and the vehicle type proportion in time is solved.

The invention discloses a self-adaptive parking space recommendation method for flow fluctuation in festivals and holidays, and relates to the technical field related to intelligent traffic, and the method comprises the steps: obtaining a target travel request of a user side, at least including a destination and travel time; through festival and holiday flow prediction and parking space demand pre-judgment, in combination with a target travel request, a festival and holiday travel scene is identified, and a scene rule base including recommendation priority rules and path planning preferences is loaded; generating a parking space recommendation scheme based on a multi-dimensional decision model by fusing the real-time parking space state, the road condition information and the user portrait; and planning a full-link travel path, and displaying the full-link travel path on a terminal interface. The technical problems that in the prior art, due to the fact that the contradiction between supply and demand of parking spaces in holidays and festivals is sharp and the adaptability of parking space recommendation is poor, users are difficult to find parking spaces, and surrounding traffic jam is aggravated are solved, intelligent and efficient matching recommendation of parking space resources is achieved through scene pre-judgment, and the user experience is improved. And the user travel experience and the regional traffic operation efficiency are improved.

This invention relates to the field of air traffic forecasting technology, and in particular to an air traffic forecasting and uncertainty quantification method and system based on MSGF-Net. The method includes: preprocessing air trajectory data and extracting traffic data; constructing and normalizing input features based on the preprocessed air trajectory data and extracted traffic data; constructing an MSGF-Net-based traffic forecasting model; optimizing and training the constructed traffic forecasting model based on a loss function; predicting the input features based on the trained traffic forecasting model; and outputting the prediction result. This invention, through a parallel multi-scale encoder and gating fusion mechanism of TCN and GRU, solves for the first time the aforementioned deficiency of standard models in capturing multi-scale temporal patterns, greatly improving the model's generalization ability.

The invention provides a traffic prediction method, device and equipment for an urban road network under an abnormal event, and the method comprises the steps: constructing a fusion feature matrix based on the data of a current road network and the information of the current abnormal event; performing space-time calibration on the fusion feature matrix by using a space-time attention mechanism to obtain a space-time calibration feature matrix; determining time characteristic representation based on the abnormal event individual causal effect and historical traffic space-time state data, and determining an adjacency matrix for dynamic causal based on the space-time calibration characteristic matrix and the time characteristic representation; determining spatial feature representation based on the dynamic causal adjacency matrix and the space-time calibration feature matrix; and determining a flow prediction result of the target road network at a future moment by using the dynamic causal adjacency matrix, the time feature representation and the spatial feature representation. By adopting the traffic prediction method, device and equipment under the abnormal event of the urban road network, the prediction precision of the speed of the urban road network is improved.

The invention relates to a metering station instantaneous flow prediction method which comprises the following steps: S1, acquiring historical instantaneous flow data which comprises gas instantaneous flow per hour in multiple days; s2, preprocessing the historical instantaneous flow data, and dividing the historical instantaneous flow data into a training set and a verification set; s3, constructing a CNN + LSTM-based hybrid neural network model, wherein the model comprises a CNN module and an LSTM module; and S4, taking instantaneous flow data of two consecutive days as input, and training the CNN + LSTM model to predict an instantaneous flow sequence of the next day. The method has more remarkable superiority and practical value in the aspect of urban gas volume prediction.

The invention relates to the technical field of intelligent planning, in particular to an aerocar station site selection method, device and equipment based on multi-stage optimization, and the method comprises the steps: selecting map data of an analysis target area and user travel data in different periods, selecting a plurality of aggregation blocks as candidate stations according to the highest demand quantity, and generating a travel demand thermodynamic diagram, substituting candidate site data into a site capability scoring formula, a site connectivity degree scoring formula, a service traffic prediction model formula and a decision model formula, constructing a deployment optimization model taking profit maximization as a core, performing probability modeling on user travel selection behaviors, and establishing a deployment optimization model taking profit maximization as a core. The method truly reflects the substitution potential of eVTOL in a multi-mode traffic system, improves the economic feasibility, scheduling efficiency and service capability of a site selection scheme, and is suitable for the intelligent planning of dynamic demands and large-scale candidate regions. Therefore, the problems of poor eVTOL station scheduling collaboration, low operation flexibility, poor urban scale multi-source data processing performance, low calculation efficiency and the like are solved.

This invention relates to the field of intelligent transportation technology, and more particularly to a multi-strategy improved traffic flow prediction method, device, and medium. Based on acquired traffic spatiotemporal data, this method obtains the tuning parameters of a preset traffic flow prediction model through an optimization algorithm layer; updates the preset traffic flow prediction model based on the tuning parameters to obtain a first traffic flow prediction model; trains the first traffic flow prediction model using training set data to obtain a second traffic flow prediction model; updates the second traffic flow prediction model to obtain an improved traffic flow prediction model; the improved traffic flow prediction model is used to output traffic flow prediction values. This invention uses a whale optimization algorithm to update the tuning parameters, and the improved preset traffic flow prediction model enhances the model's ability to extract multi-scale spatiotemporal features of traffic spatiotemporal data and its ability to focus on key time step information.

The application provides a data and knowledge jointly driven traffic flow prediction method, and belongs to the technical field of traffic flow prediction. The method comprises the following steps: preprocessing traffic flow data of a current road network; configuring parameters of a traffic flow prediction neural network model, and constructing the traffic flow prediction neural network model; training the traffic flow prediction neural network model by using the preprocessed traffic flow data; and predicting future traffic flow signals of the road network by using an optimal traffic flow prediction neural network model obtained through training according to historical road network traffic flow data. The application solves the problems of insufficient knowledge integration and precision improvement bottleneck of a traditional deep learning traffic flow prediction method.

The invention discloses a highway traffic flow prediction method based on an STGCN-Transform hybrid model, and belongs to the technical field of intelligent traffic, and the method comprises the steps: obtaining data through a highway portal system, and constructing a road network topological graph; cooperatively constructing three types of adjacent matrixes of Euclidean distance, connectivity and time sequence similarity to describe a spatial relationship in a multi-dimensional manner; respectively representing time sequence position features and global road network structure information by adopting learnable time information embedding and a node2vec algorithm; the features are input into a time sequence Transform module and a space graph convolution module for joint training, and a hybrid model is obtained; in the prediction stage, the static graph and the real-time node representation are adaptively fused through a dynamic graph convolution module, a dynamic graph structure is generated, and a flow prediction result is output. The method can comprehensively improve the precision of traffic flow prediction, the depiction capability on complex space-time dependence and the adaptability to dynamic traffic states.

The invention relates to the field of intelligent traffic systems, and discloses an abnormal traffic flow prediction method and system based on multi-scale spatial-temporal feature fusion, and the method comprises the following steps: carrying out the feature enhancement of input traffic data through a multi-dimensional embedded sensing module, and generating a dynamic embedded representation of fusion time, space and traffic state information; and inputting the dynamic embedded representation into a dynamic space-time multi-scale interaction module, and extracting and interacting multi-scale space-time features by enhancing the synergistic effect of a time convolutional network, a graph convolutional network and a hypergraph convolutional network. Through deep integration of time parameters, spatial dependence and traffic state multi-source features by a multi-dimensional embedded sensing module, cooperative operation of an enhanced time convolutional network, a graph convolutional network and a low-rank hypergraph convolutional network in a dynamic space-time multi-scale interaction module is matched; and high-order and non-periodic space-time correlation contained in abnormal traffic flow can be accurately captured.

The application provides an airport ground traffic passenger flow prediction method and system, which is applied to the field of prediction data processing; the application forms a dynamic data pool by integrating flight dynamic data, traffic flow data, weather forecast data and passenger movement data, ensures that the system has a comprehensive and timely information base, enables the system to dynamically update and timely reflect the real-time conditions of the airport and its surroundings, improves the prediction accuracy and response speed, and simultaneously ensures that only when the data is complete and up-to-date, the subsequent prediction and scheduling operation is triggered, avoids inaccurate prediction caused by insufficient or outdated data, and improves the reliability of system decision-making.

The invention discloses an intelligent traffic flow prediction method and system based on distributed cloud computing, and relates to the technical field of intelligent traffic systems.The method comprises the steps that distributed cloud nodes are divided according to traffic flow relevance and computing power load balance, multi-source traffic data are distributed to the nodes, and a standardized local feature set is obtained through preprocessing and feature extraction; issuing an initial prediction model for training and uploading, and determining a global optimization model for iteration by the cloud; task priorities are divided according to road segment importance and time periods, and node computing power is combined for dynamic allocation; and checking and correcting after node prediction to obtain a final flow prediction result, and transmitting the final flow prediction result to a traffic management platform to support road network scheduling and personalized query. The technical problems of low data processing efficiency, insufficient prediction result accuracy and unreasonable resource utilization of a traditional traffic flow prediction mode are solved, and the technical effects of improving the traffic flow prediction efficiency and accuracy and realizing resource configuration optimization are achieved.

The application discloses a traffic flow prediction fused traffic light adaptive control method and system, and relates to the technical field of intelligent traffic, comprising: obtaining real-time traffic flow data of a target intersection; obtaining a current traffic light control strategy of the target intersection; obtaining a traffic flow prediction result; performing change degree evaluation according to the real-time traffic flow data and the traffic flow prediction result, obtaining a traffic flow change coefficient, and whether it is greater than or equal to a traffic flow change threshold; if the traffic flow change coefficient is greater than or equal to the traffic flow change threshold, generating a traffic light adjustment instruction, adjusting the current traffic light control strategy according to the traffic flow prediction result, generating a future traffic light control strategy, and performing traffic light adaptive control of the target intersection. The application solves the technical problems of inaccurate traffic flow prediction and inflexible traffic light control strategy in the prior art, and achieves the technical effects of improving traffic efficiency, reducing traffic congestion and optimizing traffic light control.

The present application relates to the technical field of traffic flow prediction, and discloses a traffic flow prediction and early warning method, device, equipment and storage medium, comprising: acquiring real-time traffic data and historical traffic data of a target road section; performing explicit decoupling on the real-time traffic data to obtain a basic flow component and an event congestion component; inputting the basic flow component into a preset multi-task prediction model to obtain a multi-period basic flow prediction value; performing future flow prediction based on the event congestion component to obtain an event influence flow value; performing flow fusion calculation based on the multi-period basic flow prediction value and the event influence flow value to obtain a final flow prediction value; performing effective traffic capacity calculation based on the event congestion component and the historical traffic data to obtain a real-time effective traffic capacity value; and comparing the final flow prediction value with the real-time effective traffic capacity to generate traffic flow early warning information; the present application optimizes the traffic flow prediction and early warning effect through multi-period prediction and decoupling analysis.

The invention discloses a traffic flow prediction scheduling method, system and device driven by edge computing, and relates to the related field of intelligent traffic, and the method comprises the steps: respectively arranging a plurality of master-slave data collection units at a plurality of edge computing point locations of a target area; performing continuous video frame acquisition in a preset prediction window to obtain a plurality of main intersection video frame sequences and a plurality of auxiliary road section video frame sequence sets; performing dual uncertainty traffic flow prediction to obtain a plurality of traffic flow prediction results; and executing traffic scheduling strategy optimization according to the plurality of traffic flow prediction results and the position connection relation of the main intersections corresponding to the plurality of edge calculation points, and obtaining a target area traffic strategy. According to the method and the device, the technical problem that the prediction accuracy and the scheduling strategy adaptability are insufficient in the existing traffic flow prediction scheduling is solved, and the technical effect of improving the traffic flow prediction accuracy and the scheduling strategy adaptability is achieved.

The invention discloses a sewage pipe network flow prediction algorithm based on rainfall and liquidometer data, and belongs to the field of flow prediction.The sewage pipe network flow prediction algorithm based on rainfall and liquidometer data comprises the following steps that historical and real-time multi-dimensional data from multiple sources are continuously collected and integrated; performing cleaning, calibration and time alignment processing on the multi-dimensional data to obtain model training data based on historical data and model prediction input data based on real-time data; the method has the advantages that multi-dimensional data are collected and processed systematically, fuzzy manual observation is replaced, historical hydrological laws are converted into a quantifiable sewage pipe network flow prediction model, judgment depending on personal experience is replaced, accurate flow prediction in several hours in the future is carried out based on the model, and the flow prediction efficiency is improved. Passive emergency is converted into active early warning, and the hysteresis and subjective defects caused by dependence on artificial experience in the prior art are overcome fundamentally.

The invention provides a traffic flow prediction method based on floating car data and mutual information topology reconstruction, and the method comprises the steps: obtaining non-full-sample floating car trajectory data, and generating a traffic flow time sequence of each road node; based on the traffic flow time sequence of each road node, a mutual information value between any two road nodes is calculated, an adjacent matrix is constructed according to the mutual information values, and elements of the adjacent matrix represent a dependency relationship between the corresponding nodes; a traffic network diagram is constructed according to the adjacency matrix, the traffic network diagram comprises a node set, an edge set and the adjacency matrix, the node set represents road nodes, and the edge set represents connectivity between the nodes; taking the traffic network graph and the traffic flow time sequence as input, and training a traffic flow prediction model by using a graph neural network model; and the trained traffic flow prediction model is utilized to predict the traffic flow in the future time period and output the prediction result, so that the accuracy of traffic flow prediction is effectively improved.

The invention relates to a traffic flow prediction method, which comprises the following steps: obtaining traffic flow data of a to-be-monitored area and spatial association data capable of representing spatial topology and traffic association attributes among sub-areas, constructing a directed weighted traffic network graph, and taking the sub-areas as nodes, traffic channel directions as directed edges and historical flow data as edge weights in the graph; and the association between the traffic flow and the space structure in the road network is intuitively and accurately presented. On the basis, a node feature matrix and a directed weighted adjacency matrix of the graph are obtained and input into a preset graph convolutional network, a node embedding matrix fused with node information is obtained, and historical flow data of directed edges and spatial features determined based on spatial association data are combined to obtain a node embedding matrix fused with node information; and constructing a directed edge feature vector containing rich time sequence and space information. And finally, inputting the feature vectors into a preset multi-layer perceptron regression model to obtain a future traffic flow prediction value of each directed edge, and obtaining a traffic flow prediction result of the to-be-monitored area.

The invention relates to a traffic flow prediction method and device based on model lightweight, and a medium. The method comprises the following steps: S1, obtaining a traffic flow prediction model to be optimized; s2, calculating hierarchy importance of all middle layers of the trained traffic flow prediction model; s3, obtaining the normalization importance of each intermediate layer; s4, adopting cumulative contribution proportion constraint and absolute proportion constraint to select and reserve a plurality of middle layers of which the normalization importance is higher, so as to obtain a temporary traffic flow prediction model; s5, judging whether the model precision meets the requirement or not, if yes, executing the step S6, and otherwise, executing the step S7; s6, taking the temporary traffic flow prediction model as a current traffic flow prediction model, and returning to the step S2; and S7, outputting the current traffic flow prediction model as a lightweight result. Compared with the prior art, accurate prediction of the traffic flow is realized on a computing platform with low computing power.