17 results about "Traffic forecast" patented technology

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 application discloses a kind of urban rail transit travel path recommendation methods considering ride comfort, comprising the following steps: obtaining urban rail transit line network operation information, and constructing road network topology diagram;According to train timetable and passenger entry and exit station card swiping time, the travel path and ride train number of passenger are calculated;The passenger capacity of train passing through each section is calculated, and the section passenger flow is counted;Predict the section passenger flow in future period, and distribute to the train passing through the section;According to the predicted train passenger capacity, the train ride comfort and the comfort of section are calculated;Based on comfort, travel time, transfer delay and the like, the comprehensive right of way is calculated, and the shortest path set between each station is updated;Recommended travel path is generated.The method proposed in the application quantitatively represents train ride comfort on the basis of section passenger flow prediction, and generates recommended path by comprehensively considering ride comfort and travel efficiency, which has positive significance for improving passenger travel satisfaction and rail transit operation management level.

This enables more accurate prediction of traffic flow. [Solution] A traffic flow prediction device is provided, comprising: a traffic volume prediction unit that predicts a second inflow of traffic into a range corresponding to congestion data at a second time after the first time based on a first inflow of traffic that entered the range at a first time, and predicts a second outflow of traffic that leaves the range at a second time based on a first outflow of traffic that left the range at a first time, and calculates a cumulative inflow of traffic by accumulating the first inflow of traffic and the second inflow of traffic, and a cumulative outflow of traffic by accumulating the first outflow of traffic and the second outflow of traffic; a congestion traffic volume calculation unit that calculates the difference between the cumulative inflow of traffic and the cumulative outflow of traffic as the congestion traffic volume; a congestion area prediction unit that predicts a congestion area at a second time based on the congestion traffic volume; and a traffic density prediction unit that predicts the traffic density of a target location at a second time based on the congestion area.

The application belongs to the technical field of traffic flow prediction, and particularly relates to a spatio-temporal traffic flow prediction method fusing multi-graph structure and knowledge enhancement, comprising the following steps: obtaining historical observation data of traffic monitoring nodes at continuous multiple time steps; constructing enhanced features based on the historical observation data; splicing the enhanced features and the historical observation data to obtain enhanced input features; inputting the enhanced input features into a pre-trained traffic flow prediction model; and the traffic flow prediction model predicting traffic flow at one or more future time steps. The application realizes joint modeling of multi-source spatial correlation, complex time dynamics and historical period knowledge in traffic flow data, and improves the accuracy and robustness of future multiple time step traffic flow prediction.

The application discloses a multi-modal freight transport path optimization method driven by endogenous congestion and multi-dimensional overlap, aiming to solve the technical problem that the existing model cannot simultaneously process multi-dimensional endogenous correlation such as link congestion feedback, hub transfer bottleneck, path physical overlap and mode perception similarity. The application constructs a multi-layer directed multi-modal transport network and generates a candidate path set; establishes a generalized path cost function containing road section and hub endogenous congestion; constructs a road space correlation penalty term based on shared length and a mode similarity penalty term based on hub betweenness centrality; incorporates the above elements into a multi-objective optimization framework based on maximum entropy, and converts it into an improved nested fixed point equation; uses instrumental variable substitution method to solve the endogeneity problem in parameter estimation, and obtains network equilibrium flow through iterative solution. The application breaks through the independent and irrelevant assumption of the traditional model, and significantly improves the accuracy and behavior explanation ability of freight flow prediction in a complex multi-modal transport network.

The present disclosure provides a method and apparatus for traffic flow prediction and relates to the technical field of information processing. The method comprises: determining a plurality of traffic flow detection groups based on intersection positions and sensor locations; determining a first distance between any two sensors and a second distance between any two road intersections; acquiring first traffic flow data and performing aggregation processing on the first traffic flow data collected by the sensors in each traffic flow detection group to obtain second traffic flow data; using the first distance and the first traffic flow data as first sample data and using the second distance and the second traffic flow data as second sample data.Training several different types of initial traffic flow forecasting models using the first sample data and the second sample data, constructing a traffic flow forecasting optimization model based on the trained initial traffic flow forecasting models, and performing a traffic flow forecast using the traffic flow forecasting optimization model. By applying the above procedure and traffic flow forecasting apparatus, the problem of inaccurate traffic flow forecast results is solved.

The application discloses a kind of traffic AI scheduling decision-making methods based on multi-source geographic big data, it is related to intelligent transportation technology field, including, collection multi-source traffic data and pre-processing, generate after processing traffic dataset;Using trained long short-term memory network, the multi-scale time series analysis is carried out to after processing traffic dataset, generates traffic flow prediction result;Using particle swarm optimization algorithm, traffic flow prediction result is adjusted, generates candidate traffic scheduling scheme;Candidate traffic scheduling scheme is dynamically optimized, generates after optimization traffic flow control scheme;Optimization after traffic flow control scheme is compared and analyzed with newly collected multi-source traffic data, generates adjusted traffic flow control scheme, and based on real-time traffic flow feedback, adjusted traffic flow control scheme is dynamically adjusted, forms continuous feedback cycle.The application improves the traffic capacity of road and resource use efficiency.

The application discloses a campus navigation method and device based on people flow analysis, equipment and medium, relates to intelligent navigation technical field, including: creating the campus electronic grid map of the target campus; the campus electronic grid map is divided into several map grids; based on the campus electronic grid map and historical campus people flow data, people flow prediction processing is carried out, and people flow prediction data on each map grid is obtained; through acquisition equipment, current real-time campus people flow data is continuously collected and projected to corresponding map grid to obtain people flow real-time data; the acquisition equipment is arranged in the target key place of the target campus; based on the people flow prediction data and the people flow real-time data, the target people flow data on each map grid is determined; the actual cost function of the preset path planning algorithm is adjusted by using the target people flow data and combining the campus electronic grid map, and navigation service is provided for the user terminal in the target campus based on the adjusted path planning algorithm.

This invention provides a method and system for optimizing tunnel lighting energy consumption based on ambient light perception, relating to the field of lighting control technology. It involves decomposing the temporal ambient light sequence into light wave inertia to obtain low-frequency light inertia components and high-frequency light impact components. A light field strain distribution map is constructed using the lighting unit grid, the low-frequency light inertia components, and the high-frequency light impact components. A compensation boundary is then determined based on the traffic flow prediction sequence and the light field strain distribution map. Within the compensation boundary, a multi-objective light energy redistribution is performed to obtain a light efficiency trade-off cluster. Based on this cluster, strain feedback values ​​for different lighting units are determined. Finally, a relaxation correction is applied to the multi-objective light energy redistribution process based on all strain feedback values. This invention enables decoupled perception of slow-changing trends and fast-changing disturbances in ambient light, and integrates traffic flow forecasting and relaxation correction of light field strain feedback to improve the energy consumption optimization capability of tunnel lighting under various operating conditions.

This invention relates to a traffic signal control method based on spatiotemporal attention and safety constraints, comprising: acquiring real-time traffic state data of traffic intersections and constructing state vectors; constructing a spatiotemporal graph convolutional network to predict traffic flow and obtain future traffic flow prediction values; utilizing a spatiotemporal attention gating mechanism with conservative cold start, dynamically weighting the future traffic flow prediction values ​​with confidence to generate enhanced state representations; outputting optimal signal phase actions; performing legality verification and logical correction on the optimal signal phase actions, and outputting safe execution signal phase actions; constructing a composite reward function to calculate multi-objective composite reward values, and using these composite reward values ​​to update the weight parameters of a dual-input deep Q-network to achieve real-time closed-loop adaptive control of the road network signal. This invention improves the physical executability, training stability, forward-looking response capability, and control adaptability under complex traffic scenarios of traffic signal control strategies.

This invention relates to a method and system for predicting daily average freight volume in cold regions, integrating holiday and emergency response scenarios, belonging to the field of logistics transportation and time series forecasting technology. The invention first constructs a generalized external disturbance factor system incorporating multi-stage effects of holidays and three-level states of emergency response. Preprocessing of cold region freight time series data is completed using the Z-score method and STL decomposition. Then, the importance quantification of disturbance factors and automatic screening of high-impact factors are achieved through the XGBoost-SHAP interpretable framework. The screened factors are then embedded into the Prophet model to construct an XGBoost-SHAP-Prophet hybrid prediction architecture, completing hyperparameter optimization and multi-route-specific model training. Finally, through multi-route parallel prediction and residual correction mechanisms, high-precision prediction results for daily average freight weight and parcel quantity are output. The prediction accuracy of this invention is significantly better than mainstream time series forecasting models, and can directly provide data support for capacity planning, vehicle scheduling, and carbon emission reduction decisions for logistics companies in cold regions.

The invention discloses a traffic flow prediction method based on deep learning and a multi-scale clustering unit, and relates to the technical field of intelligent traffic, and the method comprises the following steps: multi-source heterogeneous data collection and preprocessing: collecting original data from a plurality of channels, and carrying out the cleaning, standardization and space-time alignment; constructing a multi-scale dynamic traffic clustering unit: firstly constructing a multi-scale feature matrix, then performing dynamic clustering, and constructing an analysis unit reflecting the dynamic function area of the city; feature engineering and fusion: preparing input features for the deep learning model, and fusing traffic features and point of interest (POI) semantic features; constructing and training a traffic prediction model based on deep learning: training an end-to-end traffic prediction model by using the fused features; predicting and outputting the traffic flow by using the flow prediction model; according to the method, the urban dynamic function areas are divided and analyzed by constructing the multi-scale clustering unit, and then high-precision and fine-grained traffic flow prediction is achieved.