1820 results about "Traffic flow" patented technology

The invention relates to an intelligent driving safety system and method based on AI multi-source data fusion. The system comprises an environment modeling sensing module which obtains vehicle end multi-mode sensing data and vehicle size parameters to construct a surrounding environment model, and multi-vehicle environment data of collaborative sensing is formed through vehicle-vehicle communication; the behavior scene generation module analyzes the traffic flow characteristics of the multi-vehicle environment data, calculates the attention weight of the vehicle characteristics, associates the attention weight with the target size information, and generates a unified behavior scene representation. The collision risk judgment module fuses the unified behavior scene representation and the dynamic environment modeling data to generate multi-target fusion trajectory data, and if the uncertainty exceeds a threshold value, a historical database is checked to judge the risk level; and the path planning generation module performs classification according to risk levels and risk levels, and performs matching and speed adjustment instruction integration on the collaborative path optimization instruction to obtain a path planning rule. By adopting the system, the sensing precision, risk response capability and cooperative efficiency of the automatic driving vehicle can be improved, and the driving safety is guaranteed.

The invention discloses a predictive order dispatching system based on digital twinning, and relates to the technical field of intelligent order dispatching, the predictive order dispatching system comprises four core modules: an urban transport capacity digital twinning construction module integrates order dispatching platform historical orders, real-time traffic flow and urban GIS data, constructs and updates a twinning model, and divides standard grid units; a short-term order demand prediction module obtains grid order, traffic and environment feature sequences based on the model, and predicts order quantity and thermodynamic diagrams in 15-30 minutes in the future; a transport capacity supply and demand gap early warning module analyzes the gap and generates early warning; the active intervention and optimization module generates an instruction according to a preset strategy, dispatches transport capacity through order pre-dispatching and the like, and then evaluates and optimizes the strategy according to feedback. The system realizes order pre-judgment, accurate transport capacity allocation, reduction of supply and demand imbalance, shortening of user waiting time, reduction of operation cost, and improvement of delivery efficiency and service quality.

The invention provides a traffic flow intelligent prediction method based on multi-source data fusion, and the method comprises the steps: calculating the historical proportional relation between floating traffic flow and actual traffic flow at different time periods and different nodes according to historical time sequence data; identifying a change mode of the permeability and calculating to obtain a reference dynamic permeability value; establishing a permeability time relation matrix based on the reference dynamic permeability value; inputting the floating traffic flow data into the permeability time relation matrix to obtain a query dynamic permeability value; dividing the floating traffic flow data by the corresponding query dynamic permeability value to obtain a continuous estimation sequence of the traffic flow of the whole road network; fusing the continuous estimation sequence with multi-source historical traffic data to generate space-time fusion features; based on the space-time fusion features, the traffic flow prediction result of the future time period is output, the traffic flow prediction precision is significantly improved, the model generalization ability is enhanced, the prediction real-time performance and continuity are improved, and the problem of large prediction deviation is effectively solved.

The invention belongs to the technical field of computer vision, deep learning and time-space prediction, and discloses an end-to-end time-space prediction method based on improved three-dimensional rotation position coding, which is suitable for various time-space sequence prediction scenes such as weather, traffic flow and the like. According to the invention, through four key improvements, a position coding mechanism is optimized; three-dimensional coding proportions of time, height and width are dynamically adjusted so as to adapt to different scenes; fusing the absolute time and the relative space position, and strengthening local space-time correlation modeling; the position information directly guides attention calculation, and the fusion with an Attention module is deepened; and a rotation matrix cache mechanism is introduced to reduce redundant calculation. Meanwhile, the model is matched with a Patch embedding layer, an adaptive Transform encoder and an MLP de-wharf, a complete link of'feature embedding-position encoding-space-time fusion-prediction output 'is constructed, and the precision, generalization and reasoning efficiency of space-time prediction are effectively improved.

The invention relates to an intelligent traffic flow prediction analysis method based on artificial intelligence, and the method comprises the steps: collecting and fusing traffic flow, environmental factors and event information according to traffic levels, and achieving the standardization and automatic clustering preprocessing of multi-level space-time attributes through regional factor labels; and then, expressing a multi-dimensional structure and a dynamic attribute of each node by using regional factor vectorization, dynamically modeling a spatial node heterogeneous adjacency relationship in combination with a self-organizing graph neural network, introducing a cross-level dynamic attention mechanism to perform weighted fusion on multiple spatial and temporal features, and outputting multi-granularity traffic prediction through a hierarchical fusion decoding network. And the model is combined with actual feedback to realize self-adaptive optimization of the area factors and model parameters. The method has the advantages that high-precision prediction of the traffic flow under multiple scales of roads, blocks, cities and the like is achieved, the self-learning and self-adaptive capacity for heterogeneous information, emergencies and spatial dynamic changes is improved, and hierarchical decision making and flow management are supported.

The invention discloses a low-altitude traffic flow collaborative awareness and conflict prediction method and system based on a multi-modal large model. The method comprises the following steps: collecting multi-source heterogeneous data of an aircraft, fusing and mapping the multi-source heterogeneous data to a space-time grid with dynamically adjustable granularity based on a real-time traffic situation, and realizing adaptive characterization; the method comprises the following steps of: constructing a robust special prediction model by introducing aircraft dynamics constraint and airspace rule knowledge as priori and performing fine adjustment by adopting a loss function containing an adversarial regularization item based on a pre-trained large model of the body-equipped agent; inputting spatial-temporal characteristics into the model, outputting behavior intentions and probability trajectories in an end-to-end manner, constructing an incomplete information game deduction model based on predicted trajectories, and calculating a comprehensive collision risk index fusing trajectory uncertainty, a motion state and a game deduction result; and generating a hierarchical early warning and collaborative avoidance strategy, and performing network distribution. According to the method, the accuracy, the robustness and the decision intelligence of conflict prediction under the low-altitude dense traffic flow are remarkably improved.

The invention belongs to the technical field of traffic management and control, and particularly relates to a congestion feed-forward intervention method based on traffic flow phase change critical point recognition, which comprises the following steps: collecting and preprocessing multi-source heterogeneous traffic data; carrying out multi-scale traffic flow feature engineering; identifying a traffic flow phase change critical point based on a space-time dynamic graph neural network and critical moderation effect analysis; generating a multi-objective optimization congestion feedforward intervention strategy; and performing intervention, evaluating the effect and performing adaptive learning. According to the technical scheme, accurate prevention and early intervention can be performed before congestion occurs, and the operation efficiency and reliability of an urban traffic system are remarkably improved.

The invention discloses a congestion management system and method based on vehicle-road cooperation and dynamic group path optimization, and relates to the technical field of intelligent traffic systems. The method comprises the following steps: S1, collecting original traffic data through a multi-modal sensor array to carry out space-time alignment, and constructing a microscopic traffic flow data set; s2, bidirectional information interaction is carried out through a vehicle-road cooperative communication network; s3, calculating a multi-modal fusion confidence coefficient parameter based on the data quality index, and generating traffic state information and road section real-time saturation; s4, fusing historical and static road network data, constructing a dynamic digital twinborn model and a road network state feature map, and generating a road network load balancing index; and S5, making a decision by adopting a hierarchical-distributed architecture, and generating a group path induction strategy through multi-objective optimization. The efficient collaborative decision is realized through the graph convolutional network and the attention mechanism, and the road network traffic efficiency is comprehensively improved through stable and reliable multi-objective optimization on the premise of guaranteeing the user fairness.

A system for detecting the motion state of a vehicle behind a mobile maintenance vehicle based on thunder-vision fusion belongs to the technical field of traffic intelligent control and comprises a multi-source sensing module, a target detection module, a trajectory tracking module and a vehicle motion state modeling module. A structured state output module performs standardized integration on vehicle target trajectory information provided by a detection and tracking module based on a unified data expression model to form a multi-dimensional structured data format including fields such as a relative distance, a relative speed, an acceleration, a vehicle type, a lane number, a frame timestamp and the like; consistency analysis and downstream calling can be conveniently carried out among different systems, the problem that a traditional detection system is difficult to integrate due to lack of a structured interface is avoided, the system supports flexible butt joint with a road sensing platform, a vehicle-mounted control system and an upper-layer data analysis module, good expansibility and cross-platform adaptation capacity are achieved, and the system is suitable for being popularized and applied. And the engineering availability and deployment efficiency of the traffic flow state information are obviously improved.

The invention discloses a global dynamic perception space-time traffic flow prediction method based on graph packet representation learning, and belongs to the technical field of traffic flow prediction, and the method comprises the following steps: S1, traffic data input, S2, traffic graph packet construction, S3, graph packet initial feature extraction, S4, time sequence feature extraction, S5, spatial feature extraction, and S6, traffic flow prediction and output. Through a space-time modeling technology of graph packet representation learning and global dynamic perception, space-time characteristic elements of a traffic road network can be comprehensively covered, traditional traffic indexes such as flow and speed are concerned, elements such as road network topological association and cross-regional multi-hop association are also included, a dynamic dependency relationship between a time sequence and a spatial dimension is deeply mined, and a real-time dynamic perception effect is achieved. Therefore, the prediction result can reflect the real evolution law of the traffic flow more accurately, and a more scientific basis is provided for traffic management and decision making.

The invention relates to the technical field of intelligent traffic control, and discloses a road traffic AI adaptive edge computing server. The server comprises a traffic situation sensing module, a traffic flow intention analysis module, a control strategy construction module, a control scheme generation module and an efficiency rolling optimization module. The server synchronously receives the original data flow of the heterogeneous traffic sensor, and extracts and generates a microscopic traffic behavior sequence after timestamp alignment and cleaning. A behavior sequence is matched with a historical scheme library, a control strategy knowledge graph based on a traffic entity relationship is constructed, and a candidate control scheme set is reasoned according to the control strategy knowledge graph. And performing conflict detection and rolling optimization on the candidate schemes based on a short-time traffic flow prediction result, and outputting a final adaptive control instruction set. According to the invention, deep understanding and foresight control of a complex traffic scene are realized, and the intersection passing efficiency and the control adaptive capability are improved.

The invention provides a traffic flow prediction method combining a dynamic graph neural network and a Mama mechanism. The future short-term traffic flow is predicted by using historical traffic data. According to the method, firstly, normalization preprocessing is carried out on traffic state data collected by multiple sensors, a training sample is generated by adopting a sliding window, and a traffic flow value in the next one hour is predicted according to data in the past 24 hours. On the basis of the model structure, a time modeling module composed of multiple layers of MambaBlocks is constructed and used for capturing historical time sequence dependence; constructing a spatial modeling module of dynamic graph convolution, and combining a static adjacency matrix of the road network with a learnable adaptive adjacency structure to extract spatial association; and finally, the outputs of the modules are fused, and a prediction result is obtained through a prediction output module. In the training process, a Huber loss function is used as an optimization target, and evaluation indexes such as a mean absolute error (MAE), a root mean square error (RMSE) and a mean absolute percentage error (MAPE) are used for evaluating the performance of the model. According to the method, the traffic space-time dynamic characteristics are effectively mined, and the long-range dependence modeling capability and the prediction precision are improved.

The invention discloses a self-supervised traffic flow prediction method based on multi-scale space-time-frequency fusion. The method comprises the following steps: acquiring enhanced data; performing multi-scale spatial-temporal feature coding; performing frequency domain residual filtering; generating a traffic flow prediction result; and carrying out joint target optimization. According to the invention, the multi-scale space-time frequency encoder is designed, local and global time features are captured at the same time through the mixed time encoding module in the time dimension, the multi-scale space encoding module aggregates space features under different distances in the space dimension, and the prediction precision is significantly improved. A frequency domain residual filtering module is embedded in the encoder to adaptively purify frequency domain features in an end-to-end mode, enhance key periodic features and suppress irrelevant noise, space-time features are fused through residual connection, space-time-frequency three-dimension collaborative modeling is achieved, meanwhile, frequency domain consistency loss is introduced in the optimization stage, and time-frequency three-dimension collaborative modeling is achieved. And the method is more robust when facing real traffic data containing noise.

The invention discloses an LED (Light Emitting Diode) energy-saving street lamp system self-adaptive to an ambient light effect and an illumination adjusting method thereof, and belongs to the technical field of novel illumination control and green energy conservation. The system comprises a light environment sensing module, a traffic flow monitoring module, an LED driving power supply and an electroluminescent illumination module composed of a plurality of light emitting diodes. The main control module is configured to execute active lighting effect decoupling logic, namely, when the electroluminescent lighting module keeps steady-state lighting, the driving power supply is controlled to inject a micro-disturbance modulation signal which cannot be perceived by human vision into output current, and illuminance response data of the light environment perception module are synchronously collected; the road surface reflectivity coupling coefficient is obtained in real time by calculating the change ratio of the response data to the modulation signal, then the reflected light component excited by the street lamp itself is accurately removed from the total illumination value, and the pure environment background illumination is decoupled. The problems of misoperation and energy waste caused by self-luminous interference of a traditional light-operated street lamp are solved.

The invention provides an intelligent parking guidance system based on voice interaction and intelligent matching. The intelligent parking guidance system comprises a voice interaction recognition module, an intelligent video module, a path planning module and a parking space scheduling and management module. Wherein the voice interaction recognition module is deployed in an entrance area of a parking lot, interacts with a driver and recognizes a parking position demand; the intelligent video module is arranged at a key node in a parking lot, identifies a vehicle, constructs a vehicle movement track, and analyzes and obtains the overall traffic flow information of the parking lot. The path planning module receives information provided by the voice interaction recognition module and the intelligent video module, carries out path planning, and issues the path planning to the parking space scheduling and management module. And the parking space scheduling and management module is distributed in the parking lot and guides nearby vehicles according to the received route plan.

The invention provides a dynamic traffic scene-oriented unmanned aerial vehicle charging base station site selection and scheduling collaborative optimization method. The method comprises the following steps of: 1, establishing a dynamic traffic flow space-time distribution model and an emergency event probability model based on a GIS (Geographic Information System) platform and traffic monitoring data; step 2, constructing a multi-target dynamic optimization model; 3, solving the multi-target dynamic optimization model by adopting an improved multi-target genetic algorithm; 4, a site selection and scheduling double-layer optimization structure is constructed, and unmanned aerial vehicle task allocation and base station utilization rate balance is realized through an unmanned aerial vehicle charging task scheduling model; and 5, realizing dynamic deployment and scheduling optimization closed loop of the base station through real-time data feedback. The method has remarkable advantages in the aspects of coverage rate, energy consumption, response time delay, system stability and the like. The emergency response speed and the energy utilization efficiency are remarkably improved, the system operation and maintenance cost is reduced, and the method is suitable for scenes such as intelligent traffic and emergency communication.

The invention relates to an ice and snow disaster variable speed limit control method and system based on a friction coefficient, and belongs to the field of intelligent traffic. According to the method, a set of variable speed limit control units are arranged on a road at intervals, and all the variable speed limit control units are in communication connection with a centralized decision-making unit through communication modules; each set of variable speed-limiting control unit detects traffic flow data, meteorological environment data and road condition data of a lane level in real time, uploads the data to the centralized decision-making unit, determines an optimal lane-level variable speed-limiting control scheme and an optimal deicing and snow-removing scheme through a decision-making optimization algorithm, and issues the optimal lane-level variable speed-limiting control scheme and the optimal deicing and snow-removing scheme to the variable speed release module; and the variable speed release module releases a lane level variable speed limit control scheme of a corresponding section, namely the lowest speed limit value, the highest speed limit value, the suggested speed and the like of each lane, and performs deicing and snow removal operation according to the deicing and snow removal scheme so as to ensure road traffic safety in ice and snow weather. The road traffic safety guarantee level is improved through variable speed limiting.

The invention relates to the technical field of environmental noise monitoring, and discloses a road traffic noise intelligent monitoring and three-dimensional sound field reconstruction system, which comprises an acoustic sensor module, a data collection and storage module, a data analysis and evaluation module, a three-dimensional sound field construction and display module and a traffic flow feature library. According to the system, a differential geometry principle is adopted, a sound field is regarded as a Riemannian manifold with a local microstructure, and accurate description of an irregular sound field is realized through a curvature self-adaptive sound field manifold construction technology; introducing a covariant derivative in Riemannian geometry, and constructing a sound propagation model adapted to a complex road environment; and realizing hierarchical decomposition and reconstruction of the sound field by using a multi-scale analysis theory. According to the method, the sound source positioning precision and the calculation efficiency are improved, seamless analysis from microcosmic to macroscopic is realized, an innovative solution is provided for traffic and noise collaborative management, and intelligent traffic and environmental noise management are effectively supported.

The invention relates to a traffic flow prediction method and system based on a dynamic perception expert network, and the method comprises the steps: obtaining traffic observation data, constructing a traffic network diagram, carrying out the feature embedding, and generating an initial spatial-temporal feature vector; inputting the initial spatial-temporal feature vector into a double-path time encoder, and respectively extracting a personalized time sequence feature vector and a time sequence dynamic feature vector through parallel channel independent paths and channel mixed paths; carrying out vector fusion through a gating mechanism to obtain a time context feature vector, inputting the time context feature vector into a multi-scale hybrid expert model, activating a plurality of most relevant time scale experts, and generating a corresponding routing weight; and generating a spatial dependency graph through a scale condition dynamic graph generator, performing graph convolution to extract a plurality of spatio-temporal feature vectors, performing weighted aggregation, sending the spatio-temporal feature vectors into a prediction model, and generating a traffic prediction value. Compared with the prior art, the model constructed by the method is relatively high in prediction precision and relatively high in robustness in a complex traffic scene.

The invention provides a hybrid vehicle energy management system and method based on a traffic state, a storage medium and a computer program product, and the system comprises the steps: constructing a congestion prediction model based on a deep learning model, the congestion prediction is used for predicting the traffic flow and the driving speed of a future time period according to the historical traffic flow data and the historical driving speed data; calculating a first congestion index according to the predicted traffic flow in the future period; calculating a second congestion index according to the predicted driving vehicle speed sequence of the future time period; performing weighted calculation on the first congestion index and the second congestion index to obtain a comprehensive traffic congestion index in a future time period; traffic jam types are divided according to the interval where the comprehensive traffic jam index is located; and determining an energy management mode and / or a target SOC of the hybrid vehicle based on the traffic jam type. According to the invention, multi-source data are collected and analyzed in real time, congestion is accurately quantified by using a deep learning algorithm, an energy distribution strategy of vehicles is dynamically adjusted, and the energy utilization efficiency is improved.

The present application belongs to the technical field of highway traffic control. Disclosed in the present application are a method and device for dynamically evaluating the degree of impact of a highway traffic accident, which method and device are used for solving the existing technical problem of after a traffic accident occurs on a highway, transportation efficiency being prone to being subjected to severe negative impacts caused by it being difficult to dynamically predict the degree of impact of the highway traffic accident, which is not conducive to effectively estimating the severity of the accident. The method comprises: determining a local highway network of an accident site; performing index fusion on preset structural indexes and functional indexes, and performing continuous equalization processing on the severity of a highway traffic accident on the basis of comprehensive indexes obtained after fusion, so as to obtain an accident severity evaluation system for the highway traffic accident; and performing data fusion on information of the natural evolution patterns of traffic flows, information of the severity of the accident at the moment when the accident occurs, and information of abrupt changes in the traffic flows that are induced by the accident, so as to obtain an accident impact factor system of the highway traffic accident.

The invention relates to the technical field of intelligent traffic and Internet of Vehicles, in particular to a traffic and air pollution bidirectional coupling flow prediction method based on double-path dynamic fusion. Comprising the following steps: collecting traffic flow and air pollutant concentration data, and carrying out space-time alignment and reversible instance normalization; the data is divided into two branches, the first branch extracts time-dependent features through gated convolution and probability sparse self-attention, and the second branch obtains variable interaction features through dimension remodeling, context extraction and reversible coupling transformation; bidirectional feature interaction is carried out through cross attention, weights are dynamically generated based on channel attention, and residual connection is carried out after weighted fusion; and performing linear mapping and inverse normalization on the fused features to obtain a traffic flow predicted value. According to the method, the prediction precision and robustness in a pollution sensitive scene are remarkably improved.

The invention belongs to the technical field of urban traffic planning and intelligent traffic systems, particularly relates to an intersection phase structure optimization method based on a large language model, and aims to improve the intelligent level and operation efficiency of traffic signal control. According to the method, semantic mapping cues of traffic flow and a phase structure are constructed, and a large language model is guided to generate a phase structure scheme adapted to an actual traffic state. Compared with a traditional scheme depending on artificial experience and a fixed structure, the method can automatically generate diversified and data-driven phase structure combinations, and has higher adaptability and generalization ability. In the aspect of technical implementation, the method fuses prompt engineering and guides a large language model to generate an initial phase scheme, and performs evaluation and feedback by using a value network, so that optimization of a phase structure is realized, and the overall operation efficiency of a traffic system is improved.

The invention discloses a road carbon emission evaluation method and system, and relates to the technical field of carbon emission evaluation, and the method comprises the following steps: S1, collecting the traffic flow data and environment data of a target road section in real time through a roadside sensing array; s2, constructing a road body carbon emission calculation model; s3, establishing a maintenance activity carbon emission compensation model; s4, constructing a driving behavior carbon emission correction model; s5, establishing a climate accumulation effect correlation model; and S6, generating a dynamic emission coefficient matrix, and establishing a carbon emission coefficient dynamic correction mechanism of different generations of vehicles. According to the method, the road body carbon emission calculation model is constructed, the unit mileage road maintenance carbon emission factor is dynamically generated, oxygenolysis carbon emission of the asphalt concrete material is considered, the influence of the road surface flatness on the vehicle rolling resistance is also taken into account, and therefore comprehensive and accurate accounting of the road carbon emission is achieved, and the calculation efficiency is improved. And the accuracy of the evaluation result is obviously improved.

The invention relates to a ground penetrating radar parameter optimization and general survey method for highway subgrade condition detection. The method comprises four core modules: one is ground penetrating radar parameter optimization configuration, and automatic parameter correction during medium change is realized through static basic configuration and dynamic adaptive adjustment in combination with real-time sensing and PID (Proportion Integration Differentiation) control; the second method is rapid general survey execution, traffic flow, pavement vision and historical disease data are fused, a route is optimized through a Dijkstra algorithm, and abnormity is judged through multi-feature fusion; thirdly, imaging processing is optimized, multi-layer medium correction time delay imaging and complex disease classification imaging are provided, and the deep disease recognition rate is increased; and fourthly, maintenance decision linkage is realized, the disease level and priority are quantified, the maintenance scheme is automatically output, and the decision period is shortened. The method solves the problems of poor dynamic adaptation, difficulty in complex disease identification and disjunction in decision making in the prior art, has been verified in multiple sections, and is suitable for highway subgrade disease full-chain monitoring and maintenance.

The invention belongs to the technical field of urban traffic flow prediction, and more specifically relates to a traffic flow prediction method based on self-supervision spatio-temporal representation and scene adaptation. The method comprises the following steps: acquiring traffic flow data, environment data and static region semantic embedding data, respectively performing preprocessing operation, and fusing the three data to obtain standardized tensor input; meanwhile, constructing structure prior data to constrain and correct subsequent model prediction output; constructing a traffic flow prediction model, inputting the preprocessed data into the prediction model, and outputting a future traffic flow prediction result; a road mask and a capacity upper bound are introduced in training and reasoning for constraint, and the stability of prediction result output is improved. The invention aims to enhance the modeling capability for nonlinear space-time dependence, sudden disturbance and exogenous environment coupling influence.

The invention discloses a time prediction method and system based on double-domain feature fusion. The method and system adapt to long and short term time series prediction requirements of multiple scenes such as weather forecast, energy scheduling, traffic flow and financial exchange rate. The method comprises the steps that a multi-field data set is obtained and preprocessed, and instance normalization is carried out; performing double-domain multi-scale characteristic decomposition by adopting down-sampling and discrete wavelet transform to obtain continuous trend and high-frequency mutation details; a local unit is obtained through patch cutting and embedding, local time sequence association is mined through depth separable convolution, cross-patch global interaction is achieved in combination with a multi-layer perceptron, and local-to-global progressive fusion is completed; and constructing bidirectional attention flow enhanced cross-domain and cross-scale collaboration, and combining with standardized data training to obtain a prediction model. According to the invention, the method can improve the depiction capability of non-stable and non-linear complex time sequence data containing abrupt change and multi-period superposition, gives consideration to the adaptability of long and short term prediction, remarkably improves the accuracy of multi-field time sequence prediction, and promotes the application of the prediction technology in multiple scenes.

The invention belongs to the technical field of road tunnel illumination, and particularly relates to a control method and system for adjusting road tunnel illumination based on dynamic traffic, which comprises the following steps: firstly, acquiring vehicle information through a high-definition camera array, a microwave radar detector and an illumination intensity sensor in a multi-source manner, then preprocessing the multi-source data, and applying an algorithm to adjust the illumination of a road tunnel; traffic flow statistics and trend prediction, vehicle driving state analysis and vehicle type accurate classification statistics are realized; based on this, the traffic flow is counted and predicted in real time through the dynamic traffic information acquisition and analysis module, the illumination brightness reference value is set and corrected based on the traffic flow by combining the multi-dimensional illumination parameter intelligent decision module, and then the illumination execution and dynamic adjustment module accurately executes the brightness instruction. The method has the advantages that the illumination brightness is dynamically matched with the traffic flow, the traffic safety requirement during high traffic flow is met, and energy waste during low traffic flow is avoided.

The invention discloses a traffic flow prediction method based on a multi-scale time window adaptive graph bias neural network, and belongs to the field of deep learning and intelligent traffic. The method comprises the following steps: collecting flow, speed and occupancy data of traffic network nodes, and constructing a historical data set; constructing a time embedding module, and extracting intra-day and intra-week time features; constructing a multi-scale time window trend sensing module, and capturing short-term fluctuation and long-term trend of the traffic flow; a time condition adaptive graph bias module is constructed, a graph bias matrix is dynamically generated according to the time context, and time-varying spatial dependence is modeled; a sparse space attention module is constructed, the calculation complexity is reduced, and spatial-temporal features are fused; and a self-adaptive double-end output module is constructed, a gating coefficient is generated based on the volatility and the quartile distance, and linear and nonlinear branches are fused to output a multi-step prediction result. According to the method, multi-scale spatial-temporal feature fusion and adaptive prediction of the traffic flow are realized, and the prediction precision and robustness are improved.

A traffic flow prediction method based on a dynamic space-time fusion attention mechanism is characterized in that a space-time decoupling embedding strategy, a dynamic weighting time attention module and a self-adaptive dynamic graph modeling module are innovatively adopted, so that space and time characteristics can be effectively decoupled and independently modeled; and meanwhile, the long-term dependency relationship of the time dimension and the spatial relevance of the road network are captured. According to the method, the accuracy and generalization ability of the model in a complex traffic flow prediction task are remarkably improved, a more reliable and more efficient solution is provided for flow prediction in an intelligent traffic system, and the method has important application value and prospect.