3257 results about "Transportation technology" patented technology

The invention discloses a traffic transportation operation monitoring early warning and decision analysis method based on vehicle infrastructure cooperation, and relates to the technical field of intelligent traffic. According to the method, real-time collection of dynamic traffic elements is realized through a multi-dimensional sensing network of a vehicle end, a road side and an environment and V2X communication, time-space reference unification of multi-source data is ensured, a road-vehicle-environment-event semantic network is constructed, multi-dimensional recognition of abnormal events such as accidents, congestion and severe weather is realized in combination with hierarchical feature extraction, and the method has the advantages of being high in practicability and high in practicability. The method is advantaged in that identification accuracy is improved, abnormal event propagation paths can be predicted, global road network situation prediction capability is realized, differential early warning is generated based on a comprehensive risk index, multi-level responses such as traffic signal adjustment and path planning are triggered, response time is greatly shortened, emergency response efficiency is optimized, a decision execution effect real-time feedback mechanism is established, and the method is suitable for popularization and application. The system performance is continuously optimized along with data accumulation, and the defect that a big data platform lacks an intelligent decision closed loop is avoided.

The invention discloses an urban road mobile source intelligent monitoring method and system based on multi-source data coupling, and relates to the technical field of environment monitoring and intelligent traffic. Utilizing a machine learning algorithm to construct a pollutant emission, carbon emission and energy consumption prediction model; acquiring vehicle inventory data in the city, and calculating the pollutant emission, energy consumption and carbon emission of the whole city; the method comprises the following steps of: constructing a dynamic distribution diagram of automobile emission in a city by using real-time position data of vehicles and urban road network information, introducing an atmospheric diffusion model, simulating pollutant migration by combining urban geographic information and environmental data, comparing and verifying a simulated migration result with actually measured data of a national control site, and optimizing parameters of the atmospheric diffusion model; and storing the result into a real-time database, and displaying the pollutant distribution, emission, energy consumption and carbon emission of the urban road network in real time through a visual interface. According to the invention, the temporal-spatial resolution and prediction precision of data are effectively improved.

The invention relates to the technical field of intelligent traffic, and discloses a road transportation key operating vehicle intelligent supervision system, which comprises a data acquisition and fusion module used for acquiring multi-source heterogeneous data of a vehicle terminal, an external environment and the like in real time and carrying out standardization processing; the cognitive digital twinning construction module is used for constructing a dynamic heterogeneous graph representation human-vehicle-road-environment system and outputting a cognitive state vector through a graph neural network; the risk prediction and evaluation module is used for predicting a risk evolution trend based on the state vector sequence and quantifying the uncertainty of prediction by using a Monte Carlo discarding method; and the self-adaptive intervention decision module is used for combining risk prediction and uncertainty, making a decision through a reinforcement learning model and executing an optimal active intervention instruction. By constructing cognitive digital twinning and introducing uncertainty quantification and closed-loop self-checking, prospective prediction and self-adaptive intervention of driving risks are realized, and the accuracy and robustness of supervision are improved.

The invention discloses a low-altitude logistics unmanned aerial vehicle path planning method and system, and relates to the technical field of unmanned aerial vehicle logistics transportation, and the method comprises the steps: firstly, carrying out the optimization through calculating a preliminary path and combining the terrain and weather information; a sensor is used for detecting and dynamically avoiding obstacles; secondly, data transmission between the unmanned aerial vehicle and the ground control center is achieved, and the ground control center carries out monitoring, control and data processing. According to the low-altitude logistics unmanned aerial vehicle path planning system, efficient path planning is realized through multi-module cooperation. According to the invention, the flight safety, path planning accuracy and energy utilization efficiency of the unmanned aerial vehicle can be improved, the operation cost is reduced, and the system adapts to complex environmental conditions.

The invention discloses a vehicle-road cooperation path planning decision-making system based on deep learning, and belongs to the technical field of intelligent traffic. According to the system, global traffic flow data, vehicle positions and vehicle driving destinations are collected, traffic flow prediction of each road section is carried out in combination with a GNN-LSTM fusion model, and a basis is provided for global path planning; the motion trails of the participants are predicted through a Transform model, and real-time interactive decision making between the vehicles and the participants is achieved through a DQN algorithm; vehicle state data, traffic light time sequence data and intersection geographic parameters are fused based on an MPC algorithm to generate a vehicle intersection passing track, whether a dangerous space-time window exists or not is detected through an IoU algorithm, whether the MPC algorithm with constraints is adopted to correct the vehicle intersection passing track or not is determined, and intersection collaborative decision making is achieved. According to the invention, the dynamic adaptability of vehicle path planning is improved, the safety of vehicle-road cooperation and interaction with surrounding participants is enhanced, and the traffic efficiency is effectively improved.

The invention relates to the technical field of lithium ore conveying, and discloses a lithium ore hopper energy-saving conveying system based on intelligent self-adaptive control. The system comprises a data acquisition module, a self-adaptive control module, an energy-saving optimization module and an execution adjustment module. The data acquisition module acquires multi-dimensional operation data of the lithium ore hopper through a distributed sensor network, and a hopper conveying state database is constructed after standardization processing; the adaptive control module performs dynamic feature extraction on the database, generates a real-time control parameter matrix, establishes an association rule graph of each parameter, and constructs an intelligent adjustment decision model based on the association rule graph; an energy-saving optimization module extracts a key energy consumption feature vector from the real-time control parameter matrix, calculates an energy consumption influence coefficient of each operation parameter, and screens out an optimal energy-saving control sequence in combination with an intelligent adjustment decision model; and the execution adjustment module drives an execution mechanism according to the optimal energy-saving control sequence, and self-adaptive adjustment of hopper conveying parameters is completed.

The invention relates to the technical field of cold-chain commodity transportation, in particular to a temperature monitoring and control method in a cold-chain commodity transportation process, which comprises the following steps: acquiring real-time temperature data, and generating a thermal response digital file of a cold-chain commodity according to the real-time temperature data and a cold-chain commodity category database; real-time positions and external air temperature data of the cold chain commodities are collected, and a temperature threshold value of the next time period is predicted according to the heat capacity characteristic parameters reflected by the thermal response digital archive; a three-dimensional temperature field distribution diagram is constructed based on the temperature threshold value of the next time period and the vibration data of the compartment where the cold-chain commodities are located; generating a control instruction according to the coordinates of the temperature anomaly region in the three-dimensional temperature field distribution diagram; after the control weight coefficient is calculated according to the control instruction and the preset energy consumption optimization objective function, the temperature control operation is executed according to the control weight coefficient and the control instruction, and balance temperature monitoring and control and energy consumption optimization are effectively achieved.

The invention discloses a high-density stereoscopic warehouse ex-warehouse scheduling and transportation system and method based on RGVs, and relates to the technical field of warehouse ex-warehouse scheduling and transportation, and the system comprises a scheduling management center which is in communication connection with a virtual model construction module, a task analysis and planning module, a task distribution module and a real-time monitoring intervention module. Wherein the modules are connected through electric signals; and the virtual model construction module is used for constructing a virtual model of the warehouse and the RGV. By constructing the virtual models of the warehouse and the RGVs and combining the digital twinning technology, the state of a physical entity can be synchronized in real time, the space-time paths of the multiple RGVs can be accurately simulated, path conflicts and traffic congestion are effectively avoided, the efficiency of warehouse-out operation is remarkably improved, task delay caused by the path conflicts is greatly reduced, and the working efficiency of warehouse-out operation is improved. And the accuracy and timeliness of warehouse-out operation are ensured, so that the overall logistics efficiency is improved.

The invention relates to the technical field of intelligent traffic, in particular to an urban traffic flow prediction method fusing a dynamic graph convolutional network and a Transformer, which comprises the following steps: firstly, collecting traffic data in a road network to form a data set, then constructing a space-time dynamic GCN unit to capture dynamic evolution of road network topology, and extracting multi-scale space-time characteristics through expansion time convolution; then, constructing a Transform unit for modeling a global time sequence dependency relationship of the traffic flow; finally, in combination with a gating fusion prediction unit, spatial-temporal features are fused through a spatial-temporal cross attention mechanism, and the prediction precision and robustness are effectively improved. Through verification and evaluation of real data, the method is suitable for a traffic flow prediction scene in an urban road network dynamic environment, and especially has good performance in sudden road conditions and peak hours.

The invention provides a stock matching method and device and electronic equipment, and relates to the technical field of cargo transportation. The shipping matching method comprises the steps of determining shipping information corresponding to a to-be-matched cargo source, wherein the shipping information comprises the to-be-matched cargo source, a to-be-selected driver corresponding to the to-be-matched cargo source, a first shipping score, a driver cargo source pool and a second shipping score corresponding to the driver cargo source pool; determining the goods source selection probability of each goods source selected by the to-be-selected driver based on the to-be-matched goods source, the first shipping score, the driver goods source pool, the second shipping score and the historical transaction order of the to-be-selected driver; and determining a target driver matched with the to-be-matched goods source from the to-be-selected drivers by taking the maximum sum of the transaction probabilities of the to-be-matched goods source and all goods sources in the driver goods source pool as a target based on the shipping information and the goods source selection probability. According to the scheme, invalid exposure of the goods source can be reduced, and exposure resources of the goods source are saved.

The invention discloses an intelligent parking space guiding system for a hospital parking lot, relates to the technical field of intelligent traffic, and is used for solving the problems that the hospital parking lot is seriously jammed in peak hours and special vehicles lack exclusive passing authority. The system comprises a parking space monitoring module, a vehicle identification module, an intelligent guiding module and a user interaction module. The parking space state is monitored in real time through the multi-mode sensor array; recognizing entering and exiting vehicles through a deep learning recognition algorithm based on cameras deployed at entrances and exits, and obtaining corresponding vehicle information; based on parking space state information and vehicle identification information, a route optimal value is dynamically calculated, and a whole-course navigation service from an entrance to a target parking space is provided for a driver, so that accurate detection of the parking space state, special vehicle priority distribution, high-low peak dynamic route planning and whole-process intelligent guidance are realized, the hospital parking efficiency is remarkably improved, and the hospital parking experience is improved. And the congestion condition in the peak period is relieved.

The invention provides a path planning method and system based on four-AGV cooperative carrying, and relates to the technical field of automatic logistics transportation. The method comprises the steps that a high-precision grid map is constructed, a global path is generated in combination with a simulation improved A * algorithm, dynamic weight factors are adaptively adjusted according to the obstacle density, and the path search efficiency is optimized; a time window constraint method is adopted to divide path segments and dynamically allocate time windows; real-time sensing of dynamic obstacles is fused, and a local path is adjusted based on Kalman filtering and a dynamic priority scheduling algorithm; a one-master and three-slave cooperative control architecture is adopted, a master AGV tracks a simulation path, and slave AGVs dynamically adjust control parameters through a fuzzy adaptive PID algorithm; the synchronous jacking operation of the four AGVs feeds back the state to the central server in real time through the Ethernet, so that the synchronism and safety of collaborative carrying are ensured. According to the invention, the technical problems of high path conflict rate, low trajectory tracking precision and slow obstacle avoidance response of a multi-AGV system in a complex environment are solved.

The invention discloses a large-load unmanned aerial vehicle group structure, a control method, system and device and a storage medium, and relates to the technical field of material transportation in the power industry, and the method comprises the steps: selecting a proper unmanned aerial vehicle connection mode according to the working environment of transportation and the load requirement, and constructing an unmanned aerial vehicle group and a material carrying platform; based on the constructed unmanned aerial vehicle group and the material carrying platform, synchronous take-off is achieved in combination with environment and load data; the horizontal attitude of the material carrying platform is controlled through a hierarchical cooperative control architecture based on the synchronous take-off unmanned aerial vehicle group data; on the basis of unmanned aerial vehicle group data after horizontal attitude flight is controlled, the height and the attitude are combined, and a multi-mode hierarchical control strategy is adopted, so that the unmanned aerial vehicles safely land and unload materials; the method can effectively guarantee the safety, stability and high efficiency of transportation in the whole process of cargo transportation, and has important practical application value.

The invention belongs to the technical field of intelligent traffic, and particularly relates to a road intersection perception and scene understanding method combining a deep learning algorithm and a large language model, and the method comprises the steps: obtaining traffic visual data; performing deep learning target detection based on the traffic visual data to obtain an object corresponding to the traffic visual data, and recording related dynamic information to form a prompt label; based on a traffic monitoring image and a prompt label of a certain view angle of the intersection, scene description of a corresponding view angle of the intersection is obtained through processing of a large language model; and based on the intersection single-view scene description and the prompt label, enhancing the chained thinking fine-tuning large language model to obtain the traffic scene understanding and semantic description of the whole intersection.

The invention relates to the technical field of intelligent traffic, in particular to a dynamic road network collaborative capacity expansion decision-making system based on federated learning-digital twinning, which comprises the following steps of: calibrating pulse type and periodic type data flow weights through a dynamic weight distributor, and generating a normalized feature vector; fusing the normalized feature vectors of all the domains through a privacy protection aggregation engine to obtain a passenger flow pressure distribution prediction matrix; the reconstruction module is used for constructing a digital twinborn body based on the prediction matrix and initializing the digital twinborn body; and based on the initialized twinborn environment, recognizing and sensing a missing region through a blind area data reconstructor, and fusing historical features and real-time data streams of adjacent nodes by adopting a space-time correlation algorithm to reconstruct a complete road network state. According to the method, the dynamic road network collaborative expansion decision system is constructed by fusing federated learning and digital twinning technologies, and the expansion decision efficiency of the traffic road network is improved.

The invention discloses a thin film tank pump tower base device, and belongs to the technical field of LNG storage and transportation, the thin film tank pump tower base device comprises a base main body, the base main body is cylindrical, the periphery of the base main body is provided with a first connecting part, and the first connecting part is connected with a first shielding layer; wherein the first connecting part is annular, the first shielding layer is formed by splicing two corrugated plates, the two corrugated plates are integrally formed, a circular through hole is formed in the connected end face of the two corrugated plates, and the two corrugated plates are directly connected with the first connecting part. According to the pump tower base, the corrugated plate is integrally formed, the base body is directly connected with the specially-made corrugated plate, the problem that a conventional pump tower base needs to be in transition connection through a connecting plate is solved, the problem that the connecting plate and the corrugated plate are not smoothly connected is solved, the installation procedure of the pump tower base can be simplified, and the preparation efficiency of a thin film tank is improved.

The invention relates to the technical field of intelligent traffic, in particular to an intelligent network connection vehicle driving risk assessment method and a visualization system based on multi-source data fusion. According to the method, multi-source data such as vehicle perception, communication and maps are fused, an artificial potential field theory is combined, a gravitational force risk potential field function, a repulsive force risk potential field function and a road boundary repulsive force potential field function are constructed respectively, and a unified total risk potential field TPF is formed by a gravitational force risk potential field, a repulsive force risk potential field and a road boundary repulsive force potential field; according to the method, the driving risk of the intelligent networked vehicle is obtained, risk grade division and real-time visual display are realized through clustering analysis, the accuracy and dynamic response capability of risk assessment are improved, the method is suitable for safety decision support of advanced driving assistance and automatic driving systems, real-time assessment of the driving risk can be realized more accurately and efficiently, and the risk assessment efficiency is improved. And the risk assessment precision and the dynamic response capability are improved.

The invention provides a double-chain-based air-space-ground fusion vehicle-mounted network security authentication system and method, and belongs to the technical field of intelligent transportation, in an air-space-ground fusion vehicle-mounted network, a vehicle-mounted unit, a road side unit, an unmanned aerial vehicle node and a satellite node interact through a trusted mechanism and a double-chain architecture, after interaction in a single domain is completed, cross-domain interaction is performed, and the security authentication of the vehicle-mounted unit, the road side unit, the unmanned aerial vehicle node and the satellite node is completed. The authentication token is stored on the block chain after being obtained in the first interaction, and the quick interaction can be completed by directly calling the authentication token subsequently. According to the invention, through the double-chain block chain architecture, the authentication time delay is optimized, the cross-domain authentication efficiency is improved, and the privacy protection problem of the node in a high dynamic environment is effectively solved.

The invention discloses a pavement defect detection method and device, a storage medium and electronic equipment, relates to the technical field of computer vision and intelligent transportation, and aims at improving the fusion efficiency of multi-modal features by aligning multi-scale texture features and depth and reflection intensity features through a cross-modal attention mechanism. Due to the fact that visual-radar contrast learning of a cross-modal attention mechanism aligns semantic information of multi-scale texture features and semantic information of depth and reflection intensity features in a feature space, the similarity of samples in the same defect area is maximized, the similarity of negative samples is minimized, and deviation between modals is reduced. And a contrast learning loss function is introduced into the discriminator to distinguish the cross-modal consistency of the pavement generation defect and the real defect, so that the accuracy of pavement defect detection is improved. A high-precision detection model can be trained through a cross-modal data generation technology without real defect labeling, zero-sample and few-sample defect detection is realized, and the pavement defect detection cost is reduced.

The invention relates to a stacking path planning method, system and equipment based on multiple stackers and a medium, and relates to the technical field of workshop transportation, and the method comprises the steps that a dynamic risk hot area map is generated through the real-time personnel density, a two-dimensional map is updated in combination with the positions of idle stackers, and the shortest obstacle avoidance path is planned; and candidate stackers meeting a return electric quantity safety threshold value are screened based on a motion energy consumption model, the moving distance and time consumption of the candidate stackers are calculated, a weighted scoring model fusing the distance, time and path risk values is constructed, and the stacker with the optimal comprehensive score is selected to execute an emergency task. According to the method, the path planning of the stacker crane executing the emergency task and other stacker cranes can be optimized, and the continuity of executing multiple stacking tasks by the stacker cranes is improved.

The invention relates to the technical field of intelligent logistics transportation, in particular to a container environment self-adaptive control method, system and method based on an AI intelligent algorithm. The method comprises the following steps: acquiring a fermentation product transportation characteristic information set, analyzing the fermentation product transportation characteristic information set, and determining a plurality of fermentation container position parameters, fermentation product position parameters and an environment characteristic information set generated by fermentation products in a container; performing real-time comprehensive evaluation on the fermentation environment state in the container based on the environment characteristic information set in combination with the fermentation container position parameters and the fermentation material position parameters to obtain a real-time state parameter set of the fermentation container; comparing the real-time state parameter set with preset standard fermentation parameters, and analyzing parameter deviation data of the real-time state of the fermentation container and standard fermentation; and based on the parameter deviation data, determining an environment regulation and control target set, adaptively regulating the environment in the container, outputting an adaptive control log for accurately regulating and controlling the environment in the container, and ensuring that the fermentation environment is in an optimal state.

The invention provides a goods source recommendation method and device and electronic equipment, and belongs to the technical field of logistics transportation. In the method, a real-time search request of a target driver is received, and a first preset number of first historical click behavior data corresponding to the target driver is obtained; performing generalization processing on each piece of first historical click behavior data and the real-time search request to calculate a total generalization score, screening the first historical click behavior data according to a preset generalization score to obtain second historical click behavior data with higher relevancy with the real-time search request, and determining a second behavior sequence; and finally, inputting the second behavior sequence into the target recommendation model, and generating a recommendation result sorted according to the relevancy. According to the method provided by the invention, the long-term interest and periodicity rule of the driver can be modeled by effectively utilizing the second historical click behavior data with a longer coverage range and higher correlation with the real-time search request under the condition that the online reasoning performance is limited, and the accuracy of a goods source recommendation result is effectively improved.

The invention discloses an open pit mine stripping semi-continuous laying method based on a backfill type deeply-buried channel, and belongs to the technical field of transportation of open pit coal mine stripping systems. The method specifically comprises the steps that an optimal stripping semi-continuous belt conveyor system layout route starting from a stripping crushing station to an outer dumping site is planned; a space gully between the inner dumping site and the outer dumping site of the optimal route is filled with stripping materials to form a dumping bridge, a stripping semi-continuous belt conveyor is laid on the dumping bridge to the outer dumping site, and a backfill type deeply-buried channel is laid below the dumping bridge in advance. According to the transportation mode, the stripping and coal mining operation route is optimized, the truck transportation distance is shortened, and the comprehensive cost is reduced by 50%. Meanwhile, the dumping space is enlarged, and the tension of the dumping space is relieved. According to the arrangement mode, stripping and coal mining transportation routes are optimized, existing coal transportation and power transmission lines are reserved, and rerouting is avoided; tail gas emission is reduced, and environmental protection and energy conservation are achieved; hidden safety accidents in truck transportation are reduced, and manpower is released; and the strip mine is promoted to develop towards a safe, green, intelligent and efficient direction.

The invention relates to the technical field of smart traffic, and discloses a smart traffic monitoring system and method based on multi-source data fusion, and the system comprises a multi-source data collection module, a spatial-temporal feature fusion engine, a hierarchical decision core, a decision execution module, and an online learning module. The method corresponds to the system. According to the method, heterogeneous traffic data are unified under the same time-space reference through a multi-modal fusion technology, and comprehensive and accurate road network state feature representation is constructed; the hierarchical decision-making core forms a closed-loop decision-making link from event identification to control strategy generation through close cooperation of an event sensing layer and a regional optimization layer, and realizes rapid response and accurate control of traffic abnormity; on-line learning continuously optimizes decision logic based on complete historical operation data so as to adapt to a continuously changing traffic environment; finally, the accuracy of traffic state perception and the timeliness of decision response are improved, and reliable technical guarantee is provided for efficient management and control of intelligent traffic.

The invention relates to the technical field of intelligent traffic, and discloses an automatic driving track prediction optimization method and an automatic driving control system, and the method comprises the steps: obtaining a prediction track of a vehicle in a first prediction time domain at a first positioning position; determining a first state based on the reference trajectory and the predicted trajectory; and updating the first positioning or the first prediction time domain based on the first state, and returning to the step of obtaining the prediction trajectory until the prediction trajectory meets a preset condition, thereby obtaining a final prediction trajectory. According to the scheme of the invention, prediction deviation caused by sensing noise, environment sudden change or model extreme scene blind areas can be sensed and corrected in time, and the trajectory prediction capability, safety and reliability of an automatic driving control system in an extreme scene are improved.

The invention provides an intelligent goods tracking method and system for a combined fleet, and relates to the technical field of shipping transportation, and the method comprises the steps: 1, deploying a goods state monitoring device on a barge and an auxiliary function ship of the combined fleet, and collecting the physical state parameters and position information of goods in real time, the monitoring device comprises a first target detection point and a second target detection point; and step 2, the fleet central control platform integrates and analyzes the physical state parameters and the position information of the goods, the temperature data of the first target detection point and the position offset data of the second target detection point to generate a target correction value. According to the invention, through real-time monitoring, intelligent analysis, collaborative response and dynamic optimization, complete-flow accurate tracking, efficient management and risk prevention and control of cargos of the combined fleet are realized.

The utility model discloses a transfer machine with a reinforcing mechanism, which belongs to the technical field of logistics transportation and comprises a frame, a conveying belt vertically mounted at the top of the frame in a lifting manner and moving along the length direction of the frame, a roller frame horizontally mounted at the top of the frame and a roller parallel to the length direction of the frame and rotatably mounted between the sides of the roller frame. Lifting air cylinders are vertically installed on the two sides of one end of the machine frame. The reinforcing mechanism composed of the lifting air cylinder, the end plate, the translation air cylinder, the push plate and the guide rollers is arranged at the end of the machine frame, the height and the position of the push plate are adjusted in advance, after goods are transferred to the top of the device, if the goods are inclined, the goods can be automatically and horizontally pushed and corrected through the push plate in the moving process, and therefore the safety of the goods is improved. And the stability of the goods is improved, the positions of the goods are reinforced, and practicability is higher.

The invention discloses a fresh food after-ripening characteristic and demand prediction transportation aging collaborative optimization method, and relates to the technical field of fresh food transportation, the method comprises the following steps: using a sensor to collect temperature and humidity, gas concentration and cell metabolite data in a fresh food after-ripening process; according to the invention, temperature, humidity, gas concentration and cell metabolite data of the fresh food are collected in real time by using a sensor in a transportation link, and deep fusion and analysis are carried out in combination with multi-source external information such as historical sales data, social media public opinions, weather disaster early warning and the like, so that precise control of the after-ripening state of the fresh food is realized; according to the method, deep learning and association rule mining technologies are applied, a dynamic decision model is constructed, and the transportation time efficiency and the distribution strategy are optimized in real time according to after-ripening characteristics and demand prediction, so that the fresh food loss can be effectively reduced, the product quality is ensured, the transportation resource utilization rate is improved, the logistics cost is reduced, the market demand is accurately matched, and stockout and overstock phenomena are reduced.

The invention discloses a signaling road network matching method based on a heterogeneous graph convolutional network and an attention mechanism, and belongs to the crossing field of mobile communication and intelligent traffic technologies. According to the method, a multi-relation graph containing a road segment set and a base station sampling point set is constructed, wherein an edge set covers associated edges of base station sampling points and road segments, topological edges of the road segments and time edges of the base station sampling points; performing feature extraction on the multi-relation graph by adopting a 3-5-layer heterogeneous graph convolutional network to obtain low-dimensional vector representation of nodes; dynamically calculating an observation probability and a transition probability based on an attention mechanism; and performing path search by using an improved Viterbi algorithm in combination with a backtracking mechanism and a pruning strategy, and outputting a path with the highest score as a matching result. The method can effectively solve the problems of poor adaptability to complex road networks, insufficient robustness to high positioning error signaling data, low precision caused by matching probability immobilization and the like in the prior art, significantly improves the accuracy and robustness of signaling road network matching in complex scenes, and can be applied to the fields of traffic flow monitoring, travel mode analysis, urban planning and the like.

The invention discloses an intelligent traffic regulation and control method and system for cities, relates to the technical field of intelligent traffic, and realizes high-precision real-time sensing of complex traffic states of urban intersections by constructing a multi-source traffic data acquisition system. A multi-modal feature fusion and semantic tag matching mechanism is adopted to recognize overlapping and dynamic changes of traffic states, a multi-strategy linkage signal timing scheme is generated in time, and the problems that a traditional signal control system is lagged in response and single in state recognition are solved. According to the method, commuting and logistics interference indexes are introduced, a release sequence adjustment and channel optimization strategy is intelligently generated according to a people flow peak and logistics concurrence situation, and the method aims at solving the problem of intersection signal timing regulation and control under the condition of complex multi-mode traffic flow superposition. And meanwhile, an execution result is collected in a closed-loop manner, a strategy deviation value is calculated in real time, error tolerance is set, adaptive iterative optimization is supported, and stable convergence of the strategy and achievement of a regulation target are ensured.