3945 results about "Traffic volume" patented technology

The invention discloses a full-period traffic flow prediction method based on spatial-temporal feature deep fusion, and aims to deeply integrate complex spatial-temporal dependence of traffic flow, form composite traffic situation perception and realize traffic multi-period comprehensive flow prediction. The method comprises the following steps: firstly, through spatio-temporal information comprehensive representation, extracting time sequence characteristics of multiple time modals and constructing a concrete real spatial relationship; in order to further construct a digital urban traffic flow prediction method fusing multi-scale and multi-granularity comprehensive elements, a comprehensive traffic flow prediction model deeply fusing short-term space-time dependence is provided for short-term traffic flow prediction, so that the sensitivity to instantaneous flow change is improved; the short-term dynamic change of the traffic flow in the multifunctional airspace node is fully modeled; in addition, a deep airspace deconstruction and time sequence feature fusion model is designed for medium and long term traffic prediction and deep extraction of complex traffic modes. Simulation results show that the method provided by the invention is superior to the existing traffic flow prediction technology.

The invention provides a private domain traffic peak identification and route scheduling method and system based on time sequence prediction, and relates to the technical field of private domain traffic management, and the method comprises the steps: predicting traffic data and confidence through a multi-dimensional heterogeneous graph network and a causal reasoning mechanism, and generating a dynamic threshold based on empirical mode decomposition and a generalized extreme value distribution model, and predicting a peak value by combining a fuzzy inference device. And then, constructing a distributed collaborative early warning mechanism, and generating graded early warning signals and early warning grades according to the multi-dimensional early warning indexes and node consensus. And finally, constructing a multi-target routing optimization model, performing routing resource grouping based on the link reliability score, searching candidate paths by using multi-agent reinforcement learning, determining a distribution proportion according to early warning information and a peak prediction result, optimizing a path selection strategy in a peak time period, and scheduling private domain traffic to a selected path. According to the method, the private domain flow peak value can be effectively identified, the service quality is guaranteed through dynamic routing scheduling, and the user experience is improved.

The invention discloses a deep reinforcement learning-based network traffic optimization scheduling method suitable for periodic traffic characteristics. The method comprises the following stages: collecting historical periodic traffic data; a network state is monitored in real time through an SDN controller, and historical periodic flow data including time delay, bandwidth utilization rate and load information are acquired; data preprocessing: performing cleaning, normalization and time sequence segmentation on the collected historical traffic data; constructing an LSTM model, constructing the LSTM model by using the preprocessed historical data, and defining an input feature and an output tag; training an LSTM model, training the LSTM model by using the training set data, and generating traffic prediction data of a next period; constructing a state space, fusing the predicted traffic data with the real-time traffic data, and constructing the state space; training a DQN model, and training a deep Q network (DQN) model by using the constructed state space; network topology and link state information are obtained, the current network topology is obtained through a topology discovery module of the SDN controller, and the bandwidth utilization rate, time delay and packet loss probability information of a link are collected in real time through a flow monitoring module; large flows and small flows are distinguished; scheduling the small flow by using the ECMP; and scheduling the large flow by using the DQN model.

The invention relates to the technical field of traffic management, in particular to a video monitoring traffic intelligent optimization system which comprises a time sequence fragment evaluation module, a path priority adjustment module, a traffic scheduling optimization module and a buffer strategy adaptation module. According to the invention, the transmission efficiency and quality of the video monitoring data are improved by analyzing the video stream in real time and adjusting the frame rate and the compression rate, the importance of each time sequence segment in the video stream is evaluated, the frame rate is adjusted according to the importance, more resources are ensured to be obtained by important events, unnecessary data transmission is reduced, network congestion is effectively reduced, and the transmission efficiency of the video monitoring data is improved. The network transmission path is monitored in real time, and the data transmission proportion is adjusted, so that the video stream passes through the network path with higher quality more preferentially, the stability and speed of video transmission are enhanced, the priority and bandwidth allocation are dynamically adjusted, and the video stream with high priority is protected to ensure that the video quality of a key monitoring area is not influenced by network fluctuation.

The invention relates to the technical field of communication data analysis, and discloses a communication network service health degree analysis method, system and device and a medium, and the method comprises the steps: obtaining real-time link state data, carrying out the quantitative analysis, and judging whether the link jitter exceeds a preset threshold value or not; when abnormality is detected, abnormal points can be positioned and the influence range of the abnormal points can be analyzed, so that the influence degree of nodes on the abnormal diffusion path can be identified; calculating a service quality index change value, and determining a starting point and a diffusion direction of chain degradation; by analyzing historical traffic data of the key nodes, a service traffic change trend and traffic dense area distribution characteristics are obtained. According to the method, the bandwidth allocation strategy is dynamically optimized, the bandwidth resources at the junction are reconfigured, and the regional service health degree is evaluated. And if the degradation is not effectively controlled, monitoring and detection mechanism parameters can be adaptively adjusted, and continuous analysis and control of link abnormity are realized, so that the network performance and the service quality are effectively improved.

The invention discloses an expressway lane control method based on real-time traffic flow. The expressway lane control method comprises the following steps of performing fusion sensing through a distributed optical fiber vibration sensor array and a millimeter wave radar; constructing a space-time diagram convolutional network model, and dynamically mapping the road topological structure into a lane connection diagram with variable weight; a layered reinforcement learning architecture is adopted, and an emergency lane dynamic management mode is triggered; and deploying a digital twin sand table to perform multi-resolution simulation verification, and when the actual traffic flow deviates from a predicted value by more than 15%, starting a causal inference engine to backtrack a decision link and update an agent strategy library. According to the method, global dynamic lane optimization is realized through a multi-source perception fusion and hierarchical reinforcement learning architecture, simulation data shows that the morning peak traffic volume is improved by 29.3%, and the accident scene traffic efficiency is improved by 28.6%; a digital twinning and causal inference engine is adopted, the strategy updating response time is shortened to 30 seconds, and the congestion propagation distance is reduced by 35%.

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

The invention discloses an intelligent decision analysis system and method based on multi-source data, and belongs to the technical field of artificial intelligence. According to the invention, multi-source data related to bus operation is acquired, real-time acquisition and uploading of bus operation data are realized, data preprocessing is carried out, and the multi-source data are integrated; feature engineering is carried out, and a passenger flow prediction model is established; based on a passenger flow prediction model, obtaining predicted passenger flows in different time periods of the day, and predicting a driver state; establishing a bus scheduling model by using a deep learning model, and inputting predicted passenger flow, predicted driver state, historical data of bus operation and urban traffic condition data to obtain a bus scheduling scheme on that day; when the dispatched buses in a certain period of time of the bus route are not enough, a route from a bus station closest to a starting station of the bus route to the starting station is obtained, and idle buses are dispatched; and if no idle bus exists in the bus station, the buses of the rescue bus route allowed to be dispatched are dispatched.

The invention relates to the technical field of network communication, and discloses a flow control and load balancing method in network communication, which comprises the following steps of: collecting and preprocessing historical network communication data by using a network monitoring tool to form a basic data set; thirdly, performing flow characteristic analysis on the basic data set, including a flow peak time period, a user behavior pattern, a network topology structure and the like, so as to construct a network communication training data set; and then, a traffic prediction model and a resource allocation model are respectively constructed by adopting a dual machine learning model design, and a residual error fitting model is constructed by utilizing residual errors of the two models, so that accurate traffic control and load balancing are realized. By training and optimizing the model, the real-time network communication data can be predicted, the potential risk can be identified, and the targeted strategy can be formulated. According to the invention, the accuracy and flexibility of flow control and load balancing are improved, and reasonable utilization and efficient operation of network resources are ensured.

The invention discloses a method and a system for realizing mine communication signal improvement based on edge computing, and relates to the technical field of mine communication signal improvement, and the method comprises the following steps: integrating a real-time monitoring system on each edge node, so as to continuously detect the fluctuation of communication flow and data request quantity, the real-time monitoring system identifies a potential communication peak period by collecting real-time data and generates an early warning signal to notify a network administrator or automatically trigger a load management program. According to the invention, through the real-time monitoring and early warning system on the edge node, active monitoring and peak prediction of mine communication are realized, the overload risk caused by traffic surge is reduced, and the stability of data transmission is ensured. And intelligent scheduling and dynamic resource allocation are combined, so that efficient execution of tasks under high load is ensured, and node overload is prevented. A self-adaptive load balancing and feedback mechanism enables the system to dynamically adjust distribution, quickly respond to a bottleneck and improve self-adaptability and stability.

The invention provides a low-orbit satellite resource allocation method and device based on beam and frequency domain collaborative optimization, and the method comprises the steps: dividing the overall bandwidth of a user region into a central sub-band and an edge sub-band through employing a dynamic soft frequency reuse scheme; all ground users are subjected to spatial clustering according to geographic positions and traffic demands, coverage cells are dynamically divided according to clustering results, and balanced service is achieved; on the basis of dynamic cell division, user clusters with high service volume are selected according to priorities, a beam activation set is generated, and a hopping beam matrix is updated; establishing a channel model between a user and a beam and a switching matrix between satellites; constructing a system utility target, and constructing a multi-target optimization problem model by taking the system utility target as a main part and integrating interference, switching overhead and delay penalty; and the multi-dimensional resource collaborative optimization framework based on deep reinforcement learning reconstructs a multi-objective optimization problem model, and outputs a solution of the multi-objective optimization problem model, including an optimal bandwidth and a power allocation result. According to the invention, resource allocation can be carried out on low-orbit satellites.

A station (STA) receives from an access point (AP) a frame indicating a start time and a wake duration of a restricted target wake time (r-TWT) service period (SP) of an r-TWT setup for the STA. The STA transitions to an awake state at or before the start time of the r-TWT SP. The STA receives, from the AP, during the r-TWT SP: a first frame comprising a traffic identifier (TID) associated with the r-TWT and having an end of service period (EOSP) field set to 0; or a trigger frame indicating an identifier of the STA. The STA transitions to a doze state, after expiration of the wake duration of the r-TWT SP, on condition of receiving, from the AP, after expiration of the wake duration of the r-TWT SP, a second frame comprising a TID associated with the r-TWT and having an EOSP field set to 1.

Disclosed embodiments generally relate to edge-based multi-Radio Access Technology (RAT) traffic management (TM) solutions to support delay-sensitive traffic over heterogeneous networks. Embodiments include delay-aware TM implementations that split and / or steer network traffic across different RATs for the edge network control plane. Embodiments also include utilization threshold-based implementations to achieve delay-aware multi-path TM at the network's edge. The multi-path TM includes multi-RAT, multi-access, or multi-connectivity traffic routes. Embodiments include strategies to sort users (or devices) for making multi-RAT traffic distribution decisions and to determinate the utilization thresholds. Embodiments also include message exchange mechanisms or learning utilization thresholds and other useful system properties. Other embodiments may be described and / or claimed.

The invention discloses an urban tunnel intelligent safety operation and maintenance method and system combined with multiple data, particularly relates to the field of intelligent traffic operation and maintenance, and is used for solving the problems of prediction deviation and congestion management caused by tunnel flow fluctuation. In combination with traffic parameters of a multi-point detector, a wave similarity analysis model is utilized to accurately evaluate a propagation path and a target section of fluctuation; meanwhile, by means of a time sequence superposition correction mechanism, a historical fluctuation rule and real-time data are fused, a traffic flow transmission prediction curve after dynamic correction is generated, and balance between physical constraint and prediction precision is achieved; finally, key indexes are output through dynamic updating of the flow prediction model, efficient linkage of signal coordination and induction management and control modules is guided, congestion accumulation and traffic risks caused by fluctuation propagation can be reduced to the maximum extent, the tunnel operation and maintenance efficiency is optimized, and the traffic safety guarantee capacity is enhanced.

The invention provides an encrypted traffic anomaly detection method based on high-performance traffic collection, and the method specifically comprises the following steps: 1) achieving the capturing and collection of high-speed traffic through the high-performance traffic collection based on DPDK, and extracting traffic features by taking a flow as a unit, and carrying out the persistence of the traffic features in a traffic database; 2) providing a two-stage technology of automatic online encrypted traffic collection and sample construction and service classification model construction based on the service classification of the encrypted traffic to realize specific service classification for the encrypted traffic; and 3) proposing construction of a device-level traffic portrait to realize space-time granularity division of a traffic information prediction result, proposing various abnormal conditions and corresponding judgment strategies according to the device-level traffic in a real network environment, constructing a traffic anomaly detection model, and realizing timely early warning of the abnormal conditions. According to the method, the support service of the whole flow of flow collection, service classification and anomaly detection is realized, the flow behavior anomaly of each service device is dealt with in time, and the effectiveness and reliability of the operation of a network and an information system are ensured.

The invention discloses a load balancing control method based on data traffic, and relates to the technical field of data transmission. Comprising the following steps: constructing a flow monitoring module based on data flow, constructing a self-adaptive flow classification model, dynamically allocating weights to load nodes with balanced loads, dynamically adjusting a transmission path of the flow, carrying out real-time load balancing scheduling, and processing abnormal flow. According to the load balancing control method based on the data traffic, the self-adaptive traffic classification model and the multi-path traffic reconstruction algorithm are introduced, so that the defects in the prior art are fundamentally overcome. The real-time performance, the stability and the resource utilization rate of the system are remarkably improved through deep classification of the traffic characteristics and a multi-path dynamic segmentation strategy. According to the method, resource allocation can be optimized in a complex traffic scene, the load balancing efficiency is improved, meanwhile, the service quality of delay-sensitive and bandwidth-intensive services is guaranteed, and the availability and reliability of the whole system are enhanced.

The invention relates to the technical field of data security and the field of financial science and technology, and discloses a permission-based interface flow limiting method, which solves the problem of low efficiency caused by unified processing of all requests by obtaining accessed service interface information and screening out key access requests according to a preset interface path rule. Permission classification is performed based on service roles, account identifiers or user group information of the users, flow limiting management is further refined, and personalized flow limiting conditions are set for the users in different permission ranges. According to the flow limiting conditions, the system dynamically selects a proper flow control strategy, such as request frequency limitation and concurrent request number control, so that system resources are reasonably distributed. According to the method, the flow limiting strategy can be dynamically adjusted according to different permissions of the user, it is guaranteed that the high-permission user is not limited too much, meanwhile, the situation that malicious users cause too large pressure on the system through frequent requests is prevented, and the overall safety and stability of the system are improved.

The invention discloses an intelligent network traffic anomaly detection and automatic isolation system, which comprises a data acquisition module, a preprocessing module, an intelligent traffic analysis module, an anomaly detection engine, an automatic isolation execution module and a visual monitoring and alarm platform, by introducing a deep learning algorithm and a multi-dimensional anomaly detection algorithm, deep mining and comprehensive analysis of network traffic can be realized, feature information is automatically learned and extracted from mass data, an accurate traffic behavior model is constructed, and abnormal behaviors in the traffic are detected in real time. And full-process automatic processing from data acquisition, preprocessing, intelligent analysis to automatic isolation is realized. When abnormal traffic is detected, the system can automatically execute isolation measures and monitor the isolation purpose in real time, and compared with a traditional method based on a rule base or threshold judgment, the method is higher in detection accuracy and real-time performance.

To easy the triggering by an AP MLD of uplink communications of low latency streams from non-AP MLD, the invention proposes that a local traffic stream be identified using a Stream Classification Service, SCS. The local SCS traffic stream is mapped onto a target TID which was previously mapped with an impacted UP. The local SCS stream is preferably assigned to an alternate queue of an AC. Said impacted UP is also mapped onto a fallback TID, corresponding to the primary queue of the same AC. The SCS stream is advertised to the AP using a SCS Request frame. Conventional fields can be used. A trigger frame from an affiliated AP of the AP MLD may then provide resource units to an affiliated non-AP station dedicated to the target TID, hence specific to the low latency SCS stream.

A method for optimizing coexistence of low latency, low loss and scalable throughput (L4S) traffic and non-L4S traffic in a 5G wireless system is provided, which method includes one of: a) performing one of i) a flow control between a centralized unit (CU) and a distributed unit (DU), or ii) radio resource management at the DU, to reduce latency experienced by the L4S traffic; or b) performing one of iii) a flow control between the CU and the DU to facilitate greater frequency of transmission of non-L4S traffic from CU-user plane (CU-UP) to the DU, or iv) radio resource management at the DU, to reduce a scheduling priority metric of a logical channel for the L4S traffic relative to a scheduling priority metric of a logical channel for the non-L4S traffic. To reduce latency of the L4S traffic, the L4S traffic scheduling priority is increased relative to the non-L4S traffic.

The invention discloses a dynamic traffic scheduling method and system based on an SD-WAN technology, which can timely discover potential problems in a network by monitoring performance parameters of network links and nodes in real time, and can effectively relieve network congestion and improve the overall network performance based on analysis of the performance parameters and dynamic adjustment of network routing and bandwidth allocation strategies. According to the method, a high-flow time period, a low-flow time period and key service flow are identified, so that the distribution of network resources is more reasonable and efficient, the adjusted network performance is evaluated in real time, the expected effect of each adjustment can be ensured, and if the performance does not reach a preset standard, the scheduling strategy is continuously optimized, and the scheduling efficiency is improved. According to the technical scheme, the method is beneficial to adapting to rapidly changing network environments and service requirements, the stability and reliability of the network are enhanced, the network states, scheduling strategies and performance evaluation results before and after adjustment are recorded in logs, and operation and maintenance personnel can rapidly position network problems by analyzing log data, so that the operation and maintenance efficiency and accuracy are improved.

The embodiment of the invention provides a micro-service flow anomaly monitoring method and device based on traffic data, and the method comprises the steps: receiving traffic data which is continuously uploaded by a road camera and comprises text data and image data, and storing and processing the traffic data through setting a micro-service, acquiring traffic log information when the traffic data is processed by the micro-service, calculating the volatility and the variation trend of the time sequence data, and constructing a model training data set by adopting a sliding time window method according to the traffic log information; collecting traffic log information of the micro-service per minute through a parallel mechanism, and inputting the traffic log information into the trained traffic data flow analysis model to obtain a peak ratio, a change rate and a duration output by the traffic data flow analysis model; processing different levels of early warning by adopting log recording, alarm pushing and automatic current limiting measures respectively; according to the invention, the micro-service flow anomaly monitoring efficiency and accuracy of traffic data can be effectively improved.

The invention discloses a micro-service full-link gray level traffic management system and method based on PaaS, and relates to the field of traffic management, and the system comprises an intelligent traffic analysis and decision center module, a micro-service arrangement and management platform, a full-link data analysis module, a dynamic safety protection and compliance auditing module, and a distributed configuration center. According to the micro-service full-link gray flow management system and method based on the PaaS, dynamic self-adaptive gray strategy formulation can be carried out, the latest service target, the gray version release plan and the system performance index threshold can be synchronously obtained in cooperation with a distributed configuration center, and the flow management efficiency is improved based on the information and the intelligent screening result of the flow. A routing strategy and a version switching strategy of gray traffic can be dynamically generated, and in the strategy making process, the real-time load condition of a system, the availability of micro-services and key index changes of services are fully considered.

The invention provides a sequential network traffic prediction method and system based on swarm intelligence parameter optimization, and relates to the technical field of network traffic prediction. The method comprises the following steps: acquiring indexes such as throughput packet loss rate and round-trip delay of a target link by using a network probe, and performing deletion filling normalization and multi-scale decomposition to obtain a standardized traffic sequence; calculating information entropy, constructing a traffic complexity feature vector, and dividing a training set and a verification set; constructing a hybrid depth prediction model composed of a one-dimensional convolutional network and a gating cycle unit, and establishing a hyper-parameter search space; using particle swarm optimization and entropy-driven inertia weight adjustment and mutation probability mapping to reconstruct a speed and position updating strategy, and iteratively outputting a global optimal hyper-parameter; and generating a benchmark prediction result according to full-amount training, extracting a residual error, training a nonlinear residual error compensation model to carry out superposition correction and reverse normalization, obtaining a final flow prediction result, and improving prediction precision and generalization ability.

The invention discloses a configuration system and method for dynamically adjusting a business process, particularly relates to the technical field of business adjustment, and aims to dynamically group users accurately according to the degree of dependence of the users on different network services so as to enable resource allocation to be more accurate, and dynamically adjust a bucket dividing strategy according to the change of dependence of the users on the services so as to improve the efficiency of business process adjustment. According to the method, changes of markets and user behaviors can be quickly responded, and a network service provider can more accurately adjust priorities of the user bucket groups by comprehensively analyzing the hidden danger degree of abnormal user traffic distribution and network resource demands in peak periods; the preventive analysis and adjustment method not only can effectively predict and relieve the potential service interruption risk, but also optimizes the resource allocation, and through the dynamic and comprehensive adjustment strategy, the network operator can improve the service reliability and the user satisfaction, and reduce the service quality problem caused by improper resource allocation at the same time.

The embodiment of the invention discloses a multi-lane shunting management and control method, equipment and a medium, is applied to the technical field of intelligent traffic, and is used for solving the problem that an existing shunting mode is low in efficiency and low in accuracy. The method comprises the following steps: dividing monitoring sub-regions based on road network data, and determining topological connection data of each sub-region by using historical vehicle driving data; and identifying target traffic characteristics of each sub-region through clustering analysis, and determining a corresponding shunting traffic region according to the target traffic characteristics. And identifying the current congested road section and the congested direction according to the real-time vehicle driving data, and formulating a shunting strategy in combination with the condition of the shunting traffic area. And inputting the passing speed of the current congested road section, the driving data of the shunting traffic area and the shunting strategy into a preset flow prediction model, and outputting and adjusting the shunting strategy according to the model to realize dynamic shunting management and control.

The invention discloses a network security protection method, system and device, and a medium, particularly relates to the technical field of network information security, and is used for solving the problem that the attack of constructing a covert channel by using a time interval is difficult to find in time in the prior art. Through sliding window segmentation and multi-granularity time standardization, extracting multi-scale time sequence characteristics of network traffic; classifying time sequence modes by using a bidirectional long short-term memory network, and separating normal protocol traffic from covert channel behaviors; further constructing a cross-scale causal transfer graph through symbolization discrete mapping, and combining continuous coherence analysis to quantify the traffic topology stability to form a multi-dimensional anomaly criterion to improve the detection precision; aiming at covert channel confrontation requirements, dynamic random delay parameters are generated based on Poisson distribution, a target data stream is injected, channel time synchronism is destroyed, a protocol baseline template is updated adaptively, and it is ensured that traffic after interference still conforms to protocol statistical characteristics.

The invention relates to the technical field of communication base station energy-saving control, and discloses an energy-saving optimization control method and system for a communication base station. The method comprises the following steps: collecting and preprocessing traffic energy consumption data of a communication base station to obtain standardized characteristics; inputting the features into a double-flow space-time convolutional network, and carrying out parallel calculation through time and space branches to predict a load; performing hierarchical quantitative pruning on the network, and distributing bit width according to the influence degree to obtain a compression structure; and processing the real-time data based on the compression network, and generating an energy-saving control strategy for radio frequency resource configuration and power regulation. Based on accurate load prediction and differentiated resource scheduling strategies, the optimal balance between energy saving and service quality is realized, the problems of passive response and coarse-grained control in a traditional method are effectively solved, and the energy saving effect is maximized on the premise of ensuring communication quality.

The invention discloses an intelligent traffic flow dynamic regulation and control method and system based on multi-source data fusion, and relates to the technical field of data processing. The method comprises the following steps: executing multi-source data acquisition through a data acquisition interface to obtain a multi-source traffic data set; performing spatial fusion on the multi-source traffic data set to obtain a flow marking map; performing current traffic state analysis based on the flow marking map, identifying local and global congestion, and constructing a traffic situation map; and performing traffic flow state prediction in a preset future time zone based on the traffic situation map, performing regulation and control decision based on a prediction result, and generating a traffic flow regulation and control strategy. The technical problem that traffic flow prediction and regulation are not accurate enough in the prior art is solved, and the technical effects that intelligent traffic flow dynamic regulation is achieved through multi-source data fusion and space-time analysis, and the traffic management precision and the response speed are improved are achieved.

The invention provides an air-railway combined transportation network passenger flow prediction method fusing LSTM and GNN. The method comprises the steps that firstly, a graph model of a user travel scheme interaction data set is established through a user portrait data set and a travel scheme record data set; then constructing a weight matrix as the input of the traffic prediction model; and predicting the future traffic of the air-railway combined transportation travel scheme by adopting a traffic prediction model based on a long-short-term memory network and a graph neural network. According to the method, the long-term dependency relationship in the time sequence data is captured by using the LSTM, and the graph structure between the travel schemes is constructed in combination with the GNN to process the spatial relationship data, so that the complex characteristics of the traffic change of the travel schemes can be captured more comprehensively. Simulation results show that the proposed method is superior to a single LSTM, GNN or SFM or other benchmark methods in indexes such as MSE, MAE, RMSE and MAPE.