The invention designs a traffic flow prediction method based on static and dynamic multi-graph fusion, which comprises the following steps of: firstly, acquiring a traffic flow data set, processing the traffic flow data set, then sequentially constructing a static region similar graph, a dynamic flow similar graph and a dynamic region connected graph based on the traffic flow data set, constructing a multi-graph module, and training a TransGCN network model according to the multi-graph module; and finally, the trained TransGCN network model is verified. In the prior art, static data is established, and influence of the subway surrounding environment and flow data changing every day are not considered, so that environmental factors around the subway station and dynamic flow information are considered, a dynamic matrix can be constructed every day to capture dynamic changes of the flow, and therefore, the dynamic change of the flow can be captured. And the prediction effect of the model is more accurate.

    本发明设计一种基于静态和动态多图融合的交通流量预测方法,首先获取交通流量数据集对其进行处理,然后基于此依次构建静态的区域相似图、动态的流量相似图和动态的区域连通图,构建多图模块,并以此训练TransGCN网络模型;最后对训练好的TransGCN网络模型进行验证;现有技术都是建立在一个静态的数据上的,没有考虑到地铁周围环境的影响和每天变化的流量数据,因此本发明考虑到了地铁站周围的环境因素以及动态的流量信息,可以每天构建一个动态矩阵来捕获流量的动态变化,使得模型的预测效果更佳准确。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method based on static and dynamic multi-graph fusion


    Weitere Titelangaben:

    一种基于静态和动态多图融合的交通流量预测方法


    Beteiligte:
    YU RUIYUN (Autor:in) / WANG CHEN (Autor:in)

    Erscheinungsdatum :

    2023-05-02


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Multi-view fusion space-time dynamic graph convolutional network urban traffic flow prediction method

    YUAN GUAN / ZHAO WENZHU / ZHANG YANMEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Dynamic multi-graph convolutional network traffic flow prediction method based on graph transformation

    HU YONGLI / PENG TING / GUO KAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Traffic flow prediction method based on multi-view dynamic graph convolutional network

    HUANG XIAOHUI / YE YUMING / LING JIAHAO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Method for predicting traffic flow by using dynamic multi-graph fusion

    ZHANG QIANG / WANG PENGFEI / SHEN BO | Europäisches Patentamt | 2023

    Freier Zugriff

    High-speed traffic flow prediction method based on multi-modal fusion and graph attention mechanism

    RUAN TAO / WU DEXING / XU LEI | Europäisches Patentamt | 2020

    Freier Zugriff