The invention discloses a dynamic multi-graph convolution network traffic flow prediction method based on graph transformation. A supported traffic prediction model is mainly composed of four modules: a space attention module based on graph transformation, a dynamic multi-graph convolution module, a time convolution module and an output module. The space attention module based on graph transformation is composed of a space attention mechanism module with a sparse matrix and a graph transformation module. Different multi-graph adjacency matrixes are constructed through a graph transformation module so as to capture the intrinsic characteristics of the traffic flow. The time convolution module is used for capturing time characteristics of traffic data flow, and the time convolution module is composed of a time gating convolution module and a time attention mechanism module. The output module is composed of two Relu modules and two linear modules, and a mean absolute error is used as a loss function. According to the method, multiple graphs are constructed through graph transformation to process the traffic flow data influenced by multiple factors, so that the internal characteristics of the traffic data are captured, and the traffic prediction is more accurate.

    本发明公开了基于图变换的动态多图卷积网络交通流量预测方法,所依托的交通预测模型主要由四个模块组成:基于图变换的空间注意力模块、动态多图卷积模块、时间卷积模块和输出模块。基于图变换的空间注意力模块,由有稀疏矩阵的空间注意力机制模块和图变换模块组成。通过图变换模块构建不同的多图邻接矩阵从而捕获交通流的内在特性。时间卷积模块为了捕获交通数据流的时间特性,时间卷积模块由时间门控卷积和时间注意力机制两个模块组成。输出模块由两个Relu模块和两个线性模块组成,使用平均绝对误差为损失函数。本方法通过图变换构建多图以处理受多因素影响的交通流量数据,从而捕获交通数据的内在特性,使得交通预测更准确。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

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


    Weitere Titelangaben:

    基于图变换的动态多图卷积网络交通流量预测方法


    Beteiligte:
    HU YONGLI (Autor:in) / PENG TING (Autor:in) / GUO KAN (Autor:in) / SUN YANFENG (Autor:in) / YIN BAOCAI (Autor:in)

    Erscheinungsdatum :

    2022-01-14


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    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

    Temporal Multi-Graph Convolutional Network for Traffic Flow Prediction

    Lv, Mingqi / Hong, Zhaoxiong / Chen, Ling et al. | IEEE | 2021


    Multi-scale traffic flow prediction method based on graph convolutional neural network

    ZHANG MEIYUE / WANG SENZHANG / MIAO HAO et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    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

    POI-based double-layer graph convolutional network traffic prediction method

    SU LI / ZHAO XINHAO / WU ZHE et al. | Europäisches Patentamt | 2023

    Freier Zugriff