The invention relates to an urban traffic flow space-time prediction scheme based on a graph convolutional neural network. The urban traffic flow space-time prediction scheme comprises the following steps of obtaining an urban road network topological structure graph and historical flow data, constructing and training an ST-GCN network model, predicting to obtain predicted flow of all A-type intersections, obtaining predicted flow of all B-type intersections by using an Adagent algorithm, obtaining predicted flow of all the C-type intersections by using an Adject algorithm, then, using a Similar algorithm for obtaining the predicted flow of the D-type intersection, and finally outputting the predicted flow of all intersections. Compared with the prior art, the scheme has the advantages that the predicted flow of the intersection with historical flow data is obtained by constructing and training the ST-GCN network model, the predicted flow of the intersection without historical flow data is obtained according to the predicted flow of the adjacent intersection through the Adjent-Similar algorithm, and as for 'isolated island' intersections,similar intersections are searched, the predicted flow of the similar intersection is used as the predicted flow of the intersection, so that a new solution is provided for flow prediction of intersections without historical flow data.

    本发明涉及一种基于图卷积神经网络的城市交通流量时空预测方案,包括以下步骤:获取城市路网拓扑结构图和历史流量数据;构建并训练ST‑GCN网络模型;预测得到所有A类路口的预测流量;使用Adjacent算法得到所有B类路口的预测流量;使用Adjacent算法得到所有C类路口的预测流量;再使用Similar算法得到D类路口的预测流量;最后输出所有路口的预测流量。与现有技术相比,本发明首先通过构建和训练ST‑GCN网络模型,得到有历史流量数据路口的预测流量,再通过Adjacent‑Similar算法,对于无历史流量数据的路口,根据其相邻路口的预测流量得到其预测流量,对于“孤岛”路口,寻找其相似路口并用相似路口的预测流量作为该路口的预测流量,为无历史流量数据路口的流量预测提供了新的解决思路。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Urban traffic flow space-time prediction scheme based on graph convolutional neural network


    Weitere Titelangaben:

    一种基于图卷积神经网络的城市交通流量时空预测方案


    Beteiligte:
    ZHANG RONGQING (Autor:in) / WANG HANQIU (Autor:in) / LI BING (Autor:in)

    Erscheinungsdatum :

    2021-03-12


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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



    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


    Topological Graph Convolutional Network-Based Urban Traffic Flow and Density Prediction

    Qiu, Han / Zheng, Qinkai / Msahli, Mounira et al. | IEEE | 2021


    Traffic flow prediction method based on time attention circulation graph convolutional neural network

    FAN WENDONG / SHU MIN / SONG YUN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Space-time normalized graph convolutional neural network traffic flow prediction method and system, and medium

    WANG CHUNZHI / WANG LU / YAN LINGYU et al. | Europäisches Patentamt | 2024

    Freier Zugriff