The invention discloses a traffic accident prediction method based on a graph convolutional network, and belongs to the technical field of traffic prediction, and the method comprises the steps: obtaining accident data information of a prediction region in historical time; dividing the prediction area into traffic cells, taking the traffic cells as nodes of the graph convolutional network, and constructing and obtaining an adjacent matrix of the graph convolutional network; according to the accident data information, constructing and obtaining a spatial feature vector, a time feature vector and a spatial-temporal feature vector; performing traffic accident prediction on the prediction area by using a pre-constructed deep learning model based on a graph convolutional network, and training the deep learning model according to the nodes, the adjacent matrix, the spatial feature vector, the time feature vector and the spatial-temporal feature vector to obtain a traffic accident prediction model; and obtaining a traffic accident occurrence probability prediction result by using the traffic accident prediction model. According to the method, the non-Euclidean structure influence factors of the traffic accident can be fully excavated, and the occurrence probability of the traffic accident can be predicted more effectively and accurately.

    本发明公开了一种基于图卷积网络的交通事故预测方法,属于交通预测技术领域,方法包括:获取预测区域历史时间内的事故数据信息;将预测区域划分为交通小区,并将交通小区作为图卷积网络的节点,构建获取图卷积网络的邻接矩阵;根据事故数据信息,构建获取空间特征向量、时间特征向量和时空特征向量;利用预构建的基于图卷积网络的深度学习模型对预测区域进行交通事故预测,并根据节点和邻接矩阵,以及空间特征向量、时间特征向量和时空特征向量,对深度学习模型进行训练,获取交通事故预测模型;利用交通事故预测模型,获取交通事故发生概率预测结果。该方法能够充分挖掘交通事故的非欧几里得结构影响因素,对交通事故发生概率进行更加有效、准确的预测。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic accident prediction method based on graph convolutional network


    Weitere Titelangaben:

    一种基于图卷积网络的交通事故预测方法


    Beteiligte:
    YANG QIAO (Autor:in) / LI RUI (Autor:in) / QI TIANJING (Autor:in)

    Erscheinungsdatum :

    2023-08-22


    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



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

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

    Freier Zugriff

    MG-TAR: Multi-View Graph Convolutional Networks for Traffic Accident Risk Prediction

    Trirat, Patara / Yoon, Susik / Lee, Jae-Gil | IEEE | 2023


    Traffic jam prediction method based on tense graph convolutional neural network

    ZHANG HAO / ZHANG GE / HUA QIFAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method based on adaptive graph fusion convolutional network

    XU YAN / LU YU / ZHANG QIYUAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    A model of traffic accident prediction based on convolutional neural network

    Wenqi, Lu / Dongyu, Luo / Menghua, Yan | IEEE | 2017