The invention belongs to the field of intelligent traffic, and particularly relates to an adaptive space-time diagram neural network traffic flow prediction method and system based on Transform, and the method comprises the steps: obtaining historical data, and splicing the historical data as input data; expressing the input data by using vectors, and obtaining an adjacent matrix and a traffic flow feature matrix which represent road network spatial features; according to the connectivity of the road network and the node feature matrix, extracting the temporal correlation of the nodes and the spatial-temporal correlation among different nodes to obtain a first traffic flow feature matrix, and according to the hidden spatial correlation in the road network structure, obtaining a second traffic flow feature matrix; fusing the first traffic flow feature matrix and the second traffic flow feature matrix to obtain a final traffic flow feature, and inputting the feature into a prediction model for prediction to obtain a prediction result; the long-time traffic flow prediction method has a good prediction effect on the long-time traffic flow under the condition of complex traffic.

    本发明属于智能交通领域,具体涉及一种基于Transformer的自适应时空图神经网络交通流预测方法及系统,方法包括获取历史数据,将历史数据拼接后作为输入数据;将输入数据使用向量进行表示,并获取表征路网空间特征的邻接矩阵和交通流特征矩阵;根据路网的连通性和节点特征矩阵,提取节点自身的时间相关性、不同节点间之间的时空相关性获得第一交通流特征矩阵,并根据路网结构中的隐藏的空间相关性,获得第二交通流特征矩阵;将第一交通流特征矩阵与第二交通流特征矩阵进行融合,得到最终的交通流特征,将该特征输入预测模型进行预测得到预测结果;本发明在复杂交通的状况下对较长时交通流具有良好的预测效果。


    Access

    Download


    Export, share and cite



    Title :

    Transform-based adaptive space-time diagram neural network traffic flow prediction method and system


    Additional title:

    一种基于Transformer的自适应时空图神经网络交通流预测方法及系统


    Contributors:
    WANG RONG (author) / ZHAO JIANKUAN (author) / LI MIAOFEI (author) / JIANG JIANCHUN (author) / ZHAO WEIFENG (author)

    Publication date :

    2022-05-13


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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 / G06K Erkennen von Daten , RECOGNITION OF DATA / 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 Transform space-time diagram convolutional network

    ZHENG LINJIANG / CHEN YILING / LIU WEINING et al. | European Patent Office | 2022

    Free access

    Traffic flow prediction method and system based on space-time diagram convolutional neural network

    WU JIANQING / XU YE / HUO YANQIANG et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on space-time diagram wavelet convolutional neural network

    MAO GUOJUN / ZHAO SHIHAO / WANG XIANG | European Patent Office | 2022

    Free access

    Ship traffic flow prediction method based on improved space-time diagram attention neural network

    JIANG BAODE / LUO HAIYAN / SONG YUWEI | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on space-time diagram convolutional network

    JIANG CONG / SONG YUN / DENG ZELIN et al. | European Patent Office | 2023

    Free access