The invention discloses an attention-based dynamic space-time diagram convolution traffic flow prediction system and method, and relates to the field of intelligent traffic, and the system comprises an input layer, n space-time layers which are connected in sequence, and an output layer. Wherein the input layer receives input data and is connected with the first space-time layer, and the input layer performs data preprocessing and inputs the data into the first space-time layer for training; the output layer is connected with the nth space-time layer and outputs prediction data; each time-space layer comprises a multi-granularity trend self-attention module, a semantic adaptive graph convolution module and a gating time convolution module. The method comprises the following steps of: 1, preprocessing input data by an input layer; 2, the space-time layers receive input data, and a training result is formed after the input data are processed by a plurality of space-time layers; each time-space layer comprises a multi-granularity trend self-attention module, a semantic adaptive graph convolution module and a gating time convolution module; and step 3, the output layer converts the training result into prediction data and outputs the prediction data.

    本发明公开了一种基于注意力的动态时空图卷积交通流预测系统与方法,涉及智能交通领域,所述系统包括:1个输入层、依次连接的n个时空层和1个输出层;其中,输入层接收输入数据并与第1个时空层连接,输入层进行数据预处理,并输入到第1个时空层中进行训练;输出层与第n个时空层连接并输出预测数据;每个时空层包括:多粒度趋势自注意力模块、语义自适应图卷积模块和门控时间卷积模块。所述方法包括:步骤1、输入层预处理输入数据;步骤2、时空层接收输入数据,经过若干个时空层处理后形成训练结果;每个时空层包括:多粒度趋势自注意力模块、语义自适应图卷积模块和门控时间卷积模块;步骤3、输出层将训练结果转换为预测数据并输出。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Attention-based dynamic space-time diagram convolution traffic flow prediction system and method


    Weitere Titelangaben:

    一种基于注意力的动态时空图卷积交通流预测系统与方法


    Beteiligte:
    JI ZHENYUAN (Autor:in) / HUAN YUEHUI (Autor:in) / YANG GENKE (Autor:in) / CHU JIAN (Autor:in) / WANG HONGWU (Autor:in)

    Erscheinungsdatum :

    2023-11-14


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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 prediction method and device based on dynamic space-time diagram convolution attention model

    ZHANG TINGTING / LI RUI | Europäisches Patentamt | 2021

    Freier Zugriff

    Traffic prediction method based on dual dynamic space-time diagram convolution

    SUN YANFENG / JIANG XIANGHENG / HU YONGLI et al. | Europäisches Patentamt | 2022

    Freier Zugriff

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

    SUN YONG / ZHANG ANQIN / CHEN JINGJING | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method of attention-based deep residual space-time diagram convolutional network

    XU SHIJIAN / ZHANG XUHONG / WU YUEDONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method of space-time convolution fusion probability sparse attention mechanism

    ZHANG HONG / CHEN LINBIAO / CHEN LINLONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff