The invention relates to a traffic flow prediction technology, and discloses a traffic volume prediction method based on a lightweight space-time diagram convolution model, and the method comprises the steps: constructing a traffic space-time network structure diagram according to a road sensor and a road network relation; collecting traffic flow data characteristics by using the traffic space-time network structure chart to obtain time sequence data, and generating a traffic flow network sequence according to the time sequence data and the traffic flow data characteristics; extracting traffic flow spatial features of the traffic flow network sequence, and extracting traffic flow time features of the traffic flow network sequence according to the traffic flow exogenous factors; training the space-time diagram convolution model by using the traffic flow spatial features and the traffic flow time features to obtain a road network traffic volume prediction model; and predicting the road network traffic volume of the target region according to the road network traffic volume prediction model. The invention further provides a device for predicting the traffic volume based on the lightweight space-time diagram convolution model. The accuracy of road network traffic volume prediction can be improved.

    本发明涉及交通流预测技术,揭露了一种基于轻量级的时空图卷积模型对交通量的预测方法,包括:根据道路传感器及路网关系构建交通时空网络结构图;利用交通时空网络结构图对交通流数据特征进行采集,得到时间序列数据,根据时间序列数据及交通流数据特征生成交通流量网络序列;提取交通流量网络序列的交通流空间特征,根据交通流外源因素提取交通流量网络序列的交通流时间特征;利用交通流空间特征及交通流时间特征对时空图卷积模型进行训练,得到路网交通量预测模型;根据路网交通量预测模型对目标地区的路网交通量进行预测。本发明还提出一种基于轻量级的时空图卷积模型对交通量的预测装置。本发明可以提高路网交通量预测的准确度。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic volume prediction method and device based on lightweight space-time diagram convolution model


    Weitere Titelangaben:

    基于轻量级的时空图卷积模型对交通量的预测方法及装置


    Beteiligte:
    LI JIA (Autor:in)

    Erscheinungsdatum :

    2023-06-02


    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



    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

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

    JI ZHENYUAN / HUAN YUEHUI / YANG GENKE et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method based on adaptive lightweight time convolution network

    ZHANG SHUAI / YIN XIANG / ZHANG WENYU et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Traffic flow prediction method and system based on trend space-time diagram convolution, and medium

    ZONG XINLU / YU FAN / WANG CHUNZHI et al. | Europäisches Patentamt | 2023

    Freier Zugriff