The invention discloses a traffic flow prediction model considering a dynamic space relation, and belongs to the field of intelligent traffic. According to the method, the dynamic space relation of the traffic network is not directly calculated, the method for efficiently and simply calculating the dynamic space relation of the traffic network is designed, real-time traffic flow information is converted into the dynamic space relation of the traffic network through a time-space conversion module, an auto-encoder and a graph normalization module, the dynamic space relation is recorded as a time-varying space graph, and the dynamic space relation of the traffic network is calculated through the time-varying space graph. The method truly reflects the time-varying characteristics of the dynamic space relationship of the traffic network, and then carries out the spatial-temporal feature extraction of the traffic flow data according to a time-varying space diagram and a stable space diagram based on the node position of the traffic network, and carries out the fusion of the spatial-temporal features, thereby obtaining the spatial-temporal fusion characteristics of the traffic flow. The characteristic reflects the stable spatial-temporal characteristic of the traffic flow and also reflects the dynamic spatial-temporal characteristic of the traffic flow, so that the traffic flow prediction can be realized more accurately.

    本发明公开了一种考虑动态空间关系的交通流预测模型,属于智能交通领域。本发明并没有直接计算交通网络的动态空间关系,而是设计了一种高效、简便地计算交通网络动态空间关系的方法,该方法通过时空转换模块、自编码器、图归一化模块,将实时的交通流信息转化为交通网络的动态空间关系,记为时变空间图,其真正意义上反映了交通网络动态空间关系的时变特性,然后分别根据时变空间图和基于交通网络节点位置的稳定的空间图对交通流数据进行时空特征提取并进行融合得到交通流的时空融合特征,该特征既反映了交通流的稳定时空特征也反映了交通流的动态时空特征,因而能够更加精准地实现交通流预测。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method considering dynamic space relationship


    Weitere Titelangaben:

    一种考虑动态空间关系的交通流预测方法


    Beteiligte:
    ZENG WEI (Autor:in) / ZHAO ZHENXING (Autor:in) / TANG CHENJIA (Autor:in)

    Erscheinungsdatum :

    2023-03-24


    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 flow prediction method considering space-time similarity

    ZHENG JIAJIA / CHEN CONG | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method based on air traffic space-time dynamic graph

    CAI KAIQUAN / YANG YANG / ZHU JIALE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Electric vehicle energy consumption prediction method considering dynamic road network traffic flow

    LI LEI / LIU WEIDONG / LI XIAOHUI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Traffic flow prediction method based on dynamic space-time correlation

    ZHANG XU / ZHANG LANGWEN / XIE WEI et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Traffic flow prediction method based on graph space-time Transform model considering human mobility

    KONG XIANGJIE / ZHAO ZHENZHEN / SHEN GUOJIANG et al. | Europäisches Patentamt | 2022

    Freier Zugriff