The invention claims to protect a traffic flow prediction method based on a multi-graph convolutional network of aggregated space-time multi-dimensions, which comprises the following steps: respectively starting from a time dimension, a space dimension and a fused space-time dimension, mining dynamic space relevance, space-time synchronism, space-time heterogeneity and periodicity of traffic data, respectively constructing corresponding adaptive graph structures, and predicting the traffic flow based on the multi-graph convolutional network of aggregated space-time multi-dimensions. A space-time fusion graph structure and a mode similar graph structure are adopted, various space-time characteristics of traffic flow data are perfectly considered, and the problem that traffic data properties are not completely captured in current research is solved. The main innovation point of the invention is that a multi-graph aggregated network framework is provided based on the analysis of potential characteristics of traffic data, and comprises an adaptive graph which is not fixed to prior data and is generated through data self-learning, and a space-time fusion graph of which the space dimension is always changed under the influence of the time dimension; and a pattern similarity graph with periodicity and similarity. According to the invention, the prediction accuracy is improved.

    本发明请求保护一种基于聚合时空多维的多图卷积网络的交通流预测方法,分别从时间维度、空间维度和融合时空维度出发,挖掘交通数据的动态空间关联性,时空同步性和时空异质性,周期性,并分别构建相应的自适应图结构,时空融合图结构,模式相似图结构,完善考虑交通流数据的多种时空特征,解决当前研究中交通数据性质捕获不完全的问题。本发明主要创新点是基于对交通数据的潜在特征的分析,提出一种多图聚合的网络框架,分别包含不固定于先验数据,通过数据自学习生成的自适应图,空间维度受时间维度影响一直变化的时空融合图,以及存在周期性和相似性的模式相似图。本发明提高了预测的准确性。


    Access

    Download


    Export, share and cite



    Title :

    Improved traffic flow prediction method based on aggregated space-time multi-graph convolutional network


    Additional title:

    一种基于聚合时空多图卷积网络改进的交通流预测方法


    Contributors:
    WANG GAOPENG (author) / LUO JUAN (author)

    Publication date :

    2024-05-28


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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



    Urban traffic flow space-time prediction scheme based on graph convolutional neural network

    ZHANG RONGQING / WANG HANQIU / LI BING | European Patent Office | 2021

    Free access

    Traffic flow prediction method based on de-noising diffusion space-time residual multi-graph convolutional network

    SHI QUAN / BAO YINXIN / CAO CHENYANG et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction method of space-time attention graph convolutional network based on multi-feature fusion

    CHEN YAJUN / DING ZHIMING / GUO LIMIN | European Patent Office | 2023

    Free access

    Ship traffic flow prediction method based on improved graph convolutional neural network

    LIU WEN / ZHAN YANG / LIANG MAOHAN et al. | European Patent Office | 2022

    Free access

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

    SHI QUAN / DAI JUNMING / SHEN QINQIN et al. | European Patent Office | 2021

    Free access