The invention discloses a traffic flow prediction method based on a self-attention mechanism and a cyclic graph convolution network, relates to the technical field of deep learning and spatio-temporal data mining, and utilizes a GRU calculation structure with graph convolution and the self-attention mechanism to construct a calculation unit ADD-GCGRU. The calculation unit ADD-GCGRU is integrated into a long sequence loop structure to form a stacked coding-decoding structure, so that the purpose of extracting spatial features and time features is achieved, decomposition incremental output is carried out by introducing uncertainty margin, dual data mining of numerical values and directions is achieved, the offset degree in a prediction result is weakened, and the prediction efficiency is improved. And finally, constructing a new evaluation index to evaluate the deviation degree of the prediction structure. According to the method, high prediction precision is guaranteed, the offset problem in time sequence prediction of traffic flow and the like is relieved, and the offset degree is evaluated.

    本发明公开了基于自注意力机制和循环图卷积网络的交通流预测方法,涉及深度学习和时空数据挖掘的技术领域,利用了带有图卷积的GRU计算结构及自注意力机制构建计算单元ADD‑GCGRU,并将该计算单元ADD‑GCGRU融入长序列循环结构形成堆叠式编码‑解码结构,以此达到空间特征和时间特征的提取目的,并通过引入不确定度余量进行分解增量式输出,实现数值和方向的双重数据挖掘,削弱预测结果中的偏移程度,最后构建一种新的评价指标对预测结构的偏移程度进行评价。本发明在保证预测高精度的同时,缓解了交通流等时序预测中的偏移问题,并对偏移程度进行了评价。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method based on self-attention mechanism and cyclic graph convolutional network


    Weitere Titelangaben:

    基于自注意力机制和循环图卷积网络的交通流预测方法


    Beteiligte:
    MENG XIANWEI (Autor:in) / LU YIXING (Autor:in) / JIA LIN (Autor:in)

    Erscheinungsdatum :

    2023-04-18


    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 based on cyclic attention coupled graph convolutional network

    CHEN LING / CHEN WEIQI | Europäisches Patentamt | 2020

    Freier Zugriff

    Traffic flow prediction method based on time attention circulation graph convolutional neural network

    FAN WENDONG / SHU MIN / SONG YUN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic Flow Forecasting of Graph Convolutional Network Based on Spatio-Temporal Attention Mechanism

    Zhang, Hong / Chen, Linlong / Cao, Jie et al. | Springer Verlag | 2023


    Graph Attention Convolutional Network: Spatiotemporal Modeling for Urban Traffic Prediction

    Song, Qingyu / Ming, RuiBo / Hu, Jianming et al. | IEEE | 2020


    Traffic flow prediction method and system of attention time-space synchronization graph convolutional network

    XIA DAWEN / WEI XIAODUO / LI HUAQING et al. | Europäisches Patentamt | 2023

    Freier Zugriff