The invention belongs to the technical field of traffic flow prediction, and discloses a traffic flow prediction method and system based on trend space-time diagram convolution, and a medium, firstly, an encoder combines time self-attention and causal convolution, and captures long-term and short-term trend time dependence of traffic flow; capturing local spatial correlation and dynamic spatial-temporal correlation through fusion of a graph convolutional network and a gated recurrent neural network; secondly, simulating space-time heterogeneity through a space-time interaction module based on time and space characteristics extracted by an encoder; the decoder and the encoder are used for learning spatial-temporal characteristics of traffic flow; and finally, on the basis of spatial-temporal characteristics extracted by a coder-decoder, the influence of historical traffic flow on future prediction is fitted by utilizing time coding and decoding attention, so that the performance problem of a traffic flow prediction model based on a Transform model is solved. Experiments are carried out on a data set in the real world, and a good experiment result is obtained.

    本发明属于交通流量预测技术领域,公开了一种基于趋势时空图卷积的交通流量预测方法、系统及介质,首先,编码器将时间自注意力和因果卷积相结合,捕获交通流量的长期和短期趋势时间依赖;再通过图卷积网络和门控循环神经网络融合,捕捉局部空间相关性和动态时空相关性;其次基于编码器提取的时间和空间特征,通过时空交互模块来模拟时空异质性;接着解码器与编码器类的是学习交通流量的时空特征;最后基于编码‑解码器提取到的时空特征,利用时间编码解码注意力来拟合历史交通流量对未来预测的影响,用来解决基于Transformer模型的交通流量预测模型的性能问题。本发明在真实世界的数据集上进行实验,取得了良好的实验结果。


    Access

    Download


    Export, share and cite



    Title :

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


    Additional title:

    一种基于趋势时空图卷积的交通流量预测方法、系统及介质


    Contributors:
    ZONG XINLU (author) / YU FAN (author) / WANG CHUNZHI (author) / YE ZHIWEI (author) / LIU WEI (author) / CHEN HONGWEI (author) / YAN LINGYU (author) / XU HUI (author)

    Publication date :

    2023-10-17


    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



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

    JI ZHENYUAN / HUAN YUEHUI / YANG GENKE et al. | European Patent Office | 2023

    Free access

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

    SUN YANFENG / JIANG XIANGHENG / HU YONGLI et al. | European Patent Office | 2022

    Free access


    Traffic prediction method and device based on dynamic space-time diagram convolution attention model

    ZHANG TINGTING / LI RUI | European Patent Office | 2021

    Free access

    Traffic flow prediction method based on space-time diagram transfer learning

    LI YUN / GAO YA / YAO ZHIXIU et al. | European Patent Office | 2023

    Free access