The invention discloses a traffic flow prediction method based on an interactive adaptive space-time diagram convolutional network, and the method comprises the following steps: collecting road network information, obtaining original data, and carrying out the normalization of the original data; constructing a convolutional network based on an interactive adaptive space-time diagram, wherein the network structure is composed of a node relevancy estimator module, a time residual learner module and a gating diagram convolutional fusion module; the node relevancy estimator module learns the dynamic space-time relevancy between the nodes by using the matrix dot product after linear transformation and the multi-head self-attention mechanism; the time residual learner module learns long sequence information in traffic data, and the gating chart convolution fusion module effectively learns spatial information in the traffic data. According to the method, the linear dot product and the multi-head self-attention mechanism are introduced to enhance the potential dynamic spatial-temporal correlation in the data, the time residual learning device module and the gated graph convolution fusion are utilized to realize the extraction of the dynamic multi-graph spatial-temporal characteristics of the traffic flow, and the traffic flow prediction precision is further improved.

    本发明公开一种基于交互自适应时空图卷积网络的交通流预测方法,包括以下步骤:采集路网信息得到原始数据,并归一化;构造种基于交互自适应时空图卷积网络,网络结构由节点相关度估计器模块、时间残差学习器模块和门控图卷积融合模块组成;节点相关度估计器模块利用线性变换后的矩阵点积和多头自注意力机制学习节点之间的动态时空相关性;时间残差学习器模块学习交通数据中的长序列信息,利用门控图卷积融合模块有效学习交通数据中的空间信息。本发明通过引入线性点积和多头自注意力机制来增强数据中潜在的动态时空相关性,利用时间残差学习器模块和门控图卷积融合实现交通流动态多图时空特征的提取,实现交通流预测精度的进一步提高。


    Access

    Download


    Export, share and cite



    Title :

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


    Additional title:

    一种基于交互自适应时空图卷积网络的交通流预测方法


    Contributors:
    SHI QUAN (author) / CAO CHENYANG (author) / BAO YINXIN (author) / SHEN QINQIN (author) / CAO YANG (author)

    Publication date :

    2024-08-30


    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



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

    JIANG YUNLIANG / XIA RENHUAN / ZHANG XIONGTAO et al. | European Patent Office | 2022

    Free access

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

    JIANG CONG / SONG YUN / DENG ZELIN et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method of space-time diagram convolutional network

    TENG FEI / WANG ZIDAN / QIAO LU et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction method based on interactive dynamic diffusion diagram convolutional network

    ZHANG SHUAI / YU WANGZHI / PENG QIFAN et al. | European Patent Office | 2024

    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