The invention provides a knowledge-driven traffic prediction method based on a knowledge representation model and a graph neural network, and the method comprises the steps: carrying out the preprocessing of collected traffic data, and constructing a traffic network topological graph according to the position of a sensor node; entities and relationships in a knowledge graph in a traffic network topological graph are converted into low-dimensional vectors, and external factors and traffic features are adaptively and dynamically fused and updated through a gating feature fusion module according to the importance of the external factors; inputting the updated traffic features and the adjacent matrix into a graph convolution GCN; through expansion causal convolution of a space-time joint capture module, traffic characteristics on a time level and a space level are jointly captured to generate a prediction speed; and training a traffic prediction model according to the loss function, and testing to obtain a predicted traffic speed. According to the importance of external factors, the traffic characteristics are adaptively fused and dynamically updated, so that the change of the traffic characteristics is better reflected, and the accuracy of the prediction model is improved.

    本发明提出了一种基于知识表示模型和图神经网络的知识驱动交通预测方法,步骤为:对采集到的交通数据进行预处理,根据传感器节点的位置构建交通路网拓扑图;将交通路网拓扑图中知识图谱中的实体和关系转换为低维向量,通过门控特征融合模块根据外部因素的重要性自适应且动态地将外部因素与交通特征进行融合并更新;将更新后的交通特征和邻接矩阵输入图卷积GCN;通过时空联合捕捉模块的扩张因果卷积对时间级与空间级上的交通特征联合捕捉生成预测速度;根据损失函数训练交通预测模型,进行测试得到预测的交通速度。本发明根据外部因素的重要性,自适应地对交通特征进行融合并动态更新,从而更好地反映交通特征的变化,提高了预测模型的准确性。


    Access

    Download


    Export, share and cite



    Title :

    Knowledge-driven traffic prediction method based on knowledge representation model and graph neural network


    Additional title:

    基于知识表示模型和图神经网络的知识驱动交通预测方法


    Contributors:
    ZHOU YI (author) / LIU YIHAN (author) / NING NIANWEN (author) / LYU YINING (author) / SHI HUAGUANG (author) / ZHANG YANYU (author)

    Publication date :

    2023-11-24


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES



    Metro Traffic Flow Prediction via Knowledge Graph and Spatiotemporal Graph Neural Network

    Shun Wang / Yimei Lv / Yuan Peng et al. | DOAJ | 2022

    Free access

    Traffic flow prediction method based on graph neural network and distribution representation matching

    XIE ZONGXIA / WANG JIAYI | European Patent Office | 2024

    Free access

    Traffic prediction method based on graph neural network

    XUE QINGYAO / WANG BONING / LIU YUFENG et al. | European Patent Office | 2024

    Free access


    Traffic flow prediction method based on future knowledge differential transformation neural network

    XIA DAWEN / BAI DEWEI / LI HUAQING et al. | European Patent Office | 2024

    Free access