The invention provides a traffic flow prediction method and system based on an NCCform model, and belongs to the technical field of computers, and the method comprises the steps: obtaining a two-dimensional matrix through carrying out the segmented embedding of a single-dimensional sequence segment of multi-dimensional time series data; inputting the two-dimensional matrix into a dual-stage attention layer to obtain a node embedding matrix and a graph adjacency matrix; updating the node embedding of each layer by using the node embedding matrix and the graph adjacency matrix through a kernel function-based full-pair message passing mode, and obtaining the output of full-pair message passing; and performing hierarchical prediction by using a preset hierarchical encoder-decoder to obtain a prediction result of each layer, and obtaining a traffic flow prediction result based on the prediction result of each layer. According to the method, the technical effects of reducing information loss, eliminating noise generated when a high-dimensional data set is processed to a certain extent and improving the accuracy of traffic flow prediction are achieved through a new all-pair message passing scheme.

    本发明提供一种基于NCCformer模型的交通流量预测方法及系统,属于计算机技术领域,通过对多维时序数据进行单个维度的序列段的分段嵌入获得二维矩阵;将二维矩阵输入双阶段注意层,获得节点嵌入矩阵和图邻接矩阵;将节点嵌入矩阵和图邻接矩阵通过基于核函数的全对消息传递的方式对每层的节点嵌入进行更新,并获得全对消息传递的输出;利用预设的分层编码器‑解码器进行分层预测获得各层预测结果,基于各层预测结果获得交通流量预测结果。本发明通过一种新的全对消息传递方案实现了减少信息损失,在一定程度上消除处理高维数据集时产生的噪声,同时提高了交通流量预测的准确度的技术效果。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method and system based on NCCformer model


    Weitere Titelangaben:

    基于NCCformer模型的交通流量预测方法及系统


    Beteiligte:
    MEI HONGYAN (Autor:in) / ZHAI XINCHEN (Autor:in) / ZHAO QIN (Autor:in) / WANG XINKE (Autor:in)

    Erscheinungsdatum :

    17.09.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    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 / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    STNR model-based traffic flow prediction method and system

    LIM CHANG-JUNG / HAN MENG / DAI QIANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    TRAFFIC FLOW PREDICTION SYSTEM, TRAFFIC FLOW PREDICTION METHOD, AND PROGRAM

    MATSUDAIRA MASAKI / OKANO KENGO | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction model construction method, traffic flow prediction model use method and electronic equipment

    CHEN KEN / TANG YONG / ZHANG SHENG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction model training method, traffic flow prediction method, device and equipment

    GU JUNHUA / CHEN CHEN / LEI WEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    TRAFFIC FLOW PREDICTION DEVICE AND TRAFFIC FLOW PREDICTION SYSTEM

    OKUDE MARIKO / NAGAI TORU / SAKAMOTO TOSHIYUKI et al. | Europäisches Patentamt | 2019

    Freier Zugriff