The invention discloses an air route network flow prediction method based on spatio-temporal feature fusion in the technical field of air route network flow prediction, and aims to solve the problems that in the prior art, air route network flow prediction mainly focuses on short-term prediction, and research on traffic flow prediction considering a spatial relationship is less. The method comprises the following steps: extracting a spatial topological structure of an air route network, and constructing an adjacent matrix and a traffic matrix; constructing a GCN model and an LSTM model, and respectively extracting and outputting time features and space features of the air route network traffic; constructing a GCN-LSTM model, and fusing the spatial features output by the GCN model and the time features output by the LSTM model; and training the GCN-LSTM model through the flow data, inputting the time sequence data into the trained GCN-LSTM model, predicting a target value, and outputting a prediction result. The method can fully extract the time characteristics and the space characteristics of the air route network flow, and improves the prediction precision.

    本发明公开了一种航路网络流量预测技术领域的基于时空特征融合的航路网络流量预测方法,旨在解决现有技术中对航路网络流量预测主要集中于短时预测,考虑空间关系的交通流量预测的研究较少等问题,其包括提取航路网络的空间拓扑结构,构建邻接矩阵、流量矩阵;构建GCN模型和LSTM模型,分别对航路网络流量的时间特征和空间特征进行提取并输出;构建GCN‑LSTM模型,将GCN模型输出的空间特征和LSTM模型输出的时间特征融合;通过流量数据对GCN‑LSTM模型进行训练,将时间序列数据输入训练好的GCN‑LSTM模型,对目标值进行预测,输出预测结果。本发明可以充分提取航路网络流量的时间特征和空间特征,提升预测精度。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Air route network flow prediction method based on spatio-temporal feature fusion


    Weitere Titelangaben:

    一种基于时空特征融合的航路网络流量预测方法


    Beteiligte:
    NIU KEXIN (Autor:in) / LI GUIFANG (Autor:in) / WAN LILI (Autor:in) / HUANG XIAO (Autor:in) / DONG XINGCHEN (Autor:in) / MENG XIAN (Autor:in) / CHENG LUYANG (Autor:in) / LI QIANQIAN (Autor:in) / TIAN YONG (Autor:in)

    Erscheinungsdatum :

    2023-11-14


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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




    Traffic flow prediction method based on spatio-temporal information fusion and storage medium

    ZOU TINGTING / LYU WENXIU / LIU XIANGYU | Europäisches Patentamt | 2024

    Freier Zugriff

    Global spatio‐temporal dynamic capturing network‐based traffic flow prediction

    Haoran Sun / Yanling Wei / Xueliang Huang et al. | DOAJ | 2023

    Freier Zugriff

    Global spatio‐temporal dynamic capturing network‐based traffic flow prediction

    Sun, Haoran / Wei, Yanling / Huang, Xueliang et al. | Wiley | 2023

    Freier Zugriff

    Urban traffic prediction method and system based on spatio-temporal data flow fusion analysis

    REN MINGLUN / HUANG XIAODI / CHU WEI et al. | Europäisches Patentamt | 2020

    Freier Zugriff