Title:
SPATIO-TEMPORAL SENSING INFORMATION PREDICTION METHOD AND SYSTEM BASED ON GRAPH NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2024/031763
Kind Code:
A1
Abstract:
Disclosed in the present invention are a spatio-temporal sensing information prediction method and system based on a graph neural network. The method comprises the following steps: step S1, constructing a sensing data monitoring network, and acquiring original sensing data by means of data collection nodes in the sensing data monitoring network; step S2, preprocessing the original sensing data and converting same into spatio-temporal graph sensing data; step S3, constructing a graph neural network model, and training parameters of the graph neural network model by using the spatio-temporal graph sensing data; and step S4, inputting the given spatio-temporal graph sensing data into the trained graph neural network model, outputting a predicted value, and sending early warning information when the predicted value exceeds a preset threshold value. In the present invention, the original sensing data is converted into the spatio-temporal graph sensing data, and the graph neural network model is used to fully mine spatio-temporal features from the sensing data, such that spatio-temporal feature information is obtained, and thus the accuracy of predicting spatio-temporal feature information of things in the future is improved.
Inventors:
CHEN HONGYANG (CN)
HU BINGYANG (CN)
QI QINGGUO (CN)
LI ZHAO (CN)
HU BINGYANG (CN)
QI QINGGUO (CN)
LI ZHAO (CN)
Application Number:
PCT/CN2022/117196
Publication Date:
February 15, 2024
Filing Date:
September 06, 2022
Export Citation:
Assignee:
ZHEJIANG LAB (CN)
International Classes:
G06N3/08; G06N3/04; G06Q10/04
Domestic Patent References:
| WO2022142418A1 | 2022-07-07 |
Foreign References:
| CN114120652A | 2022-03-01 | |||
| CN113919231A | 2022-01-11 | |||
| CN112784121A | 2021-05-11 |
Other References:
BING YU; HAOTENG YIN; ZHANXING ZHU: "Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 12 July 2018 (2018-07-12), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081327216, DOI: 10.24963/ijcai.2018/505
Attorney, Agent or Firm:
BEIJING ZHILIN HENGYUAN INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: