Network attribute prediction method and system of industrial Internet of Things

• Main Authors: JIANG YIFAN, WANG TAO, LIU ZHAOWEI, WANG ZHANYU, GUO DEZHI, XU JINDONG, WANG HAIYANG
• Format: Patent
• Language: Chinese; English
• Published: 12.01.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention relates to the technical field of industrial Internet of Things, in particular to a network attribute prediction method and system of the industrial Internet of Things, which comprises the following steps: generating a network structure information graph of the industrial Internet of Things by taking each device in the industrial Internet of Things as a node of the graph and the connection between the devices as an edge of the graph, and forming graph data to be stored in corresponding branches; by applying the federated learning technology, after the local graph neural network model trained in each branch determines respective parameters, the parameters of the model in the current branch are updated by aggregating the model parameters of the other branches, so that only knowledge in the data is shared, and the data is not shared; and the clients corresponding to the branches can jointly train the global model under the condition of not sharing private data. 本发明涉及工业物联网技术领域，具体为工业物联网的网络属性预测方法及系统，以