Internet of Things equipment behavior analysis method based on multi-flow perception

• Main Authors: LIN XIAOFENG, ZHANG HAOJIAN, ZHANG BIN, LI MING, LONG YANG, LI JIANWEI, ZHANG KAIYUE, LIU MING
• Format: Patent
• Language: Chinese; English
• Published: 02.04.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention relates to the technical field of Internet of Things equipment behavior analysis, and discloses a multi-traffic perception Internet of Things equipment behavior analysis method, which comprises the following steps: collecting Internet of Things network traffic of Internet of Things equipment under different behaviors, and carrying out multi-traffic feature importance evaluation; fusing the network traffic of the Internet of Things based on the important traffic features, and constructing a training data set; and performing behavior analysis on the Internet of Things network traffic fusion result of the Internet of Things equipment to be subjected to behavior analysis by using the solved model. According to the method, multiple traffic feature importance evaluation results of traffic features are obtained by adopting multiple different traffic feature importance calculation methods, and information loss is reduced and secondary feature information is inhibited by adding a window channel attention