Lightweight operating system identification method, system and equipment based on network flow

• Main Authors: CHEN SHUHUI, WANG FEI, ZHAO SHUANG, WEI ZILING, LI JINGZHI, YU WANRONG, ZHAO TAO
• Format: Patent
• Language: Chinese; English
• Published: 26.03.2024
• 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 a lightweight operating system identification method, system and equipment based on network flow, and the method achieves the rapid and accurate identification and output of the version information of an equipment operating system through employing a trained brand-new lightweight operating system identification model to carry out the identification processing of test data to be subjected to the identification of the operating system. Wherein the lightweight operating system identification model comprises main structures such as a convolutional layer, a pooling layer and a full connection layer, the convolutional layer is designed by using a Fire module proposed by a lightweight machine learning technology, and methods such as model pruning and data quantification are fused in research design; the lightweight operating system identification model is realized and fully adapts to public data sets and general flow data, high-order identification features are extracted from network flows f