Host cardinal number estimation method based on artificial neural network

• Main Authors: LIU JIAYIN, XU JIE, ZHUGE CHENGCHEN, JU AO, XIA LINGLING, WANG QUN, LIANG GUANGJUN, ZHANG YUJIAN, NI XUELI, MA RUPO, GUO XIANGMIN, YIN JIE, LAN HAOLIANG
• Format: Patent
• Language: Chinese; English
• Published: 18.01.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention discloses a host cardinal number estimation method based on an artificial neural network, and the method comprises the following steps: (1) scanning IP addresses in all IP messages in a time window, and estimating the cardinal number of each host in an internal network; (2) sorting and grouping each host, and grouping to construct a sampling host set; (3) constructing a training attribute set trainX and a cardinal number estimation deviation set trainY of each sampling host; (4) training an artificial neural network by using the sets trainX and trainY; and (5) predicting an intranet host cardinal number estimation error according to the trained artificial neural network, and adjusting a host cardinal number estimation value. According to the method, a sampling IP sequence is constructed, then data used during host cardinal number estimation and a cardinal number estimated value serve as attributes used during cardinal number correction, the relation between the cardinal number estimated value an