TRAINING A MACHINE LEARNING-BASED NETWORK TRAFFIC

专利名称：TRAINING A MACHINE LEARNING-BASED

NETWORK TRAFFIC ANALYZER USING APROTOTYPE DATASET

发明人：ANDERSON, Blake Harrell,McGREW, David申请号：EP18150071.1申请日：20180102公开号：EP3346667A1公开日：20180711

专利附图：

摘要：In embodiments, a device in a network generates a feature vector based ontraffic flow data regarding one or more traffic flows in the network. The device makes a

determination as to whether the generated feature vector is already represented in atraining dataset dictionary by one or more feature vectors in the dictionary. The deviceupdates the training dataset dictionary based on the determination by one of: adding thegenerated feature vector to the dictionary when the generated feature vector is notalready represented by one or more feature vectors in the dictionary, or incrementing acount associated with a particular feature vector in the dictionary when the generatedfeature vector is already represented by the particular feature vector in the dictionary.The device generates a training dataset based on the training dataset dictionary fortraining a machine learning-based traffic flow analyzer.

申请人：Cisco Technology, Inc.

地址：170 W. Tasman Drive San Jose, CA 95134-1706 US

国籍：US

代理机构：Clark, Jane Anne

更多信息请下载全文后查看