A flow anomaly detection method, device and computer readable storage medium

Abstract

The application provides a traffic anomaly detection method, device and computer readable storage medium, the method comprising the following steps: performing word segmentation extraction on to-be-detected traffic data, obtaining a to-be-detected word segmentation set, generating a word segmentation frequency set according to the to-be-detected word segmentation set, calculating a multi-dimensional feature value of the to-be-detected traffic data according to the word segmentation frequency set, calculating an anomaly degree of the to-be-detected traffic data according to the multi-dimensional feature value of the to-be-detected traffic data, and then determining whether the to-be-detected traffic data is abnormal according to the anomaly degree of the to-be-detected traffic data, so that the detection efficiency and simplicity of network abnormal traffic data are improved without using a machine learning algorithm to train a model for detection.

Images