Network intrusion behavior feature selection method and device and storage medium

The invention discloses a network intrusion behavior feature selection method and device and a storage medium, and aims to solve the technical problems of single feature selection result, inaccuracy and the like of network intrusion behaviors in the prior art. The method comprises the following steps: acquiring an original feature set of network intrusion behaviors; sorting the features in the original feature set based on the mutual information to obtain a first feature subset; processing the original feature set by using an artificial bee colony algorithm, and performing feature screening to obtain a second feature subset; performing feature combination according to the first feature subset and the second feature subset to obtain a feature selection subset; and obtaining feature classification accuracy by utilizing an SVM classifier, and circulating the operation according to the feature classification accuracy to obtain an optimal feature selection subset. According to the method, the high-quality feature