Feature selection method and device, and network equipment identification method and device

The invention discloses a feature selection method and device and a network equipment identification method and device. The feature selection method comprises the steps of obtaining a target data set; under the condition that the target data set is a multi-classification data set, multiple dichotomy data set sets are determined according to the target data set, each dichotomy data set set comprises multiple dichotomy data sets, and positive and negative sample proportion intervals corresponding to the dichotomy data sets in different dichotomy data set sets are different; and feature selection is carried out on a feature set used by the target data set according to the plurality of dichotomy data sets to obtain a first target feature set, features in the first target feature set are used for training a preset machine learning model, and data processing is carried out through the trained machine learning model. According to the invention, the technical problem of low accuracy of feature selection when feature