Disclosed are a method for extracting a feature string, a device, a network apparatus, and a storage medium. The method comprises: determining, for each candidate feature string, a transition probability for each pair of adjacent characters in the candidate feature string according to a first-order Markov transition probability matrix; detennining a transition entropy value of the candidate feature string according to the transition probability of each pair of adjacent characters and the logarithm of the transition probability; and labeling a candidate feature string having a transition entropy value greater than a pre-determined threshold as a first usable feature string, and using a valid first usable feature string as an extracted target feature string.