WEB CRAWLER DETECTION METHOD, SYSTEM, AND DEVICE EMPLOYING GRAPH NEURAL NETWORK

摘要

The present application discloses a web crawler detection method, system, and device employing a graph neural network. The method comprises: acquiring a network session sample comprising respective accessed resources (S1); extracting a resource feature from each of the resources in the network session sample, wherein the resource feature comprises an inherent feature of the resource exhibited in a website, and/or a session feature obtained when a user accesses the resource (S2); and constructing, on the basis of the extracted resource features, a resource graph of the network session sample, training the constructed resource graph by using a preset graph algorithm, and performing web crawler detection by means of a trained classification model (S3).