Abnormal information text classification method based on knowledge graph

Abstract

The invention provides an abnormal information text classification method based on a knowledge graph. According to the method, first, a domain knowledge graph is constructed, and an entity identifierand an entity link based on the domain knowledge graph are constructed; second, text feature representation vectors v<text> and entity feature representation vectors v<ent> are constructed; and last,the text feature representation vectors and the entity feature representation vectors are merged to obtain new text representation vectors v<merge> fusing knowledge features, classified training is performed on the new text representation vectors, and a final classification result is obtained.

Description

technical field [0001] The present invention relates to a classification method, in particular to a method for classifying abnormal information texts based on knowledge graphs. Background technique [0002] With the development of the Internet and the continuous growth of network information, the rapid development of network technology has made people increasingly dependent on the network. With the increasing information sharing and business promotion on the network, the security issues of network content have become prominent. Therefore, there is an urgent need for an abnormal information identification method with high accuracy and strong scalability to provide network security protection for society and individuals. [0003] In the prior art, there are mainly two types of methods for abnormal information detection: one is to use keyword filtering or artificially model abnormal information, and manually formulate a filtering keyword list to match text information; the othe...

AI Technical Summary

Problems solved by technology

However, several types of knowledge representation learning methods in the prior art are mostly used for internal problems in the field of knowledge bases such as relational reasoning and link prediction, and most of them model knowledge information alone, and have not been applied to abnormal information text recognition.

Images