Text classification method, device, equipment and computer readable storage medium

Abstract

The embodiment of the invention discloses a text classification method, a device, equipment and a computer readable storage medium. The method comprises the steps that firstly, a target corpus set of a target text is obtained, the target text comprises questions, abstracts and keywords, and the target corpus set comprises abstract corpora and question and keyword corpora; the target corpus set is imported into the trained text representation model to obtain a first feature vector of the target text, the first feature vector is used for reflecting a subject, an abstract and a keyword of the target text, then the first feature vector is imported into a first classifier to obtain a classification result of the target text, the classification result comprises a first classification category and confidence, and the first classification category is used for classifying the target text; and if the confidence coefficient is greater than or equal to a first threshold value, determining that the first classification category is the category of the target text. According to the embodiment of the invention, the accuracy and efficiency of text classification can be improved.

Description

technical field [0001] The present application relates to the technical field of data classification, in particular to a text classification method, device, equipment and computer-readable storage medium. Background technique [0002] With the development of data classification technology, in order to facilitate users to quickly obtain the required data, it often involves the classification of data. At present, with the continuous growth of the number of scientific researchers, academic literature has also increased rapidly. As a part of the data that cannot be ignored, Text classification is especially important. [0003] In the prior art, the main methods of text classification include using external knowledge bases to mine the relationship between terms within the language, or using external files to expand the features of short texts, so that most of the terms can be found Semantic relationship, but the feature expansion cannot be performed for terms that are not in the...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the main methods of text classification include using external knowledge bases to mine the relationship between terms within the language, or using external files to expand the features of short texts, so that most of the terms can be found Semantic relationship, but the terms that are not in the knowledge base cannot be extended, so the accuracy of text classification is low, and it takes a lot of time to expand with the help of external files, resulting in low efficiency of text classification

Images