Text classification method and system based on knowledge graph and electronic equipment

Abstract

The invention provides a text classification method and system based on a knowledge graph and electronic equipment, and relates to the technical field of text paragraption.The method comprises the steps that firstly, named entity recognition is conducted on to-be-parsed text data, and entity vectors and sentence vectors of the to-be-parsed text data are determined; then determining a hop entity vector corresponding to the entity vector by using the initialized knowledge graph; updating the entity vector according to the determined one-hop entity vector, and updating the sentence vector by using the updated entity vector; and finally, performing text classification prediction by utilizing the updated sentence vectors to obtain a text type corresponding to the to-be-analyzed text data. According to the method, the text data is classified and predicted by utilizing the entity information in the text data and the information of the one-hop entity corresponding to the entity in the existing knowledge graph, the content contained in the sentence vector is richer by highlighting the entity information and adding some related external information, and the classification precision of the text is further improved.

Description

technical field [0001] The present invention relates to the technical field of text analysis, in particular to a text classification method based on a knowledge graph. Background technique [0002] Today's Internet field has deeply entered the era of big data. Various social network platforms and communication platforms generate a large amount of video, sound, picture, text and other data every day. How to effectively analyze and classify these data is critical for the server and supervision. end is crucial. In actual scenarios, for the server side, more accurate big data analysis can provide users with more accurate advertising push services; Control their behavior in advance. [0003] In the prior art, the analysis and classification of network platform data is mainly aimed at text data, and the classification of text data is mainly realized by means of manual identification, which is inefficient and has a high error rate; with the popularization of natural language proc...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the analysis and classification of network platform data is mainly aimed at text data, and the classification of text data is mainly realized by means of manual identification, which is inefficient and has a high error rate; with the popularization of natural language processing technology, the use of The relevant convolutional neural network model also realizes the type analysis process of text data, but the existing network model structure is relatively complex, and the analysis accuracy needs to be improved

[0004] To sum up, in the existing technology, there is still a problem of low precision in the process of text type analysis

Images