Text classification method and device, electronic equipment and storage medium

Abstract

The invention provides a text classification method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-processed text; inputting the to-be-processed text into a pre-trained text classification model, and obtaining prediction probability values of the to-be-processed text in multiple categories; selecting the maximum prediction probability value in the prediction probability values, and determining the category corresponding to the maximum prediction probability value as the category of the to-be-processed text; wherein the text classification model is obtained by training according to triple sample data, and the loss function value of the text classification model is determined according to a cross entropy loss value and a relative loss value. According to the text classification method provided by the invention, the robustness of the NLP system can be improved, the accuracy of the voice intention is improved, and the user experience is improved.

Description

Technical field [0001] The present disclosure relates to the field of information processing, in particular, to a text classification method, device, electronic device, and storage medium. Background technique [0002] With the continuous development of speech recognition technology, the speech intelligence system has been applied to various aspects of the industrial, so that each product can be interacted with the user. [0003] In the prior art, the identification user intent in the voice intelligence system mainly takes the pipe structure, that is, the user -ASR (Automatic Speech Recognition, Automatic Speech Recognition Technology) System-NLP (Natural LanguageProcessing, Natural Language Processing) system, where the ASR system will The audio is converted into text, and then the NLP system is classified to the converted text, and the user's text intent is obtained by determining the category tag of the text. Since the input of the NLP system is the output of the ASR system, i...

AI Technical Summary

Problems solved by technology

[0004] The present disclosure provides a text classification method, device, electronic equipment and storage medium, which are used to solve the technical problem in the prior art that the accuracy of voice intention judgment is low due to the low robustness of the NLP system, and to improve the robustness of the system Purpose of sex and phonetic intent accuracy

Images