Intention recognition model training method and device, electronic equipment and storage medium

Abstract

The invention provides an intention recognition model training method and device, electronic equipment and a storage medium. The method comprises the steps that an original data set is acquired; data enhancement simulation is conducted on the original data set, a simulation data set is obtained, the simulation data set comprises multiple categories of known intention texts and one category of unknown intention texts, the known intention texts and the original texts do not have logic conflicts, and the unknown intention texts and the original texts have logic conflicts; screening out a plurality of positive sample texts and a plurality of negative sample texts from the original data set and the simulation data set, wherein the types of the positive sample texts are different from those of the negative sample texts; the multiple positive sample texts and the multiple negative sample texts are used for conducting comparative learning training on the text classification neural network, a trained intention recognition model is obtained, and the intention recognition model is used for recognizing the intention category of the text.

Description

technical field [0001] The present application relates to the technical field of natural language processing, in particular, to an intention recognition model training method, device, electronic equipment and storage medium. Background technique [0002] At present, the text classification model based on the neural network structure is usually used to identify the intent category of the text content, so as to obtain the semantically expressed intention result of the text content. However, in the actual practice process, it is found that these text classification models have a good accuracy rate for the trained intent category texts, and it is difficult to identify unknown intent category texts that have not been trained. Contents of the invention [0003] The purpose of the embodiments of the present application is to provide an intention recognition model training method, device, electronic equipment and storage medium, which are used to improve the problem that it is dif...

AI Technical Summary

Problems solved by technology

However, in the actual practice process, it is found that these text classification models have a good accuracy rate for the trained intent category texts, and it is difficult to identify untrained unknown intent category texts.

Images