TEXT QUALITY INSPECTION METHOD, ELECTRONIC APPARATUS, COMPUTER DEVICE AND STORAGE MEDIUM

摘要

Disclosed are a text quality inspection method, an electronic apparatus, a computer device and a storage medium. The method comprises: collecting a plurality of keywords of a WeChat text, and labelling the plurality of keywords to obtain a quality inspection text data set with a quality inspection label (301); constructing a neural network, and dividing, by means of the neural network, the quality inspection text data set into a training set and a verification set according to a fixed ratio (302); carrying out word segmentation on texts in the training set and the verification set by using a Chinese word segmentation tool to obtain a plurality of words, and mapping each word into a word vector (303); splitting the mapped training set into a plurality of training subsets, alternately training a plurality of quality inspection models by using the plurality of training subsets, and in the training process, saving a quality inspection model meeting a requirement from among the plurality of quality inspection models (304); and carrying out prediction by using the quality inspection model meeting a requirement, and re-checking a prediction result, wherein the prediction refers to using the saved quality inspection model to check the WeChat text (305). According to the text quality inspection method, the electronic apparatus, the computer device and the storage medium, there is a certain semantic comprehension capability, thereby improving the quality inspection accuracy rate, alleviating the pressure on quality inspection personnel, and greatly improving the text quality inspection efficiency.