TEXT TOPIC EXTRACTION METHOD, APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM

摘要

A text topic extraction method, relating to the technical field of artificial intelligence, and comprising: constructing a text topic extraction model (S1); training the text topic extraction model (S2); obtaining a text word vector corresponding to a text sample (S3); inputting the text word vector into the trained text topic extraction model (S4); and outputting a text topic corresponding to the text sample (S5). The text topic extraction model comprises a convolutional neural network and an attention mechanism; the attention mechanism comprises a position attention mechanism and a channel attention mechanism; the position attention mechanism and the channel attention mechanism are established in parallel, are both connected to an activation layer of the convolutional neural network, and respectively apply a position attention weight and a channel attention weight; an output result of the position attention mechanism and an output result of the channel attention mechanism are both input into a fully connected layer of the convolutional neural network. Also disclosed are an apparatus, an electronic device, and a storage medium. According to the method, the operation efficiency of the text topic extraction model is improved, and the precision of text topic extraction is improved.