Research and Construction of Junior High School Subject Q&A System Model based on Deep Learning

Answering questions occupies a very important position in course education. But the traditional face-to-face approach to answering questions, both for educators and learners, has gradually failed to meet the needs. However, there are many deficiencies in the automatic question answering system of education. In recent years, deep learning has made great progress in the field of Natural Language Processing, which makes it possible to apply it in the field of junior high school education. In this paper, on the basis of the improved cyclic neural network, the mixed deep neural network is firstly constructed to better learn the deep characteristics of the sentence by deep learning and word2vec. Finally, the experiment is carried out on the data set of junior high school biology, and the validity of the model is proved by the experimental results.