A Hybrid BERT-CNN-Based Medical Question-Answering System with TF-IDF Word2Vec Semantic Matching

With the rapid advancement of artificial intelligence technology, the demand for intelligent question-answering systems in the medical field has been growing significantly. This paper designs and implements a medical question-answering system based on deep learning, aiming to provide users with efficient and accurate health consultation services. The system integrates BERT (Bidirectional Encoder Representations from Transformers) and CNN (Convolutional Neural Network) models for intent recognition and employs a TF-IDF (Term Frequency-Inverse Document Frequency) weighted Word2Vec algorithm to calculate text similarity. Experimental results demonstrate that the system performs well in terms of accuracy and practicality for medical domain question answering.