Abstract
BACKGROUND: With the rapid development of the medical industry and the gradual increase in people's awareness of their health, the use of the Internet for medical question and answer, to obtain more accurate medical answers. It is necessary to first calculate the similarity of the questions asked by users, which further matches professional medical answers. Improving the efficiency of online medical question and answer sessions will not only reduce the burden on doctors, but also enhance the patient's experience of online medical diagnosis. METHOD: This paper focuses on building a bidirectional gated recurrent unit(BiGRU) deep learning model based on Siamese network for medical interrogative similarity matching, using Word2Vec word embedding tool for word vector processing of ethnic-medical corpus, and introducing an attention mechanism and convolutional neural network. Bidirectional gated recurrent unit extracts contextual semantic information and long-distance dependency features of interrogative sentences; Similar ethnic medicine interrogatives vary in length and structure, and the key information in the interrogative is crucial to similarity identification. By introducing an attention mechanism higher weight can be given to the keywords in the question, further improving the recognition of similar words in the question. Convolutional neural network takes into account the local information of interrogative sentences and can capture local position invariance, allowing feature extraction for words of different granularity through convolutional operations; By comparing the Euclidean distance, cosine distance and Manhattan distance to calculate the spatial distance of medical interrogatives, the Manhattan distance produced the best similarity result. RESULT: Based on the ethnic medical question dataset constructed in this paper, the accuracy and F1-score reached 97.24% and 97.98%, which is a significant improvement compared to several other models. CONCLUSION: By comparing with other models, the model proposed in this paper has better performance and achieve accurate matching of similar semantic question data of ethnic medicine.