Medical question-answering system based on generative dialogue technology

Abstract

The invention provides a medical question-answering system based on the generative dialogue technology, which is used for generating a corresponding reply text for a question text input by a patient, and is characterized by comprising a department classification module, which is used for classifying the question text by using a pre-trained department classification model to obtain a department coding vector; the department number generation module converts the department coding vector into a first number vector corresponding to a department according to a preset dictionary file, converts the problem text into a second number vector according to the dictionary file, and splices the first number vector and the second number vector to obtain a spliced number vector; and the reply text generation module inputs the splicing number vector into a pre-trained generative dialogue model to generate a reply text. According to the medical question-answering system based on the generative dialogue technology, the questions corresponding to the patient questions can be automatically generated in real time without the support of a huge retrieval database, the shortage of medical resources is relieved, and the problems of the patient can be rapidly solved.

Description

technical field [0001] The invention belongs to the field of medical care informatics, in particular to a medical question answering system based on generative dialogue technology. Background technique [0002] Today, with the vigorous development of artificial intelligence technology, man-machine dialogue technology is widely used. For example, in scenarios such as smart speakers and smart customer service, man-machine dialogue technology has become very common. However, in the medical field, patients’ questions in most scenarios are still answered manually, and most online consultation services require doctors to answer patients’ questions in person, and many of the questions are repetitive or similar. The application of machine dialogue technology can effectively save medical resources. [0003] Dialogue systems are generally divided into three categories: rule-based dialogue systems, retrieval dialogue systems, and generative dialogue systems. [0004] Among them, the ...

AI Technical Summary

Problems solved by technology

However, the existing generative dialogue systems directly predict the patient's question without pre-analyzing the department to which the question belongs, which may lead to situations where the answer has nothing to do with the question due to the wrong department.

Also, it will result in a higher error rate for reply text generation

Images