Knowledge graph assisted automatic diagnosis dialogue system

Abstract

The invention relates to a knowledge graph assisted automatic diagnosis dialogue system, which comprises a front-end module, a data acquisition module, a data storage management module, a symptom expansion module and a module doctor-patient dialogue processing module, wherein the front-end module transmits user input into the doctor-patient dialogue processing module and displays the user input and corresponding system feedback; the data acquisition module is used for completing acquisition of doctor-patient dialogue corpora and disease regulations; the data storage management module receives the data from the data acquisition module, constructs a knowledge graph, and perfects a user information symptom table and a medical data selection table; the symptom expansion module expands a doctor-patient dialogue model training corpus, inquires a knowledge graph to obtain key symptoms and large-probability symptoms causing diseases, and transmits the key symptoms and the large-probability symptoms into the medical data selection table; and the doctor-patient dialogue processing module trains a doctor-patient dialogue model, receives front-end user input, decides a next action to be adopted by using the doctor-patient dialogue model, generates a sentence or a diagnosis result, transmits the sentence or the diagnosis result to the front-end module, and displays the sentence or the diagnosis result to the user.

Description

technical field [0001] The invention relates to a dialogue system, in particular to an automatic diagnosis dialogue system assisted by a knowledge map. Background technique [0002] The digital medical industry is developing rapidly, especially the demand for non-contact auxiliary diagnostic technologies such as online consultation has increased sharply. However, the current online consultation is mainly based on the doctor’s online diagnosis rather than an intelligent automatic diagnosis. Patients often need to wait for the doctor’s online reply, and the diagnosis lacks real-time performance. A large number of questions also increase the doctor’s response burden. An automatic diagnostic dialog system for knowledge graphs. [0003] The knowledge map is a structured semantic knowledge base, which expresses massive Internet information into a semantic representation that can be recognized by the objective world. It has powerful semantic expression and storage capabilities, an...

AI Technical Summary

Problems solved by technology

[0004] Some current disease diagnosis systems have the following problems: Most of them are simple single-hop question-answering systems, which only use one input from the user to get the diagnosis result based on keyword matching, ignoring the relationship between symptoms and diseases, which do not conform to real life During the consultation process in the hospital, the diagnosis results lacked rigor

The "black box" problem brought about by the model obtained by learning a large number of corpus and cases through machine learning and deep learning technology makes the diagnostic results lack interpretability, causing doctors to have concerns about this type of diagnostic system

The model training corpus is too simple or the doctor-patient dialogue is missing, resulting in insufficient symptoms of the training model, resulting in low efficiency and low accuracy of the trained model

Images