Intelligent questioning-answering system construction method and system based on deep learning and knowledge atlas

Abstract

The invention discloses an intelligent questioning-answering system construction method and system based on deep learning and a knowledge atlas. A crawler is utilized to obtain an interrogation medical dataset of the internet, and data preprocessing is conducted to obtain a labeled dataset; a word-splitting dictionary based on the medical field is constructed through the further utilization of a hospital electronic medical record, and is merged with a medical dictionary to serve as a word-splitting dictionary of the system; the knowledge atlas associated with diseases and symptoms is constructed, and disease entity aligning and symptom entity aligning are conducted; according to disease entity aligning, the labeled dataset is obtained; a language model based on deep learning is constructed; a query optimization algorithm which is combined with contextual information of a user and is based on the knowledge atlas is constructed; a training dataset merged by the language model and the knowledge atlas is constructed for model merging training, and a pre-diagnosis merging model based on the language model and the knowledge atlas is obtained. By means of the intelligent questioning-answering system construction method and system based on deep learning and the knowledge atlas, active interrogation interaction through the further utilization of self-reported information of the user anddisease pre-diagnosis according to the self-reported information and interrogation information of the user are achieved.

Description

technical field [0001] The present invention relates to the field of deep learning, visualization and question answering systems, in particular to a method and system for constructing an intelligent question answering system based on deep learning and knowledge graphs. Background technique [0002] At present, China is facing a series of health risks: the aging population, the huge number of patients with chronic diseases, the "younger" senile diseases, the normalization of sub-health, the rise of medically sensitive groups, and serious psychological problems. The medical field has always been an important direction of informatization development, and the scale of informatization investment in the medical industry has been increasing year by year. After a period of development, the online medical system has gradually changed from illusion to reality, which has become an inevitable trend. Through the online question-and-answer system, users can consult the medical system wit...

AI Technical Summary

Problems solved by technology

[0003] However, as far as the traditional medical question answering system is concerned, it usually faces the following important problems: (1) It is impossible to accurately locate the disease based on the shared symptoms; (2) The unprofessional description of the user causes ambiguity; (3) It does not have the active interaction function combined with the context

There are two main strategies for the construction of intelligent diagnosis and treatment question answering system: (1) data-based method, mainly through the search mechanism of the Internet, to search for similar information from the massive data on the Internet to assist in the diagnosis, and the amount of data collected corresponding to this strategy It is very large, and the number of disease categories that can be covered is also large; however, the knowledge density of network-based text data is low, and it is impossible to form an effective reasoning mechanism. 2) Knowledge-based reasoning mechanism, which mainly introduces fuzzy decision-making technology into disease classification. The advantage of this strategy is that it is easy to use existing deterministic disease knowledge, and can form understandable and displayable decision-making basis. Provide direct auxiliary support; but the disadvantage is that it relies too much on high-quality data, and the coverage of the total number of diseases and categories will be very limited

Images