Abstract
To meet the high-efficiency question answering needs of existing patients and doctors, this system integrates medical professional knowledge, knowledge graphs, and question answering systems that conduct man-machine dialogue through natural language. This system locates the medical field, uses crawler technology to use vertical medical websites as data sources, and uses diseases as the core entity to construct a knowledge graph containing 44,000 knowledge entities of 7 types and 300,000 entities of 11 kinds. It is stored in the Neo4j graph database, using rule-based matching methods and string-matching algorithms to construct a domain lexicon to classify and query questions. This system has specific practical value in the medical field knowledge graph and question answering system.
Highlights
At present, there are many problems in China’s manual medical interrogation system [1]–[4], mainly in: first, the allocation of medical resources in urban and rural areas is hugely unbalanced, some underdeveloped regions are short of professional medical personnel, and the quality of manual interrogation services needs to be improved urgently; Second, with the rapid growth and aging of China’s population in recent years, the allocation of medical resources has gradually failed to meet the increasing medical needs of the people, and many experts are hard to find one vote
Based on the above issues, this paper proposes a knowledge graph based Q.A. system based on reliable medical data and studies the technical issues involved
To construct a high-quality knowledge graph, When the data sources are relatively small, this paper focuses on optimizing and improving the knowledge fusion part of the knowledge graph construction algorithm
Summary
There are many problems in China’s manual medical interrogation system [1]–[4], mainly in: first, the allocation of medical resources in urban and rural areas is hugely unbalanced, some underdeveloped regions are short of professional medical personnel, and the quality of manual interrogation services needs to be improved urgently; Second, with the rapid growth and aging of China’s population in recent years, the allocation of medical resources has gradually failed to meet the increasing medical needs of the people, and many experts are hard to find one vote. Based on Semantic Parsing: This kind of way transforms people’s natural language into logical forms that can be processed by machines searches for and gives answers in the database This method involves some linguistics and traditional NLP methods [8], requires many manual design rules, and has high accuracy but lacks generalization ability. Vector Modeling: This kind of approach graphs the entities in the knowledge base and natural language questions to the same vector space and finds the answer by comparing these vectors’ similarities This method is a data-driven modeling method [10], which does not need too much preprocessing of data and is easy to implement. Use keywords to represent knowledge content in isolation, ignoring the influence of context, which will affect the accuracy of the result [11]
Sign-in/Register to view highlights & summary 
Paper version not known (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call