Research on the construction technology of cardiovascular disease Q&A system based on knowledge graph

Minhui Liang

doi:10.1117/12.2683094

16 June 2023 Research on the construction technology of cardiovascular disease Q&A system based on knowledge graph

Minhui Liang

Proceedings Volume 12703, Sixth International Conference on Intelligent Computing, Communication, and Devices (ICCD 2023); 127032H (2023) https://doi.org/10.1117/12.2683094
Event: Sixth International Conference on Intelligent Computing, Communication, and Devices (ICCD 2023), 2023, Hong Kong, China

Abstract

Cardiovascular disease is a serious threat to human life and health, with high prevalence, high disability and high mortality. Cardiovascular disease Q&A system is more targeted and reliable than search engines, and users can get more concise and clear information. As a structured data source of the Q&A system, the knowledge graph enhances the flexibility and accuracy of the system. In this paper, knowledge extraction from authoritative medical websites and Baidu Baike using web spiders, knowledge fusion with reference to medical textbooks on cardiovascular diseases, and knowledge storage using Neo4j graph database were used to build the knowledge graph of cardiovascular diseases. On this basis, the Q&A system was built based on template matching and vector parsing methods, using word2vec model, TF-IDF algorithm, Naive Bayes classifier and support vector machine classifier from the perspective of doctors and patients respectively. The experiments showed that the Q&A system can effectively answer most of the questions on cardiovascular diseases.

Citation Download Citation

Minhui Liang "Research on the construction technology of cardiovascular disease Q&A system based on knowledge graph", Proc. SPIE 12703, Sixth International Conference on Intelligent Computing, Communication, and Devices (ICCD 2023), 127032H (16 June 2023); https://doi.org/10.1117/12.2683094

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available