Home Self-medication Question-Answering System for the Elderly Based on Seq2Seq Model and Knowledge Graph Technology

Baoxin Wang, Shaofu Lin, Zhisheng Huang, Chaohui Guo

Abstract: With the deepening of aging, chronic diseases of the elderly are the main burden of disease in most countries in the world. The prevalence of chronic diseases in urban areas in China is as high as 75%. Many elderly people use multiple drugs for a long time. Home self-medication problems occur frequently. In order to alleviate this problem to a certain extent, knowledge graph technology and a deep learning model are used to design a home self-medication question-answering system for the elderly and their caregivers. Explore a feasible way of providing automated online consultation intelligent services. In this paper, we have collected medication as well as professional Q&A (question and answer) data in the field of aging health, and constructed a knowledge graph that meets the characteristics of medication use in the elderly. Based on the matching rules in the question judging module, the problems entered by users are classified. For professional knowledge related to diseases and medications of the elderly, the question-answering system uses the knowledge graph to search for answers. For other basic knowledge related to elderly health, the system uses the BERT model to vectorize its users’ questions, then matches the questions by calculating cosine similarity, thus finding the corresponding answers. The system adds the Seq2Seq model as a supplement to the answer retrieval method of the knowledge graph. The testing results shows that the system provides online consultation services more accurately and efficiently for home self-medication for the elderly and their caregivers.