Article Details

Abstract

In recent years, with the rapid development of Artificial Intelligence technology, the application of large models and Knowledge Graphs in various fields becomes increasingly in-depth. More and more people are accustomed to using AI to understand or diagnose physical symptoms. However, when answering professional medical questions, ordinary models produce answers that do not match the actual problem due to unclear descriptions and non-prominent keywords. Therefore, this paper designs and implements a question-answering system strongly related to professional medical knowledge by combining Java technology and a Knowledge Graph. This system combines natural language processing technology and constructs a medical Knowledge Graph to identify and replace non-standard vocabulary used by users during questioning, effectively solving problems such as semantic ambiguity and unclear descriptions in traditional question-answering systems. The system uses RESTful services provided by the Spring Boot framework, combined with a MySQL database and a Neo4j graph database to store business data and Knowledge Graph information. By integrating AC automata, TF-IDF and Naive Bayes classifiers, as well as Java open source NLP libraries and pre-trained models in the medical field, the system precisely understands user intents and provides professional responses, which has significant market potential and application value.

Keywords

Artificial Intelligence; Knowledge Graph; medical Q&A; Java; Spring Boot

References

1. [1] Huang Chengning, Yin Xiaolei, Chen Wu Research and Application of Medical Question Answering System Based on Knowledge Graph [J]. Information Technology and Informatization, 2024 (5): 210-215
2. [2] Deng J Z.Research on Automatic Question Answering Systems Based on Medical Knowledge Graphs[J].Journal of Intelligence and Knowledge Engineering，2024，2（3）：137-147.
3. [3] Wang X，Luo Z J，He R，et al. Novel Medical Question and Answer System: Graph Convolutional Neural Network Based with Knowledge Graph Optimization[J/OL].Expert Systems With Applications，2023，227：120211.https://doi.org/10.1016/j.eswa.2023.120211.
4. [4] Huang Yong, Xian Juan Xia, Guan Chengbin Smart Healthcare Question Answering System Based on BERT BiGRU Model [J]. Software Engineering, 2024, 27 (3): 11-14, 25
5. [5] Ahmet H. Interactive Voice Response Systems: The Doubled-edged Sword of AI and the Culture of Hospitality in Healthcare[J/OL].International Journal of Hospitality Management，2023，112：103463.https://doi.org/10.1016/j.ijhm.2023.103463.
6. [6] Li Shiqi, Zhang Hao, Diao Yufeng Research on Question Answering System Based on Medical Knowledge Graph [J]. Journal of Inner Mongolia University for Nationalities (Natural Science Edition), 2024, 39 (5): 68-73
7. [7] Wang Jisheng Design and Implementation of a Medical Question Answering System Based on Knowledge Graph [D]. Taiyuan: Taiyuan Normal University, 2024
8. [8] Reichenpfader D，Rösslhuemer P，Denecke K. Large Language Model-Based Evaluation of Medical Question Answering Systems: Algorithm Development and Case Study[J]. Studies in Health Technology and Informatics，2024，313：22-27.
9. [9] Wang Dongjie, Yang Xuebo, Ren Huanhai Design and Implementation of a Small Training Institution Course Management System Based on Django [J]. Modern Information Technology, 2025, 9 (9): 156-161
10. [10] Yang Bo, Sun Xiaohu, Party Jiayi, etc A Large Language Model Named Entity Recognition Method for Medical Question Answering Systems [J]. Computer Science and Exploration, 2023, 17 (10): 2389-2402

Funding

Shandong Huayu Institute of Technology's 2024 "Specialized Innovation Integration" Course Construction Project - Java Web Development

About the authors

Wang Dongjie (1988-), female, Han ethnicity, from Dezhou, Shandong, lecturer, bachelor's degree, research interests include software development; Li Tong (2000-), male, Han ethnicity, from Heze, Shandong, bachelor's degree, research interests include software development.