醫院的藥師是醫護人員與民眾之間溝通的重要角色，而用藥的衛教也是醫院藥師專業服務的重要業務之一。民國 110 年起，藥師加入全民健保提出的全民健康保險腎臟病之病人照護與衛教計畫，透過用藥配合度諮詢服務、用藥整合性服務、藥師藥事指導等，強化腎臟病病人用藥衛教，並釐清用藥相關問題。
研究顯示慢性腎病病人因對腎臟疾病的認知不足、對藥物的誤解、多重用藥、頻繁的調整藥物、副作用、不良的醫病溝通等因素而有較低的醫囑遵從性，而不良的醫囑遵從性更進一步使使腎病惡化。如何利用自然語言處理技術來提供多元化的服務、有效率的解決需求，將是對社會非常重要的貢獻。
因此，本篇論文提供了一種分析問句意圖的方法，藉由抽取問句中的 C-Q-V-A-M-O-D 結構來分析慢性腎病用藥之相關問題，且透過知識圖譜和答案模板進行模擬藥師與民眾對談的方式進行回答。

Hospital pharmacists play an role between Health professional and patients, and education for medication is also an important service provided by hospital pharmacists. In 2021, pharmacists joined the programs of National Health Insurance Pre-ESRD patient care and health education. By providing consultation of medicine, medication integration service, and medication guidance, efforts are made to strengthen medication education for patients in the Pre-ESRD and clarify medication-related concerns.
Studies have shown that patients with chronic kidney disease have low medication adherence due to misunderstanding, polypharmacy, side effects and other factors, which make the kidney disease worsening. How to apply Natural Language Processing to provide diversified services and efficiently solve user needs will be a very important contribution to society
This paper provides a method to analyze intents in the question by extracting C-Q-V-A-M-O-D structures in sentences to analyze the questions about medicine for Pre-ESRD patient education. In addition, we use Knowledge Graph and Template Answers to simulate pharmacist-patient dialogues.

[1] A. R. W. Tjiptomongsoguno, A. Chen, H. M. Sanyoto, E. Irwansyah, and B. Kanigoro, “Medical chatbot techniques: A review,” in Software Engineering Perspectives in Intelligent Systems (R. Silhavy, P. Silhavy, and Z. Prokopova, eds.), (Cham), pp. 346–356, Springer International Publishing, 2020.
[2] L. Xu, L. Sanders, K. Li, and J. C. L. Chow, “Chatbot for health care and oncology applications using artificial intelligence and machine learning: Systematic review,” JMIR Cancer, vol. 7, p. e27850, Nov 2021.
[3] 衛生福利部國民健康署 and 台灣腎臟醫學會, 早期慢性腎臟病照護手冊. 10341 台北市大同區塔城街 36 號: 衛生福利部國民健康署, 第一版 ed., 1 2022. 本書同 時登載於國民健康署網站.
[4] R. Tamrakar and N. Wani, “Design and development of chatbot: A review,” 04 2021.
[5] C.-Y. Yeh, “A patient education chatbot for colonoscopy based on food and medicine knowledge graph,” 2021.
[6] D.-H. You, “Atc-5-level knowledge graph model: Anatomical therapeutic chemical(atc) classification code encoder of single ingredient and complex product,” 2022.
[7] K.-D. Chen, “Integration of chinese and western medicine knowledge graph,” 2022.
[8] E. Adamopoulou and L. Moussiades, “An overview of chatbot technology,” Artificial Intelligence Applications and Innovations, vol. 584, pp. 373–383, May 6 2020.
[9] P. Amiri and E. Karahanna, “Chatbot use cases in the Covid-19 public health response,” Journal of the American Medical Informatics Association, vol. 29, pp. 1000–1010, 02 2022.
[10] M. Kale and A. Rastogi, “Template guided text generation for task-oriented dialogue,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), (Online), pp. 6505–6520, Association for Computational Linguistics, Nov. 2020.
[11] R. Kamdi and A. Agrawal, “Keywords based closed domain question answering system for indian penal code sections and indian amendment laws,” International Journal of Intelligent Systems and Applications, vol. 7, pp. 57–67, 11 2015.
[12] C. Xu, J. Xu, Z. Dong, and J.-R. Wen, “Semantic sentence matching via interacting syntax graphs,” in Proceedings of the 29th International Conference on Computational Linguistics, (Gyeongju, Republic of Korea), pp. 938–949, International Committee on Computational Linguistics, Oct. 2022.
[13] H. Cheng, Y. Shen, X. Liu, P. He, W. Chen, and J. Gao, “UnitedQA: A hybrid approach for open domain question answering,” in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), (Online), pp. 3080–3090, Association for Computational Linguistics, Aug. 2021.
[14] P. F. Brown, V. J. Della Pietra, P. V. deSouza, J. C. Lai, and R. L. Mercer, “Classbased n-gram models of natural language,” Computational Linguistics, vol. 18, no. 4, pp. 467–480, 1992.
[15] H. He and J. D. Choi, “The stem cell hypothesis: Dilemma behind multi-task learning with transformer encoders,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, (Online and Punta Cana, Dominican Republic), pp. 5555–5577, Association for Computational Linguistics, Nov. 2021. Available at https://aclanthology.org/2021.emnlp-main.451.
[16] T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei, “Language models are few-shot learners,” in Advances in Neural Information Processing Systems (H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, eds.), vol. 33, pp. 1877–1901, Curran Associates, Inc., 2020.
[17] P.-L. Chen and S.-H. Wu, “以語言模型判斷學習者文句流暢度 (analyzing learners ‘writing fluency based on language model)[in chinese],” in ROCLING/IJCLCLP, 2015.
[18] J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: pre-training of deep bidirec tional transformers for language understanding,” CoRR, vol. abs/1810.04805, 2018