簡易檢索 / 詳目顯示

回結果列表
研究生： 陳坤鈿
Chen, Kun-Dian
論文名稱： 中西醫療知識圖譜整合
Integration of Chinese and Western Medicine Knowledge Graph
指導教授： 楊中平
Yang, Chung-Ping
共同指導教授: 盧文祥
Lu, Wen-Hsiang
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2021
畢業學年度： 109
語文別： 英文
論文頁數： 40
中文關鍵詞： 中西醫 、知識整合 、知識圖譜
外文關鍵詞： Chinese and Western Medicine, knowledge integration, knowledge graph
相關次數： 點閱：158  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 在台灣，中西醫療皆十分發達，且許多大醫院也設立了中西醫的聯合門診，這也告訴了我們，中西醫能夠互相彌補對方的不足。
    我們在觀察後發現，其實很多線上醫療諮詢的使用者，常常會詢問醫生有某個疾病或症狀的時候，能否吃某項中藥，抑或者是要做某項檢查前是否需要停藥，如:做心導管檢查前需要停用中藥嗎。
    為了解決上述問題，本研究蒐集了中西醫的疾病與中藥方、藥材的資訊，並以此建構知識圖譜，再透過疾病相似度演算法，來推論西醫疾病是否適合吃某些中藥。經過我們整理過後的中西醫知識圖譜，再搭配疾病相似度演算法，我們找出一些中西醫疾病上的關聯性，且有一半以上的相關度超過8成。未來我們會設計多種使用者可能會詢問的意圖，並建構聊天機器人，來回答使用者中西醫的相關問題。

    In Taiwan, not only Western medicine is developed, but Chinese medicine also has a place, and it has won many people's support. Many major hospitals have also set up joint outpatient clinics for Chinese and Western medicine, which also tells us that Chinese and Western medicine can make up for each other's shortcomings.
    In our observation, we found that in fact, many online medical consultation users often ask their doctors whether they can take a certain Chinese medicine when they have a certain disease or symptom, or whether they need to stop the medicine before a certain examination, such as : Do I need to stop Chinese medicine before cardiac catheterization?
    In order to solve the above-mentioned problems, this research collected information on Chinese and Western medicine diseases and Chinese medicine prescriptions and medicinal materials, and constructed a knowledge graph based on this, and then used the disease similarity algorithm to infer whether Western medicine diseases are suitable for taking certain Chinese medicines. After constructing the Chinese and Western Medicine’s knowledge graph and calculation of disease similarity, we find out some relations between Chinese and Western Medicine’s diseases. The correction between these diseases also over than 80%. Finally, design a variety of intents that users may ask, and construct a chat robot to answer users' questions about Chinese and Western medicine.

    摘要 I Abstract II 誌謝 IV List of Content V List of Tables VII List of Figures VIII Chapter 1 Introduction 1 1.1 Background 1 1.2 Motivation 3 1.3 Method 4 1.4 Contribution 5 1.5 Organization of this Dissertation 5 Chapter 2 Related Work 6 2.1 Studies of Chinese and Western Medicine Entities Tagging 6 2.2 Studies of Knowledge Graph 7 2.3 Studies of Disease Similarity 8 Chapter 3 Method 9 3.1 System Architecture 9 3.2 Data Source 10 3.2.1 Online Chinese Medicine Information 10 3.2.2 Western Medicine Knowledge Base 11 3.3 Corpus Preprocessing 11 3.3.1 Observation of Chinese Medicine Information 11 3.3.2 CKIP Tagger Tool 12 3.3.3 Correction of 4- character Symptom 12 3.4 Symptom Vector 15 3.4.1 Key Entity Dimension 15 3.4.2 Status Dimension 17 3.4.3 Orientation 17 3.5 Chinese Medicine Knowledge Graph Construction 18 3.5.1 Observation of Chinese Medicine Data 18 3.5.2 Knowledge Graph Construction 22 3.6 Chinese and Western Medicine Knowledge Integration 23 3.6.1 Refine Western Medicine Knowledge Base 23 3.6.2 Knowledge Graph Integration 24 Chapter 4 Experiment 28 4.1 Dataset 28 4.2 Evaluation Metrics 28 4.3 Evaluation on Medical Entity Recognition 29 4.3.1 Experiment Setup 29 4.3.2 Experiment Result 29 4.3.3 Error analysis 30 4.4 Evaluation on Knowledge Integration 31 4.4.1 Experiment Setup 31 4.4.2 Experiment Result 31 4.4.3 Error analysis 34 4.5 Application Evaluation on Intent Classification 35 4.5.1 Experiment Setup 35 4.5.2 Experiment Result 35 4.5.3 Error analysis 36 Chapter 5 Conclusion and Future Work 37 5.1 Conclusion 37 5.2 Future Work 37 Chapter 6 Reference 39

    [1] “衛生福利部統計處” , [Online]. Available:
    https://dep.mohw.gov.tw/dos/lp-5033-113.html
    [2] T.-Y, Ko, Structural Analysis and Standardization System Design of Traditional Chinese Medicine Symptoms, 2011.
    [3] J.-C. Cai, Summary Generation for Chinese Patient Complaint based on Medical Entity Recognition and Medical Terminology Mapping, 2019.
    [4] W.-C. Wu, A Health-preserving Suggestions Chatbot based on Disease Knowledge-graph, 2019.
    [5] Amazon Web Services AI, COVID-19 Knowledge Graph: Accelerating Information Retrieval and Discovery for Scientific Literature, ACL 2020
    [6] Pantano, E., & Pizzi, G.. Forecasting artificial intelligence on online customer assistance: Evidence from chatbot patents analysis. Journal of Retailing and Consumer Services, 55, 102096. 2020
    [7] TING-HAO K. HUANG, AMOS AZARIA, OSCAR J. ROMERO, JEFFREY P. BIGHAM, InstructableCrowd: Creating IF-THEN Rules for Smartphones via Conversations with the Crowd, arXiv, 2019
    [8] “A+醫學百科” , [Online] Available:
    http://cht.a-hospital.com/w/%E9%A6%96%E9%A1%B5
    [9] “醫砭”, [Online] Available:
    http://yibian.hopto.org/
    [10] “衛福部中醫藥司” , [Online] Available:
    https://dep.mohw.gov.tw/docmap/lp-759-108.html
    [11] P.-Y. Chiu, A Health-Advisory Chatbot Based on Relation Path Searching of Healthcare Knowledge Base, 2020.
    [12] “CkipTagger”, [Online]. Available:
    https://github.com/ckiplab/ckiptagger
    [13] “Neo4j”, Neo4j, Inc., [Online]. Available: https://neo4j.com/.
    [14] “Cypher Query Language”, Neo4j, Inc., [Online]. Available: https://neo4j.com/developer/cypher-query-language/.
    [15] “台灣E院” , [Online] Available:
    https://sp1.hso.mohw.gov.tw/doctor/Index1.php

    無法下載圖示 校內：2026-10-15公開
    校外：2026-10-15公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE