淡江大學機構典藏:Item 987654321/34307
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62830/95882 (66%)
Visitors : 4107849      Online Users : 817
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/34307


    Title: 資訊檢索結合文字探勘之應用-以中醫婦科專題文獻資料庫為例
    Other Titles: Information retrieval and text mining: a case study of the Chinese medicine gynecology monographic database
    Authors: 童瓊慧;Tung, Chiung-huei
    Contributors: 淡江大學資訊與圖書館學系碩士班
    歐陽崇榮;Ouyang, James C.
    Keywords: 概念檢索;文字探勘;中醫婦科;Concept Retrieval;text mining;Chinese Medicine Gynecology
    Date: 2008
    Issue Date: 2010-01-11 05:08:30 (UTC+8)
    Abstract: 本研究將資訊檢索與文字探勘技術相結合並應用於『中醫藥專題文獻資料庫』中,建立中醫婦科知識主題並利用機器學習的實例學習方式進行肯定(正例)與否定(反例)評價訓練,使中醫藥從業人員能快速檢索到最相關之文獻並促進中醫實證醫學之發展。研究者首先要找出一套穩定的知識主題訓練策略來進行訓練,再以此訓練模式作為範例,供其他使用者參考利用,且可依其需求作適當地調整;主要是透過訓練完成的知識主題分享給他人取用,達到知識交流與分享之目的。
    本研究採用文獻分析與系統實證方式,對資訊檢索、文字探勘與中醫藥相關文獻進行探討分析,再實際進行系統實證部份,敘述整體實證過程、舉例並分析其結果;最後歸納出以下結論:
    (一)建立中醫藥相關詞彙至系統詞庫內為首要之步驟,可提高斷詞與檢索比對結果。
    (二)知識主題訓練策略為先收集再過濾,因此要先進行肯定評價訓練(收集相關資料),再進行否定評價訓練(刪除不相關資料)。
    (三)訓練文件的選擇要謹慎,對訓練結果影響甚鉅。
    (四)知識主題檢索與一般關鍵詞檢索結果相比,精確率確實有所提高;最高可達到100%,其平均值有74%。
    (五)中醫藥文獻目前持續成長中,推動中醫實證醫學之發展。
    (六)促進中醫藥從業人員間的知識交流,達到知識分享之目的。
    This study combines information retrieval with text mining and applies to Chinese Medicine Gynecology Monographic Database.
    Researcher should find out a set of steady strategy to train first, and then regard this training way as the example, utilize for other users'' reference, and can adjust properly in accordance with its demand.
    This research adopts the literature review and information system attestation methods. Induct the following conclusion:
    1.The first step is to build the relevant vocabularies of Chinese Medicine.
    2.Secondly the search strategy is established by knowledge title collecting and filtering.
    3.The choice of the trained document is prudent.
    4.To compare the result of knowledge title retrieval with general keyword retrieval, the precision rate really improves to some extent. It can be up to 100% and its average has 74%.
    5.Chinese Medicine literatures grow up continuously as well as promote the development of Evidence-Based Chinese Medicine.
    6.To facilitate information exchange among staff members of Chinese Medicine can achieve knowledge sharing.
    Appears in Collections:[Graduate Institute & Department of Information and Library Sciences] Thesis

    Files in This Item:

    File SizeFormat
    0KbUnknown317View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback