朱子豪Chu, Tzu- How臺灣大學:地理環境資源學研究所羅元輔Luo, Yuan-FuYuan-FuLuo2010-05-052018-06-282010-05-052018-06-282009U0001-1807200921303400http://ntur.lib.ntu.edu.tw//handle/246246/179739以往GIS領域在如何增進使用者介面親和力有許多的切入面向，自然語言即為其中一種，但自然語言缺乏正規的表達方式，常造成關鍵字搜尋與語意式查詢間的語意落差，導致查詢行為受到限制。研究嘗試援引「語意網」的技術於地理知識搜尋領域，並分成建立語意網、定義關係、定義反應行為、串聯、聚焦及擴充六階段，透過Java為系統撰寫語言，結合中研院詞性標註系統、Protege及ArcGIS等工具，建構一基於語意網的圖文整合平台，期能於閱讀文件時適時提供空間元素對應的GIS資料，並經由文件斷詞、語意推論及圖台展示等過程，改善現有空間知識獲取的方式，最後再以五種模擬情境驗證系統，分析語意推論引擎介入前後影響搜尋結果的差異，實驗結果證明推論引擎可有效提升符合語意的搜尋結果滿意度。研究之成果，首先為調整現存之語意網建立與應用方法，加以正式化後用於空間知識搜尋領域，及本研究所建立之語意推論模組，可作為發展增加使用者語意彈性的搜尋引擎所使用，最後再將提出的概念落實於實務中，藉以改良現有之圖文整合架構。由新架構獲得的搜尋結果更能滿足人類的語意搜尋求，使閱讀的方式除了心象圖的產生之外，更有實際客觀的資料可加以輔助及驗證。There have been many approaches to using natural languages to make user interfaces of GIS more friendly. However, the lack of systematic expressions in natural languages frequently causes semantic gaps between users’ keyword searches and semantic inquires and thus inhibits functions of inquiry. his paper applies "semantic web" technology to search for geospatial knowledge, with the application involving the following six steps: establishment of semantic webs, definition of relationships, definition of the behavior of reactions, connection of multiple semantic nets, focus of the inference, extension the semantic net. This paper uses the Java language to combine tools such as Taiwan Academia Sinica''s "Chinese Parsing System", Protege and ArcGIS to create a semantic framework to integrate documentations and GIS, providing GIS data relevant to the document in use. In addition, Chinese Parsing Module, Semantic Matching Engine, and GIS display are used to improve existing methods of obtaining geospatial knowledge. Finally, this paper uses five scenarios to test the system mentioned above and analyze the effect of the Semantic Matching Engine in improving the performance of search. The results show the Semantic Matching Engine is significantly effective in this respect.his paper aims to make adjustment in existing establishment and application of semantic webs to specifically make them suitable for use in search for geospatial information. In addition, the Semantic Matching Engine developed in this paper can be used in search engines for increasing users’ semantic flexibility. The concepts in this paper are expected to be practically used to improve existing frameworks of GIS information integration to reach better performance in semantic searches.口試委員審定書 .............................................i謝 ......................................................ii文摘要 .................................................iii文摘要 ..................................................iv一章 緒論 ................................................1一節 研究動機 ............................................1二節 研究目的 ............................................3三節 研究範疇與限制 ......................................4、研究範疇 ...............................................4、研究限制 ...............................................4二章 文獻回顧 ............................................7一節 圖文整合與自然語言斷詞 ..............................7、圖文整合 ...............................................7、自然語言斷詞 ...........................................9二節 語意搜尋 (Semantic Search) 與知識本體 (Ontology) ...11、語意搜尋定義 ..........................................11、知識本體定義 ..........................................11、知識本體應用 ..........................................12、知識本體種類 ..........................................13、知識本體語言 (Ontology Language) ......................15、國內外過去與本體論相關的研究 ..........................19三節 語意網 (Semantic Web) ..............................19、語意網 ................................................19、明顯的詮釋資料 (MetaData) .............................20、邏輯 (Logical) ........................................21、語意網的演進架構 ......................................21、國內外過去與語意網相關的研究 ..........................23三章 研究方法 ...........................................25一節 研究架構 ...........................................25二節 研究流程 ...........................................26、研究背景界定階段 ......................................27、研究範疇界定階段 ......................................28、文獻回顧階段 ..........................................28、知識建構階段 ..........................................29、知識整合階段 ..........................................29、知識驗證階段 ..........................................29三節 研究方法 ...........................................29、建立語意網 ............................................29、定義語意網的空間與非空間關係 ..........................33、定義關係的反應行為 ....................................36、串聯語意網 ............................................44、聚焦 ..................................................45、語意資料庫的擴充機制 ..................................48四節 研究工具 ...........................................49、語意網建立工具：Protege 3.4 ...........................49、查詢定位圖台：ArcGIS 9.2 ..............................50、系統整合工具：Java ....................................51、詞性標註工具：中研院中文斷詞系統 ......................51四章 研究成果與討論 .....................................55一節 詞彙庫及語意關聯研究成果 ...........................56二節 文件斷詞模組 .......................................59、系統簡介 ..............................................59、系統範例 ..............................................61、小結 ..................................................62三節 語意推論模組 .......................................63、系統簡介 ..............................................63、系統範例 ..............................................65四節 查詢定位圖台 .......................................66、系統簡介 ..............................................66、系統範例 ..............................................69五節 查詢情境設計 .......................................71境一：無推論之關鍵字比對 ................................71境二：透過空間外部語意關聯的推論 ........................73境三：透過空間內部語意關聯的推論 ........................74境四：透過屬性外部語意關聯的推論 ........................75境五：透過屬性內部語意關聯的推論 ........................76五章 結論與未來發展 .....................................77一節 結論 ...............................................77、推論引擎 ..............................................77、語意網的建立 ..........................................77、詞性標註 ..............................................78、簡單關係的定義 ........................................78、有限資源的最大化 ......................................78二節 未來發展 ...........................................78、文本限制 ..............................................78、自動化文件語意網粹取 ..................................79、引用現有的語意網 ......................................79、語意網來源的選擇 ......................................79、同義字的誤判 ..........................................80、單向串連 ..............................................80考文獻 ..................................................81錄一、中研院平衡語料庫詞類標記集 ........................85錄二、中文詞類分析總表 ..................................87錄三、文件斷詞模組部份程式碼 ...........................101錄四、語意推論模組部份程式碼 ...........................121錄五、查詢定位圖台部份程式碼 ...........................133application/pdf2582437 bytesapplication/pdfen-US空間知識管理語意網本體論Spatial Information ManagementSemantic WebOntologythesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/179739/1/ntu-98-P96228002-1.pdf