以本體論為基礎運用模糊正規化與SPARQL查詢語言之研究

The Study of Documents Query System Based on Domain Ontology Using FFCA and SPARQL

陸韋銘(Wei-Ming Lu)

指導教授 ： 陳榮靜

朝陽科技大學/資訊學院/資訊管理系/碩士(2010年)

摘要

在網際網路的盛行中，用戶分享了問題和解答，讓不懂得解決問題的使用者很快獲得相關資訊。但是在尋找資訊的同時需要花費時間成本在瀏覽網頁與文件上，以決定是否為有用資訊。一般民眾對於慢性病(如糖尿病、高血壓等)知識並不是很足夠，民眾須尋求相關資料，來充實相關知識。在目前醫院宣導慢性病防護的方式，包括醫護人員解說，書本、網站宣導等。其中網站架設的常見問答集(Frequently Asked Questions, FAQ)是最快呈現給民眾，但是常見問答集的多寡影響到瀏覽時間成本。為了解決在搜尋時能傳回符合使用者問題解答，而不是花時間在尋找資訊上，本研究以本體論(Ontology)建立糖尿病衛生教育領域知識，將FAQ建置於本體論中。當使用者提出問題字句，利用模糊正規化(Fuzzy Formal Concept Analysis, FFCA)分析出問題與衛生教育文件之符合程度，針對問題回應文件。針對本體論的架構與回應文件特性，本研究利用SPARQL(SPARQL Protocol and RDF Query Language) 查詢語言從本體論中將文件存取出來，幫助使用者在尋找文件時能夠快速找到所需要的文件。

關鍵字

模糊正規化分析 ； 本體知識 ； 常見問答集 ； 糖尿病 ； SPARQL

並列摘要

The Internet, a rapidly growing phenomenon, provides an unlimited resource to discover information on chronic diseases. There are abundance of web forums that discuss questions and answers about disease facts, drug
information, and even coping mechanisms. However, this process can be time consuming and might not provide simple, comprehensible facts. With chronic diseases, many people do not know the proper ways to care for themselves because they lack of the knowledge of their disease (such as diabetes, high blood pressure, etc.). In hospitals, it is possible for chronic diabetes patients to learn care information from the books, websites, or hospital employees. An online service system FAQ (Frequently Asked Questions) was constructed on some hospitals’ websites that can provide immediate information to users. In this study, we set up document query system based on domain ontology for diabetes’ health education. We used former patient questions and analyzed the degree of similarity between the questions asked and the content of the diabetes health education document using the Fuzzy Formal Concept Analysis (FFCA) method. In this study, we used SPARQL (SPARQL Protocol and RDF Query Language) language to get documents in the framework of ontology. In our research, we built the domain ontology by collecting 50 diabetes health education documents and test forty-six sentences to evaluate the precision of our system.

並列關鍵字

FAQ ； Fuzzy Formal Concept Analysis ； Ontology ； Diabetes ； SPARQL

參考文獻

[28]黃秋玲、陳淑芬、唐善美、戴研光(2006)，探討糖尿病患者衛生教育介入措施前後之成效，福爾摩莎醫務管理雜誌，第2卷，第1期，第28-35頁。

[30]行政院衛生署著(2007)，糖尿病與我，行政院衛生署國民健康局。

[32]張麗春(2008)，健康素養－評價衛生教育計畫成效的新指標，護理雜誌，第55卷，第1期，第81-96頁。

[3]Ghassan Beydoun, (2009), “Formal concept analysis for an e-learning semantic web,” Expert Systems with Applications, Vol. 36, No. 8, pp. 10952-10961.

[4]Yu-Liang Chi , (2009), “Ontology-based curriculum content sequencing system with semantic rules,” Expert Systems with Applications, Vol. 36, No.4, pp. 7838-7847.