資訊科技的進步，許多科技的文明病因此而增加，而一般在就診過程中，也因為人數眾多問診的時間卻被壓縮得更少，且得到的病情狀況卻往往不如期望。 由於網際網路的發達，搜尋引擎的進步，通常只要把大略知道的病因輸入即可列舉出許多相關的病情，但大部分都是模糊而無法找出相似的病情，許多相關的醫療機構都會提供給病患所謂的衛教資訊，但這些資訊都是透過預先制定及條列式的病況需求，也因為這樣的機制讓問診者無法有效率獲知相關資訊。 本研究藉由從線上網路醫院之醫病回覆內容中收集大量資料，應用文字探勘技術找出非結構化的回覆內容並利用中央研究院提供的中文斷詞系統，將有用的資訊回傳並歸類成相關詞彙。 因此本研究將建構一套疾病問答系統，將問診者所提出的問題分析、比對相關詞彙再依權重比例挑選出相似度較高的答案，來幫助問診者更有效率地進行疾病問答，更可讓問診者在就醫前的參考值。 With the advancement of information technology, many diseases of civilization have appeared and increased the demand for outpatient services. As a result, patients are allowed less time for consulting physicians and usually cannot obtain as much information as expected. Due to the advent of the Internet and fast development of online search engines, it is now easy for patients to search for sick conditions and causes by symptoms. However, the search results are not entirely accurate. Many medical institutions will also provide health information to patients, but such health information is usually arranged based on a predefined list of sick conditions and cannot effectively help patients obtain necessary disease information. This study collected a large amount of information from replies of an online hospital and used text mining technique to find unstructured content of the replies. Later, this study applied the Chinese Word Segmentation System provided by Academia Sinica to convert useful information into phrases. The objective of this study was to build a Disease Question Answering System that can analyze questions brought up by patients and find answers to the most similar questions by weight from the database to help patients obtain necessary information efficiently and use it as a reference before seeking outpatient services.
