近來，旅遊資訊廣被旅遊者在網路上使用。雖然網路上的資訊十分豐富，但是使用者仍常常難以找尋到精準的資訊。而旅遊商品的特性為無形的，所以使用者不能實際地來評估這個服務直到他實際地體驗之後。也就是因為此種特性，所以如何讓使用者在真正體驗到之前能夠取得可信與真實的旅遊資訊變得十分重要。為了解決此問題，語意網絡的概念即出現來解決人與電腦間溝通的問題。而一個本體即是由一個正式化的、某一具有精確規格概念的領域來提供之可實行的平台來發展可信的旅遊資訊服務。 在本論文中，我們探討了旅遊推薦系統的發展、其遭遇的問題、語意網相關之技術包含了：網路本體語言、資源描述架構、和一些目前現有的旅遊本體發展的情況。此外，為了要能提供更智慧化的旅遊行程規劃推薦服務，我們將語意的想法帶入了此領域。我們會提出一個方法讓智慧型旅遊行程推薦服務能在本體論的基礎上實現。所以，一系列的旅遊本體會被建構發展，來讓我們的芻形系統能夠做出行程推薦的服務。此提出的系統能夠驗證語意網的概念在旅遊推薦領域的可行性。它亦能利用屬性與之間的關係來推薦出更智慧型的資訊，找出個人化的景點、活動與行程給旅行者。 / Nowadays, travel information is increasing to appeal the tourists on the web. Al- though there are numerous information provided on the web, the user gets puzzled in nding accurate information. The tourism product has an intangible nature in that cus- tomers cannot physically evaluate the services on oer until practically experienced. This makes access to credible and authentic information about tourism products before the actual experience very valuable. In order to solve these problems, the concept of seman- tic web comes into existence to have communication between human and computer. An Ontology being a formal, explicit specication of concepts of a domain provides a viable platform for the development of credible tourism information services. In this paper, we discuss the development of travel recommendation system, the problems it encounters, the related technology about semantic web including OWL, RD- F/RDFS, and some current circumstances of the existing tourism ontologies as well. Futhermore, in order to make more intelligent travel planning recommendation services, we bring the idea of semantic into tourism domain. We will present an approach aimed at enabling intelligent recommendation services in tourism support systems using ontolo- gies. A suite of tourism ontologies was developed and engaged to enable a prototypical tourism system with recommednation capabilities. The proposed system can verify the feasibility and concept of taking semantic web technology into tourism recommendation systems domain. It also can recommend more intelligent information using properties, relationships of travel ontology, and is responsible for nding personalized attractions, activities and a trip itinerary for travelers.

摘要 　　觀光旅遊是現今十分興盛的休閒活動，根據 2010 至 2012 年交通部觀光局統計資料顯示，國人國內旅遊以非旅行社承辦平均高達約 88%，因此如何有效規劃行程內容及安排各景點間的交通路線，就成為旅遊前的重要準備工作。 　　檢視目前旅遊規劃的數位服務平台並無法真正解決旅遊需求。故本研究設計與建置一套旅遊支援平台，首先藉由訪談，了解使用者需求，歸納出平台設計重點，分析系統的使用流程，再設計功能模組化與操作介面，最後建置平台並進行原型評估。本平台以雲端資料庫為基礎，無縫結合網站與行動應用兩端的資訊流。使用者在行前利用網站規劃行程內容，完成後上傳至雲端資料庫，網站端內容會自動同步於行動應用端，並以適合行動應用的界面呈現。使用者之行程安排因此更便利與彈性，在行動中亦能利隨時以手機查看行程，並依當地情況修改行程、即時安排交通路徑，使得旅遊行程計畫可以依實際的變化機動調適。而更新後的行程亦同步儲存於雲端。 　　本研究未來方向可以往更多的服務串流發展，如景點的多媒體內容、社群結合、智慧邏輯排程或外部資訊連結等等。隨著未來資訊技術的提升，將為系統平台帶來更多可能性、讓整體服務擁有更佳的整合性，提供使用者更好的體驗。 / Nowadays, touring is a popular leisure activity. According to statistics from the Taiwan Tourism Bureau, people arranged their own domestic travels as high as 88%. Because backpacking can be economical and more flexible, many young people tend to travel by themselves. Therefore travel planning has become the most important preparation work. How to plan an effective schedule and how to arrange the routes between attractive points are the tasks that backpackers often need to face. However there are few information services for the needs currently. The thesis designed and implemented a travelling support platform. First, the research identified design key elements by interviewing users and analyzing travelling behaviors. Second, the research mapped the touring process into functional models. Finally, we built and tested the platform prototype. This platform is Cloud-based and seamlessly integrates both website and mobile application to achieve the information service. Users use the website to schedule their trips and upload the schedules to the cloud database. Then the user can access the same schedule made at website on the mobile APP synchronously. They can check their schedule while they are traveling on the mobile phones. In addition, they can edit the schedule and rearrange new traffic routes real-time to adjust to the local circumstances. The further developments of the platform will include more integrated services, such as multimedia contents, social network, and intelligent logic scheduling. With the evolution of the technology in the future, the platform will provide better user experience.

近年來隨著全球化的發展，自助旅行的風氣蔚為風潮。背包客可以根據自己的喜好與條件，自己規劃旅遊路線與行程。一般規劃旅遊行程的過程費時而繁瑣，除了必須決定旅遊景點，還必須將景點開放時間、景點停留時間、交通方式、旅遊順序與路線、時間限制、住宿地點、經費等列入考量。 針對旅遊行程規劃，除了參考網友的行程規劃，目前已普遍有景點推薦、行程編輯系統，協助使用者規劃行程。但少有旅遊行程自動規劃系統。因此，本論文研發實作旅遊行程的自動規劃系統MyTripPlan。MyTripPlan具備景點推薦、景點停留與拜訪時間預估、路線規劃、行程規劃及行程調整的功能。 本系統MyTripPlan在離線時，先透過爬蟲程式由景點推薦網站取得熱門景點資訊、由相片分享網站取得景點相片時間以推估景點停留及拜訪時間、由交通查詢網站取得任兩景點間的推估交通時間。在線上時，當使用者輸入旅遊天數等時間限制、並由系統推薦景點勾選有興趣拜訪的景點及餐廳後，系統將運用定向排程演算法推論出符合時間限制的旅遊行程，呈現在地圖上，並結合交通網站，產生行程表。 經實驗效能驗證，以安排旅遊天數七天，五十六個景點所需要的行程規劃時間約為一秒鐘；使用者對於實作完畢的MyTripPlan系統與功能也都有滿意以上的評分。 / Travel planning process is time-consuming and tedious. To plan a trip, not only the attractions, but opening hours, timing cost, travel route, transportation, lodge, budget control and so on also need to be considered. While there are widespread attraction recommendation and itinerary editing systems to assist people to plan their trip, only few trip automated planning systems are developed. In this thesis, MyTripPlan, an automatic trip planning system, is designed and developed. MyTripPlan The system provides users the capability of attraction recommendation, visiting and stay time estimation, route planning, trip planning and itinerary adjustments. In offline process, MyTripPlan collects popular attraction information from web content for attraction recommendation, gets the timestamp of attractions from photo-sharing websites to estimate visiting and stay time, and crawls traffic information from public transportation query site to estimate the travel time between attractions. Given the trip duration, MyTripPlan recommends attractions and restaurants, schedules and produces the trip itinerary automatically based on the team orienteering scheduling algorithm. The generated itinerary takes the user-preferred attractions, visiting and stay time constraints, and transportation information into consideration. MyTripPlan presents the trip itinerary both in map and schedule list. The experiments show that the execution time for trip plan with fifty-six attractions in seven days requires about one second. Moreover, nineteen subjects were invited to evaluate the effectiveness of MyTripPlan. Most users were satisfied and gave excellent rating on the system performance.