English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 51281/86342 (59%)
造訪人次 : 8150284      線上人數 : 58
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/102570


    題名: 時間限制之旅遊景點推薦
    其他題名: Time-constrained scenic spots recommendation
    作者: 謝濬謙;Hsieh, Chun-Chien
    貢獻者: 淡江大學資訊工程學系碩士班
    許輝煌;Hsu, Hui-Huang
    關鍵詞: 推薦系統;網路應用程式;戶外;Recommendation System;Web App;GPS;outdoor
    日期: 2014
    上傳時間: 2015-05-04 09:59:09 (UTC+8)
    摘要: 隨著我國生活水準不斷提高,旅遊活動安排之頻率亦隨之提高,迄今已成為國人日常生活不可或缺之要素了。台灣被稱為福爾摩沙即是美麗之島之意思,因此面對國內這許多美景、古蹟、文化與藝術以及美食等特色之景點等,如何在旅遊前規劃該次主題旅遊或針對特定景點,在有限的時間內,連同周邊特色景點一併瀏覽,是一件值得開發與探究之主題。基此;本研究即使要建構一個務實之景點推薦系統,會主動偵測使用者所在位置,並在接收使用者所輸入旅遊時間後自動估算,推薦旅遊路線給使用者,該系統擬採用WebApp的形式來服務不同平台的使用者,透過無遠弗屆與便利之網際網路,讓想旅遊之國人,能在任何有網路的地方來使用這套系統。本系統是以新北市為測試標的,首先收集並彙整新北市各特色景點並依其行政區編撰旅遊景點資料庫,接著使用HTML5 Geolocation API,Geolocation API能讓伺服器藉由使用者裝置上的感應器定位使用者位置,再透過Google Distance Matrix API辨識最接近的行政區,此時系統查詢景點資料庫便會讀取這個行政區裡的旅遊景點,再次利用Distance Matrix計算使用者位置到景點以及景點之間的移動時間,最後根據使用者輸入的時間限制,把這些資料都傳送給推薦演算法。
    我們的推薦演算法跟傳統的推薦系統有很大的差異,傳統的推薦方法常利用分析資料或是找出使用者間的關聯性來做推薦,但是這些方法無法解決我們的問題,因此我們採用了一個新的演算法,從使用者附近的旅遊景點裡進行搜索,尋找滿足使用者時間限制而且分數最高的旅遊路線,最後把包含花費時間最少的旅遊路線在內總共兩條路線推薦給使用者,根據實驗的結果,高於九成五的測試者願意使用我們的推薦系統進行屢有規劃。基此;本研究所開發之”時間限制之旅遊景點推薦系統”是一個值得用來規畫旅遊管理之好系統。
    As the people''s living quality improvement,the frequency of outdoor activities especially traveling was increased as well. The most headache problem of traveling is we don`t have enough time to visit all spots which we are interested. And we are also afraid to spend too much time in moving, especially the time was limited. If there is a inquire system could give us a suitable suggestion to plan our journey according our location and our time, it will be helpful for us to plan a good, a meaningful trip.
    The goal of this study is to build a time-constrained scenic spots recommendation system of trip which is not only to search user`s location, but also to consider the traveling time of user, then give a recommend set of significant spots to users. Nowadays internet was well developed, we could build a WebApp system to service users from different platforms, and people could use this system in everywhere if the internet is available.
    The New Taipei city was selected to be the test sample for system, and to collect and integrate the character spots of this city was the first step of this system. Then we compile the scenic spots data bank of this city based on the district of previous spots.
    In this system, HTML5 Geolocation API could help us to locate users, and to know which district is nearest by Google Distance Matrix API. Then inquiry system will identify all spots in this district, and estimate the moving time from one scenery to another by Distance Matrix. Finally, Base on the previous information and the available traveling time of user, the system will deductive the best two sightseeing way to user, including the minimum spent time for touring.
    According the feedback of real test, we got highly recognized,and more than 95% tester expressed that they will use this system to schedule their travel plan. Obviously; time-constrained scenic spots recommendation system is worthy to be a tour management system.
    顯示於類別:[資訊工程學系暨研究所] 學位論文

    文件中的檔案:

    檔案 大小格式瀏覽次數
    index.html0KbHTML66檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

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