請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58426
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 吳家麟(Ja-Ling Wu) | |
dc.contributor.author | Cheng-Yao Fu | en |
dc.contributor.author | 傅承堯 | zh_TW |
dc.date.accessioned | 2021-06-16T08:14:44Z | - |
dc.date.available | 2014-02-26 | |
dc.date.copyright | 2014-02-26 | |
dc.date.issued | 2014 | |
dc.date.submitted | 2014-02-13 | |
dc.identifier.citation | [1] [Yahoo! Travel] http://travel.yahoo.com/trip
[2] [tripadvisor] http://www.tripadvisor.com/ [3] Xin Lu et al, “Photo2Trip: Generating Travel Routes from Geo-Tagged Photos for Trip Planning”, In ACM MM, 2010. [4] Dunstall S et al (2003), “An automated itinerary planning system for holiday travel”, Inf Technol Tour 6:195–210. [5] Ardissono L et al (2005), “A multi-agent infrastructure for developing personalized web-based systems”, ACM Trans Internet Tech 5:47–69. [6] Yu Zheng et al, “Learning Travel Recommendations from User-Generated GPS traces”, ACM Transactions on Intelligent Systems and Technology, January 2011. [7] Hyoseok Yoon et al, “Smart Itinerary Recommendation Based on User-Generated GPS Trajectories”, Ubiquitous Intelligence and Computing, 2010. [8] Hyoseok Yoon et al, “Social itinerary recommendation from user-generated digital trails”, Journal of Personal and Ubiquitous Computing, 2012. [9] Zhijun Yin et al, “Diversified Trajectory Pattern Ranking in Geo-Tagged Social Media”, In Proceedings of the Eleventh SIAM International Conference on Data Mining, SDM 2011. [10] Xin Cao et al, “Keyword-aware Optimal Route Search”, VLDB, 2012. [11] Hsun-Ping Hsieh et al, “Exploiting Large-Scale Check-in Data to Recommend Time-Sensitive Routes”, UrbComp, 2012. [12] Steven Van Canneyt et al, “Time-Dependent Recommendation of Tourist Attractions using Flickr”, In 23rd Benelux conference on Artificial Intelligence, 2011. [13] Jinyoung Kim et al, “TripTip: A trip planning service with tag-based recommendation”, ACM CHI’09. [14] Takeshi Kurashima et al, “Travel route recommendation using geotags in photo sharing sites”, ACM CIKM’10. [15] Jiang et al, “ContextRank: Personalized Tourism Recommendation by Exploiting Context Information of Geotagged Web Photos”, IEEE International Conference on Image and Graphics, 2011. [16] An-Jung Cheng et al, “Personalized Travel Recommendation by Mining People Attributes from Community-Contributed Photos”, ACM MM’11. [17] Zhang Mu et al, “Design and development of the travel recommendation system”, IEEE International Conference on Management and Service Science, 2009. [18] D. Lowe, “Distinctive image features from scale-invariant keypoints”, Int. J. Computer Vision, 60(2), 2004. [19] A. Oliva and A. Torralba, “Modeling the shape of the scene: a holistic representation of the spatial envelope”, Int. J. Computer Vision, 42(3), 2001. [20] Golden et al, “The orienteering problem”, Naval Research Logistics (NRL), Volume 34, Issue 3, pages 307–318, June 1987. [21] P. Vansteenwegen et al, “The orienteering problem: A survey”, European Journal of Operational Research 209 (2011). [22] P. Vansteenwegen et al, “Iterated local search for the team orienteering problem with time window”, Computers & Operational Research 2009. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58426 | - |
dc.description.abstract | 旅遊規劃一直以來都是件非常繁雜且耗時的作業。規劃者通常必須花費大量的氣力將旅遊地點的相關資料搜索閱覽過,才有辦法得到有用的資訊,進而規劃出高質量的旅遊行程。隨著社群網站的蓬勃發展,規劃者現在可以根據旅遊網誌、照片等等,直接遵循前人的旅遊行程。然而,每個規劃者都有其不同需求,例如:出發時間、想去的景點、想看的景色以及住宿地點…都會有差異。再加上景點的開放時間限制,因此景點的抵達時間合理性也必須被妥善考慮。這些因素都將使得前人的旅遊行程無法直接被套用,規劃者通常需要再搜索資料並做個人化的修改。如此可以看出,規劃者仍需花費非常多的時間才能規劃出高質量的旅遊行程。為解決此問題,我們提出了一個考慮抵達時間合理性及客製化需求的旅遊行程規劃系統。確切地說,我們的系統從Flickr上蒐集各景點的照片,並利用這些資料自動估算出景點及路線的熱門程度、景點開放時間…。接著使用者可以加入進一步的客製化需求例如:指定的必去景點、抵達時間、住宿地點…。最後,系統會在滿足抵達時間合理性及客製化需求這些條件的情況下計算出一高質量的旅遊行程。由於最後計算行程的步驟是一NP-hard的問題,因此我們提出了一個快速且有效的啟發式演算法來解決。此外,我們也設計了一個可以自動挑選出景點在不同季節、不同時段之代表性景色的使用者介面,以幫助使用者完成其客製化行程的需求。在研究中,我們經由客觀及主觀評估的實驗結果驗證了該系統規劃行程的有效性。而使用者研究的實驗結果也證實了本文所提出的使用者介面可以有效地幫助使用者進行行程規劃。 | zh_TW |
dc.description.abstract | Trip planning is a very taxing and time-consuming task. Planners usually have to put a lot of effort into searching over data about their travel destination to obtain useful information so that they can arrange a high-quality itinerary. With the rapid development of social websites, now planners can just follow other people’s previous itineraries by viewing their travelogue, travel photos, etc. However, every planner has different needs, for example, the starting travel time, attractions to go, scenery to see and hotels of different planners would all differ. Plus attractions’ available visiting time interval in a day should also be considered. All these factors would make other people’s previous itineraries not directly applicable, so planners have to search over data again and then modify other people’s previous itineraries to suit their needs. In other words, planners still need to spend lots of time on planning an itinerary with high-quality. To solve this problem, we propose a trip planning system considering arrival time feasibility and specific customer’s need. More specifically, our system first crawled photos of every attraction from Flickr, and facilitate these data to mine the popularity of attractions, popularity of paths among them, available visiting time interval of attractions, and so on. Next, users can input their customized needs, for instance, must-go attractions, specified arrival time, hotels, etc. Finally, our system will generate a high-quality itinerary given that conditions of arrival time feasibility and customized needs are fulfilled. Since the final step is an NP-hard problem, we propose an efficient and effective heuristic algorithm to solve it. We also design an UI which can select each attraction’s representative visual scenes in different seasons and different timing in a day, to help users complete their customized needs. In this work, experimental results of objective and subjective evaluation both prove the effectiveness of itinerary generated by our system. The results of user study also show that the proposed UI can effectively help users plan their trips. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T08:14:44Z (GMT). No. of bitstreams: 1 ntu-103-R00944012-1.pdf: 2328974 bytes, checksum: 15cc0215383bff7c3bc5975d58876a02 (MD5) Previous issue date: 2014 | en |
dc.description.tableofcontents | 口試委員議定書 i
致謝 ii 中文摘要 iii ABSTRACT iv CONTENTS v LIST OF FIGURES vii LIST OF TABLES ix Chapter 1 Introduction 1 Chapter 2 Related Work 5 Chapter 3 Travel Information Extraction 8 3.1 Estimation of Popularity of Attraction and Paths 8 3.2 Estimation of Typical Stay Time 9 3.3 Estimation of Available Visiting Time Interval In a Day 9 3.4 Featured Visual Scenes Generation 12 Chapter 4 Route Planning 15 4.1 Problem Statement 15 4.2 The Proposed Heuristic Algorithm 17 4.2.1 Insertion Phase 18 4.2.2 Local Search Phase 21 4.2.3 Improved Algorithm 23 Chapter 5 Experimental Results 25 5.1 Estimation of available visiting time interval in a day 25 5.1.1 Settings 25 5.1.2 Results 26 5.2 Route Planning 26 5.2.1 Execution Time 27 5.2.2 Objective Evaluation 30 5.2.2.1 Settings 30 5.2.2.2 Results 31 5.2.3 Subjective Evaluation 40 5.2.3.1 Settings 40 5.2.3.2 Results 41 5.3 System UI 44 Chapter 6 Conclusion and Future Works 46 Bibliographay 48 | |
dc.language.iso | zh-TW | |
dc.title | 考慮抵達時間合理性及客製化需求之旅遊行程規劃系統 | zh_TW |
dc.title | A Trip Planning System Considering Arrival Time Feasibility and Specific Customer’s Need | en |
dc.type | Thesis | |
dc.date.schoolyear | 102-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 朱威達(Wei-Ta Chu),胡敏君(Min-Chun Hu),陳炳宇(BY Chen) | |
dc.subject.keyword | 資料探勘,旅遊行程推薦,路線規劃,使用者介面, | zh_TW |
dc.subject.keyword | Data mining,travel recommendation,route planning,user interface, | en |
dc.relation.page | 49 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2014-02-13 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-103-1.pdf 目前未授權公開取用 | 2.27 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。