近年來，適地性社群網路(Location-Based Social Network, LBSN)越來越受歡迎，它們提供了一個平台讓使用者透過打卡記錄分享他們到訪的地點和經驗，由此發展出許多應用，旅遊推薦就是其中之一。一般來說，使用者旅遊時會以群組的方式去旅遊，把他喜歡的景點以及附近的一些景點遊覽完再移動到下一個區域，我們稱之為景區(Region Of Interest, ROI)，以前的景點推薦系統(Point Of Interest, POI Recommendation)多數以TOP-K方式推薦使用者K個POI，而使用者需要自己再從這些結果中規劃行程，POI Recommendation並沒有完全幫使用者規劃好真正屬於該使用者的行程，失去了旅遊推薦能為使用者進行個人化規劃的目的。此外，POI recommendation推薦的POIs很可能距離太遠或不適合，以這些結果來規劃行程會更不準確。因此我們提出了景區推薦系統，在offline的部分，利用LBSN的打卡記錄統計各天數行程的單天行程，然後分別利用距離、機率、圖劃分出各天數景區，在online的部分，我們根據使用者喜好和景區熱門程度推薦適合景區給使用者，使系統更符合旅遊推薦系統的2個初衷：(1)符合使用者旅遊時的行為，(2)省時又能個人化規劃。

In these years, Location-Based Social Network, LBSN, becomes more and more popular. A platform for users to share their visits and experiences through check-ins records is provided and thereby many applications are being developed. Travel recommendation system is actually one of them. Users normally visit the spots in groups when they travel. They will only move to the next travel area after visited all their favorite spots and some nearby attractions in one area. We call this Region Of Interest (ROI). The recent travel recommendation systems (Point Of Interest, POI Recommendation) normal recommend the spots in amount of K to the users by the TOP-K calculation method. Users need to plan their trips from these results themselves. The POI Recommendation system does not help the users to plan a prefect visiting schedule entirely and thus cannot fulfill the purpose of personalized visiting schedule planning. Moreover, POIs recommended by the POI recommendation system are always too far away of each other or unsuitable for traveling. The planned schedules with these results are inaccurate. Therefore, we propose a scenic spot recommendation system which uses the LBSN's check-ins records to count every single-day schedule of the trips in different days in the offline section. Then divide the scenic spots in areas according to the days of trip by distance, probability and map. Finally recommend the suitable attraction areas to the users according to their preferences and the popularity of the attraction areas in the online section. So that such system is more in line with the two original intentions of the travel recommendation system: (1) in line with the users’ traveling behavior, (2) time-saving and personalized schedule planning.

[1] Li, Huayu, et al. “Point-of-Interest Recommender Systems: A Separate-Space Perspective,” Data Mining (ICDM), 2015 IEEE International Conference on. IEEE, 2015.
[2] J. Bao, Y. Zheng, and M. F. Mokbel, “Location-based and Preference-Aware Recommendation Using Sparse Geo-Social Networking Data, ” in SIGSPATIAL 2012.
[3] H. P. Hsieh, C. T. Li, S. D. Lin, “TripRec: Recommending Trip Route from Large Scale Check-in Data, ” in WWW 2012.
[4] Long Guo, Jie Shao, Kian Lee Tan, Yang Yang, “WhereToGo: Personalized Travel Recommendation for Individuals and Groups,” Mobile Data Management (MDM).
[5] A. jameson and B. Smyth, “Recommendation to groups,” 2007.
[6] Quan Yuan, Gao Cong and Aixin Sun, “Graph-based Point-of-interest Recommendation with Geographical and Temporal Influences,” CIKM 2014.
[7] Wan Ting Hsu, Yu Ting Wen, Ling Yin Wei and Wen Chih Peng, “Skyline Travel Routes: Exploring Skyline for Trip Planning,” Mobile Data Management (MDM).
[8] J. J. Levandoski, “LARS:A location-aware recommender system,” ICDE2012.
[9]Yu Zheng, Xing Xie, “Learning travel recommendations from user-generated GPS traces,” ACM Transaction on Intelligent Systems and Technology.
[10] Bin Yang, Chenjuan Guo, Christian S. Jensen, Manohar Kaul, Shuo Shang, “Stochastic Skyline Route Planning Under Time-Varying Uncertainty,” ICDE 2014.
[11] H. P. Hsieh, C. T. Li, and S. D. Lin, “Exploiting Large-Scale Check-in Data to Recommend Time-Sensitive Routes,” SIGKDD pp. 56-62, 2012.
[12] G. Linden, B. Smith, and J. York, “Amazon.com recommendations: item-to-item collaborative filtering,” IEEE Internet Comput., no. February, 2003.
[13] Yehuda Koren, “The BellKor Solution to the Netflix Grand Prize,” Netflix prize documentation, Vol. 81, pp. 1-10, 2009.
[14] E. H. C. Lu, C. Y. Chen, and V. S. Tseng,“Personalized Trip Recommendation with Multiple Constraints by Mining User Check-in Behaviors,” in SIGSPATIAL 2012.
[15] Wen, Yu-Ting, et al. "KSTR: Keyword-aware skyline travel route recommendation." Data Mining (ICDM), 2015 IEEE International Conference on. IEEE, 2015.
[16] Y. Arase, X. Xie, T. Hara, and S. Nishio, “Mining People’s Trips from Large Scale Geo-tagged Photos,” Proceedings of the ACM Multimedia International Conference (ACM-MM), pp. 133-142, 2010.
[17] A. J. Cheng, Y. Y Chen, Y. T. Huang, W. H. Hsu, and H. Y. M. Liao, “Personalized Travel Recommendation by Mining People Attributes from Community-Contributed Photos,” Proceedings of the 19th ACM international conference on Multimedia. ACM, pp. 83-92, 2011.
[18] T. Horozov, N. Narasimhan, and V. Vasudevan, “Using location for personalized POI recommendations in mobile,” Int. Symposium on Applications and the Internet, pp. 1-6, 2006.
[19] X. S. Khoshgoftaar, “A Survey of Collaborative Filtering Techniques,” In Advances in Artificial Intelligence, vol. 19, no. 4, 2009.
[20] J. Sang, T. Mei, J. T. Sun, C. Xu, and S. Li, “Probabilistic sequential POIs recommendation via check-in data,” Proceedings of the 20th International Conference on Advances in Geographic Information Systems, ACM, pp. 402-405, 2012.
[21] M. Sarwat, J. J. Levandoski, A. Eldawy, and M. F. Mokbel, “LARS*: A Scalable and Efficient Location-Aware Recommender System,” IEEE Transactions on Knowledge and Data Engineering TKDE, 2014.
[22] H. Wang, T. Manolis, and M. Nikos, “Location recommendation in location-based social networks using user check-in data,” SIGSPATIAL pp,374-383, 2013.
[23] J. J. C. Ying, E. H. C. Lu, W. N. Kuo, and V. S. Tseng, “Urban point-of-interset recommendation by mining user check-in behaviors,” SIGKDD pp. 55-62, 2012.
[24] “Foursquare,” https://foursquare.com.
[25] “Netflix,” http://www.netflix.com.
[26] “Flickr,” http://www.Flickr.com.
[27] “Amazon,” http://www.amazon.com/.