基於現今地域型社交網絡（LBSN）與路徑資訊網站的普及，旅遊規劃因此成為熱門研究議題，例如POI和旅遊行程推薦。然而，基於路徑資料的行程推薦難以取得大量資料。而生成旅遊行程則可以靠提取POI的特徵來篩選熱門景點並組合成旅遊行程。然而，日前的旅遊行程推薦研究缺乏除了問券以外，基於準確性的驗證方法。基於上述缺點，本研究以增強學習建立旅遊推薦系統以生成和推薦旅遊行程。通過限制迭代(Limit iteration)的設計，使用者能根據自己想去旅行的地點和日期長度的進行客製化。而為達到生成熱門旅遊行程之目的，模型將提取POI特徵以構建獎勵函數(Reward function)以對POI進行排名並評估各景點熱門程度。驗證方面，基於旅行社提供的歷史旅遊行程資料提出兩大驗證模型，旅行預測神經網路模型(Trip Prediction Network model)和路徑相似模型(Trajectory similarity model)實現成團預測，並實驗及檢驗旅遊推薦行程的成團率。實驗結果顯示預測模型高於國內知名比賽的預測準確度，而旅遊推薦行程和成團行程基於統計方法上沒有顯著差異。

Due to the popularity of Location based social network(LBSN) and Trajectory related site nowadays, trip planning researches became hot issue, such as POI and travel package recommendation. However, travel package recommendation suffers from data collecting difficulty of trajectory data. As to generating travel packages for recommendation, it may be a task it may be a task to extract the characteristic between POIs and proposed a ranking method for POI selection while generating travel packages. Finally, the research mainly lies on questionaires and lack of precision based on validation methodologies. Based on the drawbacks metioned above, a recommendation framework based on Reinforcement learning was proposed to generate and recommend travel packages. By a limit iteration technique design, the model can retrieve customized packages with the quried place and day length required by the user. To reach the objective of the generating popular travel packages, POI chracteristics were extracted to construct the reward function to rank POIs and evaluate their popularity. Based on labeled travel package data provided by travel agency, two prediction methodologies, Deep learning and Trajectory similarity were applied for trip guaranteed prediction, which was provided for validating the recommended packages generated from the reinforcmenet learning model. The results shows the precisions of the two prediction models were acceptable, while the recommended packages takes no statistic significant difference with the uncanceled packages.

[1] L.-Y. Wei, W.-C. Peng, W.-C. Lee, “Exploring Pattern-Aware Travel Routes for Trajectory Search”, ACM Transactions on Intelligent Systems and Technology, Vol. 3, No. 3, Paper No. 48, 2013
[2] Zhiwen Yu, Yun Feng, Huang Xu, Xingshe Zhou “Recommending travel packages based on mobile crowdsourced data”, IEEE Communications Magazine, Vol 52, Issue 8, 2014
[3] David Silver, Aja Huang, Chris J. Maddison, “Mastering the game of Go with deep neural networks and tree search.”, Nature, volume 529, pages 484–489, 2016
[4] Matthew S. Emigh ; Evan G. Kriminger ; Austin J. Brockmeier ; José C. Príncipe ; Panos M. Pardalos, “Reinforcement Learning in Video Games Using Nearest Neighbor Interpolation and Metric Learning”, IEEE Transactions on Computational Intelligence and AI in Games, 2016
[5] Mufti Mahmud, Mohammed Shamim Kaiser, Amir Hussain, Stefano Vassanelli, “Applications of Deep Learning and Reinforcement Learning to Biological Data”, IEEE Transactions on Neural Networks and Learning Systems , 2018
[6] Dongxia Zhang, Xiaoqing Han, Chunyu Deng, “Review on the Research and Practice of Deep Learning and Reinforcement Learning in Smart Grids”, CSEE Journal of Power and Energy Systems, 2018
[7] Tommaso Mannucci, Erik-Jan van Kampen, Cornelis de Visser, Qiping Chu,“Safe Exploration Algorithms for Reinforcement Learning Controllers,”IEEE Transactions on Neural Networks and Learning Systems., vol.29, Issue.4, 2016
[8] Mehdi Mohammadi, Ala Al-Fuqaha, Mohsen Guizani, Jun-Seok Oh, “Semisupervised Deep Reinforcement Learning in Support of IoT and Smart City Services”, IEEE Internet of Things Journal, 2017
[9] Yueh-Hua Wu, Shou-De Lin, “A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents,” The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 2017
[10] Ricardo Grunitzki, Gabriel de Oliveira Ramos, Ana Lucia Cetertich Bazzan, “Individual Versus Difference Rewards on Reinforcement Learning for Route Choice,” Brazilian Conference on Intelligent Systems, 2014
[11] Kathleen M. Jagodnik, Michael S. Branicky, “Training an Actor-Critic Reinforcement Learning Controller for Arm Movement Using Human-Generated Rewards”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017
[12] Jin-Ling Lin ,Kao-Shing Hwang ,Wei-Cheng Jiang ,Yu-Jen Chen, “Gait Balance and Acceleration of a Biped Robot Based on Q-Learning, IEEE Access Vol.4, 2016
[13] Jui-Hung Chang, Chen-En Tsai, Jung-Hsien Chiang, “Using Heterogeneous Social Media as Auxiliary Information to Improve Hotel Recommendation Performance”, IEEE Access Vol.6, 2018
[14] Rong Gao, Jing Li, Bo Du, Xuefei Li, Jun Chang, Chengfang Song, Donghua Liu, “Exploiting geo-social correlations to improve pairwise ranking for point-of-interest recommendation”, China Communications, 2018
[15] Liu L, Mehandjiev N, Xu D-L,“Multi-criteria service recommendation based on user criteria preferences,”In: Proceedings of the fifth ACM conference on recommender systems. ACM, pp 77–84, 2011
[16] Santos, F., Almeida, A., Martins, C., Oliveira, P., Gonçalves, R. “Tourism recommendation system based in user’s profile and functionality levels” In: Desai, E. (ed.) Proceedings of the Ninth International C* Conference on Computer Science and Software Engineering, pp. 93–97. ACM, New York, 2016
[17] Wayne Xin Zhao, Ningnan Zhou, Aixin Sun, “A time-aware trajectory embedding model for next-location recommendation” , Knowledge and Information Systems, Volume 56, Issue 3, pp 559–579, 2018
[18] Frikha M, Mhiri M, Gargouri F, “Designing a user interest ontology-driven social recommender system: Application for Tunisian Tourism”, 13th Conference on Practical Applications of Agents and Multi-Agent Systems in series Advances in Intelligent Systems and Computing, Vol. 372, pp 159-166
[19] Hai-Tao Zheng ; Yingmin Zhou ; Nan Liang “Exploiting User Mobility for Time-aware POI Recommendation in Social Networks”, IEEE Access, Early Access , 2017
[20] Weimin Zheng ; Xiaoting Huang ; Yuan Li ,”Understanding the tourist mobility using GPS: Where is the next place”, Tourism Management, 2017
[21] Shuhui Jiang, Xueming Qian, Tao Mei, Yun Fu “Personalized Travel Sequence Recommendation on Multi-Source Big Social Media”, IEEE Transactions on Big Data, vol.2, Issue.1, 2016
[22] Qi Liu ; Enhong Chen ; Hui Xiong ,“A Cocktail Approach for Travel Package Recommendation”, IEEE Transactions on Knowledge and Data Engineering, vol.26, 2014
[23] Jui-Hung Chang, Chien-Yuan Tseng, Ren-Hung Hwang and Mi-Chia Ma,"Using ANN to Analyze the Correlation Between Tourism-related Hot Words and Tourist Numbers: A Case Study in Japan" IEEE SC2 7th, Japan Kanazawa, Nov 22-25, 2017
[24] J.P.Teixeira, P.O.Fernandes,“Tourism time series forecast with artificial neural networks,” Tekhne, vol. 12, no. 1-2, pp. 26-36. Jan-Dec , 2014
[25] A.Majid, L.Chen, G.Chen, H.T.Mirza, I.Hussain, J.Woodward, “A context-aware personalized travel recommendation system based on geotagged social media data mining,” International Journal of Geographical Information Science, vol. 27, no. 4, pp. 662-684, 2013
[26] O.Claveria, S.Torra,“Forecasting tourism demand to Catalonia: Neural networks vs. time series models,” Economic Modelling, vol. 36, pp. 220-228, Jan 2014
[27] H.A.Constantino, P.O.Fernandes, J.P.Teixeira, “Tourism demand modelling and forecasting with artificial neural network models: The Mozambique case study,” Tékhne, May 2016
[28] Hassan.M., Hamada.M, “A Neural Networks Approach for Improving the Accuracy of Multi-Criteria Recommender Systems”Applied Science, 2017
[29] Dongjie Wang, Yan Yang, Shangming Ning, “DeepSTCL: A Deep Spatio-temporal ConvLSTM for Travel Demand Prediction”, 2018 International Joint Conference on Neural Networks (IJCNN), 2018
[30] Junyi Ji ; Jun Hou, “Forecast on Bus Trip Demand Based on ARIMA Models and Gated Recurrent Unit Neural Networks”, 2017 International Conference on Computer Systems, Electronics and Control (ICCSEC) , 2017
[31] Yu-Jun Zheng, Wei-Guo Sheng, Xing-Ming Sun, Sheng-Yong Chen, “Airline Passenger Profiling Based on Fuzzy Deep Machine Learning”, IEEE Transactions on Neural Networks and Learning Systems, Vol. 28, Issue 12
[32] Chaiyaphum Siripanpornchana ; Sooksan Panichpapiboon ; Pimwadee Chaovalit “Travel-Time Prediction With Deep Learning”, IEEE Region 10 International Conference, 2016
[33] Yangdong Liu , Yizhe Wang , Xiaoguang Yang , Linan Zhang, “Short-term travel time prediction by deep learning: A comparison of different LSTM-DNN models”, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017
[34] Zhihao Zhang , Peng Chen , Yunpeng Wang , Guizhen Yu, “A hybrid deep learning approach for urban expressway travel time prediction considering spatial-temporal features” , 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017
[35] Ai Dong, Zhijiang Du, Zhiyuan Yan, “Round Trip Time Prediction Using Recurrent Neural Networks With Minimal Gated Unit”, IEEE Communications Letters, Vol.23, Issue. 4
[36] Xiong Gang, Wenwen Kang, Feiyue Wang, Fenghua Zhu, Yisheng Lv, Xisong Dong, Jukka Riekki, “Continuous Travel Time Prediction for Transit Signal Priority Based on a Deep Network”, 2015 IEEE 18th International Conference on Intelligent Transportation Systems, 2015
[37] Yu-Wei Chang ; Chih-Yung Tsai “Apply deep learning neural network to forecast number of tourists”, International Conference on Advanced Information Networking and Applications Workshops (WAINA), 2017
[38] Lu Sun, Wei Zhou, Baichen Jiang, Jian Guan,“A Real-time Similarity Measure Model for Multi-source Trajectories”, International Conference on Computing Intelligence and Information System ,2017
[39] Na Ta ,Guoliang Li, Yongqing Xie, Changqi Li, Shuang Hao, Jianhua Feng, “Signature-Based Trajectory Similarity Join”, IEEE Transactions on Knowledge and Data Engineering, 2017
[40] Chunyang Ma ; Hua Lu ; Lidan Shou ; Gang Chen ,“KSQ: Top-k Similarity Query on Uncertain Trajectories”, IEEE Transactions on Knowledge and Data Engineering, vol.25, 2013