在進入人人都擁有智慧行動裝置與物聯網的時代後，實體店面的零售業者開始在店內布置各式智慧裝置，藉此收集消費者的資訊並在行動裝置上推薦各式促銷商品。然而，網路與實體零售業者目前皆受限於資訊碎片化的可應用範圍之限制，導致無法更全面性的瞭解使用者的偏好，造成推薦內容常常不是消費者真正需要的，更無法讓廣告內容成為對消費者有用的資訊。另外，消費者無法自主地擁有與跨場域的應用屬於自己的偏好資訊，且消費者的智慧行動裝置與周遭智慧裝置的互動是單向且固定的，導致智慧裝置僅提供制式化服務，因此消費者只能被動地接受店家提供的廣告推薦服務，也無法充分發揮物聯網時代應有的效益。基於上述問題，本研究希望透過「潛行式消費偏好收集與發掘模組（Market and Discover，或MnD）」自然地收集使用者與日常生活相關物件互動之情境資訊，在不影響使用者日常生活的前提下達到持續發掘使用者的潛在偏好，再藉由「移動式本體資訊即時雲端匹配模組（Match and Recommend，或MnR）」，提供有效率與準確的雲端匹配，讓使用者可以透過所儲存的偏好資訊主動與店家微定位裝置協同提供客製化可攜式或是跨應用場域服務，最後透過「伺機式（Probabilistic）智慧元件跨協定互動模組（Meet and Interact，或MnI）」，透過此模組讓使用者裝置與隨機所遇到的環境智慧裝置建立動態且互惠地連接及互動，並藉此提供使用者更輕鬆製作可攜式服務，讓系統能更根據當下環境的既有設備自動重構服務，達到服務自動跟隨的效果，上述的模組將可大大降低在智慧環境中的人力介入，更能因應物聯網系統跨螢與碎片化時代所帶來的挑戰。透過測試，MnD在探索等級越高的情況下，使用者偏好本體的節點數在使用初期會成長越快速，但只要經過一定時間的使用後，由於使用者的偏好已大致探索完成，所以節點數量會成長趨緩並漸漸收斂。此外透過MnR的匹配可比傳統的匹配技術更能精確探索出相似的物品並根據不同的本體樹大小減少15%~50%的時間。最後利用MnI可成功與環境智慧裝置互動，不再局限制式化的服務，本研究也透過展示情境來展現其效益。

The upcoming IoT era enables everyone to own various mobile smart devices, and a retailer with a physical store begins to deploy all kinds of smart devices in the store to collect consumers’ information for recommending advertisements via mobile smart devices. However, both the data collected by online and physical retailers can only partially reflect customers’ daily lives, resulting in very limited understanding of their preferences. The fragmented preferences often lead to undesirable service recommendations. In addition, the consumers cannot autonomously apply their own preferences for cross-field services, which reduces the system reusability and forces the consumers to passively accept unwanted advertising service. Furthermore, the interactions between consumers' mobile devices and the ambient ones are unidirectional and non-customizable, leading to inflexible services and being unable to fully leverage the benefits of IoT. To address the above issues, this study first collects more comprehensive information from various shopping (or purchasing) sources, i.e., on-line and off-line stores, through the "Market and Discover, or MnD" module to implicitly and continuously explore customers’ potential preferences. Next, the customers can quickly and efficiently match their preferences with the ones from nearby stores to receive more flexible and desirable services through the "Match and Recommend, or MnR" module. Finally, the proposed "Meet and Interaction, or MnI" module enables the cusomers’ mobile devices to dynamically connect with a variety of smart sensors and actuators, integrated via the beacons of a smart store, to establish reconfigurable services such that bidirectional interactions can be realized to leverage the benefits from ever-increasing ambient smart things around us. With the above modules, the resultant IoT-enabled recommendation system will be able to reduce human intervention and make better use of IoT benefits and advances. In our experimental results, when the MnD chose higher level to explore, user preference nodes increased drastically in the beginning, but converge when the system has explored the users’ preferences. The MnR can recommend more accurately than those of the previous matching technologies and faster by about 15%~50% in execution time. Finally, in the testing scenario the MnI enables the mobile devices to connect flexibly with a variety of smart sensors and actuators in different fields.

[1] "Worldwide Retail Ecommerce Sales Will Reach $1.915 Trillion This Year," https://www.emarketer.com/Article/Worldwide-Retail-Ecommerce-Sales-Will-Reach-1915-Trillion-This-Year/1014369.
[2] "THE BEACONS REPORT: Growth Forecasts For The Most Important Retail Technology Since The Mobile Credit Card Reader," http://www.businessinsider.com/beacons-are-the-most-important-new-retail-tech-2014-7.
[3] "Connected: A Way Of Life," https://www.mediapost.com/publications/article/279008/connected-a-way-of-life.html.
[4] C.-N. Hsu, H.-H. Chung, and H.-S. Huang, "Mining Skewed and Sparse Transaction Data for Personalized Shopping Recommendation," Machine Learning, journal article vol. 57, no. 1, pp. 35-59, October 01 2004.
[5] D. Kelly and J. Teevan, "Implicit feedback for inferring user preference: a bibliography," in ACM SIGIR Forum, 2003, vol. 37, no. 2, pp. 18-28: ACM.
[6] M. Tu, Y.-K. Chang, and Y.-T. Chen, "A Context-Aware Recommender System Framework for IoT based Interactive Digital Signage in Urban Space," in Proceedings of the Second International Conference on IoT in Urban Space, 2016, pp. 39-42: ACM.
[7] A. Paul and S. Rho, "Probabilistic Model for M2M in IoT networking and communication," Telecommunication Systems, journal article vol. 62, no. 1, pp. 59-66, May 01 2016.
[8] A. Krause, A. Smailagic, and D. P. Siewiorek, "Context-aware mobile computing: Learning context-dependent personal preferences from a wearable sensor array," IEEE Transactions on Mobile Computing, vol. 5, no. 2, pp. 113-127, 2006.
[9] I. Arapakis, Y. Moshfeghi, H. Joho, R. Ren, D. Hannah, and J. M. Jose, "Enriching user profiling with affective features for the improvement of a multimodal recommender system," in Proceedings of the ACM International Conference on Image and Video Retrieval, 2009, p. 29: ACM.
[10] X. Amatriain, "Mining large streams of user data for personalized recommendations," ACM SIGKDD Explorations Newsletter, vol. 14, no. 2, pp. 37-48, 2013.
[11] A. Makazhanov, D. Rafiei, and M. Waqar, "Predicting political preference of Twitter users," Social Network Analysis and Mining, vol. 4, no. 1, p. 193, 2014.
[12] A. H. Nabizadeh et al., "Predicting User Preference Based on Matrix Factorization by Exploiting Music Attributes," presented at the Proceedings of the Ninth International C* Conference on Computer Science & Software Engineering, Porto, Portugal, 2016.
[13] Y. Zheng, B. Mobasher, and R. Burke, "Emotions in context-aware recommender systems," in Emotions and Personality in Personalized Services: Springer, 2016, pp. 311-326.
[14] M. F. Alhamid, M. Rawashdeh, H. Dong, M. A. Hossain, and A. El Saddik, "Exploring latent preferences for context-aware personalized recommendation systems," IEEE Transactions on Human-Machine Systems, vol. 46, no. 4, pp. 615-623, 2016.
[15] J. Wang, M. Qiu, B. Guo, Y. Shen, and Q. Li, "Low-power sensor polling for context-aware services on smartphones," in High Performance Computing and Communications (HPCC), 2015 IEEE 7th International Symposium on Cyberspace Safety and Security (CSS), 2015 IEEE 12th International Conferen on Embedded Software and Systems (ICESS), 2015 IEEE 17th International Conference on, 2015, pp. 617-622: IEEE.
[16] S. E. Middleton, D. C. De Roure, and N. R. Shadbolt, "Capturing knowledge of user preferences: ontologies in recommender systems," in Proceedings of the 1st international conference on Knowledge capture, 2001, pp. 100-107: ACM.
[17] M. Y. Kiang, J. Gilsdorf, and R. T. Chi, "Understand user preference of online shoppers," in e-Technology, e-Commerce and e-Service, 2004. EEE'04. 2004 IEEE International Conference on, 2004, pp. 123-130: IEEE.
[18] Z. Yu, G. Chen, Z. Yu, and X. Zhou, "Extracting user preference from human natural interactions with physical items," in Signal Processing, Communications and Computing (ICSPCC), 2011 IEEE International Conference on, 2011, pp. 1-5: IEEE.
[19] J. Ho and C.-M. Wang, "User-Centric and Real-Time Activity Recognition Using Smart Glasses," in Green, Pervasive, and Cloud Computing: Springer, 2016, pp. 196-210.
[20] S. Rezaei and M. Amin, "Exploring online repurchase behavioural intention of university students in Malaysia," Journal for Global Business Advancement, vol. 6, no. 2, pp. 92-119, 2013.
[21] T. Lu and T. Li, "Predicting Customer's Preference in E-Commerce Recommendation System: A Genetic Algorithm Approach," in Innovative Computing, Information and Control, 2007. ICICIC'07. Second International Conference on, 2007, pp. 420-420: IEEE.
[22] Y. Kim, J. Lee, S. Park, and B. Choi, "Mobile advertisement system using data push scheduling based on user preference," in Wireless Telecommunications Symposium, 2009. WTS 2009, 2009, pp. 1-5: IEEE.
[23] D. Byun, J. Cho, S.-J. Moon, and D. Hong, "S-Beacon: Next generation BLE beacon solution for enhanced personalization," in Consumer Electronics (ICCE), 2016 IEEE International Conference on, 2016, pp. 166-167: IEEE.
[24] V. Hans, P. S. Sethi, and J. Kinra, "An approach to IoT based car parking and reservation system on Cloud," in Green Computing and Internet of Things (ICGCIoT), 2015 International Conference on, 2015, pp. 352-354.
[25] M. Zhu et al., "Public Vehicles for Future Urban Transportation," IEEE Transactions on Intelligent Transportation Systems, vol. PP, no. 99, pp. 1-10, 2016.
[26] M. S. Biradar, "Recommender Systems: A Survey," 2016.
[27] K. Kotis and A. Katasonov, "An ontology for the automated deployment of applications in heterogeneous IoT environments," Semantic Web Journal, 2012.
[28] J. Euzenat and P. Shvaiko, Ontology matching. Springer, 2013.
[29] P. M. Sahu and D. Sable, "Targeted Advertising using Location," International Journal of Research and Engineering, vol. 4, no. 1, pp. 16-21, 2017.
[30] G. Sato, G. Hirakawa, and Y. Shibata, "Push Typed Tourist Information System Based on Beacon and Augumented Reality Technologies," in 2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), 2017, pp. 298-303.
[31] D.-Y. Liu, C.-S. Wang, and K.-S. Hsu, "Beacon applications in information services," in Advanced Materials for Science and Engineering (ICAMSE), International Conference on, 2016, pp. 438-440: IEEE.
[32] J. Dunkel, "On Sensor Fusion for Location-Based Recommender Systems," in Computing and Networking (CANDAR), 2016 Fourth International Symposium on, 2016, pp. 266-271: IEEE.
[33] S. Cirani et al., "A Scalable and Self-Configuring Architecture for Service Discovery in the Internet of Things," IEEE Internet of Things Journal, vol. 1, no. 5, pp. 508-521, 2014.
[34] P. Dhar and P. Gupta, "Intelligent parking Cloud services based on IoT using MQTT protocol," in 2016 International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT), 2016, pp. 30-34.
[35] L. Otero-Cerdeira, F. J. Rodríguez-Martínez, and A. Gómez-Rodríguez, "Ontology matching: A literature review," Expert Systems with Applications, vol. 42, no. 2, pp. 949-971, 2015.
[36] F. Giunchiglia, P. Shvaiko, and M. Yatskevich, "S-Match: an algorithm and an implementation of semantic matching," in European semantic web symposium, 2004, pp. 61-75: Springer.
[37] "電子發票應用API規格 1.4.4 版," https://www.einvoice.nat.gov.tw/home/Article!showArticleDetail?articleId=1458552353387.
[38] G. Bajaj, R. Agarwal, P. Singh, N. Georgantas, and V. Issarny, "A study of existing Ontologies in the IoT-domain," arXiv preprint arXiv:1707.00112, 2017.