This paper proposes a recommendation systembased on big data framework and rule-based system in theera of Internet of Things. With the emergence of the smartdevices beginning from smart phones extends to the generalelectronic devices such as smart tv sets, refrigerators, washingmachines, robot vacuums, and so on. Such smart devicesmake it possible to collect the device-usage logs of end userswhereby a system is able to analyze it to find the usage patternsof the end users and make recommendations to the endusers. Furthermore, this allows to make recommendations onthe individual users since the smart devices have their ownidentifiers such asMAC address and IPv6 address. The smartdevices also have matched informationwith the end user id/s.In this study, we propose a method for analyzing the devise-usage patterns in semi-real time based on the big-data systemarchitecture. We also present a recommendation frameworkwhich makes device-usage recommendations by using a rulebasedsystem architecture with the analyzed usage patterns.Lastly, we introduce a segmentation-based analysis and recommendationframework to make recommendations basednot only on his or her own usage patterns, but also on the commonusage patterns of the users who are living in a similarcontext. The segmentation is formed also based on the typesof the device usages, so that the analysis can be performed ina batch process thereby enabling to make the recommendationsin real time based on the pre-analyzed usage patterns.
Recommendation system; Rule-based system; Big data; Internet of Things