Mining same-taste users with common preference patterns for ubiquitous exhibition navigation

In a ubiquitous exhibition, an intelligent navigation service that can provide booths' information, recommend interesting booths and plan touring path is required for both visitors and vendors. The preference mining module is the kernel. This paper proposes a group-based user preference pattern mining method, which can be implemented as a preference mining module in this service. When the visiting traces that imply the preference of users are recorded, the method discovers user preference patterns with high representativeness and high discrimination from the historical visiting logs. According to the discovered model, collaborative recommendation can be accomplished, and then the intelligent navigation service can plan personalized touring path based on the recommendation lists. For demonstrating the performance of the proposed method, we engage some experiments, and then indicate the characteristics of the proposed method.