A Recommendation Framework towards Personalized Services in Intelligent Museum

Museum visitors are being overloaded with increasing amount and variety of information that heavens their burden to locate what is really interesting. Development of personalized service for museum visitors makes a promising effort to alleviate the problem. In this paper, a recommendation framework and the related algorithms are proposed for intelligent museum. Using both the explicit and implicit visit behaviors data, preference learning algorithm computes the preference of a visitor in exhibits. Exhibit recommendation algorithm takes a visitorpsilas preference and the public evaluation history on exhibits into account in the pre-selection and refinement of recommended exhibits. We implemented the recommendation framework based on our previously developed smart museum platform, iMuseum. The effectiveness of the proposed framework and algorithms are verified through experiments.