Modern smart environments pose several challenges, among which the design of intelligent algorithms aimed to assist the users. When a variety of points of interest are available, for instance, trajectory recommendations are needed to suggest users the most suitable itineraries based on their interests and contextual constraints. Unfortunately, in many cases, these interests must be explicitly requested and their lack causes the so-called cold-start problem. Moreover, lengthy travelling distances and excessive crowdedness of specific points of interest make itinerary planning more difficult. To address these aspects, a multi-agent itinerary suggestion system that aims at assisting the users in an online and collaborative way is proposed. A profiling agent is responsible for the detection of groups of users whose movements are characterised by similar semantic, spatial and temporal features; then, a recommendation agent leverages contextual information and dynamically associates the current user with the trajectory clusters according to a Multi-Armed Bandit policy. Framing the trajectory recommendation as a reinforcement learning problem permits to provide high-quality suggestions while avoiding both cold-start and preference elicitation issues. The effectiveness of the approach is demonstrated by some deployments in real-life scenarios, such as smart campuses and theme parks.
|Numero di pagine||17|
|Rivista||CAAI Transactions on Intelligence Technology|
|Stato di pubblicazione||Published - 2021|
All Science Journal Classification (ASJC) codes