Smart City: A Rule-based Tourist Recommendation System
We are presenting the architecture of a personalised recommendation system using probabilistic reasoning. The system creates plans for visiting interesting objects and events on the trip, based on the personal preference profile. We will provide a short d
- PDF / 1,403,273 Bytes
- 12 Pages / 595.32 x 785.16 pts Page_size
- 28 Downloads / 198 Views
Abstract We are presenting the architecture of a personalised recommendation system using probabilistic reasoning. The system creates plans for visiting interesting objects and events on the trip, based on the personal preference profile. We will provide a short description of the system architecture, its main components and the probabilistic reasoner along with a small ruleset example with score calculations. The described architecture and components comprise the first iteration of the Smart City system. Keywords: Recommendation engine; tourism; semantic web; rule-based reasoning
1
Introduction
People planning a trip often start investigations by looking for materials on the Internet. The user can find a large amount of information about the city and its popular tourism objects, but it takes a long time to select the most interesting objects and create a good plan for a visit. For example, consider a tourist planning a two-day visit to Paris. If she wants to put together an organized plan for those days, she will first have to find all the potentially interesting objects in Paris. Then she will have to decide which ones she would like to visit. After that she will have to organize the selected objects into a schedule. It may turn out that some of the objects do not fit into the time schedule, in which case she will have to select different objects. All this takes a lot of effort. Our project focuses on automating the object selection and visit schedule creation. Smart City (SC) is a semantic recommender and route composer system for tourists. A tourist can specify her location, time of the visit and her preferences about different types of objects and events. Based on the created profile, the suggestion engine finds interesting objects for the given user. For each found object a score of "interestingness" is found. The objects that the user probably likes have a higher score and vice versa. The objects and events are organized into a timetable based on their location and time. Finally the schedule and the trip route will be presented to the user. The tourist has an option to modify the suggested objects and to create a more suitable timetable.
R. Law et al. (eds.), Information and Communication Technologies in Tourism 2011 © Springer-Verlag/Wien 2011
52
The system is currently undergoing the public test phase (see http://gn61.zone.eu/gui/) and will be properly deployed at the beginning of 2011 with the initial launch in Tallinn, Estonia, to be followed by several cities outside Estonia. The adequate business analysis of the first deployment phase can be given after the system has been fully exploited for at least several months/half a year. However, we would like to point out our initial business assumptions and foreseeable business implications. First of all, the system is not targeting the functionality of traditional tourism sites, hence it would obviously make sense to deploy the system as a search/planning component of a larger tourism site. This is exactly the plan for the initial deployment in Tallin
Data Loading...
