An Intelligent Tour Assistant Using CBR (Case Based Reasoning)

Abstract

This master thesis describes the general architecture and function of an intelligent recommendation system aimed at supporting a leisure traveller in the task of planning a good holiday package. In the paper researcher present such a system, called “intelligent Travel Assistant” a system that can learn about user preferences over a time and suggest travel plans that fit in to these preferences. The system enables the users to identify their own destination and to personalize the travel by aggregating elementary items such as additional locations to visit within the selected destination, additional services like accommodation, transport, guide and activities like things to do and things to see during the holiday. Case-Based Reasoning (CBR) methodology; a branch of Artificial intelligence is one way to solve this problem by enabling the user to browse a repository of past travel plans and make possible the ranking of the elementary items included in a recommendation when these are selected from a case base. To solve a current problem: the problem is matched against the cases in the case base, and similar cases are retrieved. The retrieved cases are used to suggest a solution which is reused and tested for success. If necessary, the solution is then revised. Finally the current problem and the final solution are retained as part of a new case that is added to the case base. Case-based reasoning is liked by many people as they feel happier with examples rather than conclusions separated from their context. A case library can also be a powerful corporate resource, allowing everyone in an organisation to tap into the corporate case library when handling a new problem. The system can integrates data and information originating from external databases, already existent system, tourist portals and data mapping techniques, similarity-based retrieval and online recommendation processing. There are main two specific objectives of this research implementation. Help tourists to plan their own tours via online through a web based intelligent travel recommender system and organizations can automate their tour planning process, increasing the interest and maximizing the client involvement via tour planning to improve the end customers’ satisfaction. The ultimate goal of this web-based intelligent recommender system is to represent an interactive tool capable of adapting to the dialogue process as it learns about user. This project will also bring innovative results in the area of Cased-Based recommendations systems and tourist destination modelling.