Nowadays personalization is becoming one of the main requisites of tourism sector. A step toward this personalization is achieved through this project. It focuses on personalised tour planning, based on route planning algorithms and recommendation techniques integration. The following goals are envisaged in the project: 1) Tourism domain knowledge base modelling through the use of ontologies or concept graphs, including sights, transportation and users profiles. 2) Recommendation strategies considering adaptive content selection based on context and user interest modelling can be an effective way to select information, giving to tourist a high level of personalisation. 3) Route planning algorithms can combine places of interest with transportation alternatives and schedules, resulting in detailed planned itineraries for the personalised tour plans previously generated. 4) The use of the adaptive hypermedia through adaptive presentation can improve content understanding turning the system more attractive, adapting better to its users; It suggested by (Buhalis, 2001) that eTourism revolutionizes all business processes, the entire value chain as well as the strategic relationships of tourism organizations with all their stakeholders. So, it increasingly determines the competitiveness of the organization, and therefore, it is critical for the competitiveness of the tourism industry in the longer term. One of the most frequent problems faced by tourists when visiting a country, a particular region or a city is deciding what to do, where to go and how to reach there, in a limited amount of time available. The most widespread information is offered by means of guidebooks which contain general purpose references, with little relevance to the interest of a particular individual, often the tourist find himself lost among that information. Tailoring information to the interests of the visitor along with journey plans suggestions seems to be the best alternative in order to improve tourist’s activities. This project focuses on personalised tour planning including sights, transportation modes and users profiles, based on route planning algorithms and adaptive recommendation techniques integration. Adaptive recommendation strategies considering adaptive content selection based on context and user interest modelling can be an effective way to select information, giving to tourist a high level of personalisation. Route planning algorithms can combine places of interest with transportation alternatives and schedules, resulting in detailed planned itineraries for the personalised tour plans previously generated. The system gathers knowledge about the tourist’s profiles, creating groups and stereotypes with specific interests and features, allowing characteristics inheritance. The “tour basket” stores tourist’s travel history, where all the places he visited are stored, which leads to accumulated knowledge about personal profiles. This knowledge, together with tourist stereotypes offer a mean of learning about general and specific interests of tourists, so that this information can serve as a basis for studying new forms of tourist products, which can be useful for the tourism sector, namely public entities (e.g. city council) as well as for travel agencies. It will, also, be possible, for the tourist, to return information on accomplished tours. So, the system gathers knowledge about tourist’s opinions and preferences. Based on this knowledge and on profile groups categorised information can be delivered according to tourist specific interests, namely events, factual information, useful tips, promotional offers, recommended places to visit and more. TOURS PLAN system can be used by city councils in order to explore better their tourism resources and give tourists a personalized service, which can be very attractive and improves tourism service offer.
Ongoing since December 1st 2007, concludes in November 30 2010.
Funding entity: GECAD (ISEP).
Reference: PTDC/EIA/74310/2006
Funding: 95000.
Principal researcher: Nuno C. Marques.
Funding: 9960.