Online travel support systems have often been cited as an ideal proving ground for agent-based architectures, yet no working systems have materialized. Over the last few years we have been considering various aspects of the design of such travel support systems. The aim of this note is to present the current state of our comprehensive framework for delivering personalized travel services using agent infrastructure. 1.

We consider the construction and management of user profiles for an agent-based travel support system, with the goal of providing personalized content for individual users of the system. Profiles consist of statements about the "world of travel." Conditional probabilities for each statement model the strengths of user preferences. These probabilities are derived from implicit and explicit observations of user behavior.

This paper describes our efforts to semantically describe travelrelated documents on the Internet. We focus on the areas of lodging and gastronomy, with allowance for further expansion into other aspects of the world of travel. Based on an analysis of currently-available data, we develop hotel ontology. Furthermore, we explicitly define an ontology for the Chefmoz project data, which has no official schema. Finally, we sketch a way to combine these two ontologies for use in an integrated travel framework. 1.

Typically, when marketing specialists approach commerce, they relay heavily on statistical models that make predictions about the behavior of the entire customer population, or divide potential buyers into groups that are similar according to a selected criterion. We believe that e-commerce requires further individualization of buyer-seller relations. However, to achieve a true content personalization including expertise of a psychologist would be of extreme importance.

In order for software agent technology to come to full fruition, it must be integrated in a realistic way with existing production technologies. In this paper we address one of the interesting problems of real-world agent integration: the interaction between agents and non-agents. The proposed solution is designed to provide non-agents (client software in particular) access to agent services, without restricting the capabilities of agents providing them.

In order for software agent technology to come to full fruition, it must be integrated in a realistic way with existing production technologies. In this paper we address one of the interesting problems of real-world agent integration: the interaction between agents and non-agents. The proposed solution is designed to provide non-agents (client software in particular) access to agent services, without restricting the capabilities of agents providing them. 1. Introduction. The

In this paper we look at the ways leading Internet content providers such as Yahoo! and Google categorize travel-related web resources, and contrast their methods to an alternate scheme underlying the business-communication specification of the Open Travel Alliance. Our analysis reveals some inherent weaknesses in each approach to resource categorization and a need for a more comprehensive solution. In formulating a new classification scheme for travel resources we attempt to take advantage of the strengths and improve on the weaknesses of existing systems. 1.

In this paper we discuss the problem of indexing information available on the Internet, with the ultimate goal of delivering personalized content to users of an Internet-based travel support system. We introduce the form of index tokens that will be stored in the system and describe an agent-based subsystem designed to support the indexing function. Finally, we discuss the search agent that was developed to provide the system with index tokens and allow to experiment with the proposed design.. 1

In this note we discuss the problem of indexing information from the Internet, with the goal of delivering personalized content to users of an Internet-based travel support system. We introduce the form of index tokens that will be stored in the system and describe an agent-based subsystem designed to support the indexing function.

As indicated in the literature, agent-based technology should naturally fit the architecture of a travel support system. However, proposals presented thus far have been relatively limited in scope or have not gone beyond early planning stages. The aim of this note is to introduce a comprehensive framework for delivering personalized travel services using an agent infrastructure. 1.