Towards an automatic multi-agent system for joining information from specialized Web sites

In many cases the information required is on the Internet in different formats and comes from heterogeneous data sources. There are mainly two ways of retrieving and integrating information with those features: a manual or an automatic process. In the latter case, it is needed to develop a system according to certain rules and criteria. This paper presents a multi-agent system that integrates information from heterogeneous specialized Web sites. Every agent in the group has different abilities and activities, such as the following: retrieving automatically information about call for papers for conferences from different specialized Web sites., which have different structures; extracting information from them; concentrating it in their own storage system; and visualizing it through a flexible Web site with different search options. Additionally., a Web service interface is provided by the multi-agent system., which allows other systems to retrieve call for papers from it., establishing a certain degree of interoperability to the full system by providing its information in a standard XML format.