agents and web services

Abstract. This paper presents an architecture and a methodology for agent-based Web service discovery and composition. We assume that Web services are described with declarative specifications like DAML-S. Based on the declarative information about services, symbolic reasoning can be applied while searching for or composing automatically new services. We propose that symbolic agent negotiation could be used for dynamic Web service discovery and composition. Symbolic negotiation, as we consider it here, is a mixture of distributed planning and information exchange. Therefore, by using symbolic negotiation for automated service composition, we support information collection and integration during service composition. The latter aspect has been largely neglected in automated service composition until now. 1

The realization of the Semantic Web needs a set of specialized middleware as its infrastructure. In this paper we describe the principles of tuplespace computing, explain why tuplespaces are a suitable middleware for the Semantic Web, envision “Semantic Web Spaces ” 1 and outline how our tuplespace platform XMLSpaces can be extended to support Semantic Web technologies, like RDF(S) and OWL. 1.

Abstract not found

Abstract. In a real world scenario Semantic Web applications must be capable to cope with the large scale, distributed, heterogeneous, unreliable and insecure environment of the World Wide Web if they are to truly represent added value to Web users. This includes issues of persistent storage, efficient reasoning, data mediation, scalability, distribution of data, fault tolerance and security. In this paper we present a coordination middleware for the Semantic Web and demonstrate its relevance to these vital issues for Semantic Web applications by elaborating a typical use case from the traffic management domain. 1

Abstract. Various Web resources and services are usually assumed to be used and accessed by human users (current Web) or by software agents on behalf of human users (emerging Semantic Web). However industry emerges also a new group of “users”, which are smart industrial devices, robots or any other objects, which can be adapted to the (Semantic) Web environment. They would need special services for e.g. online condition monitoring, information provisioning, remote diagnostics, maintenance support, etc. The goal of this paper is to specify main requirements to Web services that automatically follow up and predict the performance and maintenance needs of field devices. Semantic Web enabled services form a Service Network based on internal and external service platforms and OntoShell software. Concepts of a “Global Understanding Environment ” and a “mobile service component ” suppose that any component can be adapted to Semantic Web environment and executed at any platform from the Service Network, including service requestor side. This allows delivering not only a service results but also a service itself. Mobile service component within an OntoShell (agent) can move to a field device’s local environment (embedded agent platform) and perform its activities locally. Service components improve their performance through online learning and communication with other components. Heterogeneous service components’ discovery is based on semantic P2P search. 1

We describe the development of a knowledge management platform for web-enabled environments featuring intelligence and insight capabilities. The effort is the result of a FP5 project under the IST initiative involving 3 universities, a technology provider and 5 user companies. The main objective of the platform is to analyse, search and present information retrieved from the web) (or any other type of document). This is achieved through the use of Multi-Agent Systems and ontologies.

In a celebrated essay on the new electronic media, Marshall McLuhan wrote in 1962: Our private senses are not closed systems but are endlessly translated into each other in that experience which we call consciousness. Our extended senses, tools, technologies, through the ages, have been closed systems incapable of

Abstract. Accessing up-to-date information in a fast and easy way implies the necessity of information management tools to explore and analyse the huge number of available electronic resources. The Web offers a large amount of valuable information, but its human-oriented representation and its size makes extremely difficult any kind of computer-based processing. In this paper, a combination of distributed AI and information extraction techniques is proposed to tackle this problem. In particular, we have designed a multiagent system that composes ontologies from taxonomies of terms. Moreover, the obtained ontology is used to represent, in a structured way, the currently available web resources. The paper analyses the application of this approach in some examples in the medical domain. 1

Abstract. The Web has changed from a mere repository of information to a new platform for business transactions where organizations deploy, share and expose business processes via Web Services. New promising application fields such as the Semantic Web and Semantic Web Services are leveraging the potential of deploying those services, but face the problem of discovering and finding them. Finally, the fact of the users expressing their wishes in natural language is hindering the efficiency of the previous approach. In this paper, we present GODO, a fully-fledged solution that combines natural language analysis and semantically-empowered techniques to ascertain how the user needs can be best fit. Our approach is backed with a proof-of-concept implementation and the empirical results of a use case where the efficiency has been proved. 1