Integrating Knowledge-Level Agents in the (Semantic) Web: an Agent-based Open Service Architecture (original) (raw)

An ontology, intelligent agent-based framework for the provision of semantic web services

Expert Systems With Applications, 2009

Intelligent agents and semantic web services are two technologies with great potential. Striking new applications can be developed by using the tools and techniques they provide. However, semantic web services need for an upper software entity able to deal with them and, on the other hand agent technology has historically suffered from a number of drawbacks that must be addressed. Integrating these two technologies in a joint environment can overcome their problems while strengthening their advantages. In this paper, the necessity for integrating these technologies and the potential benefits of their combination are analyzed. Based on this study, we present SEM-MAS, an ontology-based framework for seamlessly integrating Intelligent Agents and Semantic Web Services. The basics of the framework are detailed and a proof-of-concept implementation described.

Intelligent web servers as agents

2004

Software agents have been recognized as one of the main building blocks of the emerging infrastructure for the Semantic Web, but their relationship with more standard components, such as Web servers and clients, is still not clear. At the server side, a possible role for agents is to enhance the capabilities of servers using their intelligence to provide more complex services and behaviors. In this paper we explore the role of agents at the server side presenting an Open Service Architecture (OSA) which extends the centralized Internet Reasoning System (IRS-II) to a distributed scenario. The architecture uses a distributed facilitation protocol which integrates Web Services with agent communication languages. Finally we present an implementation which extends Tomcat with these features.

Implementing Agent-based Web Services

2003

As part of the Agentcities project, we have developed a prototype of an Evening Organiser application which allows users to flexibly and dynamically schedule activities within an itinerary. The Evening Organiser and the Web-accessible restaurant and cinema services which it uses have been developed within a generic service environment and the implementation of this has been built using the April Agent Platform, the DAML+OIL ontology language, the DAML Query Language and the Java Theorem Prover. This service environment is populated with agents of different natures, such as service instances and service finders. Service instances represent individual business entities, such as restaurants and cinemas. Service finders represent aggregated views over service instances, such as Yahoo!-hosted restaurants or Citysearch-hosted cinemas. The details of the implementation of these Web Services are described through the use of a motivating scenario.

Agents based on Semantic Web Services Initiative Architecture

The Semantic Web Services Initiative Architecture (SWSA) describes the overall process of discovering and interacting with Semantic Web services in three phases and denes a conceptual model to accomplish the specied requirements of these phases. This conceptual model is based on semantic service agents that provide and consume semantic web services and includes architectural and protocol abstractions. In this paper 1 , a software platform is dened which fullls fundamental requirements of SWSA's conceptual model including all its sub-processes. Based on this software platform, requirements of the planner module are identied and such a planner has been implemented. The developed planner has the capability of executing plans consisting of special tasks for semantic service agents in a way that described in SWSA. These special tasks are predened to accomplish the requirements of SWSA's sub-processes and they can be reused in real plans of semantic service agents both as is and as specialized according to domain requirements.

Semantic Web Services for Multi-Agent Systems Interoperability

Progress in Artificial Intelligence, 2019

Agent-based technologies are often used including existing web services. The outputs of some services are also frequently used as inputs for other services, including other MAS. However, while agent-based technologies can be used to provide services, these are not described using the same semantic web technologies web services use, which makes it difficult to discover, invoke and compose them with web services seamlessly. In this paper, we analyse different agent-based technologies and how these can be described using extensions to OWLS. Additionally, we propose an architecture that facilitates these services' usage, where services of any kind can be registered and executed (semi-)automatically.

An Agent Platform for the Semantic Web

This paper presents the FRED system, a development environment for agent-based applications that utilize Semantic Web resources. The FRED system consists of an agent runtime environment based on ontologies as the underlying data model and offers a tool suite for application development. It uses progressive technologies for task-service-resolution that detect suitable problem solving implementations to solve tasks assigned to agents.

Agent Technology Meets the Semantic Web: Interoperability and Communication Issues

Advanced Information and Knowledge Processing, 2010

This overview paper is a survey of recent research on agent technologies and how this technology can serve the scopes of the Semantic Web project. In a short time, Web has become the dominant database for information retrieval. Due to the exponential growth of the Web and the information it provides, finding accurate information is becoming more and more difficult. In the near future, access to Web will be mediated by intelligent applications and software agents that will assist users in finding accurate information and complete transactions successfully. Concisely, the Semantic Web means ontologies and semantics, software agents means multi-agents systems (MASs) built in FIPA [11] and other agent platforms with their own standards, and Web services means XML. We will try to investigate the way these technologies can cooperate without changing their specifications.

Web-Services based Ontology Agent

The 2nd International Conference on Distributed Frameworks for Multimedia Applications, 2006

The Multi-Agent Systems (MAS) represent an environment for the design, development and deployment of Intelligent and Distributed Processing Systems focused on sophisticated applications, as the collaborative learning [1] and the auctions [2]. This paradigm aims for the encapsulation of specific functionalities in an intelligent and autonomous software component called Agent. So in order to support a cooperative platform among Agents is necessary to share the knowledge domain and to make easy the administration of the Ontologies repositories. This kind of role is carry out by an Ontology Agent, which receives demands of specific services from the Agents of the MAS, deals with them and responds with the appropriate message. Therefore in this work is depicted a methodology for building Ontology Agents that are encoded as Web Services to federate functionalities regarding to the administration of Ontologies through the Internet. The aim of the paper is to encourage the development of specialized Agents that integrate all the tasks for managing Ontologies, and that offer them to the Agents community.