An Ontology Solution for Language Interoperability between Agents
Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)
Traditional negotiation systems have been implemented using agent architectures, where agents communicate exchanging negotiation primitives generated by each system, based on particular language definitions implicitly encoded, giving different syntax and semantics to their messages. In this paper we address the problem of communicating heterogeneous negotiation agents in a Web-based environment, considering differences in their message implementations. Our research is based in the development
... a shared ontology for publishing definitions of negotiation primitives, and a translator module, which is executed only when a misunderstanding occurs. We implemented a service-oriented architecture for executing negotiations and conducted experiments incorporating heterogeneous agents. The results of the tests show that the proposed solution improves communication between negotiation agents. Keywords Ontology, multi-agent systems, electronic negotiation. INTRODUCTION E-business and e-commerce applications have gained attention from software vendors, system integrators, solution providers, business and research community. Participating in open markets based on Internet represents a great opportunity to increase the number of potential contracts and alliances between enterprises. But software platforms have not achieved the maturity needed to automate business processes over the Internet. Such is the case of electronic negotiation systems, which is the central point of our research. Electronic negotiation is a process in which two or more software agents interact and take decisions for mutual gain. Communications in electronic negotiation systems are essential to achieve cooperation and take decisions. Traditional negotiation systems have been implemented in controlled and homogeneous agent-based environments, where agents communicate through the exchange of messages based on standard language specifications, for example KQML (Finning, 1994) or FIPA ACL (FIPA, 2003). Although negotiation messages are based in one of these specifications, detailed syntax and meaning of such messages differ from one system to another depending on the developer' s convenience, causing heterogeneity. Recently there has been a growing interest in conducting negotiations over Internet, and integrating multiple negotiation agents into a public Web-based marketplace. The challenge of deploying and integrating heterogeneous agents in open and dynamic environments is to achieve interoperability at the communication level, reducing misunderstandings of exchanged messages during negotiation processes. The language used by agents to exchange messages is defined as agent communication language (ACL). An ACL allows an agent to share information and knowledge with other agents, or request the execution of a task. KQML was the first standardized ACL from the ARPA knowledge project. KQML consists of a set of communication primitives aiming to support interaction between agents. KQML includes many performatives of speech acts. Another standard ACL comes from the Foundation for Intelligent Physical Agents (FIPA) initiative. FIPA ACL is also based on speech act theory, and the messages generated are considered as communicative acts. The objective of using a standard ACL is to achieve effective communication without misunderstandings, but this is not always true. Because, standards specify the semantics of communicative acts, but the software implementation is not explicitly defined, leaving developers to follow their own criteria. Furthermore, standard ACL specifications consider the incorporation of privately developed communicative acts.