Automated Negotiation Between Autonomous Computational Agents And It's Application In Electronic Commerce

Intelligent agents are a new paradigm for developing software applications. More than this, agent-based computing has been hailed as 'the next significant break-through in software development' (Sargent, 1992), and 'the new revolution in software' (Ovum, 1994). Currently, agents are the focus of intense interest on the part of many sub-fields of computer science and artificial intelligence. Agents are being used in an increasingly wide variety of applications, ranging from comparatively small systems such as email filters to large, open, complex critical systems such as air traffic control. Especially the rapid development of Internet provides agents a wide stage .Electronic commerce , on-line education, science computing, web-based information filtering and data mining all are suitable to this technology.In systems composed of multiple agents, negotiation is a key form of interaction. Particularly because the agents are autonomous and cannot be assumed to be benevolent, agents must influence others to convince them to act in certain ways, and negotiation is thus critical for managing such inter-agent dependencies.Electronic commerce is changing the way business is conducted.Electronic negotiation is the vital part of it [1][2][3]. Agents provide a new paradigm for automated negotiation in electronic commerce. This thesis based on the background of electronic commerce proposes a practically computational model of automated negotiation between intelligent agents and two kinds of negotiation strategies based on it. More an learning-based electronic commerce negotiation algorithm is given and an agent-based virtual electronic market prototype system is developed .