• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.89-96
• /
• 2001

Agent-mediated electronic markets have been a grow-ing area of agent research and developmen tin recent year. There exist a lot of e-commerce sites on the In-ternet(e.g. Priceline, com, Amazon, com etc). These e-commerce site have proposed new business models for effective and efficient commerce activity. Intelli-gent agents have been studied very widely in the field of artificial intelligence, For purpose of this paper, an agent can act autonomously and collaboratively in a network environment on behalf of its users. It is hard for people to effectively and efficiently monitor, buy, and sell at multiple e-commerce sites. If we intro-duce agent technologies into e-commerce systems, we can expect to further enhance the intelligence of their support. In this paper, we propose a new coopera-tion mechanism among seller agents based on exchang-ing their goods in our agent-mediated electronic market system. G-Commerce. On G-Commerce, seller agents and buyer agents negotiate with each other. In our model, seller agents cooperatively negotiate in order to effectively sell goods in stock. Buyer agents coopera-tively form coalitions in order to buy goods based an discount proices. Seller agent's negotiation goods. Our current experiments show that exchanging mechanism enables seller agents to effectively sell goods in stock. Also, we present the Pareto optimality of our exchang-ing mechanism.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.16-22
• /
• 2001

There is no doubt that agents play an increasingly predominant role in e-commerce, whether these are business-to-consumer or business-to-business applications. However most of the current e-commerce agents only support a single bid for a product at a fixed price. Although price is an important factor, it is not the only concern of both business and consumer. There is doubt as to whether such agents satisfv both parties. Negotiation on a variety of issues is needed in order to reach an agreement. In this paper, a computational agent negotiation(CAN) model is proposed to facilitate multiple-issue negotiation via an agent. The main contribution of the CAN model is it enables agent to participate actively in the negotiation with various feedback instead of simply an agreement or rejection.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제28권11호
• /
• pp.842-854
• /
• 2001

오늘날의 1세대 구매 에이전트는 상품의 전체 특징 변수(attribute)에 대해서보다는 주로 판매자들이 제시한 가격만 비교해서 구매행위를 대행해 주고 있으며, 간혹 가격 이외의 변수에 대한 비교를 해주는 에이전트의 경우에도 협상(negotiation) 과정에서 전체 변수를 적절하게 고려해주는 협상 모델은 찾아보기 힘들다. 따라서 전자 상거래의 협상 모델(negotiation model)을 가격 변수뿐만 아니라 상품의 전체 변수로 확장 시켜 주는 것이 절실히 요구되고 있다. 본 논문에서는 유틸리티(utility) 이론과 간결한 휴리스틱스(simple heuristics)에 바탕을 두어서 가격, 상품의 특성, 보장 기간, 서비스 정책 등에 대해서 협상을 벌이는 에이전트 중재에 의한 전자 상거래 협상 모델을 제시하고, 이를 구현하는 프레임워크 Pmart의 원시 시스템에 관해서 논한다. Pmart는 객체 지향 기술에 바탕을 둔 소프트웨어 재사용과 확장성을 제공하고 있으며, 네트워크 투명성과 플랫폼 독립성을 위하여 Java와 CORBA를 이용하여 구현하고 있다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.11-15
• /
• 2001

The explosion of the Internet, and most recently e-commerce, has caused great interest in agent technologies. The development of virtual environments has also increased in the last few years. A growing number of real-time applications use graphics with photorealistic quality, especially in the field of training, but also in the areas of design and ergonomic research. We describe an attempt to develop a framework that provides customers with multimedia information and interactive experiences with a virtual shopping environment. The application presented consists on a virtual visit to a music -store where the user is guided by an intelligent agent named Lizeth which responds in real-time to user's requests with precise information about music, artist's biographies, prices and related products to help the user to make decisions. The potential of UML and the Java programming language is discussed to show their application in the field of intelligent agents as mediators on shopping processes. We conclude that the proposed framework leads to the creation of application with a potentially significant impact in the development of e-commerce systems embedded in virtual environments.