• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.112-114
• /
• 2001

최근 인터넷 및 정보통신 기술이 급속하게 발달함에 따라서 네트워크를 기반으로 한 응용 소프트웨어 및 네트워크 관련 기술들이 많이 연구, 개발되고 있다. 이와 관련하여 과거 인공지능 분야에서 많이 연구되어 왔던 에이전트 기술이 최근의 네트워크 기술을 기반으로 하여 다시 활발한 연구가 진행되고 있다. 특히, 네트웍 상을 이동하면서 특정 사용자의 요구를 만족시키는 이동 에이전트 기술은 네트웍 응용시스템 개발에서 많이 이용되고 있는 기술이다. 본 논문에서는 이동 에이전트기술을 이용하여 가상 시장 환경 모델과 협상 시스템을 설계하고 그 구연 방법을 설명한다. 본 논문에서 기술하는 이동 에이전트 환경은 시장 에이전트, 호객 에이전트, 데이터베이스 에이전트로 크게 세 부분으로 나눈다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.797-802
• /
• 2023

In an environment where English is a foreign language, English learners can use AI voice chatbots in English-speaking practice activities to enhance their speaking motivation, provide opportunities for communication practice, and improve their English speaking ability. In this study, we propose a teaching-style AI voice chatbot that can be easily utilized by lower elementary school students and enhance their learning. To apply the Teachable Agent system to language learning, which is an activity based on tense, context, and memory, we proposed a new method of TA by applying the Teachable Agent to reflect the learner's English pronunciation and level and generate the agent's answers according to the learner's errors and implemented a Teachable Agent AI chatbot prototype. We conducted usability evaluations with actual elementary English teachers and elementary school students to demonstrate learning effects. The results of this study can be applied to motivate students who are not interested in learning or elementary school students to voluntarily participate in learning through role-switching.

• Journal of Korea Game Society
• /
• v.9 no.5
• /
• pp.117-125
• /
• 2009

In real-time strategy simulation (RTS) game each team is composed of agents and executes strategies to win other team. Strategy needs agents' cooperation in each team. This needs multi-agent system (MAS). Centralized decision making, one of decision making in MAS, selects actions not to agents but to team by a coordinated agent. Decentralized decision making costs high because each agent communicates with each other. In this paper we propose a system which controls agents by grouping and allocates roles through negotiation by a coordinated agent. Then, when one of allocated actions is not executed or failed, a coordinated agent allocates its role to another agent. We make experiments in starcraft, famous RTS game. When a proposed method is applied, the performance of attack and defense is increased. The improved agents' team wins eight times per ten games.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.217-225
• /
• 1999

협상은 상거래에 있어서 매우 중요한 요소 중 하나이다. 현재의 웹 기반 전자상거래 시스템은 이러한 중요한 협상 구조를 상거래에 잘 반영하지 못하는 문제점을 가지고 있다. 이러한 문제점중 기업과 소비자간의 미비한 협상 구조를 보안하기 위해 실세계 상거래에서 존재하는 점원을 전자상거래상의 가상점원으로 모델링하여 회사의 정책과 구매자의 특성을 반영하여 구매자와 전략적으로 자동 협상을 수행할 수 있는 에이전트의 구조를 설계하고 표현하고, 그 제안에 대한 평가 내용과 결정사항을 전달할 수 있는 언어적인 구조가 필요하며, 협상의 대상이 되는 사안들의 특성을 반영할 수 있는 표현 구조도 요구된다. 또한 이러한 협상에서 전략을 세우고 알맞은 제안을 제시하며 상대의 제안에 대하여 전략적으로 반응할 수 있는 의사결정 모델이 요구된다. 본 논문에서는 회사의 정책 모델과 구매자의 모델을 정의하고 이를 이용한 협상 모델을 설계 구현하였다. 협상 구조의 모델링을 위해 KQML(Knowledge Query Manipulation Language)을 기반으로 전자상거래 프로토콜로 설계하고, 논쟁 기반 협상 모델을 기초로 협상언어를 설계하였다. 또한 협상에서의 전략적인 의사결정을 위해 게임이론을 이용하고, 규칙 기반 시스템으로 이를 보충하였다. 마지막으로 가상점원 모델을 바탕으로 조립 컴퓨터 판매를 위한 가상점원으로 구현하였고, 이에 대한 실험을 통하여 가상점원의 유용성을 보였다.

• Architectural research
• /
• v.14 no.1
• /
• pp.3-9
• /
• 2012

Owing to the advent of ubiquitous computing technologies, the concept of Intelligent Environments has emerged, as an alternative approach to overcome the limitation of the built environment. Intelligent Environments can be more responsive to user-and context-specific human activities by automatically and dynamically modifying their settings without explicit human intervention. However, the conventional approach to the development of Intelligent Environments has mainly focused on the technical issues without paying much attention to the dynamic interrelationship between the user and the built environment. Therefore, differing or conflicting needs of multiple simultaneous users remain unresolved. The objective of this study is to present types of environmental conflicts and their resolution through agent collaboration and negotiation. For the demonstration and validation of the conflict resolution process, a set of hypothetical test cases is simulated in a 3D test environment. The result of the case simulations shows that the proposed approach is computationally feasible and applicable to the development of Intelligent Environments, and, furthermore, it can overcome the drawback of the conventional approach.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.325-327
• /
• 2001

멀티에이전트 시스템(MAS: Multi-Agent System)에서 에이전트는 각자의 목표 달성을 위해 주위 에이전트들과 상호작용하여 목표의 충돌이 없는 일치 상황에 도달하도록 설계될 필요가 있다. 이러한 상호작용은 MAS에서의 협동, 공조, 그리고 협상 등의 분양에 필수적인 요소이다. 본 연구에서는 MAS에서 믿음(Belief), 소망(Desire), 그리고 의도(Intention)를 에이전트 구조의 핵심 요소로 가정하고, FIPA Agent Communication Language(ACL) 사양과 interaction 프로토콜의 변형에 기초하여 BDI 에이전트를 위한 협상 프로토콜을 소개한다. 또한 Java와 Prolog를 결합시킨 InterProlog 프로그래밍 언어로 목표 충돌을 일으키는 BDI 에이전트들을 생성하고 에이전트들이 협상 프로토콜을 사용하여 협상하는 과정을 시험적으로 구현한다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.2
• /
• pp.150-161
• /
• 1999

This paper deals with the design and development of a real-time integrated communication architecture for heterarchical SFCS(Shop Floor Control System). In autonomous agent-based heterarchical SFCS, each functional unit of parts and resources is equipped with an intelligent controller (agent) that acts as the representative of the entity. The controllers communicate and negotiate with other controllers on a real-time basis through message passing and bidding protocol to achieve mutual agreements for task sharing. ICPL(Integrated Communication Protocol and Language) is proposed for this purpose. ICPL is a language and a protocol for supporting communication among intelligent controllers. Based on the speech act theory, this paper proposes a semantic description for ICPL that associates the description of the cognitive states of controllers with the use of language primitives (message_type). Semantics for the basic set of ICPL messages is described. Eventually, an ICPL-based communication architecture can provide the implementation of the distributed and heterarchical SFCS, and makes the intelligent controller transparent to the negotiation problem.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• 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.

• The KIPS Transactions:PartC
• /
• v.8C no.6
• /
• pp.855-864
• /
• 2001

With the increasing importance and complexity of EC (Electronic Commerce) across the Internet, the need and expectation for intelligent software agents to support both consumers and suppliers through the whole process of EC are growing rapidly. To realize the intelligent EC. a multiagent based EC system. which includes foundational technologies such as the establishment of standard product ontology the definition of message and negotiation protocol and brockering, is required. In this paper we propose an intelligent EC System named ICOMA(Intelligent electronic CO mmerce system based on Multi-Agent) as an open infrastructure of multiagent-based EC. Concretely we have proposed. designed and implemented an architecture of multiagent-based EC system including 6-types of agents message protocol for inter-agent negotiation, personalized produst retrieval and filtering., We have confirmed the effectiveness of the system through experiments.

• The KIPS Transactions:PartC
• /
• v.15C no.6
• /
• pp.455-468
• /
• 2008

In this paper, we propose FAS model for establishing trust based on digital certificates in Grid security framework. The existing RBAC(Role Based Access Control) model is extended to provide permissions depending on the users‘ roles. The FAS model is designed for a system independent integrated Grid security by detailing and extending the fundamental architecture of user, role, and permission. FAS decides each user’s role, allocates access right, and publishes attribute certificate. FAS is composed of three modules: RDM, PCM, and CCM. The RDM decides roles of the user during trust negotiation process and improves the existing low level Grid security in which every single user maps a single shared local name. Both PCM and CCM confirm the capability of the user based on various policies that can restrict priority of the different user groups and roles. We have analyzed the FAS strategy with the complexity of the policy graph-based strategy. In particular, we focused on the algorithm for constructing the policy graph. As a result, the total running time was significantly reduced.