• 제목/요약/키워드: Recommendation Agents

검색결과 42건 처리시간 0.024초

온라인 추천 서비스를 위한 감성 기반 웹 에이전트 개발 (Development of Human Sensibility Based Web Agent for On-line Recommendation Service)

  • 임치환;정규웅
    • 대한인간공학회지
    • /
    • 제23권3호
    • /
    • pp.1-12
    • /
    • 2004
  • In recent years, with the advent of e-Commerce the need for personalized services and one-to-one marketing has been emphasized. To be successful in increasingly competitive Internet marketplace, it is essential to capture customer loyalty. In this paper, we provide an intelligent agent approach to incorporate human sensibility into an one-to-one recommendation service in cyber shopping mall. Our system exploits human sensibility ergonomics and on-line preference matching technologies to tailor to the customer the suggestion of goods and the description of store catalog. Customizing the system`s behavior requires the parallel execution of several tasks during the interaction (e. g., identifying the customer`s emotional preference and dynamically generating the pages of the store catalog). The recommendation agent system composed of five modules including specialized agents carries on these tasks. By presenting goods that are consistent with user interests as well as user sensibility, the accuracy and satisfaction of the recommendation service may be improved.

Molecular Targeting Agents in Cancer Therapy: Science and Society

  • Shaikh, Asim Jamal
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제13권4호
    • /
    • pp.1705-1708
    • /
    • 2012
  • The inception of targeted agents has revolutionized the cancer therapy paradigm, both for physicians and patients. A large number of molecular targeted agents for cancer therapy are currently available for clinical use today. Many more are in making, but there are issues that remain to be resolved for the scientific as well as social community before the recommendation of their widespread use in may clinical scenarios can be done, one such issue being cost and cost effectiveness, others being resistance and lack of sustained efficacy. With the current knowledge about available targeted agents, the growing knowledge of intricate molecular pathways and unfolding of wider spectrum of molecular targets that can really matter in the disease control, calls for only the just use of the agents available now, drug companies need to make a serious attempt to reduce the cost of the agents. Research should focus on agents that show sustained responses in preclinical data. More needs to be done in laboratories and by the pharmaceutical industries, before we can truly claim to have entered a new era of targeted therapy in cancer care.

지능형 소프트웨어 에이전트에 기반한 피크 기간에서의 여행 계획 추천 시스템 (Intelligent Agent-based Travel Planning Recommendation System in Peak Seasons)

  • 임홍순;안형준;김종우;박성주
    • 경영과학
    • /
    • 제21권3호
    • /
    • pp.39-54
    • /
    • 2004
  • This paper presents a multi-agent system for intelligent recommendation of travel plans to users. The goal of the system is to provide alternative and preferable travel plans to users when the availability of tickets is low such as in vacations, holidays, weekends, or peak seasons. The multiple agents in the system search for available alternatives for a target travel in collaboration with other agents and recommend best alternatives by analyzing them using a multi-criteria decision-making model. A prototype online travel support system was constructed and a simulation experiment was performed for evaluation and comparison with different travel planning strategies.

Context-Aware Active Services in Ubiquitous Computing Environments

  • Moon, Ae-Kyung;Kim, Hyoung-Sun;Kim, Hyun;Lee, Soo-Won
    • ETRI Journal
    • /
    • 제29권2호
    • /
    • pp.169-178
    • /
    • 2007
  • With the advent of ubiquitous computing environments, it has become increasingly important for applications to take full advantage of contextual information, such as the user's location, to offer greater services to the user without any explicit requests. In this paper, we propose context-aware active services based on context-aware middleware for URC systems (CAMUS). The CAMUS is a middleware that provides context-aware applications with a development and execution methodology. Accordingly, the applications based on CAMUS respond in a timely fashion to contextual information. This paper presents the system architecture of CAMUS and illustrates the content recommendation and control service agents with the properties, operations, and tasks for context-aware active services. To evaluate CAMUS, we apply the proposed active services to a TV application domain. We implement and experiment with a TV content recommendation service agent, a control service agent, and TV tasks based on CAMUS. The implemented content recommendation service agent divides the user's preferences into common and specific models to apply other recommendations and applications easily, including the TV content recommendations.

  • PDF

모바일 환경을 위한 지능형 추천 에이전트에 관한 연구 (A Study on Intelligent Recommendation Agent for a Mobile Envionment)

  • 주복규;김만선
    • 한국콘텐츠학회논문지
    • /
    • 제6권4호
    • /
    • pp.55-62
    • /
    • 2006
  • 유비쿼터스 시대가 시작되면서 유비쿼터스 환경을 어떻게 제시할 것인지와 어떤 서비스와 이용 방법을 사용자에게 제공할 것인지가 중요해지고 있다. 본 논문에서는 모바일 환경에서 지능형 멀티 에이전트를 통해 사용자에게 도움되는 정보를 능동적으로 제공할 수 있는 시스템을 제안한다. 프로파일 모듀르 규칙 생성 모듈, 필터링 모듈, 서비스 모듈 구조로 구성된다. 추천 에이전트를 이용하여 미리 등록한 사용자의 정보를 기반으로 지능적인 사용자의 요구 파악을 가능하게 구성하였다. 이것을 응용하여 구현하고 실험을 통해 확인하였다.

  • PDF

메타버스와 AI 추천서비스를 활용한 국내 대표 키오스크 사용서비스 안내 개발 (Using Metaverse and AI recommendation services Development of Korea's leading kiosk usage service guide)

  • 최수현;이민정;박진서;서연호;문재현
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2023년도 추계학술발표대회
    • /
    • pp.886-887
    • /
    • 2023
  • This paper is about the development of kiosks that provide four types of service. Simple UI and educational videos solve the complexity of existing kiosks and provide an intuitive and convenient screen to users. In addition, the AR function, which is a three-dimensional form, shows directions and store representative images. After storing user information in the DB, a learning model is generated using user-based KNN collaborative filtering to provide a recommendation menu. As a result, it is possible to increase user convenience through kiosks using metaverse and AI recommendation services. It is also expected to solve digital alienation of social classes who have difficulty using kiosks.

번들상품추천시스템 개발을 위한 객체지향 사례베이스 설계와 유사도 측정에 관한 연구 (An Object-Oriented Case-Base Design and Similarity Measures for Bundle Products Recommendation Systems)

  • 정대율
    • 지능정보연구
    • /
    • 제9권1호
    • /
    • pp.23-51
    • /
    • 2003
  • 인터넷 쇼핑몰에서 사례기반추론기법을 통한 유사상품의 탐색과 사용자 요구에 적합한 상품추천을 위해서는 다양한 요구에 부응할 수 있는 사례베이스의 구축이 우선되어야 한다. 그리고 구축된 사례베이스로부터 유사한 사례를 검색하여 재 사용하거나 필요시 수정하고, 그 결과를 다시 저장하는 기능이 요구된다. 사례기반 상품추천시스템 개발에 있어 가장 중요한 요소는 사례의 표현문제이다. 본 연구에서는 인터넷 수산물 쇼핑몰의 상품추천시스템에서 번들상품 구성문제(집안 이벤트 시 필요한 수산물의 집합)를 표현하는데 적합한 사례표현기법을 개발하며, 유사사례를 추출하기 위한 유사도 척도의 개발에 연구의 첫 번째 주안점을 둔다. 본 논문에서는 번들상품추천을 위한 사례표현기법으로 객체모델링(OMT)기법을 사용하고 있다. 또한 다양한 사례 속성 유사도 측정방법을 적용하며, 유사도 측정에서 분류법(taxonomy)의 의미와 그 적용방법을 제시한다.

  • PDF

웹 로그 분석을 이용한 추천 에이전트의 개발 (Development of Recommendation Agents through Web Log Analysis)

  • 김성학;이창훈
    • 한국컴퓨터산업학회논문지
    • /
    • 제4권10호
    • /
    • pp.621-630
    • /
    • 2003
  • 웹 로그는 사용자가 웹 사이트의 데이터를 액세스할 때 웹 서버에 의해 기록되는 정보로써 최근 인터넷 이용의 급속한 증가로 인해 웹 로그의 활용가치가 더욱 중요하게 되었으며, 웹 로그의 분석 결과는 쇱 사용자들의 행위를 나타내는 패턴을 분석하거나 웹 사이트의 구조를 재배치 하는데 이용될 수 있다. 이를 실현하기 위한 많은 연구들은 주로 연관규칙과 순차패턴을 이용하고 있는데, 대다수는 Apriori 알고리즘을 기본으로 하고 있어서 대용량의 데이터베이스에 적용하기에는 컴퓨팅 시간적 측면에서 비효율적이다. 따라서 본 논문에서는 웹 환경에서 흥미있는 패턴을 탐사하는 새로운 알고리즘을 개발하여 보다 빠르게 패턴탐사를 수행하고, 많은 사용자들이 관심있게 순차적으로 접근하고 있는 정보를 시스템 관리자에게 제공할 수 있는 추천에이전트를 개발한다.

  • PDF

관계적과 강제적 영향전략이 본사 신뢰에 미치는 영향 : 영업사원 신뢰의 매개역할 (Effects of Relational and Mandatory Influence Strategies on Sales Representatives and Headquarter Trust)

  • 이창주;이필수;이용기
    • 유통과학연구
    • /
    • 제14권6호
    • /
    • pp.53-63
    • /
    • 2016
  • Purpose - This study examines the effects of the influence strategies on sales representative and headquarter trust, and investigates how sales representative trust plays a mediating role in the relationship between influence strategies and headquarter trust. For these purposes, a structural model which consists of several constructs was developed. In this model, influence strategies that consist of relational influence strategies (information exchange, recommend, promise) and mandatory influence strategies (legal plea, request, threat) were proposed to affect the sales representative trust and in turn, increase the headquarter trust. Thus, this study proposed that sale representative trust plays a core mediating role in the relationship between relational and mandatory influence strategies and headquarter trust in B2B food materials distribution context. Research design, data, and methodology - For these purposes, the authors collected the data from 208 B2B specialized complex agents. We used the 2,200 B2B specialized complex agents which trade with CJ, Ottogi, and Daesang firms and supply food materials to restaurant, school cafeteria, supermarket and traditional market as a sample frame. Once we identified 330 B2B specialized complex agent owners, CEOs, and/or Directors who had agreed to participate in this study, we dropped off a questionnaire at each B2B specialized complex agent and explained the purpose of this study. The survey was conducted from October 1, 2015 to December 15, 2015. A total of 230 questionnaires were collected. Of these collected questionnaires, 28 questionnaires excluded since they had not been fully completed. The data were analyzed using frequency test, reliability test, measurement model analysis, and structural equation modeling with SPSS and SmartPLS 2. Results - First, information exchange, recommendation, and promise of relational influence strategies had positive effects on sales representative trust. The threat of mandatory influence strategies had a negative effect on sales representative trust, but legal plea and request did not have a significant effect on sales representative trust. Second, information exchange and recommendation of relational influence strategies had positive effects on headquarter trust, but promise did not. Also, legal plea, request, and threat of mandatory influence strategies did not have a significant effect on headquarter trust. Third, this findings show that sales representative trust plays a partial mediator between information exchange and headquarter trust, and threat and headquarter trust, and a full mediator between promise and headquarter trust, and recommendation and headquarter trust. Conclusions - The aim of this study was to examine the effects how diverse dimensions of relational and mandatory influence strategies relate to sales representative trust and headquarter trust. To do so, we integrated the influence strategies and the trust transfer theory to hypothesize that various influence strategies increase sales representative and headquarter trust. The findings of this study suggest that headquarter firms should establish and enforce proper influence strategies guidelines to make clear what proper actions sales representatives should implement in relationship with B2B specialized complex agents. Also, relational and mandatory influence strategies must be regarded as a long-term and ongoing strategy that eventually build a long-term orientation with B2B specialized complex agents and guarantee a company's sustainable growth and success.

전자상거래에서 제품 정보 추천을 위한 멀티 에이전트 시스템의 워크플로우 구축 (Construction of Multi-Agent System Workflow to Recommend Product Information in E-Commerce)

  • 김종완;김영순;이승아;진승훈;권영직;김순철
    • 정보처리학회논문지B
    • /
    • 제8B권6호
    • /
    • pp.617-624
    • /
    • 2001
  • 전자상거래가 활성화됨에 따라 제공되는 상품의 정보와 서비스의 내용이 점차 다양해지고 있다. 따라서 구매자들은 가격 정보뿐만 아니라 다양한 상품 정보들을 검색 추천해주는 에이전트 개발을 요구하고 있다. 본 논문에서는 전자상거래에서 도서 정보 검색과 관련하여 사용자의 선호도를 프로파일 형태로 표현하고, 도서 정보를 검색 및 추출하고 이를 추천하는 멀티 에이전트 시스템을 제안한다. 제안된 멀티 에이전트 시스템은 정보검색, 정보추천, 사용자 인터페이스, 웹 로봇과 같은 여러 개별 에이전트들의 동작들을 조정 에이전트의 설계 및 구현을 통하여 통제하고 관리한다. 본 멀티 에이전트 시스템을 윈도우즈 NT 서버에 구현하였다. 조정 에이전트의 관리 기능으로 중복된 정보 검색을 제거할 수 있었으며, 고객들에게 여러 온라인 도서 사이트의 도서 정보들을 실시간으로 제공할 수 있게 되었다.

  • PDF