• 한국IT서비스학회지
• /
• 제2권2호
• /
• pp.87-95
• /
• 2003

With the increasing proliferation of World Wide Web, electronic mail systems have become very widely used communication tools. Researches on e-mail classification have been very important in that e-mail classification system is a major engine for e-mail response management systems which mine unstructured e-mail messages and automatically categorize them. in this research we develop e-mail classifiers for e-mail Response Management Systems (ERMS) using naive bayesian learning and centroid-based classification. We analyze which method performs better under which conditions, comparing classification accuracies which may depend on the structure, the size of training data set and number of classes, using the different data set of an on-line shopping mall and a credit card company. The developed e-mail classifiers have been successfully implemented in practice. The experimental results show that naive bayesian learning performs better, while centroid-based classification is more robust in terms of classification accuracy.

• Journal of Information Technology Applications and Management
• /
• 제10권4호
• /
• pp.51-63
• /
• 2003

This study designs and implements a new approach to the classification of e-mail requests from customer based on machine learning techniques. The work on building an electronic mall classifier can be cast into the framework of text classification, since an e-mail is a viewed as a document, and judgement of interest is viewed as a class level given to the e-mail document. It is also implemented an e-mall based automated response system that integrate with Call Center in a practical use.

• 지능정보연구
• /
• 제9권2호
• /
• pp.121-133
• /
• 2003

Due to the rapid growth of Internet, means of communication with customers in a traditional customer support environment such as telephone calls are being replaced by mainly e-mail in a Web-based customer support system. Although such a Web-based support is efficient and promises potential benefits for firms, including reduced transaction costs, reduced time, and high quality of support, there are some difficulties associated with responding to many types of customer's inbound e-mails appropriately. As many types of e-mail are received, considerable attention is being paid to methods for increasing the efficiency of managing and responding e-mails. This research proposes an intelligent system for managing customer's inbound e-mails in organizations by applying case based reasoning technique for responding to various customers' inbound e-mails more effectively. In this approach, a case is represented as a frame-typed data structure corresponding to an inbound e-mail, keywords, and its reply e-mail. In the retrieval procedure, keywords and affinity set is developed to index a case, and then the case is represented as a vector, a case vector. Also, cosines value is calculated to measure the similarity between a new inbound e-mail and the cases in the case base. In the adaptation procedure, we provide several adaptation strategies to adapt and modify the retrieved case. The strategies guide to make an outbound e-mail using product databases, databases for customer support, etc. Additionally, the Web-based system architecture is proposed to implement our methodology. The proposed methodology and system will be helpful for developing more efficient Web-based customer support.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2003년도 Proceeding
• /
• pp.185-190
• /
• 2003

Due to the rapid growth of Internet, means of communication with customers in a traditional customer support environment such as telephone calls are being replaced by mainly e-mail in a Web-based customer support system. Although such a Web-based support is efficient and promises potential benefits for firms, including reduced transaction costs, reduced time, and high quality of support, there are some difficulties associated with responding to many types of customer’s inbound e-mails appropriately .As many types of e-mail are received, considerable attention is being paid to methods for increasing the efficiency of managing and responding e-mails. This research proposes an intelligent system for managing customer’s inbound e-mails in organizations by applying case based reasoning technique for responding to various customers' inbound e-mails more effectively. In this approach, a case is represented as a frame-typed data structure corresponding to an inbound e-mail, keywords, and its reply e-mail. In the retrieval procedure, keywords and affinity set is developed to index a case, and then the case is represented as a vector, a case vector. Also, cosines value is calculated to measure the similarity between a new inbound e-mail and the cases in the case base. In the adaptation procedure, we provide several adaptation strategies to adapt and modify the retrieved case. The strategies guide to make an outbound e-mail using product databases, databases for customer support, etc. Additionally, the Web-based system architecture is proposed to implement our methodology. The proposed methodology and system will be helpful for developing more efficient Web-based customer support.

• 산업공학
• /
• 제18권1호
• /
• pp.10-21
• /
• 2005

With the increasing proliferation of World Wide Web, electronic mail systems have become very widely used communication tools. Researches on e-mail classification have been very important in that e-mail classification system is a major engine for e-mail response management systems which mine unstructured e-mail messages and automatically categorize them. In this research we compare the performance of Naive Bayesian learning and Centroid-Based Classification using the different data set of an on-line shopping mall and a credit card company. We analyze which method performs better under which conditions. We compared classification accuracy of them which depends on structure and size of train set and increasing numbers of class. The experimental results indicate that Naive Bayesian learning performs better, while Centroid-Based Classification is more robust in terms of classification accuracy.

• 인터넷정보학회논문지
• /
• 제9권2호
• /
• pp.139-145
• /
• 2008

CRM(Customer Relationship Management)은 비즈니스 환경에서 기업의 이익과 경쟁적 우위를 차지할 수 있도록 하는 비즈니스 전략이다. 기업의 고객 응대 기법으로는 인터넷, E-mail, SMS(Short Message Service), 텔레포니 서비스, DM(Direct Mail)이 이용되고 있다. 최근 수익성 모델 향상을 위한 노력으로 기존 고객의 이탈 방지 및 유지, 신규 고객의 가입 및 유지를 통한 비즈니스 모델을 다각화하고 있다. 또한 고객의 최초 접점이 될 수 있는 CRM 센터의 업무 프로세스 재설계(Business Process Re-engineering), 업무 프로세스 관리(Business Process Management)가 빈번하게 발생하고 있다. 본 논문에서는 고객응대 CRM 모델 구축시의 고려 사항을 제시하고 콜 객체 라우팅(Call Object Routing)을 위한 에이젼트(Agent)를 제안하고 구현 및 성능평가를 하였다. 제안한 모델은 대 고객 응대 CRM 모델로 효율적으로 이용될 수 있다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제13권7호
• /
• pp.520-533
• /
• 2007

CRM(Customer Relationship Management)은 새로운 비즈니스 환경에서 기업의 이익과 경쟁적 우위를 차지할 수 있도록 하는 비즈니스 전략 모델이다. CRM 모델의 고객 응대 기법으로는 인터넷, E-mail, SMS(Short Message Service), 텔레포니 서비스, DM(Direct Mail)이 고객 접근 방법 매체로 이용된다. 최근 기업들의 수익성 모델 향상을 위한 노력으로 기존 고객의 이탈 방지 및 유지, 신규 고객의 가입 및 유지를 통한 비즈니스 모델을 다각화하고 있다. 본 논문은 CRM 채권 센터의 Avaya사의 예측발신시스템(Predictive Dialing System)을 기반으로 하였다. 예측발신시스템 구축 시 인입 콜(Call) 객체 처리를 위한 회선에 비해 대기 상담원이 적을 경우 실시간적 고객응대에 한계가 발생하였다. 기업의 입장에서 충분한 대기 상담원을 준비하지 못하는 이유는 고가의 유지비용 때문인데, 이를 해결하기 위해 본 논문에서는 불필요한 아웃바운드 상담을 줄이고, 과도한 콜백(CallBack) 적재를 감소시키기 위해서 고객 채널 통합을 위한 콜 객체 관리 메커니즘을 제안하고, 설계 구현 하였다. 성능 평가는 제안된 모델과 이전 모델의 실 데이타 값으로 평가 하였다. 제안된 모델은 대형 CRM 센터에서 효율적으로 이용될 것이다.

• 정보처리학회논문지C
• /
• 제9C권3호
• /
• pp.359-366
• /
• 2002

인터넷의 발전과 더불어 해킹기법 또한 함께 발전하고 있다. 최근의 검색공격 형태는 한 기관의 네트워크를 대상으로 하기보다는 상위 도메인을 대상으로 대규모적인 공격 형태를 지니고 있다. 실질적으로 대응하기 위해서는 중앙시스템에서 취약점 검색공격을 탐지, 분석하고 조치할 수 있는 시스템이 있어야 한다. 침입시도탐지 관리시스템은 현재 국내 주요기관들에 설치된 다수의 침입시도탐지 시스템들로부터 받은 여러 탐지 정보를 실시간으로 수집 분석하여 효과적으로 이용하는데 유용하다. 대규모 네트워크의 환경에 적절한 구조를 갖으며 보다 고수준의 통합된 분석을 할 수 있는 실시간 침입시도탐지 관리시스템을 개발하였다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 봄 학술발표논문집 Vol.28 No.1 (B)
• /
• pp.445-447
• /
• 2001

본 논문에서는 콜센터를 위하여 설계 및 구현된 전자메일 자동응답 및 관리 시스템 주에서 서버 시스템에 해당하는 뿐을 기술하였다. 본 연구에서는 도메인에 특성화된 표현 형식 개발을 개발하여 보다 효율적인 3단계 매칭방법을 가진 자동응답기, 학습에 기반한 도메인 비의존적인 자동분류기 및 적용방법의 재배열이 가능한 담당자 분배기를 구현하였다.

• 한국정보처리학회논문지
• /
• 제7권5S호
• /
• pp.1708-1718
• /
• 2000

In the operating of electronic commerce system, the information about consumer purchasing intention to product through e-mail has caused the problems in the management aspects. These are the using of information again and response to the situations promptly in consumer purchasing intension, etc. Moreover, it has brought out the issues timely to operate the electronic commerce system strategically with reapplication of consumer intention information. In this studies, the agent system AWEC(Agent Windows for EC) was proposed as an alternative paln, which charges of he getting and transmitting information of consumers intension in the electronic commerce system. In this proposed AWEC, the functional structure and working allocation were executed. And also eh performance of the proposed system is analyzed and evaluated through experiment.