고개관계관리(CRM)을 위한 전자메일 응답관리 시스템의 아키텍처 설계
Design an Architecture of Electronic Mail Response Management System for Customer Relationship Management
김승욱(중앙대학교)
15권 2호, 213~235쪽
초록
As the Internet grows at a phenomenal rate, electronic mail has become a widely used electronic form of communication on the Internet. Everyday, a huge number of people exchange messages in the fast and inexpensive way. With the excitement on electronic commerce growing, the usage of electronic mail will increase more dramatically. However, the advantage of electronic mail also make it overused by companies, organizations or people to promote products and spread information, which server their own purposes. The mailbox of user/companies may often be crammed with electronic mail messages some or even large portion of which are not of interest to her/him. Searching for interesting messages everyday is becoming tedious and annoying. As a companies, it is impossible everyday to classy a number of thousand electronic mail by human resources. As a consequence, electronic mail classification in indeed needed. But many of Korean companies do not manage properly and rapidly for customer's requesting electronic mai. In this case, customer have a lot of dissatisfaction for the company, after all their customer want to break off business relations for the company. The work on building an electronic mail classifier can be cast into the framework of text classification. because an electronic mail is a viewed as a document, and judgement of interesting or not is viewed as a class level given to the electronic mail document. While text classification has been well explored and various techniques has been reported, for instance, Native -Bayesian method, decision tree, Nearest Neighbor Classifier, Neural Networks etc. Finally, the purpose of this study is to design an new architecture of electronic mail automated response system for Customer Relationship Management (CRM). and this study researched for practical use to integrate with the other CRM(Customer Relationship Management) system.
Abstract
As the Internet grows at a phenomenal rate, electronic mail has become a widely used electronic form of communication on the Internet. Everyday, a huge number of people exchange messages in the fast and inexpensive way. With the excitement on electronic commerce growing, the usage of electronic mail will increase more dramatically. However, the advantage of electronic mail also make it overused by companies, organizations or people to promote products and spread information, which server their own purposes. The mailbox of user/companies may often be crammed with electronic mail messages some or even large portion of which are not of interest to her/him. Searching for interesting messages everyday is becoming tedious and annoying. As a companies, it is impossible everyday to classy a number of thousand electronic mail by human resources. As a consequence, electronic mail classification in indeed needed. But many of Korean companies do not manage properly and rapidly for customer's requesting electronic mai. In this case, customer have a lot of dissatisfaction for the company, after all their customer want to break off business relations for the company. The work on building an electronic mail classifier can be cast into the framework of text classification. because an electronic mail is a viewed as a document, and judgement of interesting or not is viewed as a class level given to the electronic mail document. While text classification has been well explored and various techniques has been reported, for instance, Native -Bayesian method, decision tree, Nearest Neighbor Classifier, Neural Networks etc. Finally, the purpose of this study is to design an new architecture of electronic mail automated response system for Customer Relationship Management (CRM). and this study researched for practical use to integrate with the other CRM(Customer Relationship Management) system.
- 발행기관:
- 대한경영학회
- 분류:
- 경영학