• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.735-738
• /
• 2000

인터넷의 대중화와 함께 데이터 통신서비스에 대한 수요로 데이터 통신망은 그 양과 종류가 급격하게 증가하고 있어서 통신망 운용에 따른 망구성 및 고장처리 체계의 정립이 필요하게 되었다. 더더구나 앞서가는 통신업자들은 사이버상에서도 양질의 고객응대 서비스를 제공하려고 노력하고 있다. 현재 통신망연구소에서 개발중인 데이터 통신망 통합 고장처리시스템은 한국통신에서 제공하고 있는 데이터망들에 대한 고장신고를 접수하고, 고장에 대한 시험 및 수리를 수행하며, 그 결과를 고객에게 통보하는 전과정에 관련된 기술을 포함하고 있다. 본 논문에서는 데이터 통신망에 대한 고장시험, 가입자정보관리, 망상태관리에 관련된 시스템들과의 체계적인 연동을 통한 통합고장처리 방안, 시스템 개발 구조 등을 기술한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.484-491
• /
• 2021

This study was undertaken to identify success factors of traditional market delivery apps and lead digital transformation of traditional markets. The success factors of traditional market delivery apps are represented by four variables: system characteristics of the app, delivery, products, and responsibility towards customer responses. These factors were analyzed to examine their impact on the operations performance. Data was collected by surveying 148 traditional market business owners. Results of the empirical analysis revealed that the app system characteristics, delivery characteristics, and product sales promotion, impart a significant effect on the operations performance. Conversely, the customer response characteristics showed no significant effects. This could be because some apps lack the function to check customer reviews and respond appropriately. Currently, where traditional market delivery apps are in the early stages of implementation and are gradually expanding, data obtained from this study helps to identify characteristics of traditional market delivery apps, and offers suggestions to create development indicators of the traditional market delivery apps by analyzing their effects on operational performance, thereby contributing to the revival of traditional markets through digital transformation.

• Journal of Internet Computing and Services
• /
• v.10 no.1
• /
• pp.123-134
• /
• 2009

The CRM(Customer Relationship Management) is a business strategy model which can reap higher profits and can provide a competitive edge to an enterprise in today's new business environments. Early next year (2009), the Capital Market Consolidation Act will be in effect in South Korea. This is required for a qualitative growth to provide QoS (Quality of Service) and ensure growth in finance, IT industry & service. Accordingly, the securities and insurance companies, banks and other financial institutions make efforts to improve their derivative financial product and also enhance their services. In this paper we design and implement a Channel Server model for a Scalable Service Channel Server to efficiently manage the high volumes of inbound customer interactions based on the requirements of a CRM center. The proposed Scalable Service Channel Server supports integration with other third party service and standardization of multiple inbound service channels. The proposed model can be efficiently used in an inbound CRM center of any banking, finance, securities and insurance establishments.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.272-275
• /
• 2017

대면 서비스보다 비대면 서비스를 선호하는 소비자들의 증가로 인해 기업의 고객 응대의 형태도 변해가고 있다. 기존의 전화 상담보다는 인터넷에 글을 쓰는 형식으로 문의를 하는 고객이 증가하고 있으며, 관련 기업에서는 이와 같은 변화에 효율적으로 대처하기 위해, 텍스트 기반의 상담시스템에 대한 다양한 연구 및 투자를 하고 있다. 특히, 입력된 질의에 대해서 자동 답변하는 챗봇(ChatBot)이 주목받고 있으나, 낮은 답변 정확도로 인해 실제 응용에는 어려움을 겪고 있다. 이에 본 논문에서는 상담원이 중심이 되는 텍스트 기반의 상담시스템에서 상담원이 보다 쉽게 답변을 수행할 수 있도록 자동으로 답변을 추천해주는 자동답변추천 시스템을 제안한다. 실험에서는 기존 질의응답 시스템 구축에 주로 사용되는 문장유사도 알고리즘과 더불어 합성곱신경망을 이용한 자동답변추천 기법의 답변추천 성능을 비교한다. 실험 결과, 문장유사도 기반의 답변추천 기법보다 본 논문에서 제안한 합성곱신경망(Convolutional Neural Networks) 기반의 답변추천시스템이 더 뛰어난 답변추천 성능을 나타냄을 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.272-275
• /
• 2017

대면 서비스보다 비대면 서비스를 선호하는 소비자들의 증가로 인해 기업의 고객 응대의 형태도 변해가고 있다. 기존의 전화 상담보다는 인터넷에 글을 쓰는 형식으로 문의를 하는 고객이 증가하고 있으며, 관련 기업에서는 이와 같은 변화에 효율적으로 대처하기 위해, 텍스트 기반의 상담시스템에 대한 다양한 연구 및 투자를 하고 있다. 특히, 입력된 질의에 대해서 자동 답변하는 챗봇(ChatBot)이 주목받고 있으나, 낮은 답변 정확도로 인해 실제 응용에는 어려움을 겪고 있다. 이에 본 논문에서는 상담원이 중심이 되는 텍스트 기반의 상담시스템에서 상담원이 보다 쉽게 답변을 수행할 수 있도록 자동으로 답변을 추천해주는 자동답변추천 시스템을 제안한다. 실험에서는 기존 질의응답 시스템 구축에 주로 사용되는 문장유사도 알고리즘과 더불어 합성곱신경망을 이용한 자동답변추천 기법의 답변추천 성능을 비교한다. 실험 결과, 문장유사도 기반의 답변추천 기법보다 본 논문에서 제안한 합성곱신경망(Convolutional Neural Networks) 기반의 답변추천시스템이 더 뛰어난 답변추천 성능을 나타냄을 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.37-45
• /
• 2007

In this paper, we proposed a new customized e-Ring(Enterprise Ring Back Tone) system which could be represented each user and organization feature. The e-Ring system provided the ring back tone and additional services to reduce the waiting time when the client called an organization. This system was for an appropriate organization public relations instead of the meaningless ring back tone which was used usual call, also was maximized the service availability and work efficiency which was obtained from the automatic response and service suppling to users who had needs and questions.

• Information Systems Review
• /
• v.17 no.2
• /
• pp.29-48
• /
• 2015

This study proposes an integrated operational model of branches with customer center at stock brokerage firms and suggests ways to improve existing systems. This suggested integrated model of branches and customer centers can increase customer satisfaction and customer values for the specific services at each channel. This integrated model also enables customers to make transactions at a desired specific time, make it possible to inquire whatever the customer wished to ask, and select desired contact channels. In addition, the firms can bring in improved effectiveness of internal resources by integrating all the resources the firm has. Personal resources and system resources are distributed by the characteristics of channels that can be selected by the customers. Then agents also can provide more speedy and accurate responses to the engaged customer interactions matching to his/her job in charge. Also, the model makes it possible to collect the latest customer and transaction information at the moment of each interactions, by which the firm can provide customized services specifically tailed to each customers' preferences. However, systematic interactions between branches and customer center, and completed system should be equipped with in order to provide the highest quality services.

• KSCI Review
• /
• v.14 no.1
• /
• pp.205-212
• /
• 2006

In this paper, we proposed a new customized e-Ring(Enterprise Portal Back Tone) system which could be represented each organization feature. The e-Ring system provided a call back tone and additional services to reduce the waiting time when the client called an organization. This system is for an appropriate organization public relations instead of the meaningless ring back tone which is used usual call, also is maximized the service availability and work efficiency which is obtained from the automatic response and service suppling to users who have needs and questions.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.91-102
• /
• 2022

As artificial intelligence develops, AI chatbot systems are actively taking place. For example, in public institutions, the use of chatbots is expanding to work assistance and professional knowledge services in civil complaints and administration, and private companies are using chatbots for interactive customer response services. In this study, we propose a scenario-based AI voice chatbot system to reduce museum operating costs and provide interactive guidance services to visitors. The implemented voice chatbot system consists of a watcher object that detects the user's voice by monitoring a specific directory in real-time, and an event handler object that outputs AI's response voice by performing inference by model sequentially when a voice file is created. And Including a function to prevent duplication using thread and a deque, GPU operations are not duplicated during inference in a single GPU environment.

• The Journal of Society for e-Business Studies
• /
• v.8 no.3
• /
• pp.177-195
• /
• 2003

In a traditional customer support environment, mainly call centers or service centers are responsible for receiving inquiries from their customers via telephone calls. Due to the rapid growth of Internet with its widespread acceptance and accessibility, means of communication with customers in the traditional customer support center, such as telephones, letters, and direct-visiting, have been replaced by e-mails and bulletin board systems (BBSs) using the Internet constantly. BBSs are basically question and answer systems, they require some lead time to get answer from administrator. To reduce lead time, BBSs enable remote customers or users to log on and tap into a knowledge database that is generally formatted in the form of Frequently Asked Questions (FAQs) that provide answers and solutions to the common problems. And, many different types of the questions are mixed on the BBS. It is a burden to administrator. To build FAQs and to support BBS adminstrator, a supporting tool which is to categorize questions is helpful. In this research, we suggest an interactive question categorizing methodology which consists of steps to present question using keywords, identifying keywords' affinity, computing similarity among questions, and clustering questions. This methodology allows users to interact iteratively for clear manifestation of ambiguous questions. We also developed a prototype system, IQC (interactive question categorizer) and evaluated its performance using the comparison experiments with other systems. IQC is not a general purposed system, but it produces a good result in a given specific domain.