• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.99-120
• /
• 2010

Due to the wide spread of customers' frequent access of non face-to-face services, there have been many attempts to improve customer satisfaction using huge amounts of data accumulated throughnon face-to-face channels. Usually, a call center is regarded to be one of the most representative non-faced channels. Therefore, it is important that a call center has enough agents to offer high level customer satisfaction. However, managing too many agents would increase the operational costs of a call center by increasing labor costs. Therefore, predicting and calculating the appropriate size of human resources of a call center is one of the most critical success factors of call center management. For this reason, most call centers are currently establishing a department of WFM(Work Force Management) to estimate the appropriate number of agents and to direct much effort to predict the volume of inbound calls. In real world applications, inbound call prediction is usually performed based on the intuition and experience of a domain expert. In other words, a domain expert usually predicts the volume of calls by calculating the average call of some periods and adjusting the average according tohis/her subjective estimation. However, this kind of approach has radical limitations in that the result of prediction might be strongly affected by the expert's personal experience and competence. It is often the case that a domain expert may predict inbound calls quite differently from anotherif the two experts have mutually different opinions on selecting influential variables and priorities among the variables. Moreover, it is almost impossible to logically clarify the process of expert's subjective prediction. Currently, to overcome the limitations of subjective call prediction, most call centers are adopting a WFMS(Workforce Management System) package in which expert's best practices are systemized. With WFMS, a user can predict the volume of calls by calculating the average call of each day of the week, excluding some eventful days. However, WFMS costs too much capital during the early stage of system establishment. Moreover, it is hard to reflect new information ontothe system when some factors affecting the amount of calls have been changed. In this paper, we attempt to devise a new model for predicting inbound calls that is not only based on theoretical background but also easily applicable to real world applications. Our model was mainly developed by the interactive decision tree technique, one of the most popular techniques in data mining. Therefore, we expect that our model can predict inbound calls automatically based on historical data, and it can utilize expert's domain knowledge during the process of tree construction. To analyze the accuracy of our model, we performed intensive experiments on a real case of one of the largest car insurance companies in Korea. In the case study, the prediction accuracy of the devised two models and traditional WFMS are analyzed with respect to the various error rates allowable. The experiments reveal that our data mining-based two models outperform WFMS in terms of predicting the amount of accident calls and fault calls in most experimental situations examined.

• Journal of Korean Society for Quality Management
• /
• v.34 no.4
• /
• pp.78-92
• /
• 2006

While many services appear, it are performed in the various researches about a service. Among them, as to the basic reason for measuring the service level, in order to find out the strategy improving service quality. But the method for measuring quality of services up to date was unable to make it enough the role. This research tried to propose the approach systematically analyzing the human errors in order to improve service quality about the call center which utilizes the information technology. In fact, the human errors was found in the customer contact point in which the actual service is delivered. An interaction between the element for comprising call service was classified into 3 while defining the human error as 3 group. Moreover, the process where a service is delivered was classified according to 5 step and the generated error was measured in each step. The implication of this research looks at the service failure and dissatisfaction as the occurrence of the human errors and illustrates the service quality improvement as a correction or a reduction. This approach is used that service is materially easily understood and is formulated with the quality improvement strategy.

• The Korean Journal of Health Service Management
• /
• v.5 no.2
• /
• pp.187-197
• /
• 2011

The purpose of this study is to analyze factors related to the job stress experienced by call center employees at public institutions, so as to provide basic data to relieve work-related stress and enhance the job satisfaction of such employees. To promote objectivity and representation, the study was conducted by way of survey, the subjects being call center employees in 8 public institutions that operate call centers, which are located in the Busan and Seoul areas. Of the 240 surveys distributed, 196 were collected and 173 of those were used for analysis after eliminating 25 with insufficient responses. The results of this study are as follows. First, in terms of general properties, it was determined that employees with higher levels of education and families to support had greater job stress. second, in terms of job-related properties, employees who were unsatisfied with the job, HR policies, and their relationship with superiors and/or colleagues had greater job stress. In terms of the group that was satisfied compared with the group that was unsatisfied with the job, HR policies, and their relationship with superiors and/or colleagues, regular workers had less job stress than irregular workers.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.613-617
• /
• 2021

According to the growth of the service industry, stresses from emotional labor workers have been emerging as a social problem, thereby so-called the Emotional Labor Protection Act was implemented in 2018. However, insufficient substantial protection systems for emotional workers emphasizes the necessity of a digital stress management system. Thus, in this paper, we suggest a stress detection system for customer service representatives based on deep learning facial expression recognition. This system consists of a real-time face detection module, an emotion classification FER module that deep-learned big data including Korean emotion images, and a monitoring module that only visualizes stress levels. We designed the system to aim to monitor stress and prevent mental illness in emotional workers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.171-174
• /
• 2008

컴퓨터 시뮬레이션을 통한 자연스러운 가상 성형은 컴퓨터 그래픽스와 애니메이션 분야의 오래된 연구 주제이다. 본 논문은 2D 가상 성형 시스템 용도의 가변 워핑 마스크를 이용한 시그모이드 블렌딩 방법을 제안함으로써 가상 성형의 품질 만족도와 편의성 및 실용성을 제고함에 그 목적이 있다. 제안된 2D 가상 성형 시스템은 마우스로 스머지 필터를 조작하여 얼굴 구성 요소의 윤곽 형상을 원하는 형태로 변형할 수 있는 직관적인 사용자 인터페이스를 제공한다. 얼굴 구성 요소의 스머징 전후의 윤곽선을 대상으로 다각형 근사화에 기반한 계층적 제어선 매핑을 통해 획득한 제어선 쌍들을 이용하여 반자동 필드 워핑을 수행함으로써 소스 제어선으로부터 목표 제어선까지 점진적으로 변해가는 다수의 중간 프레임들을 생성한다. 또한 이 반자동 필드 워핑을 수행할 시, 성형 부위의 변형을 따라 단계적으로 모양이 변하는 가변 워핑 마스크를 사용함으로써 변형 부위 이외의 얼굴 구성 요소들에 대해서는 왜곡을 최소화하는 지역적 변형 특성을 제고하고, 이렇게 생성된 성형 부위를 가변 모핑 마스크의 경계 영역에서 시그모이드 함수에 기반한 블렌딩을 수행하는 것이 특징이다. 제안된 2D 가상 성형 시스템은 직관적이고 편리한 사용자 인터페이스를 제공할 수 있기 때문에 시간이 적게 소요되고 작업 피로도가 낮아 실용성이 높다. 특히 짧은 시간 내에 성형의와 고객이 만족하는 직관적인 상담을 가능케 하는 것이 장점이다.

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.241-249
• /
• 2010

The purpose of this study is to provide basic information for marketing strategy for hospitals in Busan Metropolitan area by investigating of the web-site management and effect on hospital management about the web-sites managers. Survey of 53 web-site managers was taken between May 1st and May 25th 2008. The survey was carried out to gather information about characteristics of web-site managers and creating, managing and operating process of web-sites and web-sites' effect and information sharing abilities. The results of survey are as follows. First, most of hospitals' web-sites were launched between 2001 to 2005 via outsourcing. Most of hospitals spent about one to three million won for their web-sites and renew web-sites every year. Most of these web-sites have hospital PR, Q&A, and on-line support functions. Second, most of whom participated in survey have agreed that a hospital web-site has influence in hospital management in various categories such as introducing hospital to medical examination, making doctor's appointment, providing patient guidance, providing medical information, and patient counselling. This study shows that effects of web-sites are closely related to web-site satisfaction level. Therefore, to raise the hospital satisfaction level, it is necessary for hospitals to put more efforts in creating web-site that provides more medical information and improved on-line services.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.461-467
• /
• 2020

In noisy and multi-speaker environments, the performance of speech recognition is unavoidably lower than in a clean environment. To improve speech recognition, in this paper, the signal of the speaker of interest is extracted from the mixed speech signals with multiple speakers. The VoiceFilter model is used to effectively separate overlapped speech signals. In this work, clustering by Probabilistic Linear Discriminant Analysis (PLDA) similarity score was employed to detect the speech signal of the interested speaker, which is used as the reference speaker to VoiceFilter-based separation. Therefore, by utilizing the speaker feature extracted from the detected speech by the proposed clustering method, this paper propose a speaker diarization system using only the mixed speech without an explicit reference speaker signal. We use phone-dataset consisting of two speakers to evaluate the performance of the speaker diarization system. Source to Distortion Ratio (SDR) of the operator (Rx) speech and customer speech (Tx) are 5.22 dB and -5.22 dB respectively before separation, and the results of the proposed separation system show 11.26 dB and 8.53 dB respectively.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.2
• /
• pp.67-79
• /
• 2023

The bounce rate is the rate at which a user leaves immediately after visiting, and this study aimed to find out what attributes of a website affect the bounce rate. Web site evaluation items were defined as a total of 4 items and 27 evaluation attributes, including usability, information, service interaction, and technology, so that they can be commonly applied to venture companies in various industries through prior research. As a result of the study, 6 website attributes that affect the bounce rate were verified to be significant by discriminant analysis and decision tree analysis. Suggestions to reduce the bounce rate of venture business websites through this study are as follows. First, the path name of the website is displayed as mandatory and a pull-down menu function is added to facilitate movement to other pages. Second, it is good to expose core content that can attract users' attention in the form of a banner, and place internal link banners in the right place on sub-pages. Third, external links should be linked to a new window so that they do not leave the current page immediately so that they can be re-entered. Lastly, it is recommended to expose the contact information of the person in charge and consultation function as direct information for communication with customers, but if individual response is difficult, at least the consultation function must be added. These suggestions are expected to be of practical help in various fields such as website development, operation, and marketing. However, in special cases, a high bounce rate may be normal, so it should be considered according to the situation.

• The Journal of Society for e-Business Studies
• /
• v.18 no.2
• /
• pp.257-277
• /
• 2013

Those studies in the field of Management Information Systems and the Success Model of the DeLone and McLean's Information Systems suggest that some factors related to information systems should be developed and operated to affect the performance of the user's personal and companies through the introduction and use of corporate information systems. The purpose of this study is put on searching for some factors which impact on user satisfaction about the customer information management systems of call center. We did conduct on a survey of 539 people who are working as a call center counseling employees as setting up a structural equation model which reflects previous research on working environment and job satisfaction, and modified DeLone and McLean's information system success model. The results of this study are as follows. First, seven of the eleven hypotheses that three quality of the information systems might be affecting working environment, job satisfaction, user satisfaction were adopted Second, we confirmed that the working environment works as a the partial mediation and the quality of services works as a fully mediation between system/information quality and users' satisfaction. The implications of this study are that it is necessary not only to make a good working environment but also to keep improving it in order to boost the operational performance of information systems in the future.

• Journal of Digital Contents Society
• /
• v.19 no.7
• /
• pp.1365-1372
• /
• 2018

The purpose of this study is to analyze the importance of the determinants of housing sales agency's role in the sale of apartment housing. For this purpose, a hierarchical decision model was constructed to understand the role and importance of the sales agency. The analytical variable items structured by the research model were set up through literature review, precedent research, and expert brainstorming. The questionnaire consisted of two comparisons for AHP analysis and the importance of absolute importance for fuzzy analysis. Afterwards, the work of correcting the importance was carried out. As a result of the analysis, it was found that the contractor prioritized the sale conditions and the sales agency had priority over the planning for the sale. As a result of analysis, planning of customer pre-sale counseling data, planning of client subscription and contract maximization plan, planning method of advertisement public media method were found to be the most important factors. The results of measurement of absolute importance(fuzzy) & relative importance(,AHP) showed similar tendency. Therefore, it can be seen that the timing of the model house operation is an important period in which the subscription rate depends on the role of the sales agency and the marketing strategy.