• Journal of Information Technology Services
• /
• v.17 no.3
• /
• pp.17-36
• /
• 2018

In this study, we developed a chatbot (Dialogue agent) using small Q & A data and evaluated its performance. The chatbot developed in this study was developed in the form of an FAQ chatbot that responds promptly to customer inquiries. The development of chatbot was conducted in three stages : 1. Analysis and planning, 2. Content creation, 3. API and messenger interworking. During the analysis and planning phase, we gathered and analyzed the question data of the customers and extracted the topics and details of the customers' questions. In the content creation stage, we created scenarios for each topic and sub-items, and then filled out specific answers in consultation with business owners. API and messenger interworking is KakaoTalk. The performance of the chatbot was measured by the quantitative indicators such as the accuracy that the chatbot grasped the inquiry of the customer and correctly answered, and then the questionnaire survey was conducted on the chatbot users. As a result of the survey, it was found that the chatbot not only provided useful information to the users but positively influenced the image of the pension. This study shows that it is possible to develop chatbots by using easily obtainable data and commercial API regardless of the size of business. It also implies that we have verified the validity of the development process by verifying the performance of developed chatbots as well as an explicit process of developing FAQ chatbots.

• Journal of the Korean Society for information Management
• /
• v.24 no.2
• /
• pp.105-122
• /
• 2007

To understand the present status and the development of the digital reference service in Korean public libraries, a nationwide site observation was attempted in 2007. The collected data was analyzed, then compared with the previous analysis based on a 2003 data. For the 404 sites offering digital reference, operational characteristics, such as access level, service mode, link description, policy, web form, and FAQ, are analyzed, Performance analysis focused on the presence of question posting, volume of usage, response rate, and types of the questions, for the data collected for 15 days through question and answer transcript recording. Results reveal findings on the present situation as well as changes over 4 years. Related problems are identified. The conclusion includes suggestions for improving digital reference service.

• Journal of Korean Public Health Nursing
• /
• v.9 no.1
• /
• pp.59-70
• /
• 1995

The purpose of this study was identify frequent misconceptions and indirect measurenent of the attitude toward the elderly. The measurenent tool was FAQ which is short, well-docunented and consist of 20 factual items only. The Results were as follows: The average right answer was $51.4\%$. - Regarding the difference between sex, male's rate is higher than female's. $(57.4\%,\;48.4\%)$ - Subjects had considerable indirect attitude toward the elderly.

• 월간 기계설비
• /
• no.2 s.211
• /
• pp.54-55
• /
• 2008

대한설비건설협회에서 발급하고 있는 '인터넷증명서발급시스템'은 지난 2006년 9월 16일 오픈한 이래 회원사들의 호응도가 높아짐에 따라 방문 발급 대비 인터넷 발급비율이 66%를 차지하고 있습니다. 인터넷증명서 발급비율이 점차 증가추세임에 따라 본지는 인터넷증명서발급 시스템의 원활한 운영을 위하여 그동안 회원사들이 많이 했던 질문과 상담내용 및 조치방법을 안내하오니 업무에 많은 참고를 바랍니다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.931-933
• /
• 2020

자연어 처리는 인공지능의 핵심기술 중 하나이다. 그 중 오픈 도메인 챗봇 구현은 NLP 에서 어려운 태스크로 꼽힌다. 명확한 목표, FAQ 가 존재하는 기능형 챗봇과 달리 오픈 도메인 챗봇은 연속적 대화, 방대한 양의 상식 등 구현에 어려움이 많았다. 짧은 질문과 대답으로 이루어진 데이터로 학습한 모델을 대화 데이터로 학습시켜 좀더 자연스러운 챗봇을 구현해보고자 한다.

• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.438-449
• /
• 2004

More and more users are using the query e-mail according to the increment of use of internet. The operator of internet site desires the users to check the FAQ and Q＆A contents first before sending the query e-mail to the operator However the users try to get the solution for a problem easily by simply sending a query e-mail. Therefore the increment of query e-mail is inevitable, and the site operator is suffering from too heavy loads and spending too much time and cost to reply the query e-mail. In this paper, we are proposing an efficient method of classifying the query e-mail of users automatically by using a neural network. To verify the reasonability of our work, the query e-mails of KORNET are used as the test data, which is actually gathered in KT. A total of 210 learning data and 280 test data were used to test the performance of the proposed approach. From the experiments we got the encouraging result from the view point of application in real life. The proposed approach satisfied the request of users who wanted rapid response for their query e-mail.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.529-536
• /
• 2004

The main idea of this paper is to combine position information in sentence and query type classification to make the documents ranking to query more accessible. First, the use of conceptual graphs for the representation of document contents In information retrieval is discussed. The method is based on well-known strategies of text comparison, such as Dice Coefficient, with position-based weighted term. Second, we introduce a method for learning query type classification that improves the ability to retrieve answers to questions from Question Answering system. Proposed methods employ naive bayes classification in machine learning fields. And, we used a collection of approximately 30,000 question-answer pairs for training, obtained from Frequently Asked Question(FAQ) files on various subjects. The evaluation on a set of queries from international TREC-9 question answering track shows that the method with machine learning outperforms the underline other systems in TREC-9 (0.29 for mean reciprocal rank and 55.1% for precision).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.11
• /
• pp.2609-2614
• /
• 2015

National research and development projects institutions have implemented various measures in order to prevent R&D expenses abuse and negate enforcement. but it reveals a limit to prevent abuse of R&D expenses[1,2]. In this paper, to prevent abuses resulting from the R & D for the unusual trading post caught collecting information from the R & D phase implementation plan to detect unusual transactions. The results are subjective and research institutions, and specialized agencies to take advantage of shared, real-time cross-linkage between the credit card companies. Studies of data quality diagnostic techniques developed for this purpose related regulations and manuals, Q & A, FAQ, Outside-in business rules that derive from a variety of information, such as personnel interviews (Outside-In) was used for analysis.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.220-222
• /
• 2001

컴퓨터의 사용인구가 많아지고, 인터넷의 보급이 급속히 늘어남에 따라 많은 정보가 생산되고 있다. 그리고 이러한 정보를 사용자에게 좀더 효율적인 방법으로 제공하는 서비스들도 많아지게 되었다. 그러나 컴퓨터에 익숙하지 않은 사용자들은 쉽게 이러한 서비스를 이용하지 못하기 때문에 사용자를 돕는 시스템이 필요하다. 인터넷 서비스제공 업체들은 사용자의 질문에 대해 관리자가 직접 답을 해주는데, 이들 시스템을 이용하는 사용자들의 증가로 질의응답 업무의 양이 커지고 있다. 본 논문에서는 이를 해결하기 위해 사용자의 질의를 자동으로 분류하여 응답하고 사용자가 FAQ를 개념적으로 브라우징 할 수 있는 시스템의 유용성을 입증하기 위하여, 그 적용 가능성과 일반 사용자들의 이용 결과를 통계적으로 분석하였다.

• Journal of Korean Library and Information Science Society
• /
• v.26
• /
• pp.541-573
• /
• 1997

This study reviews several innovative electronic reference services that will be transformed in the age of the virtual library. This study focused on reference service via E-mail and electronic bulletin board which is regarded as the most important service in a variety of electronic reference services. Through E-mail and the electronic bulletin board, the user submits questions and the librarian responds with the answer. Though interest in using E-mail and electronic bulletin board as a basis for reference service has grown considerably in recent years, it is still in its infancy in Korea. Thus the purpose of this study is to propose a model electronic reference service system using E-mail and the electronic bulletin board for university libraries in Korea. This system consists of the following modules: electronic reference services policy, open reference service via electronic bulletin board, closed reference service via E-mail, and FAQ. This system is meant to be a guide for those considering implementing such a service.