• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.114-130
• /
• 2020

Balinese calendar is defined as a unique calendar system for combining solar-based and lunar-based system and assuming local system. It is considered as guidance of Balinese societies' activities management, starting from meeting arrangement, wedding ceremony, to religious ceremonies. Practically, it has developed in the form of printed Balinese calendar and electronic Balinese calendar, either web or mobile application. The core of the function is to find out the day with its various characteristics in the Balinese Calendar. In general, society usually asks the religious leader to find out the day in detail. The technology of NLP combined with models of pattern discoveries supports the arrangement of the interaction model in searching the good day in Balinese Calendar to equip the conventional searching system in the previous applications. This study will design a dialog model with AIML method in multi-parameter basis; therefore, the users will be dynamically able to use the searching content in various ways by chatting in similar with consulting to a religious leader. This model will be applied in a chatbot basis service in telegram machine. The addition of the context recognition section into 4 paterns has been successfully improve the ability of AIML to recognize input patterns with many criteria. Based on the testing with 50 random input patterns obtained a success rate of 92.5%.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.683-689
• /
• 2023

자연어 처리 분야는 최근에 큰 발전을 보였으며, 특히 초대규모 언어 모델의 등장은 이 분야에 큰 영향을 미쳤다. GPT와 같은 모델은 다양한 NLP 작업에서 높은 성능을 보이고 있으며, 특히 챗봇 분야에서 중요하게 다루어지고 있다. 하지만, 이러한 모델에도 여러 한계와 문제점이 있으며, 그 중 하나는 모델이 기대하지 않은 결과를 생성하는 것이다. 이를 해결하기 위한 다양한 방법 중, Retrieval-Augmented Generation(RAG) 방법이 주목받았다. 이 논문에서는 지식베이스와의 통합을 통한 도메인 특화형 질의응답 시스템의 효율성 개선 방안과 벡터 데이터 베이스의 수정을 통한 챗봇 답변 수정 및 업데이트 방안을 제안한다. 본 논문의 주요 기여는 다음과 같다: 1) QA Pair Passage RAG을 활용한 새로운 RAG 시스템 제안 및 성능 향상 분석 2) 기존의 LLM 및 RAG 시스템의 성능 측정 및 한계점 제시 3) RDBMS 기반의 벡터 검색 및 업데이트를 활용한 챗봇 제어 방법론 제안

• Knowledge Management Research
• /
• v.21 no.2
• /
• pp.177-196
• /
• 2020

Since the adoption of K-IFRS(Korean International Financial Reporting Standards), the amount of financial footnotes has been increased. However, due to the stereotypical phrase and the lack of conciseness, deriving the core information from footnotes is not really easy yet. To propose a solution for this problem, this study tried financial footnote analysis for financial ratio predictions based on text-mining techniques. Using the financial statements data from 2013 to 2018, we tried to predict the earning per share (EPS) of the following quarter. We found that measured prediction errors were significantly reduced when text-mined footnotes data were jointly used. We believe this result came from the fact that discretionary financial figures, which were hardly predicted with quantitative financial data, were more correlated with footnotes texts.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.233-234
• /
• 2021

본 논문에서는 Microsoft Bot Framework와 Microsoft Azure Service, LUIS AI를 활용하여 쇼핑몰 이용에 도움을 주는 쇼핑 챗봇을 설계하고 구현한다. 이 챗봇은 쇼핑몰을 이용하는 사용자들에게 대화형 인터페이스를 통한 편의성을 제공하고 접근성을 증가시킨다. 또한 직접 찾는 방식이 아닌 AI의 선택이 중심이 되어 검색 시간 감소로 인한 시간 절약 효과를 얻을 수 있다.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.1016-1017
• /
• 2024

본 연구는 생성형 AI와 검색 증강 생성(Retrieval-Augmented Generation, RAG) 기술을 결합하여 환각(Hallucination)을 방지하고 항만공사 환경에 특화된 챗봇 서비스를 제안한다. 주요 특징은 첫째, KMS 저장소, 벡터 데이터베이스, 검색 및 재조정 처리, LLM을 이용한 프롬프트 처리 등을 통해 사용자 질의에 최적화된 응답을 생성한다. 둘째, '챗봇 One-Step-Service'은 사용자에게 업무 처리용 Form을 제공해 업무 처리의 편의성을 향상시킨다. 해당 시스템을 항만공사에 적용하여 한정된 상담 인력 문제를 해결하고 다양한 내부 업무에 적용하여 업무 효율성이 향상될 것으로 기대된다.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.1157-1158
• /
• 2024

인공지능(AI) 기술의 발달과 함께 챗봇은 다양한 산업 분야의 필수 서비스 요소이다. 그러나 국내 챗봇의 언어가 대부분 한국어 서비스에 국한돼 글로벌 확장성에 한계가 있다. 본 연구는 다양한 나라의 언어로 실시간 번역을 하는 외국인 학생을 위한 대학교 입학안내 챗봇 제작을 제안하는 것을 목표로 한다. 이를 위해 사용자 관점에서 기존 입학안내 챗봇을 분석하였으며, 분석 결과를 바탕으로 외국어 사용자 친화적인 챗봇 제작을 제안한다.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.109-119
• /
• 2024

This study aims to contribute to the initial research on on-device AI in an environment where generative AI-based services on mobile and other on-device platforms are increasing. To derive success strategies for generative AI-based chatbot services in a mobile environment, over 200,000 actual user experience review data collected from the Google Play Store were analyzed using the LDA topic modeling technique. Interpreting the derived topics based on the Information System Success Model (ISSM), the topics such as tutoring, limitation of response, and hallucination and outdated informaiton were linked to information quality; multimodal service, quality of response, and issues of device interoperability were linked to system quality; inter-device compatibility, utility of the service, quality of premium services, and challenges in account were linked to service quality; and finally, creative collaboration was linked to net benefits. Humanization of generative AI emerged as a new experience factor not explained by the existing model. By explaining specific positive and negative experience dimensions from the user's perspective based on theory, this study suggests directions for future related research and provides strategic insights for companies to improve and supplement their services for successful business operations.

• Journal of Venture Innovation
• /
• v.7 no.3
• /
• pp.101-121
• /
• 2024

The application of chatbots on e-commerce platforms is becoming increasingly widespread. With the rapid development of artificial intelligence technology, previous research has predominantly focused on service failures occurring with the chatbots themselves. There is limited research on scenarios where chatbots handle service failures that are controllable by the sellers. This paper conducted online surveys through two experiments involving a total of 546 participants. The results indicate that, in the event of a service failure, customers are more likely to spread negative word-of-mouth about the store and have lower repurchase intentions when served by chatbots compared to human customer service representatives. This is because customers experience higher levels of anger with the chatbots. However, when customers perceive the service failure as uncontrollable by the seller, the impact of the type of customer service provider on negative word-of-mouth via customer anger is weakened while when customers perceive it as controllable the impact is strengthened. This study provides theoretical contributions for online retail enterprises to apply intelligent customer service while preventing further deterioration of service failures.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.26 no.3
• /
• pp.147-154
• /
• 2020

The purpose of this study was to research the status of logistic service-related workers about untact works by case study in the Era of COVID-19. An experimental design was used by case analysis of interviews with ten office workers from May to June 2020. The results of this research were divided into three categories: work environment, work management and work effect. First, teleworking has a significantly positive influence on business efficiency about work environment. ZOOM, One drive, Skype, Chatbot, Microsoft Teams and Remote view are used as collaborative applications. Second, work instructions in documents are needed such as e-mail and messenger using information and communication technology about work management. Third, the strong points of teleworking are both high work efficiency and job satisfaction about work effect. The weak points of teleworking are both very low-technology and misunderstanding about work effect. The result offer some insights into the case study of logistic service-related workers about untact works. Based on the results, the implications and the limitations of this study were discussed.

• Journal of Advanced Technology Convergence
• /
• v.2 no.2
• /
• pp.1-8
• /
• 2023

Due to the recent long-term economic downturn, the number of non-store and mail-order sellers is increasing as prospective entrepreneurs are concentrated due to the phenomenon of non-store start-ups with low start-up costs. In particular, in addition to unemployed young people and housewives who lack funds, many office workers who wish to have a 'two-job' are jumping into the business. Therefore, in this paper, we have moved away from provider-oriented service platforms that are dependent on specific networks, operators, and service types. In addition, we plan to design a business integration support system that can provide B2B services in the promotional material industry that contributes to business support and profit generation of wholesale and retail non-store entrepreneurs through sharing and participation. The proposed system is judged to be a business integrated operation support system applying orchestration and service management technology and enterprise business partner management technology that can provide stable operation management service.