• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.43-44
• /
• 2022

기존 자연어 처리 모델은 문맥 단위 단어 임베딩을 처리하지 못하는 한계점을 가지고 있는 한편 최근 BERT 기반 사전학습 모델들은 문장 단위 임베딩이 가능하고 사전학습을 통해 학습 효율이 비약적으로 개선되었다는 특징이 있다. 본 논문에서는 사전학습 언어 모델들을 이용하여 음식점, 배달전문점 등 음식 업종에서 발생한 고객 발화 의도를 분류하고 모델별 성능을 비교하여 최적의 모델을 제안하고자 한다. 연구결과, 사전학습 모델의 한국어 코퍼스와 Vocab 사이즈가 클수록 고객의 발화 의도를 잘 예측하였다. 한편, 본 연구에서 발화자의 의도를 크게 문의와 요청으로 구분하여 진행하였는데, 문의와 요청의 큰 차이점인 '물음표'를 제거한 후 성능을 비교해본 결과, 물음표가 존재할 때 발화자 의도 예측에 좋은 성능을 보였다. 이를 통해 음식 업종에서 발화자의 의도를 예측하는 시스템을 개발하고 챗봇 시스템 등에 활용한다면, 발화자의 의도에 적합한 서비스를 정확하게 적시에 제공할 수 있을 것으로 기대한다.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.915-922
• /
• 2024

Currently, in Korea, there is a growing interest in improving the learning ability of the education target group due to the low birth rate and aging population. The dilemma of a shrinking population ultimately causes the burden of having to come up with a plan to efficiently maximize the use of available population resources. Accordingly, this study explores the impact of learning motivation (activity-oriented motivation, learning-oriented motivation) on learner characteristics (learning value, learning efficacy) and learning satisfaction, and as a result, intention to continue participating in lifelong learning (recommendation intention, relationship continuation intention). As a results of the analysis, it shows that learning motivation had a significant effect on learning satisfaction, and the emotions formed in this way had a positive effect on recommendation intention and relationship continuation intention. In addition, the results show that learning-oriented motivation had a significant effect on both learning satisfaction and learner characteristics, but that learning efficacy had no effect on recommendation intention. This study is significant in that it presents the basis for an educational system based on relationship maintenance and learner characteristics by considering the learner's orientation, individual achievement direction, recommendation intention, and relationship continuation intention.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.2
• /
• pp.61-73
• /
• 2011

The analysis on learners made through the study focuses on the intention of the participants in the learning activities of the robot programming. Therefore, for the analysis of the learners' intention, which is tried in the study, TAM, the analysis tool used for understanding buying acts or buying intention of buyers in the business sector, is basically utilized, and the Flow theory is additionally applied, trying to know, through the quantum analysis methods, the factors to give influence on the intention for learners to take part in the robot programming lesson. For this, a quantum analysis was made by PLS analysis, a kind of structural equations. As the result of the analysis, it is confirmed that such factors as 'recognized utility' and 'recognized readiness' and 'Flow' give significant influence on the intention of learners' participation in the lesson. As the result of the synthetic analysis and in regard with the value of the programming lesson, it is found that the following factors give actual influence to the intention of learners: the group where learners belong or teaching-learning organizations together with creating social rapport, learning tasks given for learners, etc.

• The Journal of the Korea Contents Association
• /
• v.22 no.9
• /
• pp.667-677
• /
• 2022

The purpose of this study is to analyze the structural relationship among the usefulness, ease of use, use intention, and learning utilization of smart learning devices recognized by college students. In order to achieve this, the following problems were addressed: first, how do college students' recognition of ease and usefulness of smart learning devices? second, how do college students' recognition of ease and learning utilization? third, what mediating effects od use of smart learning devices and learning utilization? As for the research method, a survey of 350 students who participated in smart learning was conducted to conduct a home review, confirmatory factor analysis, and bootsrapping for structural equation estimation and mediating analysis. As a result of the analysis on this, first, it was found that the usefulness and ease of smart learning devices recognized by college students had an effect on the intention of use. Second, it was found that the perception of the usefulness and ease of smart devices perceived by college students had an effect on the use of smart learning device learning. Third, it was found that the intention to use smart devices perceived by college students mediated the relationship between usefulness and learning utilization, and it was found that it mediated the relationship between ease and learning utilization. The implications are that instructors can recognize and utilize the intention of using smart learning devices properly by allowing college students to recognize the usefulness and ease of using smart learning devices in the classroom, thereby increasing the learning utilization of smart learning devices in class. In addition, efforts are needed to enable college students to recognize the usefulness of smart devices and to expand the use of learning.

• 한국벤처창업학회:학술대회논문집
• /
• 2019.04a
• /
• pp.143-148
• /
• 2019

시대적 변화에 따른 경력성공의 관점이 변화하고 있지만 다수의 연구들은 창업과 취업을 분리하여 연구되어 왔다. 또한 환경의 변화뿐만 아니라 개인 가치관의 변화에 따라 평생 직장의 개념이 사라졌으며 전 생애에 걸친 학습의 필요성이 대두 되고 있다. 학습의 형태는 기존의 지식을 전달하는 형태에서 다양하게 변화해왔다. 교실 수업의 형태는 팀활동과 미디어 활용을 중심으로 변화하고 있으며 교실 밖 수업에서는 자율적인 동아리 활동이나 커뮤니티의 참여 등을 통해 역량을 향상시키는 기회를 제공하고 있다. 개인의 경력은 인생에 걸친 학습과 일에 관련된 경험 및 행동과 연관된 태도로부터 발생한다. 이러한 경력을 이끌어가는 태도는 새로운 환경속에서 즉각적인 요구를 받아들이는 적응학습과 새로운 행동 및 지식을 유발하는 생성학습, 그리고 상호작용 패턴 인식을 통해 새로운 시도를 하는 전환학습을 지속적으로 일으킨다. 또한 이러한 무형식 학습들은 취업과 연계 될 뿐만 아니라 창업의도에도 긍정적인 영향을 줄 수 있다. 본 연구는 자기주도성과 가치지향성을 척도로 하는 프론티언 경력태도가 창업의도에 영향을 미치지 확인함으로서 기존의 취업역량과 연결시켜왔던 연구에 새로운 시사점을 제시하고자 한다. 또한 무형식학습 활동을 매개변인으로 투입하여 학습 과정에서 자연스럽게 발생하는 학습의 효과를 확인하여 변화된 교육형태의 중요성을 확인하는데 의의가 있다. 이에 더해 스마트미디어를 활용하는 능력인 스마트미디어 리터러시와 팀 학습을 지향하는 팀학습 선호도를 조절효과로 보아 분석함으로서 스마트미디어활용 학습과 팀학습의 형태로 변화하고 있는 교육 현장의 특성을 함께 확인하고자 한다. 이를 위해 2019년 3월부터 6월까지 교육과 경력 환경의 변화의 중심에 서있는 대학생들을 대상으로 설문조사를 실시하여 이를 분석하고자 한다.

• Journal of the Korea Convergence Society
• /
• v.10 no.10
• /
• pp.215-222
• /
• 2019

The purpose of this study is to investigate the change of students' perceptions by comparing factors affecting e-learning intention before and after e-learning experience based on longitudinal data. For this purpose, a research study was conducted targeting university students at Y and K universities in Gyeongsangbuk-do. As a result, first, the convenience of learning time, the ease of learning process, and the usefulness of e-learning had an effect on e-learning intention regardless of the learning experience. Second, the convenience of the learning space was different in the perception before and after the learning experience, and it was found to affect the intention to use after the e-learning experience. Third, college students who have experienced e-learning have shown that the ease of learning process has the most influence on their intention to use. The results of this study can provide an effective direction of e-learning activation and provide basic data for longitudinal research on e-learning learners.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.283-284
• /
• 2019

규칙 기반의 챗봇(Chatbot)은 개발자가 미리 지정한 키워드와 패턴을 통해 사용자의 의도(Intent)를 파악하기 때문에, 챗봇을 응용한 어플리케이션에서는 제한적인 활용도를 보인다. 본 논문에서는 위 문제를 해결하기 위해, 프레임워크 기반의 한글 자연어 처리 챗봇 성능 향상을 위한 점진 학습(Incremental Learning)을 제안한다. DialogFlow는 규칙 기반의 챗봇 프레임워크로서, 사용자 질의 패턴에 대한 사전 학습이 치명적이다. 제안하는 점진 학습 기법은 사용자 질의가 미리 학습되어 있지 않은 경우에도, 유사도 기반으로 질의의 의도를 결정할 수 있다. 이때 entity 조합과 기존에 학습된 질의들과의 유사도를 통해 의도를 결정하여, 프레임워크를 점진적으로 학습한다. 이를 적용하여 연세대학교 정보들을 제공하는 챗봇을 개발하고, 실험을 통해 제안된 점진 학습 기법은 기존 시스템보다 다양한 종류의 질의 처리가 가능하고, 더욱 빠른 응답 속도를 나타내는 것을 확인하였다. 또한 사용자가 증가함에 따라 점진 학습을 통해 성능이 더욱 증가하는 자가 학습 모형으로서의 우수함을 확인하였다.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.12 no.6
• /
• pp.1-12
• /
• 2017

This paper is brought to asses the training effect of KS-QFD boot camp for the companies in the early growth stage. In particular, the focus of research falls on measuring transfer intension of the participants from the early stage companies older than three years old, motivating effect of applying knowledges acquired from KS-QFD training camp into their real business case. KS-QFD program is presented to help company in the early stage companies over three years old of boosting up their sales volume more than 5 times than now for the next 18 months by this training. The training program of KS-QFD is ultimately to design more practical and helpful program to real business and spread out. The research establish model by setting the learner readiness and perceived content validity by doing training design as independent variables, self-efficacy of learner as mediating variable, and transfer intension as dependant variable. Research results shows the following outcomes. First, learner readiness does not have directly effect on transfer intension under keeping statistical significance. But as the parameter of self-efficacy, it has perfect mediating effect. Second, research proves that perceived content validity have directly impact on learning transfer intension of mediating by self-efficacy partially. This research contributes on proving that learning by doing KS-QFD boot camp enable the participants to build up their self-efficacy and lead to enhance transfer intension. In more steps, the research validates that KS-QFD training camp have delivered very practical and helpful on-site knowledge to the participants.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.419-422
• /
• 2010

사용자와 환경의 변화에 적응하기 위해서 베이지안 네트워크의 다양한 학습 방법들이 연구되고 있다. 기존의 많은 학습방법에서는 학습 데이터로부터 통계적 방법을 통해서 베이지안 네트워크 모델을 학습하는데, 이러한 접근 방법은 학습 데이터를 수집하기 어려운 문제에 적용하기 힘들며, 사용자의 의도를 데이터의 패턴들로만 학습하므로 직접적으로 사용자의 의도를 반영할 수 없다. 본 논문에서는 대화에 기반하여 사용자의 의도를 직접적으로 수집하고, 이로부터 베이지안 네트워크의 파라메터를 학습하는 방법을 연구한다. 제안하는 방법에서는 사용자와의 대화를 통해서 현재의 모델의 잘못된 점 혹은 개선점을 직접적으로 입력 받고, 이를 바탕으로 베이지안 네트워크 모델을 수정하여 데이터의 수집 없이 빠른 시간에 사용자가 원하는 모델을 학습 할 수 있다. 기존의 통계적 기법을 이용한 대표적인 베이지안 네트워크 파라메터 학습 방법인 최대우도 추정(Maximum Likelihood Estimation; MLE) 방법과 제안하는 방법을 비교하여 제안하는 방법의 유용성을 확인한다.

• Journal of Korea Port Economic Association
• /
• v.36 no.1
• /
• pp.165-182
• /
• 2020

According to recent government forecasts, universities face a critical situation, due to a reduction in the number of students and a decrease in tuition income. To respond to the changed population structure and the 4th Industrial Revolution, the government is supporting universities in reorganizing the structure of academics and curricula focused on lifelong education. Considering this, this study analyzed the correlation between intention to participate in lifelong education and learning outcomes oriented to workers involved in shipping and port logistics in the Port of Gwangyang and Yeosu, who are participating or have participated in lifelong education. To expand the opportunities for participation in the lifelong education of adult learners and form a learning culture, it is necessary to analyze the intention to participate in lifelong education and how participants identify their learning outcomes. According to the analysis results, the goal orientation of intention to participate in learning has a significant influence on individual features of learning outcomes, and learning orientation has a significant influence on the social characteristics of learning outcomes. Moreover, learning outcomes and the learning orientation of the intention to participate in learning have a significant influence on the intention to continue learning. In particular, the results showing that learning outcomes reflect individual changes and that interests obtained as a product of learning influence the intention to continue learning are highly suggestive.