• Journal of Practical Engineering Education
• /
• v.14 no.3
• /
• pp.523-533
• /
• 2022

During the COVID-19 pandemic, the use of video classes and real-time online education has increased, but the lack of interaction between instructors and learners remains a challenging problem to be resolved. This paper designs and implements a learning support system that utilizes a digital human to improve faculty-student interaction, which plays an important role in increasing the educational effect and satisfaction of real-time online classes. In this paper, a digital human participates in a class as a virtual learner and asks questions raised by other learners through an anonymous chat system to the instructor on behalf of the learners. In addition, as a class facilitator, the digital human analyzes the lecturer's speech in real time and provides it to the learner in the form of a summary of the class, thereby facilitating faculty-student interaction. In order to confirm that the proposed system can be used in actual online real-time classes, we apply our system to Zoom classes. Experimental results show that facilitated Q&A and real-time class summaries are successfully provided through our digital human-based learning support system.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.1
• /
• pp.101-115
• /
• 2011

PECOLE (Peer-to-Peer Collaborative Environment) is a P2P-based multimedia distributed collaborative environment supporting a collaborative workspace which is composed of a variety of collaborative applications such as multi-chat, video conferencing, screen sharing and etc. Unfortunately, due to the PECOLE's simple group management, it is impossible to perform collaboration activities while joining multiple groups. In this paper, we present the design and implementation of PECOLE+ which is an extension of PECOLE. PECOLE+ resolves the drawback of PECOLE by providing the Group Management Service and the Workspace Management Service. The Group Management Service provides functionalities such as creating groups, joining multiple groups, and searching groups, and etc. The Workspace Management Service provides each group with an associated workspace, supporting the execution of collaborative applications over the workspace. In addition, any collaborative applications with the provided plug-in interfaces can be executed over the workspace as a PECOLE+ collaborative application.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.491-494
• /
• 2020

최근 언어 모델(Language model)의 기술이 발전함에 따라, 자연어처리 분야의 많은 연구들이 좋은 성능을 내고 있다. 정해진 주제 없이 인간과 잡담을 나눌 수 있는 오픈 도메인 대화 시스템(Open-domain dialogue system) 분야에서 역시 이전보다 더 자연스러운 발화를 생성할 수 있게 되었다. 언어 모델의 발전은 응답 선택(Response selection) 분야에서도 모델이 맥락에 알맞은 답변을 선택하도록 하는 데 기여를 했다. 하지만, 대화 모델이 답변을 생성할 때 일관성 없는 답변을 만들거나, 구체적이지 않고 일반적인 답변만을 하는 문제가 대두되었다. 이를 해결하기 위하여 화자의 개인화된 정보에 기반한 대화인 페르소나(Persona) 대화 데이터 및 태스크가 연구되고 있다. 페르소나 대화 태스크에서는 화자마다 주어진 페르소나가 있고, 대화를 할 때 주어진 페르소나와 일관성이 있는 답변을 선택하거나 생성해야 한다. 이에 우리는 대용량의 코퍼스(Corpus)에 사전 학습(Pre-trained) 된 언어 모델을 활용하여 더 적절한 답변을 선택하는 페르소나 대화 시스템에 대하여 논의한다. 언어 모델 중 자기 회귀(Auto-regressive) 방식으로 모델링을 하는 GPT-2, DialoGPT와 오토인코더(Auto-encoder)를 이용한 BERT, 두 모델이 결합되어 있는 구조인 BART가 실험에 활용되었다. 이와 같이 본 논문에서는 여러 종류의 언어 모델을 페르소나 대화 태스크에 대해 비교 실험을 진행했고, 그 결과 Hits@1 점수에서 BERT가 가장 우수한 성능을 보이는 것을 확인할 수 있었다.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.34 no.4
• /
• pp.222-228
• /
• 2023

There are two categories of online crimes related to children and adolescents: those committed by adolescents and those committed against children and adolescents. While recent trends in criminal law show consensus on strengthening punishment in cases of crimes against children and adolescents, there are mixed stances in cases of juvenile delinquency. One perspective emphasizes strict punishment, whereas the other emphasizes dispositions aligned with human rights. While various forms of online crime share the commonality in that the main part of the criminal act occurs online, they can be categorized into three types: those seeking financial gain, those driven by sexual motives, and those engaged in bullying. Among these, crimes driven by sexual motives are the most serious. Second-hand trading fraud and conditional (sexual) meeting fraud fall under the category of seeking financial gain and occur frequently. Crimes driven by sexual motives include obscenity via telecommunication, filming with discrete cameras, child and adolescent sexual exploitation material, fake video distribution, and blackmail/coercion using intimate images/videos ("sextortion"). These crimes lead to various legal issues such as whether to view vulgar acronyms or body cams that teenagers frequently use as simple subcultures or crimes, what criteria should be applied to judge whether a recorded material induces sexual desire or shame, and at what stage sexual grooming becomes punishable. For example, sniping posts, KakaoTalk prisons, and chat room explosions are tricky issues, as they may or may not be punished depending on the case. Particular caution should be exercised against the indiscriminate application of a strict punishment-oriented approach to the juvenile justice system, which is being discussed in relation to online sexual offenses. In the punishment case of online crime, juvenile offenders with a high potential for future improvement and reform must be treated with special consideration.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.451-461
• /
• 2024

Recently, various AI chatbots based on large language models have been released. Chatbots have the advantage of providing users with quick and easy information through interactive prompts, making them useful in various fields such as question answering, writing, and programming. However, a vulnerability in chatbots called "prompt injection attacks" has been proposed. This attack involves injecting instructions into the chatbot to violate predefined guidelines. Such attacks can be critical as they may lead to the leakage of confidential information within large language models or trigger other malicious activities. However, the vulnerability of Korean prompts has not been adequately validated. Therefore, in this paper, we aim to generate malicious Korean prompts and perform attacks on the popular chatbot to analyze their feasibility. To achieve this, we propose a system that automatically generates malicious Korean prompts by analyzing existing prompt injection attacks. Specifically, we focus on generating malicious prompts that induce harmful expressions from large language models and validate their effectiveness in practice.

• Herbal Formula Science
• /
• v.32 no.1
• /
• pp.1-9
• /
• 2024

Objective : This study aims to assess the potential of utilizing large language models in pattern identification education by developing a simulated patient with fatigue and dual deficiency of the heart-spleen pattern. Methods : A simulated patient dataset was constructed using the clinical practice examination module provided by the National Institute for Korean Medicine Development. The dataset was divided into patient characteristics, sample questions, and responses, and utilized to design the system, assistant, and user prompts, respectively. A web-based interface was developed using the Django framework and WebSocket. Results : We developed a simulated fatigue patient representing dual deficiency of the heart-spleen pattern through prompt engineering. To make practical tools, we further implemented web-based interfaces for the examinee's and evaluator's roles. The interface for examinees allows one to examine the simulated patient and provides access to a personalized number for future access. In addition, the interface for evaluators included a page that provided an overview of each examinees' chat history and evaluation criteria in real-time. Conclusion : This study is the first development of an educational tool integrated with a large language model for pattern identification education, which is expected to be widely applied to Korean medicine education.

• The Journal of Information Systems
• /
• v.25 no.2
• /
• pp.1-25
• /
• 2016

Purpose The innovation capability nowadays has become increasingly prominent in the universities not only for schools but also for teachers. However, due to less attention to the knowledge utilization and management, also some objective constraints, which caused the low level of the innovation capacity for our universities teachers under the current development in China. Meanwhile, transactive memory system (TMS) and knowledge sharing are important contents in knowledge management. The combination of both systems will contribute to a much more comprehensive understanding and performance of knowledge management. The purpose of this study is to investigate the structural relationships between TMS, knowledge sharing, and innovation capability among Chinese university teachers' teams, and to propose the practical implication to integrate effectively internal knowledge of the team to improve innovation capability. Design/methodology/approach In order to exam and verify the hypothesis proposed, we developed a questionnaire with 16 survey items, and each item comes with a five-point Likert-type scale. Hyperlink of online questionnaire was shared through WeChat. It's collected 201 responses from 14 universities in China, and the responders are teaching groups' leaders. And all together 191 responses were filtered out as the valid samples. And we analyze the data set and test research hypotheses by using SPSS 22.0 and AMOS 22.0. Findings All hypotheses are supported. The results reveal that knowledge sharing plays an important role in this study as the mediating role. TMS is positively associated with the innovation capability. And the knowledge sharing plays a significant role as mediating value between them, and influences the TMS's effect on innovation capability. It's thus cleared that if our teachers could well communicate, exchange and collaborate with other teachers in the same group, the innovation capability among the teachers would be improved effectively.

• The Journal of the Korea Contents Association
• /
• v.9 no.3
• /
• pp.361-371
• /
• 2009

LAMS(learning activity management system)[1] is one of the useful tools for designing and managing effectively the learning activities such as web search, chat, forum, grouping, and board. Even if LAMS has been upgraded to support the methods for making e-Learning contents conveniently, it does not have a method to communicate with external educational contents (EEC) made by external tools like Flash, Java, Visual C++, and so on. LAMS, which has been operated on Web environment, should manage all EECs like video and dynamic educational contents as educational contents in LAMS database. However, the current LAMS does not support the functionalities which can provide information of EECs to LAMS database and can also access any information about EECs from the database yet. In this paper, we propose the communication mechanism between the LAMS and EECs for solving the problem. In special, the mechanism makes many statistical data by using the information, and provides them for reflecting in education, and can control various learning management that was impossible under the original LAMS. Based on the proposed mechanism, teachers using LAMS can make more various educational contents and can manage them in the system.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.56-61
• /
• 2022

In this paper, we classify and present AI algorithms and natural language processing methods used in chatbots. A framework that can be used to implement a chatbot is also described. A chatbot is a system with a structure that interprets the input string by constructing the user interface in a conversational manner and selects an appropriate answer to the input string from the learned data and outputs it. However, training is required to generate an appropriate set of answers to a question and hardware with considerable computational power is required. Therefore, there is a limit to the practice of not only developing companies but also students learning AI development. Currently, chatbots are replacing the existing traditional tasks, and a practice course to understand and implement the system is required. RNN and Char-CNN are used to increase the accuracy of answering questions by learning unstructured data by applying technologies such as deep learning beyond the level of responding only to standardized data. In order to implement a chatbot, it is necessary to understand such a theory. In addition, the students presented examples of implementation of the entire system by utilizing the methods that can be used for coding education and the platform where existing developers and students can implement chatbots.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.1-23
• /
• 2011

The contextual subjective well-being (SWB) of context-aware system users can be very helpful in recommending relevant mental health services, especially for those who struggle with mental illness due to a metabolic syndrome or melancholia. Self-surveying measuring or auto-sensing methods have been suggested to monitor users' SWB. However, self-surveying measuring method is not inappropriate for a context-aware service due to requesting personal data in a manual and hence obtrusive manner. Moreover, auto-sensing methods still suffer from accuracy problem to be applied in mental health services. Hence, the purpose of this paper is to propose a contextual SWB estimation method to estimate the user's mental health in unobtrusive and accurate manners. This method is timely in that it acquires context data from the user's literal responses, which expose their temporal feeling. In particular, we developed a measuring method based on exposed feeling verbs and degree adverbs in chat and other text-based communications which show anger or negative feelings. Based on the proposed contextual SWB degree estimation method, we developed an idea of well-being life care recommendation. From the experiment with actual drivers, we demonstrated that the proposed method accurately estimate the user's degree of negative feelings even though it does not require a self-survey.