• Convergence Security Journal
• /
• v.24 no.3
• /
• pp.117-129
• /
• 2024

With the announcement of Transformer, a new type of architecture, in 2017, there have been many changes in language models. In particular, the development of LLM (Large language model) has enabled generative AI services such as search and chatbot to be utilized in various business areas. However, security issues such as personal information leakage and reliability issues such as hallucination, which generates false information, have raised concerns about the effectiveness of these services. In this study, we aimed to analyze the factors that are increasing the frequency of using generative AI in the workplace despite these concerns. To this end, we derived eight factors that affect the quality of LLM-based generative AI response data and empirically analyzed the impact of these factors on job satisfaction using a valid sample of 195 respondents. The results showed that expertise, accessibility, diversity, and convenience had a significant impact on intention to continue using, security, stability, and reliability had a partially significant impact, and completeness had a negative impact. The purpose of this study is to academically investigate how customer perception of response data quality affects business utilization satisfaction and to provide meaningful practical implications for customer-centered services.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.145-152
• /
• 2020

MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.41-49
• /
• 2022

Documents often contain relative time expressions, and it is important to define a schema of the relative time information and develop a system that extracts such information from corpus. In this study, to deal with the relative time expressions, we propose seven additional attributes of timex3: year, month, day, week, hour, minute, and second. We propose a way to represent normalized values of the relative time expressions such as before, after, and count, and also design a set of rules to extract the relative time information from texts. With a new corpus constructed using the new attributes that consists of dialog, news, and history documents, we observed that our rule-set generally achieved 70% accuracy on the 1,041 documents. Especially, with the most frequently appeared attributes such as year, day, and week, we got higher accuracies compared to other attributes. The results of this study, our proposed timex3 attributes and the rule-set, will be useful in the development of services such as question-answer systems and chatbots.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1784-1789
• /
• 2021

Korean sentiment classification task is used in real-world services such as chatbots and analysis of user's purchase reviews. And due to the development of deep learning technology, neural network models with high performance are being applied. However, the neural network model is not easy to interpret what the input sentences are predicting due to which words, and recently, model interpretation methods for interpreting these neural network models have been popularly proposed. In this paper, we used the LIME algorithm among the model interpretation methods to interpret which of the words in the input sentences of the models learned with the korean sentiment classification dataset. As a result, the interpretation of the Bi-LSTM model with 85.24% performance included 25,283 words, but 84.20% of the transformer model with relatively low performance showed that the transformer model was more reliable than the Bi-LSTM model because it contains 26,447 words.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.699-707
• /
• 2020

With the development of deep learning technology, voice processing-related technology is applied to various areas, such as STT (Speech To Text), TTS (Text To Speech), ChatBOT, and intelligent personal assistant. In particular, the STT is a voice-based, relevant service that changes human languages to text, so it can be applied to various IT related services. Recently, many places, such as general private enterprises and public institutions, are attempting to introduce the relevant technology. On the other hand, in contrast to the general IT solution that can be evaluated quantitatively, the standard and methods of evaluating the accuracy of the STT engine are ambiguous, and they do not consider the characteristics of the Korean language. Therefore, it is difficult to apply the quantitative evaluation standard. This study aims to provide a guide to an evaluation of the STT engine conversion performance based on the characteristics of the Korean language, so that engine manufacturers can perform the STT conversion based on the characteristics of the Korean language, while the market could perform a more accurate evaluation. In the experiment, a 35% more accurate evaluation could be performed compared to the existing methods.

• The Journal of Industrial Distribution & Business
• /
• v.10 no.3
• /
• pp.45-58
• /
• 2019

Purpose - The purpose of this study was to investigate the effects of the chatbot's characteristics (ease of use, social presence, playfulness, usefulness) on service value, customer satisfaction and reuse intention when consumers purchased fashion products in the mobile shopping environments. Research design, data, and methodology - Data were collected from Korean consumers from ages 20 to 59 who have experienced using chatbot in a mobile shopping for fashion products. After a pilot survey to 53 customers, the preliminary questionnaire was revised for the final test, and the final questionnaire was administered to 1500 customers. Out of these, 300 were collected. After deleting 48 incomplete ones, 252 questionnaires were used in the statistical analysis. Frequency analysis and exploratory factor analysis using SPSS 23.0 and confirmatory factor analysis and structure equation analysis using AMOS 18.0 were employed for data analyses. Results - First, four factors were extracted for the chatbot's characteristics: ease of use, social presence, playfulness and usefulness. Second, regarding the effect of chatbot's characteristics on service value when purchasing fashion products in the mobile shopping environment, ease of use, playfulness and usefulness of chatbot significantly affected service value. Social presence did not have significant effects on service value. Third, in terms of the effect of the chatbot's characteristics on customer satisfaction when purchasing fashion products in the mobile shopping environment, social presence, playfulness and usefulness of chatbot significantly had an effect on customer satisfaction. Ease of use did not have a significant effect on customer satisfaction. Fourth, service value of chatbot when purchasing fashion products in mobile shopping environment was found to have an effect on customer satisfaction with chatbot. Fifth, service value of chatbot on reuse intention when purchasing fashion products in the mobile shopping environment was found to have an effect on reuse intention of chatbot. Sixth, customer satisfaction with chatbot had a significant impact on the reuse intention of the chatbot when purchasing fashion products in the mobile shopping environment. Conclusions - The present study provide dimensions on the chatbot's characteristics and these may provide helpful data for further studies in this area and for marketers as well.