• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.101-109
• /
• 2023

According to data released by the Covid 19 Self-Employed Emergency Response Committee, 95.6% of small business sales due to Covid 19 have decreased over the past two years, and the damage has further increased due to social distancing for quarantine. However, as all social distancing guidelines have rebeen lifted, and the commercial district has been revitalized, the Seoul Metropolitan Government is pushing for a project to foster local brand commercial districts so that small business owners or prospective founders who have closed their businesses due to the prolonged COVID-19. Therefore, this study propose the model that recommends alley commercial districts suitable for founders among the five alley commercial districts selected for the project to foster local brand commercial districts in Seoul. The Seoul Metropolitan Government's local brand alley commercial recommendation system recommends major population age groups and major industries in the commercial district by combining the population perspective model using Xgboost and the commercial district characteristic model using Decision Tree.

• Journal of Digital Convergence
• /
• v.20 no.3
• /
• pp.211-219
• /
• 2022

The purpose of this study is to improve the operation of shopping mall by examining the effect of service characteristics of Greenanum on customer satisfaction, repurchase and recommendation intention. The hypothesis was verified with SPSS22.0 and PROCESS macro 3.5. As a result, some hypotheses were supported between satisfaction, repurchase, and recommendation for service characteristics. Second, positive effects were found between satisfaction and repurchase, and recommendation intention. Third, a mediating effect appeared. Implications include improvement of low site awareness, benchmarking, and product quality improvement. In the future, it will be necessary to study the differences in the various characteristics of the products sold rather than the differentiation of the shopping mall itself.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.370-372
• /
• 2002

대학 입시 업무에서 원서 접수방식에 있어서 원서 접수를 하기 위해 학교에 직접 방문하여 접수하거나 각 지역 접수 창구와 팩스를 통해 원서를 접수하는데 이를 유기적으로 통합하여 관리할 수 있는 인터넷 원서 접수 환경이 최근 각광을 받고 있다. 그러나, 각 대학의 입시 업무 성격, 특정 학과 선발 과정 등의 충분한 자료 검증이 수행되지 않은 인터넷 원서 접수는 수험생에게 혼란과 복잡성을 유발할 수 있다. 본 논문에서는 수험생에게 소신 지원 및 안정 지원을 위해 적합한 학과를 추천하여 수험생들의 인터넷 원서 접수를 하는데, 충분한 자료를 통해 적합한 학과를 추천해주는 지능형 진학 상담 에이전트 시스템을 설계 및 구현하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.501-506
• /
• 2022

The prolonged of the Post Corona, many Cosmetic company launched various online services. In this paper, consider about the quality of product recommendation using personal color detecting technology. Using the detecting tool which is most widely used by cosmetic company. we will do a lot of testing with this tool and also testing with color detecting equipment. For precise experimental results, it was conducted in a consistent experimental environment. This experiment can be a foundation that can be well used for the expansion of personalized product recommendation services according to the current image-based skin color measurement.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.435-439
• /
• 2022

Many of the industry was changed because of the pandemic of covid 19. It combined with the tendency of modern people to pursue convenience. The industry of Cosmetics also changed business channel from offline to online. Before, people can not get suggestions after they complete the survey. This paper research how to suggest some cosmetics products with their skin type and skin data. We will develop Beauty Concierge system that can get suggestion after the survey. It's will make people attend activity and can make more benefit to the people.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.1-17
• /
• 2023

With the recent rapid development of ICT(Information and Communication Technology) and the popularization of digital devices, the size of the online market continues to grow. As a result, we live in a flood of information. Thus, customers are facing information overload problems that require a lot of time and money to select products. Therefore, a personalized recommender system has become an essential methodology to address such issues. Collaborative Filtering(CF) is the most widely used recommender system. Traditional recommender systems mainly utilize quantitative data such as rating values, resulting in poor recommendation accuracy. Quantitative data cannot fully reflect the user's preference. To solve such a problem, studies that reflect qualitative data, such as review contents, are being actively conducted these days. To quantify user review contents, text mining was used in this study. The general CF consists of the following three steps: user-item matrix generation, Top-N neighborhood group search, and Top-K recommendation list generation. In this study, we propose a recommendation algorithm that applies an extended similarity measure, which utilize quantified review contents in addition to user rating values. After calculating review similarity by applying TF-IDF, Word2Vec, and Doc2Vec techniques to review content, extended similarity is created by combining user rating similarity and quantified review contents. To verify this, we used user ratings and review data from the e-commerce site Amazon's "Health and Personal Care". The proposed recommendation model using extended similarity measure showed superior performance to the traditional recommendation model using only user rating value-based similarity measure. In addition, among the various text mining techniques, the similarity obtained using the TF-IDF technique showed the best performance when used in the neighbor group search and recommendation list generation step.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.347-349
• /
• 2021

전문의약품은 의약품안전사용서비스(DUR)를 이용하여 병원에서 처방받은 약에서 부작용이 나타났을 때 기록하고 다음에 약을 처방받을 때 부작용이 나타난 약과 비슷한 계열의 약은 처방받지 않는다. 하지만 일반의약품은 약 구매 기록조차 남지 않아 어떤 약을 언제 처방받았는지 모르고 부작용을 관리할 수 없어 불편함을 겪는다. 이 연구를 통해 제안하는 어플은 처방내역과 복약관리, 약 추천, 약국 찾기로 구성된다. 일반의약품을 처방받은 날짜와 시간, 증상, 효과, 부작용에 대하여 기록하며, 기록을 분석하여 증상에 대한 약을 추천함으로써 치료 효과를 높일 수 있다. 환자가 스스로 투약에 관심을 가지고 기록을 관리함으로써 환자가 주체가 되어 질병을 개선할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.644-645
• /
• 2024

COVID-19 유행 이후 배달 음식의 수요가 증가했다. 이러한 배달 음식은 재료나 영양성분 파악이 어려운 경우가 많아 원하는 음식 조건이 있거나 영양 균형을 필요로 하는 개인이 곤란을 겪는다는 문제점이 있다. 따라서 맞춤형 음식을 원하는 개인이 손쉽게 요리를 할 수 있는 방안을 마련하고자, 여러 머신러닝 알고리즘을 결합한 하이브리드 모델을 이용한 레시피 추천시스템을 구현했다. 구현 후에는 웹사이트를 제작하여 직접 적용해봄으로써 그 활용성을 확인했다.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.65-76
• /
• 2019

This study aimed to primarily examine perceptions about occupational suitability made by vocational counselors for adults who stutter and associated factors. A total of 69 vocational counsellors (23 per condition) took part in this study and were randomly assigned to recordings related to three different speech conditions (fluent, less-severe stuttering, and severe stuttering versions). The participants were asked to listen to one of the three recordings and rate the speaker's communicative functioning, personal attributes, and suitability for 31 occupations, along with perceptions of the speaking demands and educational requirements of the occupations. Regarding the two stuttering conditions, it was found that suitability ratings were lower for occupations with a high speaking demand than those with a low speaking demand. In addition, the most significant factor associated with occupational suitability ratings was perceived speaking demands, followed by perceived educational requirements, and then by ratings of the speaker's personal attributes. These findings suggest that adults who stutter may face role entrapment (or occupational stereotyping) in workplace settings.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.