• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.366-367
• /
• 2023

지적 장애인은 제한된 활동 환경 범위의 제약으로 인해 자기 신체 구조에 맞는 운동법을 접할 기회가 적고, 각자의 건강 상태와 신체 구조에 따라 운동할 때 세심한 요구가 필요하다. 본 논문은 지적 장애인을 대상으로 비만 관리에 대한 필요성 인지 및 신체 활동량을 늘리기 위한 개인 맞춤형 운동 루틴 추천 시스템을 제안하였다. 제안한 시스템을 구성하기 위해 먼저 대한장애인체육회에서 제공하는 건강 상태, 신체 정보, 장애 유형 및 등급 등의 데이터를 분석하였다. 또한, 웹 사이트에서 장애인의 입력 정보가 들어오면 TF-IDF 벡터를 산출하고, 다른 사용자와의 코사인 유사성을 분석해 운동 루틴을 제안하였다. 본 연구에서 제안한 추천 시스템을 통해 지적 장애인을 대상으로 맞춤형 건강관리에 대한 인식 향상 및 건강권 보장, 운동 효율 증진 등을 기대할 수 있다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.41-63
• /
• 2023

As the online e-commerce market growing, the need for a recommender system that can provide suitable products or services to customer is emerging. Recently, many studies using the sentiment score of online review have been proposed to improve the limitations of study on recommender systems that utilize only quantitative information. However, this methodology has limitation in extracting specific preference information related to customer within online reviews, making it difficult to improve recommendation performance. To address the limitation of previous studies, this study proposes a novel recommendation methodology that applies deep learning technique and uses various linguistic factors within online reviews to elaborately learn customer preferences. First, the interaction was learned nonlinearly using deep learning technique for the purpose to extract complex interactions between customer and product. And to effectively utilize online review, cognitive contents, affective contents, and linguistic style matching that have an important influence on customer's purchasing decisions among linguistic factors were used. To verify the proposed methodology, an experiment was conducted using online review data in Amazon.com, and the experimental results confirmed the superiority of the proposed model. This study contributed to the theoretical and methodological aspects of recommender system study by proposing a methodology that effectively utilizes characteristics of customer's preferences in online reviews.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.31-49
• /
• 2023

With the growth of the food-catering industry, consumer preferences and the number of dine-in restaurants are gradually increasing. Thus, personalized recommendation services are required to select a restaurant suitable for consumer preferences. Previous studies have used questionnaires and star-rating approaches, which do not effectively depict consumer preferences. Online reviews are the most essential sources of information in this regard. However, previous studies have aggregated online reviews into long documents, and traditional machine-learning methods have been applied to these to extract semantic representations; however, such approaches fail to consider the surrounding word or context. Therefore, this study proposes a novel review textual-based restaurant recommendation model (RT-RRM) that uses deep learning to effectively extract consumer preferences from online reviews. The proposed model concatenates consumer-restaurant interactions with the extracted high-level semantic representations and predicts consumer preferences accurately and effectively. Experiments on real-world datasets show that the proposed model exhibits excellent recommendation performance compared with several baseline models.

• The Journal of Society for e-Business Studies
• /
• v.9 no.3
• /
• pp.191-205
• /
• 2004

In banking industry, as competition of retail finance is intensive, there appeared eCRM which is a kind of marketing strategy, not only screening good customers but also doing one-to-one marketing for improving customer royalty and satisfaction of goods and service of bank. The strategic importance of eCRM is increasing more and more. We studied bank to use the advantage of expert system and eCRM. The expert system is used as a tool to analyze eCRM. In this paper, first, we presented an eCRM system architecture using expert systems in banking business. Secondly, a bank financial goods recommendation system using expert system is designed and developed. Customers will receive the good quality financial services from the expert system and banks also will acquire the good quality customer data from the expert system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.149-155
• /
• 2023

Profiling-based recommendation services provide the convenience of easily accessing specialized content for individuals on the user side and provide an important profit model on the corporate side. Despite the utility of these recommendation services, the issues such as personal information infringement and restrictions on consumer options are emerging, and certain regulatory movements for profiling recommendation services are actively underway. Under the circumstance, there are concerns that the introduction of regulations without a close review of regulatory effectiveness and side effects will weaken the competitiveness of domestic companies in the global market. This study systematically analyzed how companies providing profiling-based recommendation services perceive the corresponding regulations.

• Journal of the Korea Convergence Society
• /
• v.13 no.5
• /
• pp.53-60
• /
• 2022

The purpose of this study is to identify the causal relationship of the structural model through approach motivation, avoidance motivation, and digital usage recognition in order to prepare a plan for coexistence with dental hygiene targeting 239 students from the dental hygiene department at a university in Gangwon-do. For statistical methods, SPSS Statistics 24.0 program and AMOS 21.0 were used. As a result of the structural equation model analysis, the motivation for approach was found to be significantly related to digital usage recognition and class satisfaction. In addition, digital usage perception was found to be significantly related to class satisfaction, and class satisfaction was shown to be significantly related to department satisfaction and department recommendation. Lastly, department satisfaction was significantly found in department recommendation. In other words, the coexistence plan with dental hygiene (department) is to expand the convergence of digital classes. In order to solve the problem, it is necessary for schools to establish facilities to expand teaching materials for practical classes and to devise teaching methods.

• 베이커리
• /
• no.3 s.320
• /
• pp.150-151
• /
• 1995

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.25-32
• /
• 2018

In the massive online fashion market, it is not easy for consumers to find the fashion style they want by keyword search for their preferred style. It can be resolved into consumer needs based fashion recommendation. Most of the existing online shopping sites have collected cumtomer's preference style using the online quastionnair. In this paper, we propose a simple but effective novel model that resolve the traditional method in fashion profiling for consumer's preference style and needs using implicit profiling method. In addition, we proposed a learning model that reflects the characteristics of the images itself through the deep learning-based intelligent preferred fashion model learned from the collected data. We show that the proposed model gave meaningful results through the qualitative evaluation.

• Journal of the Korean Society for Library and Information Science
• /
• v.54 no.4
• /
• pp.147-167
• /
• 2020

The purpose of this study is to analyze the factors influencing the intention of revisiting and recommending by applying a structural equation model, targeting the service quality factors of university libraries derived from previous studies. For 11 days from April 30th, 2020 to May 10th, 2020, a total of 127 user groups (undergraduate students, graduate students, professors/instructors) were surveyed on their intention to revisit and recommend. The analysis results are as follows. 'Materials' and 'service customization' were shown as quality dimensions that influence revisit. In addition, revisiting was found to have an effect on recommendation intention, and it was analyzed that 'materials' and 'service customization' affect not only revisit but also recommendation intention. In addition, 'service customization' was found to be a factor that directly affects the intention to recommend. Based on this, a method of applying the concept of customization to library services and marketing was proposed in an environment where users' needs are diversifying and becoming personalized.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.7-17
• /
• 2021

This study investigated the effect of size recommendation technology convergence on purchase intention mediated by information credibility and satisfaction. The survey for this study was conducted on Amazon Mechanical Turk targeting U. S. residing women aged 18 to 60 years old who have never used size recommendation technology. They experienced the size recommendation technology in the provided web page and returned to the survey to answer the questionnaire. The analysis was done with 213 surveys using SPSS 27.0 and Process Macro (model 6, 5,000 Bootstrapping sample). The dimensions of service quality were found to be responsiveness and ease of use, and both have a significant effect on purchase intention through information credibility and satisfaction.