• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.260-270
• /
• 2019

As the growth of developing Islamic countries, Muslims are into the world. The most important thing for Muslims to purchase food, ingredient, cosmetics and other products are whether they were certified as 'Halal'. With the increasing number of Muslim tourists and residents in Korea, Halal restaurants and markets are on the rise. However, the service that provides information on Halal restaurants and markets in Korea is very limited. Especially, the application of recommendation system technology is effective to provide Halal restaurant information to users efficiently. The profiling of Halal restaurant information should be preceded by design of recommendation system, and design of recommendation algorithm is most important part in designing recommendation system. In this paper, an Intelligent Recommendation Service system for offering Halal food (IRSH) based on dynamic profiles was proposed. The proposed system recommend a customized Halal restaurant, and proposed recommendation algorithm uses hybrid filtering which is combined by content-based filtering, collaborative filtering and location-based filtering. The proposed algorithm combines several filtering techniques in order to improve the accuracy of recommendation by complementing the various problems of each filtering. The experiment of performance evaluation for comparing with existed restaurant recommendation system was proceeded, and result that proposed IRSH increase recommendation accuracy using Halal contents was deducted.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.276-279
• /
• 2004

The location-based service is one of the most powerful services in the mobile area. The location-based service provides information service for moving user's location information and information service using wire / wireless communication. In this paper, we propose a model for personalized recommendation system which includes location information and personalized recommendation system for location-based service. For this service system, we consider mobile clients that have a limited resource and low bandwidth. Because it is difficult to input the words at mobile device, we must deliberate it when we design the interface of system. We design and implement the personalized recommendation system for location-based services(advertisement, discount news, and event information) that support user's needs and location information. As a result, it can be used to design the other location-based service systems related to user's location information in mobile environment. In this case, we need to establish formal definition of moving objects and their temporal pattern.

• 한국콘텐츠학회논문지
• /
• 제11권12호
• /
• pp.40-51
• /
• 2011

인터넷을 통해 배포되는 방대한 양의 콘텐츠에서 사용자의 취향에 적합한 콘텐츠를 제공하는 것은 추천 시스템의 중요한 요소라고 할 수 있다. 이를 위한 기존의 추천 시스템은 사용자의 프로파일과 상황정보를 활용한 알고리즘에만 중점을 두고 연구가 진행되어 추천의 정확도 향상에 크게 기여하였다. 그러나 SP(Service Provider)의 BM(Business Model)에 대한 충분한 검토가 함께 이루어지지 않았기 때문에 SP가 요구하는 추천 시스템의 구축은 기존 연구를 통해 해결하기엔 한계가 존재한다. 이에 본 논문에서는 사용자의 복합 상항정보를 이용하여 CP(Contents Provider)의 콘텐츠를 검색하고, SP의 BM에 적합한 콘텐츠를 추천하기 위해 추천 가중치 기법을 적용한 모바일 추천 시스템을 제안한다. 또한, 제안된 프로토타입 시스템의 검증을 위해 사용자 프로파일과 상황정보를 결합하는 복합 상황 정보와 SP에 의한 추천 가중치를 적용한 놀이기구 추천 서비스를 구현한다.

• 한국의상디자인학회지
• /
• 제14권4호
• /
• pp.43-61
• /
• 2012

This research aims to examine the impact of store personality and service quality on the customers' intention of revisiting the department store and their intention of recommendation to others. The participants were women in their 20s to 50s with experiences of purchasing apparel from major department stores. A total of 324 survey responses were used for the final analysis. The data were analyzed using factors analysis, reliability analysis, and multiple regression analysis with PASW 18.0. The results were as follows. First, the department store personality was composed of 3 factors; prestige, passion, sincerity. Service quality factors were defined as tangibility, responsiveness, and empathy. Second, the three dimensions of brand personality-prestige, passion and sincerity turned out to be influential factors affecting the customers' revisiting intention and recommendation intention. Also, tangibility and responsiveness of service quality factors had a significant influence on their revisiting intention, whereas tangibility, responsiveness and empathy factors had a significant influence on their recommendation intention. Third, the sub-dimensions of store personality and service quality had a different influence on the customers' revisiting intention and recommendation intention according to the department store brand.

• 농촌계획
• /
• 제24권1호
• /
• pp.89-97
• /
• 2018

Recently, interest in rural tourism for urban dwellers has increased, and rural communities are chosen as tourist destinations. Under these circumstances, the study was designed to analyze the effects of the quality of service at rural stay sites on customer satisfaction and recommendation intention. The analysis method analyzes the demographic characteristics of the survey participants and characteristics of participation in rural stay. And the quality of service for the experience of rural stay was analyzed with SERVQUAL'S five-dimensional type, reliability, assurance, responsiveness, empathy, tangible and customer satisfaction, intent of recommendation and regression. Major analysis shows that the survey subjects were found to have an average age of 41.8 years, 49 to 59 years old, and a high degree of university graduation. And as characteristic of participation, the form of company was family and relatives, the form of family meeting was many summer, the reservation was Internet, and payment by cash and card were many. As a result of the hypothesis testing, reliability, assurance, responsiveness, and empathy among the quality of service of rural stay were affected in customer satisfaction. In addition, the quality of service and the intent to recommend it were statistically significant, reliability, assurance and empathy. Therefore, it is deemed necessary to make efforts to improve service quality as the quality of service at rural stay places has relevance to customer satisfaction and recommendation intention.

• 대한인간공학회지
• /
• 제23권3호
• /
• pp.1-12
• /
• 2004

In recent years, with the advent of e-Commerce the need for personalized services and one-to-one marketing has been emphasized. To be successful in increasingly competitive Internet marketplace, it is essential to capture customer loyalty. In this paper, we provide an intelligent agent approach to incorporate human sensibility into an one-to-one recommendation service in cyber shopping mall. Our system exploits human sensibility ergonomics and on-line preference matching technologies to tailor to the customer the suggestion of goods and the description of store catalog. Customizing the system`s behavior requires the parallel execution of several tasks during the interaction （e. g., identifying the customer`s emotional preference and dynamically generating the pages of the store catalog）. The recommendation agent system composed of five modules including specialized agents carries on these tasks. By presenting goods that are consistent with user interests as well as user sensibility, the accuracy and satisfaction of the recommendation service may be improved.

• 한국ITS학회 논문지
• /
• 제8권1호
• /
• pp.119-126
• /
• 2009

최근 개개인의 취향이나 특성을 고려하여 자동으로 사용자에게 정보를 찾아주거나 추천해주는 추천 서비스 시스템이 많이 개발되고 있다. 하지만 사용자의 상황에 따른 선호도를 고려하지 않을 경우 정확한 추천이 힘든 단점이 있다. 따라서 본 논문에서는 사용자의 상황에 따른 선호도를 고려하여 정확한 추천을 할 수 있는 필터링 방법을 제안하였다. 이를 위해 상황에 따른 사용자 선호도를 구하고 피어슨 상관계수를 이용하여 사용자의 상황별 오브젝트 선호도를 구하였다. 실험 결과, 기존의 서비스 시스템들과 비교하여 precision은 11%, 2%, recall은 8%, 4% 향상되었으며, 전체적으로 precision은 77%, recall은 53%로 나타났다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권2호
• /
• pp.110-115
• /
• 2006

In pure P2P environment, it is possible to provide service by using a little real-time information without using accumulated information. But in case of using only a little information that was locally collected, quality of recommendation service can be fallen-off. Therefore, it is necessary to study a method to improve qualify of recommendation service by using users' context information. But because a great volume of users' context information can be recognized in a moment, there can be a scalability problem and there are limitations in supporting differentiated services according to fields and items. In this paper, we solved the scalability problem by clustering context information per each service field and classifying it per each user, using SOM. In addition, we could recommend proper services for users by quantifying the context information of the users belonging to the similar classification to the service requester among classified data and then using collaborative filtering.

• 한국컴퓨터정보학회논문지
• /
• 제17권8호
• /
• pp.81-90
• /
• 2012

디지털 TV에서 시멘틱 환경의 유헬스 개인화 서비스 추천은 개인의 신체조건, 질병, 건강상태를 평가해서 이루어져야 한다. 기존의 시멘틱 환경의 유헬스 개인화 추천 방법은 온톨로지에 의존하여 의미 분석으로 추천을 하기 때문에 사용자 만족도가 떨어진다. 이에 본 논문에서는 디지털 TV에서 시멘틱 환경의 유헬스 서비스를 위한 나이브 베이지안 필터링 기반 개인화 서비스 추천 방법을 제안한다. 제안하는 방법은 온톨로지를 이용하여 상황데이터를 추론하여 트렌젝션을 저장 하고, 선호도 정보를 이용한 나이브 베이지안 필터링 기법을 사용하여 온톨로지로부터 생성된 트렌젝션과 사용자 선호도 정보를 이용하여 추론하여 서비스를 제공한다. 나이브 베이지안 필터링 기반으로 추론된 서비스는 기존의 필터링 방법 보다 콘텐츠 추천의 높은 정확도와 재현율을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2743-2762
• /
• 2014

Promoted by cloud technology and new websites, plenty and variety of Web services are emerging in the Internet. Meanwhile some Web services become outdated even obsolete due to new versions, and a normal phenomenon is that some services work well only with other services of older versions. These laggard or improper services are lowering the performance of the composite service they involved in. In addition, using current technology to identify proper semantic services for a composite service is time-consuming and inaccurate. Thus, we proposed a clustering method and a recommendation method to deal with these problems. Clustering technology is used to classify semantic services according to their topics, functionality and other aspects from plenty of services. Recommendation technology is used to predict the possible preference of a composite service, and recommend possible component services to the composite service according to the history information of invocations and similar composite services. The experiments show that our clustering method with the help of Ontology and TF/IDF technology is more accurate than others, and our recommendation method has less average error than others in the series of missing rate.