• The KIPS Transactions:PartD
• /
• v.11D no.2
• /
• pp.479-484
• /
• 2004

Recently, cosmetic shop market, which is made up of company, agent, and market shop, has got into trouble caused by economic crisis and the coming of new distribution systems such as internet shopping mall. To overcome the problems, in this paper, we propose a cosmetic distribution portal system, which we call COSPO. COSPO is a portal system that has three functions. The first is automation of the business process for product distribution between the company, agent, and market shops. The second is communication between them. The final is sharing information generated through the automated process. In this paper, we build a prototype that support distribution channel of a company. Then, ultimately it should be extended to cover the distribution network of all companies. COSPO will contribute to the modernization of the cosmetic market industry in the country as well as to the increase of the profits.

• Journal of Internet Computing and Services
• /
• v.16 no.5
• /
• pp.93-98
• /
• 2015

IoT (Internet of Things) is recently burgeoning as business applications as well as ICT itself. Among the business applications of IoT, wearable devices are recognized as a leading area of customer devices. This research first identifies customer needs of activity trackers (fitness trackers), as one of representative wearable devices, and mapping the identified needs with the well-known marketing model of marketing mix (4 P's: Product, Price, Promotion, and Place). Survey was applied to university students for identifying current and potential needs for activity trackers. The needs were classified by 4 P's, and according to the results, different from other IT devices, activity trackers has more potential needs. Moreover, reliable distribution channels, offline and company owned shops were preferred, rather than online shopping mall by third parties. The results would provide some valuable implications to not only designers of activity trackers but also business management.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.1010-1014
• /
• 2010

Article-related product recommender system is an emerging e-commerce service which recommends items based on association in contexts between items and articles. Current services recommend based on the similarity between tags of articles and items, which is deficient not only due to the high cost in manual tagging but also low accuracies in recommendation. As a component of novel article-related item recommender system, we propose a new method for tagging item images based on pre-defined categories. We suggest a hypernetwork-based algorithm for learning association between images, which is represented by visual words, and categories of products. Learned hypernetwork are used to assign multiple tags to unlabeled item images. We show the ability of our method with a product set of real-world online shopping-mall including 1,251 product images with 10 categories. Experimental results not only show that the proposed method has competitive tagging performance compared with other classifiers but also present that the proposed multi-tagging method based on hypernetworks improves the accuracy of tagging.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.4
• /
• pp.687-695
• /
• 2007

There has been increasing of using Internet shopping mall like an e-business, and it means that the analysis technique of appetence for webpase visitors logging into the case of analyzing the degree of concern and using them in the personalization has been absolutely advanced. For heavy web pages, it is impossible to use click-stream based analysis in analyzing interest for each area by what kind of information the visitors are interested in to. A web browser of a limited size has difficulty in expressing on a screen information about what they want, or what hey are looking for. Pagescrolling is used to overcome such a limitation in expression. In this study, a analyzing system of degree of concern for Webpage is presented, designed and implemented using page scrolling to track the position of the scroll bar and movements of the window cursor regularly within a window browser for real-time transfer to analyze user's interest by using information received from the analysis of the visual perception area of the web page.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.2
• /
• pp.197-206
• /
• 2012

A exisiting recommedation system using association rules has the problem, such as delay of processing speed from a cause of frequent scanning a large data, scalability and accuracy as well. In this paper, using a Implicit method which is not used user's profile for rating, we propose the personalized recommendation system which is a new method using the FP-tree mining based on RFM. It is necessary for us to keep the analysis of RFM method and FP-tree mining to be able to reflect attributes of customers and items based on the whole customers' data and purchased data in order to find the items with high purchasability. The proposed makes frequent items and creates association rule by using the FP-tree mining based on RFM without occurrence of candidate set. We can recommend the items with efficiency, are used to generate the recommendable item according to the basic threshold for association rules with support, confidence and lift. To estimate the performance, the proposed system is compared with existing system. As a result, it can be improved and evaluated according to the criteria of logicality through the experiment with dataset, collected in a cosmetic internet shopping mall.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.103-110
• /
• 2008

Due to the development of the e-commerce, the shopping mall such as auction collects and manages the personal information of the customers for efficient service. However, because of the leakage of the Personal information in auction, the image of the companies as well as the information subjects is damaged. Even though the organizations and the companies store the personal information as common sentences and protect using role based access control technique, the personal information can be leaked easily in case of getting the authority of the database administrator. And also the role based access control technique is not appropriate for protecting the sensitive information of the information subject. In this paper, we encrypted the sensitive information assigned by the information subject and then stored them into the database. We propose the personal policy based access control technique which controls the access to the information strictly according to the personal policy of the information subject. Through the proposed method we complemented the problems that the role based access control has and also we constructed the database safe from the database administrator. Finally, we get the control authority about the information of the information subject.

• The Journal of the Korea Contents Association
• /
• v.18 no.11
• /
• pp.475-483
• /
• 2018

Most of logistics system has difficulties in transportation logistics tracking due to problems in real world such as discordance between logistics information and logistics flow. For the solution to these problems, through case study about corporation, suppliers that transport order items in shopping mall, we retain traceability of order items through accordance between logistics and information flow and derive transportation logistics tracking model. Through literature review, we selected permissioned public block chain model as reference model which is suitable for transportation logistics tracking model. We compared, analyzed and evaluated using centralized model and block chain as application model for transportation logistics tracking model. In this paper we proposed transportation logistics tracking model which integrated with logistics system in real world. It can be utilized for tracking and detection model and also as a tool for marketing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.241-243
• /
• 2014

In this study, that by applying the algorithm of collective intelligence in helping to select the teaching methods and learning methods of learner and teacher, develop a content recommendation system, the teacher and the learner promote effective learning, I have intended to And for this reason can be applied to education recommended system to be applied to a movie or shopping mall recently, at the time of selection, it is appropriate in accordance with the state, such as the level of the learner, learning environment, learners the theme of teaching and learning, and to provide a teaching method and learning method, the learner can to find the learning method appropriate for the user, and a more efficient, Professor system that can save time to design the teaching learning process I developed, The utility and accuracy of the learning content recommendation system developed finally, after the data is accumulated in the use of a continuous schedule of the learner and a teacher, would need to be validated through the rating.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.185-190
• /
• 2022

Open data has a lot of economic value. Not only Korea, but many other countries are doing their best to make various policies and efforts to expand and utilize open data. However, although Korea has a large amount of data, the data is not utilized effectively. Thus, attempts to utilize those data should be made in various industries. In particular, in the fashion industry, exchange and refund problems are the most common due to unpredictable consumers. Better feedback is necessary for service providers to solve this problem. We want to solve it by showing improved images of dissatisfactions along with user reviews including consumer needs. In this paper, user reviews are analyzed on online shopping mall websites to identify consumer needs, and product attributes are defined by utilizing the attributes of K-fashion data. The users' request is defined as a dissatisfaction attribute, and labeling data with the corresponding attribute is searched. The users' request is provided to the service provider in forms of text data or attributes, as well as an image to help improve the product.

• The Journal of the Korea Contents Association
• /
• v.22 no.1
• /
• pp.138-147
• /
• 2022

Recently, chatbots have been applied in various fields and have shown good results, and many attempts to use chatbots in shopping mall product recommendation services are being conducted on e-commerce platforms. In this paper, for a conversation system that recommends a fashion that a user wants based on conversation between the user and the system and fashion image information, a transformer model that is currently performing well in various AI fields such as natural language processing, voice recognition, and image recognition. We propose a multimodal-based improved transformer model that is improved to increase the accuracy of recommendation by using dialogue (text) and fashion (image) information together for data preprocessing and data representation. We also propose a method to improve accuracy through data improvement by analyzing the data. The proposed system has a recommendation accuracy score of 0.6563 WKT (Weighted Kendall's tau), which significantly improved the existing system's 0.3372 WKT by 0.3191 WKT or more.