• 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.

• Knowledge Management Research
• /
• v.11 no.2
• /
• pp.75-93
• /
• 2010

Even though there have been many efforts on driver's route recommendation, driver still should get involved to choose the driving path in a manual manner. Uncertain traffic information provided to the driver delays his arrival time and hence may cause diminished economic values. One of the solutions of reducing the uncertainty is to provide various kinds of traffic information, rather than send real-time information. Therefore, as the wireless communication technology improves and at the same time volume of utilizable traffic contents increases in geometrical progression, selecting traffic information based on driver's context in a timely and individual manner will be needed. Hence, the purpose of this paper is to propose a methodology that efficiently sends the rich traffic contents to the personal in-vehicle navigation. To do so, driver preference is modeled and then the recommendation algorithm of traffic information contents was developed using the preference model. Secondly, ontology based traffic situation analyzation method is suggested to automatically inference the noticeable information from the traffic context on driver's route. To show the feasibility of the idea proposed in this paper, an open API service is implemented in consideration of ease of use.

• ETRI Journal
• /
• v.29 no.3
• /
• pp.311-321
• /
• 2007

In this paper, we propose a user-centric conflict management method for media services which exploits personal companions for the harmonious detection and resolution of service conflicts. To detect conflicts based on the varying characteristics of individual users, the proposed method exploits the unified context describing all users attempting to access media services. It recommends and mediates users' preferred media contents through a shared screen and personal companions to resolve the detected conflicts. During the recommendation, a list of preferred media contents is displayed on the shared screen, and a personally preferred content list is shown on the user's personal companion comprising the selection of media contents. Mediation assists the selection of a consensual service by gathering the users' selections and highlighting the common media contents. In experiments carried out in a ubiHome, we observed that recommendations and mediation are useful in harmoniously resolving conflicts by encouraging user participation in conflict situations.

• Journal of the Korea Convergence Society
• /
• v.11 no.6
• /
• pp.163-171
• /
• 2020

This study analyzed the contents and changes by year of metadata research that appeared in the study of domestic movie curation from the viewpoint of art management. The research method used thesis search site to search 'movie' and 'metadata' as keywords, and analyzed them in 4 stages of change according to the research trend by year, purpose of research content, analysis by use, and type of recommendation method. As for research results, movie metadata research is highly interested in user-side research, and is developing from an introduction stage to an evolutionary stage of recommendation to a sharing and participation stage. It was concluded that movie curation evolved into 6 stages: search support, content-based, collaborative filtering, hybrid, artificial intelligence, and curation.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.282-289
• /
• 2008

Although there were some technological developments in improving the collaborative filtering, they have yet to fully reflect the actual relation of the items. In this paper, we propose the recommendation system using associative web document classification by word frequency and ${\alpha}$-cut to address the short comings of the collaborative filtering. The proposed method extracts words from web documents through the morpheme analysis and accumulates the weight of term frequency. It makes associative rules and applies the weight of term frequency to its confidence by using Apriori algorithm. And it calculates the similarity among the words using the hypergraph partition. Lastly, it classifies related web document by using ${\alpha}$-cut and calculates similarity by using adjusted cosine similarity. The results show that the proposed method significantly outperforms the existing methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.3
• /
• pp.155-164
• /
• 2009

Digital Content Marketplace based on Interactive Media is defmed as the marketplace for content service between contents supplier and consumer through iDTV environment. This Marketplace is increasing interest to u-Life service with Digital Environment. To Interactive Media, it can contribute to enhance its effectiveness by developing various contents and service model in the initial phase of broadcasting-communication convergence. This study designed metadata using Digital Content marketplace based on Interactive Media. Specially the matadata designing include recommendation-tag for supply supplementary content. It can support self-directed action. Through basic metadata with weight value, it is designed to support supplementary content customer to want on the marketplace. Recommendation-System can be built by many method and to recommend the service content including explicit properties using collaborative filtering method can solve limitations in existing content recommendation.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.238-252
• /
• 2009

Due to the rapid increase of available contents via the convergence of broadcasting and internet, the efficient access to personally preferred contents has become an important issue. In this paper, for recommendation scheme for TV programs using a collaborative filtering technique is studied. For recommendation of user preferred TV programs, our proposed recommendation scheme consists of offline and online computation. About offline computation, we propose reasoning implicitly each user's preference in TV programs in terms of program contents, genres and channels, and propose clustering users based on each user's preferences in terms of genres and channels by dynamic fuzzy clustering method. After an active user logs in, to recommend TV programs to the user with high accuracy, the online computation includes pulling similar users to an active user by similarity measure based on the standard preference list of active user and filtering-out of the watched TV programs of the similar users, which do not exist in EPG and ranking of the remaining TV programs by proposed rank model. Especially, in this paper, the BM (Best Match) algorithm is extended to make the recommended TV programs be ranked by taking into account user's preferences. The experimental results show that the proposed scheme with the extended BM model yields 62.1% of prediction accuracy in top five recommendations for the TV watching history of 2,441 people.

• The Journal of the Korea Contents Association
• /
• v.10 no.1
• /
• pp.477-485
• /
• 2010

Web based learning systems are operating with various and lots of learning contents. But it is hard to construct learning contents to fit learners when they select learning contents for learning. In this paper, we proposed the recommendation method that can support the learning contents as calculate learner's preference using the learning history information of learner's profile when learner design and compose learning course. In the applying result of this method, we've selected testing learner group and was able to know it can help to learner processing learning by themselves as we've got great learning satisfaction after test.

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.402-410
• /
• 2009

A lot of learning systems are applying self-directed learning to increase learner's learning effect. But most of this methods are hardly applied to fit the construction of learning contents considering learner's characteristics or it was processing the learning course without learner's choice. In this research, we proposed the recommendation method that can support the learning contents as calculate learner's preference contents based on learning history information when learner design the learning course. In the result, we chose test learner group and was able to know to generally increase average score of each learner after test between existing method and proposal one.

• The KIPS Transactions:PartC
• /
• v.10C no.5
• /
• pp.647-656
• /
• 2003

In Webspace, mining traversal patterns is to understand user's path traversal patterns. On this mining, it has a unique characteristic which objects (for example, URLs) may be visited due to their positions rather than contents, because users move to other objects according to providing information services. As a consequence, it becomes very complex to extract meaningful information from these data. Recently discovering traversal patterns has been an important problem in data mining because there has been an increasing amount of research activity on various aspects of improving the quality of information services. This paper presents a Dynamic Link Recommendation (DLR) algorithm that recommends link sets on a Web site through mining frequent traversal patterns. It can be employed to any Web site with massive amounts of data. Our experimentation with two real Weblog data clearly validate that our method outperforms traditional method.