• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.488-493
• /
• 2007

In general, recommendation systems quantify real-time context information obtained in the stage of collaborative filtering and use quantified context information in order to recommend services. But the recommendation systems can have problems of recommending inaccurate information because of lack of context information or classifying users into inaccurate groups because of simple classification works in the stage of quantification. In this paper, we solved the problems of lack of context information obtained in real-time by combining users' profile information used in the contents-based filtering and context information obtained in real-time. In addition, we tried collaborative filtering at the quantification stage by improving absolute classification methods to relative ones. As the result of experiments, this method improved prediction preference by 5.8% than real-time recommendation systems using context information in pure P2P environment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.281-283
• /
• 2021

The representative companies mentioned in the recommendation service in the domestic OTT(Over-the-top media service) market are YouTube and Netflix. YouTube, through various methods, started personalized recommendations in earnest by introducing an algorithm to machine learning that records and uses users' viewing time from 2016. Netflix categorizes users by collecting information such as the user's selected video, viewing time zone, and video viewing device, and groups people with similar viewing patterns into the same group. It records and uses the information collected from the user and the tag information attached to the video. In this paper, we propose a method to improve video media recommendation by automatically generating metadata of video media that was written by hand.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.51-59
• /
• 2010

There have been proposed several movie recommendation algorithms based on Collaborative Filtering(CF). CF decides neighbors whose ratings are the most similar to each other and it predicts how well users will like new movies, based on ratings from neighbors. This paper proposes a new method to improve the result predicted by CF based on genres of the movies seen by users. The proposed method can be combined to the most of all existing CF algorithms. In this paper, a performance evaluation has been conducted between an existing simple CF algorithm and CF-Genre that is the proposed genre-based method added to the CF algorithm. The result shows that CF-Genre improves 3.3% in prediction performance over existing CF algorithms.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.185-198
• /
• 2021

With the development of Internet technology, because traditional recommendation algorithms cannot learn the in-depth characteristics of users or items, this paper proposed a recommendation algorithm based on the AMITI(attention mechanism and improved TF-IDF) to solve this problem. By introducing the two-layer attention mechanism into the CNN, the feature extraction ability of the CNN is improved, and different preference weights are assigned to item features, recommendations that are more in line with user preferences are achieved. When recommending items to target users, the scoring data and item type data are combined with TF-IDF to complete the grouping of the recommendation results. In this paper, the experimental results on the MovieLens-1M data set show that the AMITI algorithm improves the accuracy of recommendation to a certain extent and enhances the orderliness and selectivity of presentation methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.263-266
• /
• 2005

현재 유비쿼터스 환경에서 대부분의 시스템이 개인화된 추천 서비스를 위한 컨텍스트 인식 과정에서 사용자의 직접 피드백을 받는 경우가 많다. 다양한 서비스가 사용자 주변에 존재한다고 하더라도 사용자가 서비스를 받기 위해 직접 피드백을 하는 경우가 많아지면 invisible service를 받을 수 없게 된다. 본 논문에서는 마이닝 기법을 기반으로 사용자의 프로파일 생성과 갱신, 선호도를 예측하여 효율적인 서비스를 제공하는 컨텍스트 마이닝 시스템을 제안한다. 본 시스템에서는 초기프로파일을 생성할 때만 사용자의 직접 피드백을 이용하고, 사용자 프로파일의 갱신과 선호도 예측, 추천 둥 컨텍스트 마이닝 과정에서는 사용자의 행동과 사용자와 유사한 그룹의 선호도, 그리고 사용자의 주변 환경과 같은 컨텍스트 정보를 이용하여 직접 피드백을 최소화한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.475-477
• /
• 2001

본 논문은 사용자의 구매 패턴을 찾아서 사용자가 원하는 상품을 추천하는 알고리즘을 제안하고자 한다. 제안하고 있는 item dependency map은 구매된 상품간의 관계를 수식화 하여 행렬의 형태로 표현한 것이다. Item dependency map의 값은 사용자가 A라는 상품을 구매한 후 B 상품을 살 확률이다. 이런 정보를 가지고 있는 item dependency map은 홉필드 네트웍(Hopfield network)에서 연상을 위한 패턴 값으로 적용된다. 홉필드 네트웍은 각 노드사이의 연결가중치에 기억하고자 하는 것들을 연상시킨 뒤 어떤 입력을 통해서 전체 네트워크가 어떤 평형상태에 도달하는 방식으로 작동되는 신경망 중의 하나이다. 홉필드 네트웍의 특징 중의 하나는 부분 정보로부터 전체 정보를 추출할 수 있는 것이다. 이러한 특징을 가지고 사용자들의 일반적인 구매패턴을 일부 정보만 가지고 예측할 수 있다. Item dependency map은 홉필드 네트웍에서 사용자들의 그룹별 패턴을 학습하는데 사용된다. 따라서 item dependency map이 얼마나 사용자 구매패턴에 대한 정보를 가지고 있는지에 따라 그 결과가 결정되는 것이다. 본 논문은 정확한 item dependency map을 계산해 내는 알고리즘을 주로 논의하겠다.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.270-283
• /
• 2012

With the advent of multi-channel TV, IPTV and smart TV services, excessive amounts of TV program contents become available at users' sides, which makes it very difficult for TV viewers to easily find and consume their preferred TV programs. Therefore, the service of automatic TV recommendation is an important issue for TV users for future intelligent TV services, which allows to improve access to their preferred TV contents. In this paper, we present a recommendation model based on statistical machine learning using a collaborative filtering concept by taking in account both public and personal preferences on TV program contents. For this, users' preference on TV programs is modeled as a latent topic variable using LDA (Latent Dirichlet Allocation) which is recently applied in various application domains. To apply LDA for TV recommendation appropriately, TV viewers's interested topics is regarded as latent topics in LDA, and asymmetric Dirichlet distribution is applied on the LDA which can reveal the diversity of the TV viewers' interests on topics based on the analysis of the real TV usage history data. The experimental results show that the proposed LDA based TV recommendation method yields average 66.5% with top 5 ranked TV programs in weekly recommendation, average 77.9% precision in bimonthly recommendation with top 5 ranked TV programs for the TV usage history data of similar taste user groups.

• 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.

• Knowledge Management Research
• /
• v.23 no.2
• /
• pp.277-299
• /
• 2022

The massive card transaction data generated in the tourism industry has become an important resource that implies tourist consumption behaviors and patterns. Based on the transaction data, developing a smart service system becomes one of major goals in both tourism businesses and knowledge management system developer communities. However, the lack of rating scores, which is the basis of traditional recommendation techniques, makes it hard for system designers to evaluate a learning process. In addition, other auxiliary factors such as temporal, spatial, and demographic information are needed to increase the performance of a recommendation system; but, gathering those are not easy in the card transaction context. In this paper, we introduce CTDDTR, a novel approach using card transaction data to recommend tourism services. It consists of two main components: i) Temporal preference Embedding (TE) represents tourist groups and services into vectors through Doc2Vec. And ii) Deep tourism Recommendation (DR) integrates the vectors and the auxiliary factors from a tourism RDF (resource description framework) through MLP (multi-layer perceptron) to provide services to tourist groups. In addition, we adopt RFM analysis from the field of knowledge management to generate explicit feedback (i.e., rating scores) used in the DR part. To evaluate CTDDTR, the card transactions data that happened over eight years on Jeju island is used. Experimental results demonstrate that the proposed method is more positive in effectiveness and efficacies.

• Journal of the HCI Society of Korea
• /
• v.5 no.2
• /
• pp.25-31
• /
• 2010

This paper proposes a hybrid tour path planning system for multiple visitors in a museum. The proposed path planning system merges individual user profiles into a group profile by exploiting the multiplicative utilization algorithm. It then generates a tour path for the users based on mixed initiative decision of the system and the involved visitors. It automatically selects visiting sites when group users have highly similar preferences while it asks users to select their appropriate visiting sites among available sites when their preferences are different. We developed the hybrid path planning system based on a tabletop display and evaluated it with four different exhibition settings and 11 participants. We found that the mixed decision of the system and users was useful in building a tour path for a group of visitors.