• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.532-535
• /
• 2008

The requirement of Digital Culture Content(Movie, Music, Animation, Digital TV, Exhibition and etc.) is increasing so variety and quantity of content is also increasing. The Movie what majority of the digital Content is developing of technology and data. In the result, the efficient retrieval service has required and user want to use a recommendation engine and semantic retrieval methods through the recommendation system. Therefore, this paper will suggest analysing trait element of digital content data, building of retrieval technology, analysing and retrieval technology base on KANSEI vocabulary and etc. For the these, we made a extraction technology of trait element based on semantics and KANSEI processing algorithm based on color information.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1380-1385
• /
• 2015

Collaborative filtering is one of the most successfully used methods for recommender systems and has been utilized in various areas such as books and music. The key point of this method is selecting the most proper recommenders, for which various similarity measures have been studied. To improve recommendation performance, this study analyzes problems of existing recommender selection methods based on similarity and presents a method of dynamically determining recommenders based on the rate of co-rated items as well as similarity. Examination of performance with varying thresholds through experiments revealed that the proposed method yielded greatly improved results in both prediction and recommendation qualities, and that in particular, this method showed performance improvements with only a few recommenders satisfying the given thresholds.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.90-97
• /
• 2020

With the development of the Internet and smartphones, digital sound sources are easily accessible, and accordingly, interest in music search and recommendation is increasing. As a method of recommending music, research using melodies such as pitch, tempo, and beat to classify genres or emotions is being conducted. However, since lyrics are becoming one of the means of expressing human emotions in music, the role of the lyrics is increasing, so a study of emotion classification based on lyrics is needed. Therefore, in this thesis, we analyze the emotions of the farewell lyrics in order to subdivide the farewell emotions based on the lyrics. After constructing an emotion dictionary by vectoriziong the similarity between words appearing in the parting lyrics through Word2Vec learning, we propose a method of classifying parting lyrics emotions using Word2Vec and LSTM, which classify lyrics by similar emotions by learning lyrics using LSTM.

• Knowledge Management Research
• /
• v.21 no.1
• /
• pp.175-195
• /
• 2020

The development of platform service based on the information and communication technology has revolutionized patterns of commercial transactions, driving the growth of global economy. Furthermore, the radical advancement of artificial intelligence(AI) presents the huge potential to innovate almost all the industrial and economic activities. Given these technological developments, the goal of this paper is to investigate AI's impact on the platform service innovation as well as its influence on the business performance. For the goal, this paper presents the review of the types of service innovation, the nature of platform services, and technological characteristics of leading AI technologies, such as chatbot and recommendation system. As an empirical study, this paper performs a multiple case study of Kakao Group which is the leading mobile platform service with the most advanced AI in Korea. To understand the role and effect of AI on Kakao platform service, this study investigated three cases, including chatbot agent of Kakao Bank, Smart Call service of Kakao Taxi, and music recommendation system of Kakao Mellon. The analysis results of the case study show that AI initiated innovations in platform service concepts, service delivery, and customer interface, all of which lead to a significant decrease in the transaction costs and the personalization of services. Finally, for the successful development of AI, this research emphasizes the significance of the accumulation of customer and operational data, the AI human capital, and the design of R&D organization.

• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.183-200
• /
• 2009

Collaborative Filtering is one of the most used recommender systems. However, basically it cannot be used to recommend new products to customers because it finds products only based on the purchasing history of each customer. In order to cope with this shortcoming, many researchers have proposed the hybrid recommender system, which is a combination of collaborative filtering and content-based filtering. Content-based filtering recommends the products whose attributes are similar to those of the products that the target customers prefer. However, the hybrid method is used only for the limited categories of products such as music and movie, which are the products whose attributes are easily extracted. Therefore it is essential to find a more effective approach to recommend to customers new products in any category. In this study, we propose a new recommendation method which applies centrality concept widely used to analyze the relational and structural characteristics in social network analysis. The new products are recommended to the customers who are highly likely to buy the products, based on the analysis of the relationships among products by using centrality. The recommendation process consists of following four steps; purchase similarity analysis, product network construction, centrality analysis, and new product recommendation. In order to evaluate the performance of this proposed method, sales data from H department store, one of the well.known department stores in Korea, is used.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.13-34
• /
• 2012

The Paper Explores The Problem Of Recommending Talks To Attend At International Research Conferences. When Researchers Participate In Conferences, Finding Interesting Talks To Attend Is A Real Challenge. Given That Several Presentation Sessions And Social Activities Are Typically Held At A Time, And There Is Little Time To Analyze All Alternatives, It Is Easy To Miss Important Talks. In Addition, Compared With Recommendations Of Products Such As Movies, Books, Music, Etc. The Recipients Of Talk Recommendations (i.e. Conference Attendees) Already Formed Their Own Research Community On The Center Of The Conference Topics. Hence, Recommending Conference Talks Contains Highly Social Context. This Study Suggests That This Domain Would Be Suitable For Social Network-Based Recommendations. In Order To Find Out The Most Effective Recommendation Approach, Three Sources Of Information Were Explored For Talk Recommendation-Whateach Talk Is About (Content), Who Scheduled The Talks (Collaborative), And How The Users Are Connected Socially (Social). Using These Three Sources Of Information, This Paper Examined Several Direct And Hybrid Recommendation Algorithms To Help Users Find Interesting Talks More Easily. Using A Dataset Of A Conference Scheduling System, Conference Navigator, Multiple Approaches Ranging From Classic Content-Based And Collaborative Filtering Recommendations To Social Network-Based Recommendations Were Compared. As The Result, For Cold-Start Users Who Have Insufficient Number Of Items To Express Their Preferences, The Recommendations Based On Their Social Networks Generated The Best Suggestions.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.229-231
• /
• 2004

내용 기반 음악 검색 시스템은 사용자가 원하는 음악에 대해 사전 정보를 모르더라도 곡의 일부로 질의를 함으로써 원하는 결과를 얻을 수 있게 한다. 그러나 내용 기반 음악 검색 시스템은 사용자의 질의에 대해 결과에 대한 순위만을 제공할 뿐 사용자의 취향이나 선호도와 같은 개인 정보를 고려하지 않기 때문에 사용자가 충분히 만족할만한 정보를 제공받지 못해 사용자의 만족도가 떨어진다. 이를 해결하기 위해 본 논문에서는 대표 선율을 이용하여 유사한 곡들로 클러스터링을 수행하고 내용 기반 검색 시 질의가 속하는 클러스터를 찾고 해당 클러스터 안에서 거리함수를 통해 질의와 유사한 곡들을 선별한다. 선별된 곡들과 사용자의 프로파일을 통해 음악 취향을 고려할 수 있는 내용 기반음악 필터링 기법을 적용하여 사용자의 만족을 증가시키는 결과를 제공한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.541-543
• /
• 2004

인터넷의 대중화로 인하여 인터넷상에 많은 음악 정보가 존재하게 되었다. 이에 따라서 사용자에게 음악 정보를 손쉽게 접근할 수 있게 해주는 서비스뿐만 아니라, 사용자에게 적절한 음악을 추천해주는 서비스의 중요성도 증가하고 있다. 본 논문에서는 사용자의 상황을 인식하고 사용자와의 대화를 통해서 적절한 음악을 추천해주는 인공 DJ를 제안한다 인공 DJ는 센서로부터 실내 온도, 습도, 조도, 소음을 입력받고, 인터넷을 통하여 날씨 정보를 입력받고, 사용자의 감정추론을 위하여 사용자가 입력하는 문장을 분석하여 Activation-Evaluation Space상에서 사용자의 감정을 표시함으로써 사용자의 주변 상황을 인식하고, 사용자의 성향을 파악하여 IF-THEN 규칙을 만들어 대수학적 연산자(algebraic operator)를 통한 퍼지 추론 방법을 이용하여 적절한 음악을 추천한다. 피험자 10명을 대상으로 실시한 설문조사 결과 제안하는 방법이 유용함을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.1112-1114
• /
• 2017

본 논문은 감정변화와 관련이 높다고 알려져 있는 생체정보인 뇌파(EEG), 심전도(ECG), 심박변이도(HRV)를 바탕으로 사용자의 감정상태를 추론하여 치유음악을 추천해주는 시스템을 제안한다. 사용자의 생체정보를 기반으로 사용자의 감정상태를 평온, 집중, 긴장, 우울의 4가지 단계로 분류하는 감성추론 시스템을 설계하고, 각각의 감정상태에 따라 적절한 카테고리의 음악을 추천함으로써 사용자의 스트레스 정도를 완화시키고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.82-84
• /
• 2011

본 논문에서는 사용자의 개인적 취향에 맞는 음악을 추천할 수 있는 사용자 감성/상황 정보 융합 기반의 협업 필터링의 확장을 이용한 음악추천시스템을 소개한다. 본 논문에서 제안하는 시스템은 확장된 협업 필터링 방식을 사용하여 추천을 해준다. 이를 위해 본 논문에서는 추천의 근거가 되는 감성과 무드를 Thayer 음악 무드 모델을 이용하여 총 12 가지의 감성 정보, 8 cluster 의 무드 정보로 분류했다. 또한 사용자의 상황 정보, 활동 & 날씨 & 시간에 대해서도 분류하였다. 분류된 정보는 음악감상 UI 를 이용하여 사용자 별 감성, 상황 그리고 음원의 무드 정보로 수집이 되었고, 수집된 정보를 기반으로 사용자 감성과 청취 곡 횟수를 퓨전하여 평가치 매트릭스를 만들었으며, 이를 바탕으로 단계적 협업 필터링에 의해 사용자 취향에 맞는 음악을 추천해 주는 방법이다.