• Title/Summary/Keyword: 사용자 특성 선호도

Search Result 237, Processing Time 0.025 seconds

A Study on the Application of SPA brand to BI Color and User Preference (SPA 브랜드의 BI 색채 적용 현황과 사용자 선호도 조사)

  • Park, Han Na;Paik, Jin Kyung
    • Design Convergence Study
    • /
    • v.17 no.2
    • /
    • pp.45-57
    • /
    • 2018
  • Sales for SPA brand names of private label apparels are on the rise in the domestic clothing market. The aim of this study is to analyze the characteristics of SPA brands and how each color system is proposed within the BI system. In this study, 8 brands were selected as the most popular SPA brands in Korea and abroad with stores based on brand power and sales and preference by consumers. Therefore, among information factors such as brand identity (BI) and color characteristic. sign system, package, and environmental factors, buildings facade and interior design of eight brands were investigated. Research into color application of BI revealed that four brands used red colors with different tones with different identity differentiation. For the other four brands, the company applied BI designs that gained the brand's character such as a black-and-white or dark blue one. Thus, it is considered important to select BI color in order to differentiate and enhance preferences in brand identity.

A study on the application of on-line card game Avatar (온라인 카드게임 아바타 활용에 관한 연구)

  • Lee, Mi-Young
    • Archives of design research
    • /
    • v.18 no.2 s.60
    • /
    • pp.133-142
    • /
    • 2005
  • Recently, on-line users prefer image and sense that are deviated from standardization pattern. Also, they need instant and mutual exchangeable communication forms. Developing the various Avatars is required to apply it to various situations. It is due to that the Avatar is used as a card in the on-line communication to represent the user's character visually. The Avatar in the on-line game, such as poker or go-stop which are the most popular nowadays, does not have different character from general community site. Therefore, it dose not satisfy owner who needs sensitive and various character of the Avatar. In this paper, we will be analysis the card game Avatar service, character and desire of the user in existing game petal sites. Also, we'll provide service method which can satisfy the user's requirements. For this, we survey recognition and design preference of users on the card game Avatar.

  • PDF

A Study of Marketing Strategies according to the Criteria of Users' Choice in Pallet Pool Services : Focused on Mettroporitan Seoul Area Warehouse Companies (파렛트 풀 서비스의 효익세분화에 따른 마케팅 전략에 관한 연구 - 수도권 창고업체들을 중심으로 -)

  • Choi, Se-Kyung;Park, Mu-Il;Lee, Kang-Dae
    • Journal of Korea Port Economic Association
    • /
    • v.25 no.3
    • /
    • pp.1-20
    • /
    • 2009
  • A survey to pallet users was conducted in an aspect of the efficiency and benefit. The questionnaire identified the preference about the main variables such as price, size, conformity, material, which are the criteria of the users' choice. staffs in the capital region was selected as respondents and Cluster Analysis and Simulations was carried out with Conjoint Analysis. The result shows that the variables of material and conformity between facilities and products were more important than the variable of size. The respondents prefer the pallets with a various range of products because warehouses should keep a range of products under various condition of temperature. In accordance, the companies that provide a pallet pool service should set up individual marketing strategy by a type of customers so as to maximize the competitiveness in domestic or international markets. Furthermore, supplying standardized pallets should be consistent with the standardization not for individual logistics units, but for whole logistic systems. To achieve this, it requires the compatibility amongst a range of logistics activity participants by their characteristics.

  • PDF

Default Voting using User Coefficient of Variance in Collaborative Filtering System (협력적 여과 시스템에서 사용자 변동 계수를 이용한 기본 평가간 예측)

  • Ko, Su-Jeong
    • Journal of KIISE:Software and Applications
    • /
    • v.32 no.11
    • /
    • pp.1111-1120
    • /
    • 2005
  • In collaborative filtering systems most users do not rate preferences; so User-Item matrix shows great sparsity because it has missing values for items not rated by users. Generally, the systems predict the preferences of an active user based on the preferences of a group of users. However, default voting methods predict all missing values for all users in User-Item matrix. One of the most common methods predicting default voting values tried two different approaches using the average rating for a user or using the average rating for an item. However, there is a problem that they did not consider the characteristics of items, users, and the distribution of data set. We replace the missing values in the User-Item matrix by the default noting method using user coefficient of variance. We select the threshold of user coefficient of variance by using equations automatically and determine when to shift between the user averages and item averages according to the threshold. However, there are not always regular relations between the averages and the thresholds of user coefficient of variances in datasets. It is caused that the distribution information of user coefficient of variances in datasets affects the threshold of user coefficient of variance as well as their average. We decide the threshold of user coefficient of valiance by combining them. We evaluate our method on MovieLens dataset of user ratings for movies and show that it outperforms previously default voting methods.

An Analysis of Recommendation Rate for Collaborative Filtering Algorithm based-on Demographic Information (인구통계학적 특성에 따른 협동적필터링 알고리즘의 추천 효율 분석)

  • 황성희;김영지;이미희;우용태
    • Proceedings of the Korea Database Society Conference
    • /
    • 2001.06a
    • /
    • pp.362-368
    • /
    • 2001
  • 본 논문에서는 고객의 특성을 고려한 최적의 추천시스템을 개발하기 위하여 기존의 인구통계학적 특성에 따른 협동적필터링 기법의 추천 효율을 비교 분석하였다. 비디오에 대한 사용자 평가 값과 예측 값간의 추천 효율에 대한 비교실험을 통하여 상품에 대한 단순한 선호도만을 고려한 기존의 협동적필터링 방법에 의한 추천시스템의 문제점을 개선하여 추천된 상품이나 콘텐츠에 대한 개인별 추천 효율을 향상시키기 위한 모델을 제시하였다. 본 연구 결과를 이용하여 인터넷 비즈니스 분야에서 활발하게 도입되고 있는 eCRM 시스템에서 가장 중요한 요소인 고객들의 인구통계학적인 다양한 특성을 고려한 협동적필터링 기반의 추천시스템을 개발할 수 있으리라 기대한다.

  • PDF

Improved Concept-base Search System Using HITS algorithm on Conceptual Graph (HITS알고리즘을 적용한 개념그래프 기반검색시스템의 성능개선)

  • 배환국;박호성;이상준;김기태
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2003.04c
    • /
    • pp.470-472
    • /
    • 2003
  • 본 논문에서는 개념 그래프 기반 검색 시스템의 검색의 성능을 개선시키고자 Hits 알고리즘을 적용하였다. 기존 개념 그래프 기반 검색 시스템의 anchor text분석을 통하여 개념을 추출하고 있는 시스템에서 더 나아가 하이퍼 링크의 선호도의 특성을 살려 하이퍼링크에 문서가 얼마나 연결되어 있는지, 참조하고 있는지에 따라 해당 검색된 문서들의 중요도를 찾아서 순위를 매기는 실험을 하였다. 종래에는 해당 검색어의 빈도순으로 개념의 결과를 나타내 주었는데, 본 시스템 구현 후에 랭킹알고리즘을 적용하여 해당검색에 유용한 정보를 가지고 있는 페이지들(authorities)과 유용한 정보를 보유하고 있는 페이지의 링크를 보유하고 있는 페이지들(hubs)를 각각 순위 순으로 보여주게 되었다. 그리하여 사용자는 실제 검색시에 개념상으로 분류된 문서 중에 중요도가 높은 문서를 사용자에게 우선으로 접하게 되었으며, hub어 의해서 중요도가 높은 문서를 한눈에 볼 수도 있을 뿐 아니라, anchor text 어서 나타나지 않은 중요한 정보를 가진 문서도 검색할 수 있었다.

  • PDF

Selecting Marketing Domains and Customer Groups by Pre-evaluation on Recommendation (추천 선행평가에 의한 마케팅 도메인 및 고객군 선정)

  • 윤찬식;이수원
    • Proceedings of the Korea Inteligent Information System Society Conference
    • /
    • 2002.11a
    • /
    • pp.220-229
    • /
    • 2002
  • 협력적 추천 기법은 유사한 이웃의 선호도를 이용하여 고객에게 개인화된 아이템을 추천해 주는 방법으로 비교적 높은 정확도를 보이며 추천 시스템의 중심으로 연구되어져 왔다. 그러나, 지금까지의 추천 시스템은 도메인의 특성을 제대로 고려하지 못한채 추천을 시행함으로써 특정 도메인에서 추천의 정확도가 떨어지는 문제점이 발생하였다. 이러한 문제점들을 보완하기 위하여 본 논문에서는 평균 고객 유사도, 평균 아이템 유사도, 밀집도 등의 추천 선행 평가 척도를 제안하고, 추천 선행평가 척도와 추천의 정확도와의 상관관계를 보이며, 이를 이용하여 짧은 수행시간 안에 추천 적용이 가능한 마케팅 도메인 및 고객군을 선정하는 방법을 제시한다.

  • PDF

Captive Portal Recommendation System Based on Word Embedding Model (단어 임베딩 모델 기반 캡티브 포털 메뉴 추천 시스템)

  • Dong-Hun Yeo;Byung-Il Hwang;Dong-Ju Kim
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2023.07a
    • /
    • pp.11-12
    • /
    • 2023
  • 본 논문에서는 상점 내 캡티브 포털을 활용하여 수집된 주문 정보 데이터를 바탕으로 사용자가 선호하는 메뉴를 추천하는 시스템을 제안한다. 이 시스템은 식품 관련 공공 데이터셋으로 학습된 단어 임베딩 모델(Word Embedding Model)로 메뉴명을 벡터화하여 그와 유사한 벡터를 가지는 메뉴를 추천한다. 이 기법은 캡티브 포털에서 수집되는 데이터 특성상 사용자의 개인정보가 비식별화 되고 선택 항목에 대한 정보도 제한되므로 기존의 단어 임베딩 모델을 추천 시스템에 적용하는 경우에 비해 유리하다. 본 논문에서는 실제 동일한 시스템을 사용하는 상점들의 구매 기록 데이터를 활용한 검증 데이터를 확보하여 제안된 추천 시스템이 Precision@k(k=3) 구매 예측에 유의미함을 보인다.

  • PDF

Exploring the Applicability of Voice-based Psychological Counseling Agent (음성 기반 심리상담 에이전트의 활용 가능성 탐색 연구)

  • Kim, Ji Geun;Yang, Hyunjung;Lee, Ji-Won
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.7
    • /
    • pp.144-156
    • /
    • 2021
  • This study was conducted to explore important factors to consider when designing voice-based psychological counseling agents amid the increasing use of conversational agents in counseling and psychotherapy. 48 participants selected their preferred agent's voice among four types (young women and men, middle-aged women and men) and had a conversation with a psychological counseling agent. They also evaluated the reasons for voice selection, mood changes, perception of the agent's characteristics, and counseling outcomes. As a results, the agent's voice type selected according to the user's gender was not statistically significant. However, the qualitative analysis showed 'comfort' of the voice was an important factor. Next, the user's mood improved significantly after the conversation with the agent, which confirmed the intervention effect. Finally, it was found that expertness and attractiveness perceptions toward the agent contributed to the counseling outcomes. The implications of the study and suggestions for future research were discussed.

Understanding Personal and Cultural Factors on the Level of UCC Participation: Centered on Korea and U.S.A (UCC 사용자 참여수준과 개인적 및 문화적 특성 요인과의 관계 - 한국과 미국을 중심으로 -)

  • Lee, Hyun-Ju;Kim, Yoo-Jung;Kang, So-Ra
    • The Journal of the Korea Contents Association
    • /
    • v.9 no.2
    • /
    • pp.216-232
    • /
    • 2009
  • The purpose of this paper is to examine the ethical implications in UCC participation. This paper aimed at examining the advent of UCC as a critical media tool in interactive two-way communication and the effect of ethical questions on the level of UCC participation. The findings show that uncertainty avoidance gives an positive and significant effect on privacy concern and regulatory preference, but it is not related to copyright invasion in Korea and U.S.A. It is shown that privacy concern does not influence on UCC retrieval in Korea whereas it is positively related to UCC retrieval in the United States. Also, privacy concern has not relationship with UCC production(modification, recreation, generation) in both nations. In the case of regulatory preference, it posits an significant and positive effect on UCC retrieval in Korea while it is not related to UCC retrieval in the United States. Also, regulatory preference does not affect on UCC production in Korea whereas it influences on UCC generation without impacting UCC modification and recreation in U.S.A. Finally, the results show that copyright invasion has stronger relationship with UCC recreation and generation than UCC modification, and it is positively related to UCC retrieval in both nations.