RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기

    생성형 인공지능을 활용한 도자기 문화유산의 디지털화 경로 연구 -명대 청화자기 시각 어휘 사례를 중심으로- = A Digitalization Pathway for Ceramic Cultural Heritage Enabled by Generative Artificial Intelligence: Evidence from the Visual Vocabulary of Ming-Dynasty Blue-and-White Porcelain

    한글로보기

    https://www.riss.kr/link?id=T17393164

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
      • URL 복사
    • 오류접수
    인용문이 복사되었습니다.

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    Driven by digital governance and open interoperability, the digitization of image-based cultural heritage is being shifted from “collection–display” toward a closed-loop workflow of “semantic specification–controlled generation–online presentation and evaluation.” Ming Dynasty blue-and-white porcelain—whose stylistic features are highly standardized and readily formalized—was selected as the study object, and the deployment of generative AI was examined for controllability, interpretability, and auditability across the “preservation–creation –transmission” chain, thereby addressing inconsistent semantic definitions and the lack of an end-to-end evidence chain linking data provenance, generation processes, and user evaluations.
    A technical pipeline of “Common Expression Element System (CEES)–controlled generation–online presentation and evaluation” was constructed and implemented. Controlled vocabularies, value ranges, and compliance constraints on allowable combinations were defined for vessel form, compositional templates, motifs and borders, linework, and color/shading, thereby yielding a reusable minimal-viable combination set and an annotation schema. Semi-structured prompt templates, a style lock, and a negative list were embedded in a cross-platform Web/App prototype, while prompts and parameters were rule-validated and, when necessary, rolled back via a Style Control Card (SCC), so that controllable outputs could be produced when text-to-image generation was invoked using GPT–DALL·E. Prompts, negative terms, selected forms/patterns/parameters, reference and provenance information, and sketch inputs were captured in a structured, field-level generation log, thereby supporting reproducibility, traceability, and auditing.
    For evaluation, evidence was collected at two levels (static viewing and mechanism analysis), and validation was conducted using Stylistic Fidelity (SF), perceived authenticity (PA), User Engagement Scale (UES), the Unified Theory of Acceptance and Use of Technology (UTAUT) scale, Cognitive Load Theory (CLT), and Torrance Tests of Creative Thinking (TTCT); additionally, the adoption mechanism was tested via an integrated PLS-SEM→ANN→NCA framework. The results indicate that, under controlled generation, SF and PA were maintained at an overall high level. Superior performance was observed for experts on style-sensitive dimensions and on Constructive Authenticity (CA) within PA, whereas non-experts exhibited greater novelty, originality, and Willingness To Use (WTU) and scored higher on Object Authenticity (OA) and Existential Authenticity – Self (EA-S) within PA. Overall differences in Extraneous Cognitive Load (ECL) were small. Mechanism analyses supported a path in which Authenticity of Cultural Elements (ACE) and Perceived Personalization (PP) affected WTU via Cultural Identity (CI), Perceived Usefulness (PU), and Perceived Ease of Use (PEOU); ANN and NCA further corroborated nonlinear importance patterns of key antecedents and identified necessary conditions and threshold constraints.
    The proposed closed loop—“semantic specification–controlled generation– log-based provenance–online evaluation”—offers a transferable, reusable, and auditable generative-AI paradigm for image-based cultural heritage by operationalizing preservation norms as generation constraints, strengthening governance and reproducibility through logging and provenance mechanisms, and providing comparable empirical evidence for the modern transmission of Ming Dynasty blue-and-white porcelain visual vocabulary.
    Keywords:Ming Dynasty blue-and-white porcelain; Common Expression Element System (CEES); controlled generation; Stylistic Fidelity (SF); perceived authenticity (PA); User Engagement Scale (UES); Unified Theory of Acceptance and Use of Technology (UTAUT) scale; Cognitive Load Theory (CLT); Torrance Tests of Creative Thinking (TTCT); Partial Least Squares Structural Equation Modeling (PLS-SEM); Artificial Neural Network (ANN); Necessary Condition Analysis (NCA).
    번역하기

    Driven by digital governance and open interoperability, the digitization of image-based cultural heritage is being shifted from “collection–display” toward a closed-loop workflow of “semantic specification–controlled generation–online pres...

    Driven by digital governance and open interoperability, the digitization of image-based cultural heritage is being shifted from “collection–display” toward a closed-loop workflow of “semantic specification–controlled generation–online presentation and evaluation.” Ming Dynasty blue-and-white porcelain—whose stylistic features are highly standardized and readily formalized—was selected as the study object, and the deployment of generative AI was examined for controllability, interpretability, and auditability across the “preservation–creation –transmission” chain, thereby addressing inconsistent semantic definitions and the lack of an end-to-end evidence chain linking data provenance, generation processes, and user evaluations.
    A technical pipeline of “Common Expression Element System (CEES)–controlled generation–online presentation and evaluation” was constructed and implemented. Controlled vocabularies, value ranges, and compliance constraints on allowable combinations were defined for vessel form, compositional templates, motifs and borders, linework, and color/shading, thereby yielding a reusable minimal-viable combination set and an annotation schema. Semi-structured prompt templates, a style lock, and a negative list were embedded in a cross-platform Web/App prototype, while prompts and parameters were rule-validated and, when necessary, rolled back via a Style Control Card (SCC), so that controllable outputs could be produced when text-to-image generation was invoked using GPT–DALL·E. Prompts, negative terms, selected forms/patterns/parameters, reference and provenance information, and sketch inputs were captured in a structured, field-level generation log, thereby supporting reproducibility, traceability, and auditing.
    For evaluation, evidence was collected at two levels (static viewing and mechanism analysis), and validation was conducted using Stylistic Fidelity (SF), perceived authenticity (PA), User Engagement Scale (UES), the Unified Theory of Acceptance and Use of Technology (UTAUT) scale, Cognitive Load Theory (CLT), and Torrance Tests of Creative Thinking (TTCT); additionally, the adoption mechanism was tested via an integrated PLS-SEM→ANN→NCA framework. The results indicate that, under controlled generation, SF and PA were maintained at an overall high level. Superior performance was observed for experts on style-sensitive dimensions and on Constructive Authenticity (CA) within PA, whereas non-experts exhibited greater novelty, originality, and Willingness To Use (WTU) and scored higher on Object Authenticity (OA) and Existential Authenticity – Self (EA-S) within PA. Overall differences in Extraneous Cognitive Load (ECL) were small. Mechanism analyses supported a path in which Authenticity of Cultural Elements (ACE) and Perceived Personalization (PP) affected WTU via Cultural Identity (CI), Perceived Usefulness (PU), and Perceived Ease of Use (PEOU); ANN and NCA further corroborated nonlinear importance patterns of key antecedents and identified necessary conditions and threshold constraints.
    The proposed closed loop—“semantic specification–controlled generation– log-based provenance–online evaluation”—offers a transferable, reusable, and auditable generative-AI paradigm for image-based cultural heritage by operationalizing preservation norms as generation constraints, strengthening governance and reproducibility through logging and provenance mechanisms, and providing comparable empirical evidence for the modern transmission of Ming Dynasty blue-and-white porcelain visual vocabulary.
    Keywords:Ming Dynasty blue-and-white porcelain; Common Expression Element System (CEES); controlled generation; Stylistic Fidelity (SF); perceived authenticity (PA); User Engagement Scale (UES); Unified Theory of Acceptance and Use of Technology (UTAUT) scale; Cognitive Load Theory (CLT); Torrance Tests of Creative Thinking (TTCT); Partial Least Squares Structural Equation Modeling (PLS-SEM); Artificial Neural Network (ANN); Necessary Condition Analysis (NCA).

    더보기

    목차 (Table of Contents)

    • 제 1 장 서론 1
    • 1.1 연구 배경 1
    • 1.2 연구 동기 및 목표 7
    • 1.3 연구 범위 및 방법 9
    • 1.3.1 연구 범위 9
    • 제 1 장 서론 1
    • 1.1 연구 배경 1
    • 1.2 연구 동기 및 목표 7
    • 1.3 연구 범위 및 방법 9
    • 1.3.1 연구 범위 9
    • 1.3.2 연구 방법 14
    • 1.4 선행 연구 17
    • 1.4.1 중국 연구 현황 분석 17
    • 1.4.2 국제 연구 동향 종설 23
    • 1.4.3 국제 연구의 지식 지도 35
    • 1.4.3.1 국제 논문 게제 추세 그래프 35
    • 1.4.3.2 청화백자 지식 그래프 38
    • 1.4.3.3 인공지능을 활용한 문화유산 주제 연구 지식 그래프 구축 44
    • 1.4.3.4 문화유산 및 디지털화에 대한 국제 연구 지식 그래프 49
    • 1.4.3.5 문화 유산 보본에 관한 국제 연구 지식 그래프 56
    • 1.4.4 선행 연구 현황에 대한 평가 63
    • 1.5 연구의 차별성과 학술실천적 공헌 67
    • 1.6 연구 문제 69
    • 1.7 논문 구성 71
    • 제2장 문헌 검토 및 이론적 배경 74
    • 2.1 생성형 AI와 문화유산 74
    • 2.2 HCI와 인지부하 이론 77
    • 2.3 도자 문화유산 개요 80
    • 2.4 청화백자의 디지털 구축 84
    • 2.5 요약 86
    • 제3장 명대 청화자기 공통 시각 어휘 체계와 표본 데이터베이스 구축 88
    • 3.1 표본 선정과 연구 범위 88
    • 3.1.1 예술적 전범성, 역사적 대표성 및 생성형 인공지능의 학습 가능성 88
    • 3.1.2 연구 범위 및 표본 기준: 시기, 기종 및 문양 90
    • 3.2 공통 시각 어휘 체계 91
    • 3.3 형식과 구성 패러다임 96
    • 3.4 문양 모티프와 시기별 특성 109
    • 3.4.1 시기별 차이 109
    • 3.4.2 '모티브-사용 결합-전형 기형' 110
    • 3.5 스타일 제어 카드(SCC) 프레임워크와 이중 사용자 구성 119
    • 3.6 출처 126
    • 3.7 소결 126
    • 제 4 장 크로스플랫폼(UI/Web) 인터페이스 설계와 추적 가능(가시화) 기반의 통제형 생성 128
    • 4.1 설계 목표, 범위 및 역할-이용자 여정 128
    • 4.1.1 설계 목표 128
    • 4.1.2 범위 및 역할 128
    • 4.1.3 사용자 여정 130
    • 4.2 크로스 플랫폼 정보 구조 및 설계 시스템 132
    • 4.3 UI 플랫폼 인터페이스 솔루션 134
    • 4.4 웹 플랫폼 인터페이스 방안 150
    • 4.5 프로토타입 재검토 및 본 장의 소결 166
    • 제 5 연구 방법 및 평가 설계 168
    • 5.1 연구방법 168
    • 5.1.1 방법 168
    • 5.1.2 데이터 수집 및 정제 171
    • 5.1.3 워크플로우 구축 172
    • 5.2 실험설계 174
    • 5.2.1 척도 체계와 측정 적합성 175
    • 5.2.2 참여자 179
    • 5.2.3 평가 도구 180
    • 5.2.4 재료 185
    • 5.2.4.1 과업 설명 185
    • 5.2.4.2 실험 플랫폼 186
    • 5.2.4.3 이미지 제시 시스템 187
    • 5.3 데이터 분석 방법 188
    • 5.3.1 신뢰도 분석 189
    • 5.3.2 타당도 분석 189
    • 5.3.3 타당도 검증 190
    • 5.3.4 총 분산 설명력 분석 190
    • 5.3.5 분산 분석 191
    • 5.4 평가 결과 191
    • 5.4.1 신뢰도 결과 191
    • 5.4.2 타당도 결과 194
    • 5.4.3 총 분산 설명력 분석 결과 196
    • 5.4.4 분산 분석 결과 198
    • 5.5 소결 203
    • 제6장 SEM–ANN–NCA 통합 분석 207
    • 6.1 자극-유기체-반응 모형 207
    • 6.1.1 정적 관찰형 인터페이스와 콘텐츠 단서(자극) 208
    • 6.1.2 인지 및 정서 평가(유기체) 209
    • 6.1.3 행동 의도(반응) 210
    • 6.2 가설 전개 및 개념 모형 구축 211
    • 6.2.1 문화 요소의 진정성 211
    • 6.2.2 정보 품질 212
    • 6.2.3 지각된 상호작용성 212
    • 6.2.4 지각된 개인화 213
    • 6.2.5 디자인 미학 214
    • 6.2.6 지각된 향락성 215
    • 6.2.7 문화 정체성 216
    • 6.2.8. 지각된 유용성 216
    • 6.2.9 지각된 사용 용이성 217
    • 6.2.10 사용 의도 217
    • 6.3 연구 방법 218
    • 6.4 데이터 수집 220
    • 6.4.1 사전 연구 분석 220
    • 6.4.2 정식 자료 수집 225
    • 6.5 응답자 특성 225
    • 6.6 SEM-ANN-NCA 방법 227
    • 6.7 결과 229
    • 6.7.1 공통방법편의 통제 229
    • 6.7.2 PLS-SEM 분석 결과 229
    • 6.7.3 측정 모형 평가 230
    • 6.7.4 구조모델 평가 235
    • 6.8 ANN 결과 238
    • 6.8.1 모형 구축 238
    • 6.8.2 ANN 검증 239
    • 6.9 NCA 결과 246
    • 6.9.1 효과 크기 및 유의성 검정 246
    • 6.9.2 병목현상 분석 248
    • 6.10 소결 251
    • 제 7장 결론 254
    • 7.1 연구 결론 254
    • 7.2 연구의 의의와 혁신점 257
    • 7.2.1 이론적 의의 257
    • 7.2.2 실천적 의의 260
    • 7.2.3 혁신점 262
    • 7.3 연구의 한계와 향후 전망 263
    • 영문집 267
    • 참고문헌 269
    • 영문초록 287
    더보기

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼