AI-Driven Framework for Customer Requirement and Quality Analysis

Сохранить в:
Библиографические подробности
Опубликовано в::ISPIM Innovation Symposium (Jun 2025), p. 1-6
Главный автор: Seo, Sumin
Другие авторы: Byun, Jeongeun, Bae, Kukjin
Опубликовано:
The International Society for Professional Innovation Management (ISPIM)
Предметы:
Online-ссылка:Citation/Abstract
Full Text
Full Text - PDF
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

MARC

LEADER 00000nab a2200000uu 4500
001 3238450778
003 UK-CbPIL
035 |a 3238450778 
045 2 |b d20250601  |b d20250630 
084 |a 268728  |2 nlm 
100 1 |a Seo, Sumin  |u Korea Institute of Science and Technology Information (KISTI), 66, Heogi-ro, Dongdaemun-gu, Seoul 02456, Republic of Korea E-mail: syg3793@kisti.re.kr 
245 1 |a AI-Driven Framework for Customer Requirement and Quality Analysis 
260 |b The International Society for Professional Innovation Management (ISPIM)  |c Jun 2025 
513 |a Journal Article 
520 3 |a This study proposes an AI-driven framework to automate the extraction and analysis of Customer Requirements (CRs) and Engineering Characteristics (ECs) from large-scale product review data. Traditional Quality Function Deployment (QFD) methods are labor-intensive, costly, and lack scalability and real-time responsiveness. To address these issues, the framework leverages recent advances in generative AI: instruction tuning improves task-specific comprehension, Retrieval-Augmented Generation (RAG) enhances contextual grounding, and prompt engineering ensures structured, actionable outputs. A domain-specific CR-EC dictionary aligns customer language with technical attributes, while instruction-response training improves model interpretability. The framework includes a scalable pipeline for data segmentation, inference, and post-processing. By enabling real-time demand sensing and reducing VOC collection costs, it supports agile product development and quality management. Future research will focus on validating the framework across domains and refining it based on empirical findings, contributing to AI-enabled, customer-driven innovation and automated product quality assessment. 
653 |a Language 
653 |a Quality management 
653 |a Dictionaries 
653 |a Customer satisfaction 
653 |a Usability 
653 |a Deep learning 
653 |a Trends 
653 |a Customer feedback 
653 |a Generative artificial intelligence 
653 |a Prompt engineering 
653 |a Automation 
653 |a Research & development--R&D 
653 |a Innovations 
653 |a Customers 
653 |a Quality assessment 
653 |a Product development 
653 |a Product quality 
653 |a Costs 
653 |a Product reviews 
653 |a Engineering 
653 |a Natural language processing 
653 |a Real time 
653 |a Quality function deployment 
700 1 |a Byun, Jeongeun  |u Korea Institute of Science and Technology Information (KISTI), 66, Heogi-ro, Dongdaemun-gu, Seoul 02456, Republic of Korea E-mail: jebyun@kisti.re.kr 
700 1 |a Bae, Kukjin  |u Korea Institute of Science and Technology Information (KISTI), 66, Heogi-ro, Dongdaemun-gu, Seoul 02456, Republic of Korea E-mail: baekj@kisti.re.kr 
773 0 |t ISPIM Innovation Symposium  |g (Jun 2025), p. 1-6 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3238450778/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3238450778/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3238450778/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch