Quantitative Mining and Genealogy Construction of Aesthetic Features of Ancient Chinese Porcelain Patterns Driven by Big Data.

Saved in:

Bibliographic Details
Title:	Quantitative Mining and Genealogy Construction of Aesthetic Features of Ancient Chinese Porcelain Patterns Driven by Big Data.
Authors:	XIAO, Xiao¹ xiaoxiao_whu@163.com
Source:	Technical Gazette / Tehnički Vjesnik. 2026, Vol. 33 Issue 3, p1233-1243. 11p.
Subjects:	Chinese porcelain, Aesthetics, Machine learning, Big data, Data analysis, Knowledge graphs
Abstract:	Porcelain, as a precious heritage in the treasure house of Chinese civilization, has become a key technology for promoting its protection and inheritance under the trend of digitalization and intelligence of cultural heritage. To improve the matching accuracy between the visual aesthetic features of ancient Chinese porcelain patterns and the corresponding textual information, this paper proposes a cross-modal entity alignment strategy based on pattern aesthetics within the visual-language pre-training framework. On this basis, a porcelain cultural knowledge graph platform based on big data is designed and developed, which integrates multiple core functional modules such as intelligent interactive questioning, speech synthesis, pattern aesthetic text generation, entity recognition, and relationship extraction. The actual system operation test shows that the average recognition accuracy exceeds 90% and the average response time is less than 5 seconds, verifying the efficiency and reliability of the system in practical applications. [ABSTRACT FROM AUTHOR]
	Copyright of Technical Gazette / Tehnički Vjesnik is the property of Tehnicki Vjesnik and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Porcelain, as a precious heritage in the treasure house of Chinese civilization, has become a key technology for promoting its protection and inheritance under the trend of digitalization and intelligence of cultural heritage. To improve the matching accuracy between the visual aesthetic features of ancient Chinese porcelain patterns and the corresponding textual information, this paper proposes a cross-modal entity alignment strategy based on pattern aesthetics within the visual-language pre-training framework. On this basis, a porcelain cultural knowledge graph platform based on big data is designed and developed, which integrates multiple core functional modules such as intelligent interactive questioning, speech synthesis, pattern aesthetic text generation, entity recognition, and relationship extraction. The actual system operation test shows that the average recognition accuracy exceeds 90% and the average response time is less than 5 seconds, verifying the efficiency and reliability of the system in practical applications. [ABSTRACT FROM AUTHOR]
ISSN:	13303651
DOI:	10.17559/TV-20251203003184