pisco_log
banner

Optimizing the International Communication Pathway of the "Yiwu Qingyi " Cultural IP Empowered by AIGC

Zixuan Wang, Muhammad Irsyad Bin Abdullah

Abstract


As the digital economy expands, cultural intellectual property (IP) increasingly functions as a lever for product differentiation and value creation in cross-border markets.Yiwu, widely recognized as a global small-commodities trading hub, also possesses a distinctive local moral tradition commonly framed as "Qingyi (??)" and operationalized through the "Six Yi " virtues. However, the international communi cation of "Yiwu Qingyi" faces persistent constraints, including the structural mismatch between human creative capacity and massive multilin gual demand, the distortion of culturally embedded meanings in cross-cultural translation, and the absence of effective evaluation mechanisms for communication outcomes. This study develops a four-layer analytical framework to optimize the international communication pathway of "Yiwu Qingyi" through the application of AIGC technologies. The framework includes: (1) cultural-gene decoding supported by knowledge graphs and curated evidence; (2) digital technology transformation through retrieval-augmented generation (RAG) and prompt engineering; (3) trade scenario reconstruction to embed cultural narratives into commercial interactions; and (4) international rule innovation to translate the credibility ethic of Yiwu into globally legible trust indicators. The study further proposes the concept of a Xinyi Index, which converts au ditable trade performance into interpretable credibility assets. By integrating cultural narratives with measurable trust indicators, the pro posed framework provides a practical pathway for coupling cultural communication with commercial trust formation in cross-border trade environments.

Keywords


AIGC;Yiwu Qingyi; Six Yi; Knowledge graph; Retrieval-augmented generation; International communication

Full Text:

PDF

Included Database


References


Chang, K., Xu, S., Wang, C., Luo,Y., Liu, X., Xiao, T., & Zhu, J. (2024). Efficient prompting methods for large language models:A sur-

vey. https://doi.org/10.48550/arXiv.2404.01077

Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., & Yin, D. (2024). A survey on RAG meeting LLMs. ACM Transactions on Information

Systems. https://doi.org/10.1145/3637528.3671470

Foka,A., & Griffin, G. (2024).AI, cultural heritage, and bias. Heritage. https://doi.org/10.3390/heritage7110287

Hogan,A., et al. (2021). Knowledge graphs.ACM Computing Surveys. https://doi.org/10.1145/3447772

Ji, Z., et al. (2023). Survey of hallucination in natural language generation.ACM Computing Surveys. https://doi.org/10.1145/3571730




DOI: http://dx.doi.org/10.70711/frim.v4i4.9053

Refbacks

  • There are currently no refbacks.