This study focuses on the use of big data and semantic analysis collaborative optimization technology to achieve 3D intelligent generation of cyberpunk costumes of Hui culture. In view of the dilemma of Hui culture inheritance and the limitations of cyberpunk costume design, data related to Hui culture architecture, costumes, patterns and cyberpunk style are widely collected through web crawlers, cooperative collection and other means, and then cleaned and annotated to construct element feature vectors. An innovative collaborative optimization algorithm based on big data and semantic analysis is designed, in which the cultural gene genetic algorithm encodes Hui culture elements into gene fragments, and realizes design evolution through operations such as selection, crossover and mutation. In the experimental stage, a comparative experiment is designed to compare with traditional hand-painted design and 3D design methods based on single style generation. In terms of design innovation, the professional designers' scores show that the proposed method scored an average of 8 points (out of 10 points), traditional hand-painted 6 points, and single-style generation 7 points; in terms of cultural element integration, the proposed method reached 85%, far exceeding the 60% of traditional hand-painted and 70% of single-style generation; the visual effect was measured by PSNR and SSIM indicators, and the PSNR value of the proposed method was 35dB and the SSIM value was 0.9. The experimental results show that this method significantly improves the design innovation and cultural integration, and has important theoretical and practical significance in the field of clothing design. 

Zihan Ma. Research on 3D Intelligent Generation Method of Cyberpunk Costumes of Hui Culture Based on Cooperative Optimization of Big Data and Semantic Analysis. The Frontiers of Society, Science and Technology (2025), Vol. 7, Issue 5: 68-76. https://doi.org/10.25236/FSST.2025.070509.

[1] Qin Zhen, Ji Tie, Liu Fang, & Liu Yonghong. Product design method based on the extension semantics of ethnic pattern primitives. Journal of Computer-Aided Design & Graphics, vol. 33, pp. 7 1595-1603, October 2021.

[2] Mao Cunli, Hao Pengpeng, Lei Xiongli, Wang Bin, Wang Hongbin, & Zhang Yafei. Cross-border ethnic cultural text retrieval based on entity semantic extension. Journal of Chinese Information Processing, vol. 36, pp. 3 101-109, November 2022.

[3] Li Xiaomin, Wang Hao, Bu Wenru, & Zhou Shu. Research on the association of ancient poetry, allusions and words from the perspective of knowledge reorganization: A method integrating fine-grained co-citation relationship and semantic features. Journal of Information Resources Management, vol. 14, pp. 1 131-142, June 2024.

[4] Ding Ning, Yu Suihuai, Chu Jianjie, Chen Chen, & Liu Huajing. Construction and application of semantic quantification model of ethnic patterns for product design. Journal of Computer-Aided Design and Graphics, vol. 35, pp.6 621-632, April 2023.

[5] Shiv Ram Dubey, Satish Kumar Singh, & Wei - Ta Chu. Vision Transformer Hashing for Image Retrieval. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 123 - 125, 2022.

[6] Bai Yan, & An Xingyu. Analysis and optimization path of projection and perceived image deviation of ancient town scenic spots: A case study of Pingyao Ancient City. Journal of Southwest University (Natural Science Edition), vol. 44, pp.10  101-111, December 2022.

[7] Zhao Guanbo, Zhang Yongbing, Mao Cunli, Gao Shengxiang, & Wang Fengxiao. Generative summarization method of cross-border ethnic culture integrating domain knowledge. Journal of Nanjing University (Natural Science Edition), vol. 59, pp. 6 620-628, April 2023.

[8] Zeng Zhen, Zhang Dan, Lin Runze, Chen Lingyan, He Tianyou, Ye Jing, & Zheng Yushan. Study on the image and perceptual characteristics of tourist destinations based on network text analysis: A case study of Yangzhou Geyuan. Journal of Southwest University (Natural Science Edition), vol. 44, pp. 7 194-201, January 2022.

[9] Yang Zhenping, Mao Cunli, Lei Xiongli, Gao Shengxiang, Lu Shan, & Zhang Yongbing. Cross-border ethnic cultural entity recognition method integrating word set information. Journal of Chinese Information Science, vol. 36, pp. 8 88-96, October 2022.

[10] Xiao Yao, Shao Ming, & Ma Yuan. Study on recreational activities and space of human settlement environment in Beijing during the Qing Dynasty based on semantic analysis of ancient documents. Landscape Architecture, vol. 29, pp. 9 134-139, February 2022.

[11] Zhang Yunzhong, Jiao Fengzhi, & Liu Jialin. Semantic description model and metadata framework for display of Tang Sancai digital cultural resources. Library and Information, vol. 41, pp. 8 87-96, March 2021.