A User Preference Recommendation System for Industry 5.0 Based on DSD-Transformer

Industry 5.0, characterized by the deep integration of the Internet of Things (IoT), artificial intelligence (AI), digital twins, and edge computing, represents a new paradigm for intelligent manufacturing and human–machine collaboration. By enabling real-time interaction between physical and cyber-physical systems, Industry 5.0 fosters personalized, adaptive, and sustainable production environments. However, the growing diversity of industrial products and user requirements presents challenges in effectively matching industrial users with suitable design solutions or manufacturing resources. Recommendation systems, particularly those based on Collaborative Filtering (CF), have emerged as powerful tools to address this issue by leveraging user preferences and behavioral data. Nevertheless, traditional CF algorithms often encounter efficiency bottlenecks when processing the high-dimensional, heterogeneous, and dynamic data typical of Industry 5.0 environments.To overcome these limitations, this paper proposes a clustering-based CF algorithm that improves recommendation efficiency by incorporating industrial user relationship modeling. Furthermore, a Density-Sensitive Distance Transformer (DSD-Transformer) framework is developed to enhance clustering precision and recommendation accuracy. Experimental evaluations conducted on real industrial datasets demonstrate that the proposed model significantly outperforms existing methods in both prediction accuracy and computational efficiency, making it well suited for Industry 5.0-oriented intelligent recommendation and decision-support applications.