A Multi-Scene Automatic Classification and Grading Method for Structured Sensitive Data Based on Privacy Preferences

The graded management of structured sensitive data has become a key challenge in data security governance, particularly amid digital transformation in sectors such as government, finance, and healthcare. The existing methods suffer from limited generalization, low efficiency, and reliance on static rules. This paper proposes PPM-SACG, a privacy preference matrix-based model for sensitive attribute classification and grading. The model adopts a three-stage architecture: (1) composite sensitivity metrics are derived by integrating information entropy and group privacy preferences; (2) domain knowledge-guided clustering and association rule mining improve classification accuracy; and (3) mutual information-based hierarchical clustering enables dynamic grouping and grading, incorporating high-sensitivity isolation. Experiments using real-world vehicle management data (50 attributes, 3000 records) and user privacy surveys verify the method’s effectiveness. Compared with existing approaches, PPM-SACG doubles computational efficiency and supports scenario-aware deployment, offering enhanced compliance and practicality for structured data governance.