Privacy Protection and Data Security Governance Strategies for Association Algorithms in the Digital Era of Enterprises

Aiming at the problems of low governance efficiency and high risk of information leakage in dynamic association analysis of large-scale data security protection in enterprises, this paper studies the privacy protection and governance strategies by combining the FP-Growth (Frequent Pattern-Growth) association algorithm to improve data security and governance efficiency. First, the sensitive data of enterprises was classified and preprocessed into three types: high sensitivity, medium sensitivity and low sensitivity, and unified format and standardization were performed. Then, the FP-Growth method was used to mine frequent patterns in the data, identify potential security threats and the relationship between sensitive information; finally, the data compression optimization method based on the tree structure was used, combining block partitioning and global indexing to improve memory utilization and algorithm operation efficiency. Experiments show that when processing large data scales, compared with the two advanced association algorithms Apriori and Eclat, FP-Growth’s running time is reduced by 24.8% and 14.5% respectively; memory consumption is reduced by 9.4% and 4.2% respectively. The conclusion shows that the FP-Growth algorithm helps to improve the level of security governance and provide effective support for enterprise digitalization.