Optimal design of data processing and data encryption detection and identification algorithm for engineering risk points based on machine learning

With the increasing scale and complexity of engineering projects, engineering audit is facing increasingly severe challenges in data processing and data encryption detection and identification of risk points. The purpose of this paper is to improve the data processing efficiency and data security of risk points in engineering audit by applying machine learning(ML) technology. In data processing, by introducing ML algorithm, intelligent cleaning, quality inspection and characteristic engineering of engineering audit data are realized, thus improving the accuracy and efficiency of audit. In the aspect of data encryption detection and identification, this paper discusses the advantages of ML algorithm in the face of the limitations of traditional encryption methods, and improves the security of data through intelligent detection and identification mechanism. In order to optimize the design of related algorithms, special attention is paid to the key steps such as algorithm selection, feature engineering and parameter tuning. Through the comparative empirical research in the improved Stacking and Bayesian Network(BN) models, this paper verifies the significant advantages of the optimization design algorithm in improving the accuracy, recall, F1 value and AUC index. This not only provides a more flexible and efficient data processing tool for engineering audit, but also provides a new idea for the security guarantee in the field of data encryption.