The promotion of the concept of sustainable development to the reform of enterprise human resource management

In order to achieve sustainable HRM, performance management needs to be properly reformed. Improved K-means clustering algorithm is proposed, and the algorithm is used for data mining of factors affecting performance management, and then feedback and suggestions on performance management reform are given according to the analysis results. In the comparison experiments of clustering analysis on 6 simulated and 2 real datasets, the DT-Kmeans algorithm has the highest clustering accuracy and the best stability in 5 simulated and 2 real datasets compared with other algorithms. K-means++ algorithm has slightly better accuracy and stability than the DTKmeans algorithm when analysing simulated dataset 4. It is concluded that the optimised algorithm has significantly improved in terms of accuracy and stability when analysing both simulated and real datasets. In terms of algorithm runtime, the DT-Kmeans algorithm has decreased only for dataset 7 compared with other methods, and has improved in all other datasets.