基于改进SVM的绩效数据智能处理与分析算法设计

Design of performance data intelligent processing and analysis algorithm based on improved SVM

绩效评估是通过各项指标对员工进行的一种综合评价,科学、完善的绩效评估方法对医院人力资源的管理与调度具有重要作用。传统的统计学方法依靠简单的指标进行绩效评估,其统一性差、无法处理当今海量的人力资源数据。针对上述问题,文中采用SVM算法完成了非线性、小样本数据的训练。同时利用LSTM可改善SVM算法无法处理时序数据问题的特点,通过将两种算法相融合并使用少量数据进行训练,进而完成对医院人力资源数据的评估分析。实验结果表明,所提算法的准确性、稳定度在对比算法中均为最优,且算法运行时间相较对比算法平均缩短了约15 s,验证了该算法具备的综合性能。

Performance evaluation is a comprehensive evaluation of employees through various indicators.Scientific and perfect performance evaluation methods play an important role in the management and scheduling of hospital human resources.Traditional statistical methods rely on simple indicators for performance evaluation,which has poor unity and can not deal with today’s massive human resources data.In view of the above problems,this paper uses SVM algorithm to complete the training of nonlinear and small sample data,and uses LSTM algorithm to improve the characteristics that SVM algorithm can not deal with time series data.By combining the two algorithms,only a small amount of training data can be used to complete the evaluation and analysis of hospital human resource data.Experimental results show that the accuracy and stability of the proposed algorithm are the best in the comparison algorithm,and the running time of the algorithm is about 15 s shorter than that of the comparison algorithm,which proves that the algorithm has good comprehensive performance.