Enterprise employee performance automatic scoring service implementation method

• Main Authors: JIAO YONGJI, LUO HAN, WU ZIMO, CHEN XIAOXUE, ZHANG XIAOMAN
• Format: Patent
• Language: Chinese; English
• Published: 29.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses an enterprise employee performance automatic scoring service implementation method, and the frame of the method is divided into three parts: data preprocessing, two layers of random forest classifiers and artificial bee colony algorithm selection features. In the data preprocessing part, a decimal calibration normalization and independent component analysis method is used, and characteristics are extracted after performance assessment indexes of employees are normalized. Each layer of classifier is a strong classifier composed of 12 random forest individual classifiers, and the structure enables the result of the whole model to have high accuracy and generalization performance, and also has good stability. And the prediction results of the first-layer classifier are integrated through the second-layer random forest classifier, so that the prediction precision of the results can be improved. And K-fold cross validation is also added when the artificial bee colony algorithm is used to se