GWO-SVM算法的教师分型分级绩效考核评价模型研究  

Study on the Grading Performance Evaluation Model of GWO-SVM Algorithm

作　　者：刘晓飞 LIU Xiaofei(School of Computer and Information,Anqing Normal University,Anqing Anhui 246133,China)

机构地区：[1]安庆师范大学计算机与信息学院,安徽安庆246133

出　　处：《佳木斯大学学报(自然科学版)》2024年第12期146-149,共4页Journal of Jiamusi University:Natural Science Edition

基　　金：安徽省高等学校质量工程教学研究重点项目(2023jyxm0472)。

摘　　要：教师分型分级绩效考核评价,是提高教学质量和促进教育公平的关键。然而目前的教师分型分级绩效考核评价局限于课堂教学,忽视了教师在教学活动的整体作用。为此,研究将全面教学活动纳入评价指标体系,并基于灰狼优化算法改进支持向量机的参数选择,以提高评价模型的精度和收敛速度。实验结果中,相较于传统支持向量机模型,改进支持向量机模型的收敛速度提高了75.38%,评价结果的平均误差减少了8.08%。实验结果表明,研究所提评价模型不仅具有更高的精度,还有更好的收敛速度表现,为教师绩效考核的客观评价提供了一种新的技术手段。Teacher classification and grading performance evaluation is the key to improve teaching quality and promote educational equity.However,the current performance evaluation of teacher classification is limited to classroom teaching,ignoring the overall role of teachers in teaching activities.Therefore,the comprehensive teaching activities are included in the evaluation index system,and we improve the parameter selection of SVM based on the grey Wolf optimization algorithm to improve the accuracy and convergence speed of the evaluation model.In the experimental results,the convergence rate of the improved SVM model is improved by 75.38%,and the average error of the evaluation results is reduced by 8.08%.The experimental results show that the proposed evaluation model not only has higher accuracy,but also has better convergence speed performance,which provides a new technical means for the objective evaluation of teacher performance appraisal.

关 键 词：灰狼优化算法 支持向量机 教师 绩效考核 评价模型 

分 类 号：G717.25[文化科学—职业技术教育学]