%0 Journal Article
%T 基于鱼群算法优化的BP神经网络模型的师范专业毕业要求达成度评价
Evaluation of Graduation Requirements of Teachers Major Based on BP Neural Network Model Optimized by Fish Swarm Algorithm
%A 王超凡
%A 朱承泽
%A 王柏淋
%A 项月
%A 邵子俊
%J Advances in Education
%P 1177-1184
%@ 2160-7303
%D 2022
%I Hans Publishing
%R 10.12677/AE.2022.124184
%X
师范人才培养质量评价对于深化高校人才培养质量保障体系改革具有重要意义，促进培养高素质、专业化、创新型教师的目标达成。师范生毕业要求达成度评价是师范专业建立以产出为导向的质量保证机制的关键环节。本文首先依据师范生毕业要求建立师范专业毕业要求达成度指标体系，对毕业生自评和专业教师的测评数据，运用基于鱼群算法优化的BP神经网络模型进行达成度评价，再通过与用人单位测评数据比较验证模型的有效性和实用性。在师范院校可对评价结果进行全面、详尽、客观的分析，以此为依据持续改进师范专业教师培养。
The quality evaluation of training of teachers is of great significance for deepening the reform of the quality assurance system for talent training in colleges and universities, and promotes the achievement of the goal of training high-quality, professional and innovative teachers. The evaluation of the degree of achievement of the graduation requirements of normal students is a key link in the establishment of a production-oriented quality assurance mechanism for normal majors. This paper firstly establishes an index system for the achievement degree of the graduation requirements of normal students according to the graduation requirements of normal students, and uses the BP neural network model optimized by the fish swarm algorithm to evaluate the degree of achievement based on the self-evaluation of graduates and the evaluation data of professional teachers. The evaluation data are compared to verify the validity and practicability of the model. In normal colleges and universities, a comprehensive, detailed and objective analysis of the evaluation results can be carried out, and on this basis, the training of teachers in normal professional schools can be continuously improved.
%K 师范认证，人才培养，毕业要求，鱼群算法，神经网络
Normal Certification
%K Talent Training
%K Graduation Requirements
%K Fish Group Algorithm
%K Neural Network
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=50632