【摘要】 课堂学习行为智能识别和大数据分析为课堂高阶认知评价带来契机。利用数据技术挖掘学生课堂学习行为对深度学习成绩的影响关系，解决识别与评价课堂高阶认知不足的现实问题。以英语和化学两门学科为例，以课堂学习行为为自变量，以测试试卷深度学习成绩为因变量，通过高斯消元、回代总样本求均方差最优解等算法，分析出课堂“听讲”“阅读”等8种课堂行为对深度学习成绩的权重影响，构建课堂学习行为与深度学习成绩间的预测模型，依据模型可识别和评价学生的高阶认知是否发生，为常态课堂高阶认知规模化评价提供科学依据和技术支撑。更多还原

【Abstract】 Intelligent identification of classroom learning behavior and big data analysis bring opportunities for higher-order cognitive evaluation in classroom. This study uses data technology to mine the relationship between students’ classroom learning behavior and deep learning performance, so as to solve the practical problem of identifying and evaluating the lack of higher-order cognition in the classroom. In both English and chemistry subject, for example, in the classroom learning behavior as the independent variable, with deep learning achievement test paper as the dependent variable, by using algorithms such as Gaussian elimination and the optimal solution of the mean squared deviation of the total sample of the return generation, etc., this study analyzes the influence of classroom “listening”, “reading” and other eight kinds of classroom behavior on deep study result, and builds a classroom learning behavior and depth prediction model between grades. The model can identify and evaluate the occurrence of students’ higher-order cognition, and provide scientific basis and technical support for the large-scale evaluation of higher-order cognition in normal classroom.更多还原