三维有偏权值张量分解在授课推荐上的应用研究
发布时间：2019-07-09 10:51
【摘要】：为解决现今学校授课安排无推荐依据这一实际问题,首先给出了一系列形式化方法用于规约教师的专业基础、课程难度及教学评价;定义了一种加权函数计算出每组专业基础、课程难度和教学评价的综合有偏权值;构建了一种基于"教师-课程-评价-权值"四元关系的三维有偏权值张量模型,张量元素使用综合有偏权值。在此基础上,设计了一种基于Tucker分解的算法,对张量进行高阶奇异值分解(HOSVD)得到降维后的近似张量,按课程分类实现了Top_N授课推荐。实验结果表明,当迭代阈值达到一个合理值时,该方法能实现精准授课推荐,可作为一种新的智能化授课推荐方法应用于各类学校。
[Abstract]:In order to solve the practical problem that there is no recommendation basis for teaching arrangement in schools, a series of formal methods are given to regulate the professional basis, curriculum difficulty and teaching evaluation of teachers, and a weighted function is defined to calculate the comprehensive biased weights of each group of professional basis, curriculum difficulty and teaching evaluation. A three-dimensional biased weighted tensor model based on the quaternion relation of "teacher-curriculum-evaluation-weight" is constructed, in which the tensor element uses the comprehensive biased weight value. On this basis, an algorithm based on Tucker decomposition is designed, and the reduced dimension approximate tensor is obtained by high order singular value decomposition (HOSVD), and the Top_N teaching recommendation is realized according to the course classification. The experimental results show that when the iterative threshold reaches a reasonable value, this method can realize accurate teaching recommendation and can be applied to all kinds of schools as a new intelligent teaching recommendation method.
【作者单位】： 怀化学院计算机科学与工程学院;武汉大学计算机学院;空军预警学院四系;
【基金】：国家自然科学基金(61272109) 湖南省教育厅科学研究项目(15C1086)
【分类号】：G642.4;TP391.3
本文编号：2512094
[Abstract]:In order to solve the practical problem that there is no recommendation basis for teaching arrangement in schools, a series of formal methods are given to regulate the professional basis, curriculum difficulty and teaching evaluation of teachers, and a weighted function is defined to calculate the comprehensive biased weights of each group of professional basis, curriculum difficulty and teaching evaluation. A three-dimensional biased weighted tensor model based on the quaternion relation of "teacher-curriculum-evaluation-weight" is constructed, in which the tensor element uses the comprehensive biased weight value. On this basis, an algorithm based on Tucker decomposition is designed, and the reduced dimension approximate tensor is obtained by high order singular value decomposition (HOSVD), and the Top_N teaching recommendation is realized according to the course classification. The experimental results show that when the iterative threshold reaches a reasonable value, this method can realize accurate teaching recommendation and can be applied to all kinds of schools as a new intelligent teaching recommendation method.
【作者单位】： 怀化学院计算机科学与工程学院;武汉大学计算机学院;空军预警学院四系;
【基金】：国家自然科学基金(61272109) 湖南省教育厅科学研究项目(15C1086)
【分类号】：G642.4;TP391.3
【相似文献】
相关期刊论文 前1条
1 任亮宝;王莉;赵爱;;大学期末考试试卷量化分析研究[J];甘肃科技纵横;2011年03期
，本文编号：2512094
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2512094.html
