【摘要】：為解決現(xiàn)今學(xué)校授課安排無推薦依據(jù)這一實(shí)際問題,首先給出了一系列形式化方法用于規(guī)約教師的專業(yè)基礎(chǔ)、課程難度及教學(xué)評(píng)價(jià);定義了一種加權(quán)函數(shù)計(jì)算出每組專業(yè)基礎(chǔ)、課程難度和教學(xué)評(píng)價(jià)的綜合有偏權(quán)值;構(gòu)建了一種基于"教師-課程-評(píng)價(jià)-權(quán)值"四元關(guān)系的三維有偏權(quán)值張量模型,張量元素使用綜合有偏權(quán)值。在此基礎(chǔ)上,設(shè)計(jì)了一種基于Tucker分解的算法,對(duì)張量進(jìn)行高階奇異值分解(HOSVD)得到降維后的近似張量,按課程分類實(shí)現(xiàn)了Top_N授課推薦。實(shí)驗(yàn)結(jié)果表明,當(dāng)?shù)撝颠_(dá)到一個(gè)合理值時(shí),該方法能實(shí)現(xiàn)精準(zhǔn)授課推薦,可作為一種新的智能化授課推薦方法應(yīng)用于各類學(xué)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.
【作者單位】： 懷化學(xué)院計(jì)算機(jī)科學(xué)與工程學(xué)院;武漢大學(xué)計(jì)算機(jī)學(xué)院;空軍預(yù)警學(xué)院四系;
【基金】：國家自然科學(xué)基金(61272109) 湖南省教育廳科學(xué)研究項(xiàng)目(15C1086)
【分類號(hào)】：G642.4;TP391.3

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 任亮寶;王莉;趙愛;;大學(xué)期末考試試卷量化分析研究[J];甘肅科技縱橫;2011年03期

，

本文編號(hào)：2512094