华南理工大学学报(自然科学版) ›› 2023, Vol. 51 ›› Issue (5): 54-62.doi: 10.12141/j.issn.1000-565X.220279

所属专题: 2023年计算机科学与技术

• 计算机科学与技术 • 上一篇    下一篇

融合遗忘和知识点重要度的认知诊断模型

刘宇鹏 张雷   

  1. 哈尔滨理工大学 计算机科学与技术学院,黑龙江 哈尔滨 150001
  • 收稿日期:2022-05-16 出版日期:2023-05-25 发布日期:2023-01-16
  • 通信作者: 刘宇鹏(1978-),男,博士,教授,主要从事自然语言处理、智能教育、认知计算研究。 E-mail:flyeagle99@126.com
  • 作者简介:刘宇鹏(1978-),男,博士,教授,主要从事自然语言处理、智能教育、认知计算研究。
  • 基金资助:
    国家自然科学基金资助项目(62172128);中国博士后科学基金资助项目(2014m561331);黑龙江省教育厅科学技术研究项目(12521073)

Cognitive Diagnosis Model Integrating Forgetting and Importance of Knowledge Points

LIU Yupeng ZHANG Lei   

  1. School of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150001,Heilongjiang,China
  • Received:2022-05-16 Online:2023-05-25 Published:2023-01-16
  • Contact: 刘宇鹏(1978-),男,博士,教授,主要从事自然语言处理、智能教育、认知计算研究。 E-mail:flyeagle99@126.com
  • About author:刘宇鹏(1978-),男,博士,教授,主要从事自然语言处理、智能教育、认知计算研究。
  • Supported by:
    the National Natural Science Foundation of China(62172128);the China Postdoctoral Science Foundation(2014m561331)

摘要:

智慧教育是人工智能的重点研究方向,如何利用试题中知识点并对学生的认知过程进行刻画是重中之重。针对认知诊断模型对学生和试题及其交互信息挖掘不充分的问题,文中提出了融合遗忘和知识点重要度的认知诊断模型。该模型根据学生对试题和知识点的历史交互,结合知识点难度信息引入遗忘因素,缓解了对学生信息挖掘不充分的问题;通过注意力机制获取试题对知识点的考查重要度信息,缓解了对试题信息挖掘不充分的问题;通过Transformer学习学生与试题间的交互,缓解了学生与试题交互不充分的问题。在经典数据集上的实验结果表明,文中模型在Math1、Math2、Assistment数据集上的准确率Acc、均方根误差RMSE、受试曲线面积AUC值分别为0.716、0.445、0.776、0.725、0.432、0.807、0.741、0.427和0.779,优于现有的其他对比模型,说明了知识重要度和时效性对于认知建模的重要性。

关键词: 认知诊断, 注意力机制, 转换器, 知识点重要度, 遗忘信息

Abstract:

Intelligence education is the key research direction of artificial intelligence. The most important is to describe the students’ cognitive process by ultilizing the knowledge points in the test questions. Aiming at the problem that the cognitive diagnosis model is insufficient for mining students, test questions and their interactive information, this study proposed a cognitive diagnosis model integrating forgetting and the importance of knowledge points. According to the historical interaction between the test questions and knowledge points, the model introduces forgetting factors in combination with the difficulty information of knowledge points, thus alleviates the problem of insufficient information mining for students. Through the attention mechanism, the importance information of the test questions to the knowledge points was obtained to alleviate the problem of insufficient information mining of the test questions. Learning the interaction relation between students and test questions through Transformer alleviates the problem of insufficient interaction information between students and test questions. The results of experiments carried out on the classic dataset show that the accuracy Acc, root mean square error (RMSE), and the area under curve (AUC) values of this method on the Math1, Math2, and Assistment datasets are 0.716, 0.445, 0.776, 0.725, 0.432, 0.807, 0.741, 0.427, 0.779, respectively. Compared with other existing models, the proposed method has better results. The proposed method illustrates the importance of knowledge importance and timeliness for cognitive modeling.

Key words: cognitive diagnosis, attention mechanism, transformer, importance of knowledge points, forgetting information

中图分类号: