作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 开发研究与工程应用 • 上一篇    下一篇

基于生物记忆原理的智能词汇记忆模型

熊万强,王蓓莉,孙晓光   

  1. (复旦大学计算机科学技术学院,上海201203)
  • 收稿日期:2014-09-04 出版日期:2015-06-15 发布日期:2015-06-15
  • 作者简介:熊万强(1989 - ),男,硕士研究生,主研方向:智能记忆,人工智能;王蓓莉,硕士;孙晓光,副教授。
  • 基金资助:

    上海市研究生教育创新计划基金资助项目(20130102)。

Intelligent Vocabulary Memory Model Based on Biological Memory Principle

XIONG Wanqiang,WANG Beili,SUN Xiaoguang   

  1. (School of Computer Science,Fudan University,Shanghai 201203,China)
  • Received:2014-09-04 Online:2015-06-15 Published:2015-06-15

摘要:

词汇学习是学习英语的基础,传统记忆模型采用机械的记忆方法,使用户在固定的时间周期内记忆词汇, 这些静态的记忆模型计划制定复杂,不利于用户有效记忆词汇。针对上述问题,提出一种智能词汇记忆模型。从生物的记忆过程出发,采用幂函数量化艾宾浩斯生物记忆曲线,利用生物记忆曲线追踪每个单词的学习情况,在单词临近遗忘的边缘提醒用户及时复习,动态调整生物记忆曲线。实验结果表明,与传统记忆模型相比,该模型能为用户制定精确的复习计划,可减少用户37. 04% 的时间用来掌握词汇,具有更高的记忆效率。

关键词: 词汇学习, 词汇记忆, 生物记忆, 艾宾浩斯遗忘曲线, 移动学习

Abstract:

Vocabulary learning is the foundation of English learning. Traditional memory models advise the user to memorize vocabulary by a specific time period. These static models are so complex in making review plan that it is not effective to memorize vocabulary for the user. This paper proposes an intelligent vocabulary memory model. It adopts the power function to quantify the Ebbinghaus biological memory curve and depicts the memory effect of every word with the curve to remind the user to review the word in time before forgetting it and dynamically adjusts the curve. Experiments show that the model can make precise review plan for the user which effectively saves about 37. 04% of the time and is more effective compared with the traditional memory models.

Key words: vocabulary learning, vocabulary memory, biological memory, Ebbinghaus forgetting curve, mobile learning

中图分类号: