一种基于文本和表达式的相似数学题推荐方法  

Mathematical Exercise Recommendation Method Based on Text and Mathematical Expression

作　　者：孙巧莉 周从华[1,2] SUN Qiaoli;ZHOU Conghua(School of Computer Science and Telecommunication Engineering,Jiangsu University,Zhenjiang 212013;Jingkou District New Generation Information Technology Industry Research Institute,Jiangsu University,Zhenjiang 212013)

机构地区：[1]江苏大学计算机科学与通信工程学院,镇江212013 [2]江苏大学京口区新一代信息技术产业研究院,镇江212013

出　　处：《计算机与数字工程》2024年第8期2372-2378,共7页Computer & Digital Engineering

摘　　要：目前数学习题的相似度计算方法主要利用的是文本信息,忽略了数学表达式信息。然而数学习题常常会包含大量的数学表达式,使得现有的相似度计算方法并不精确。为提高相似习题推荐的准确性,论文针对数学习题中文本信息计算相似度存在不足的问题,提出一种结合文本和数学表达式计算数学习题相似度的方法。该方法利用树形码计算数学表达式之间的相似度,结合文本信息和表达式信息计算得到数学习题的相似度,从而根据top-k进行习题推荐。比较论文的推荐方法和基于文本的推荐,实验结果显示该方法有效提高了推荐的准确率,是一种实用方法。At present,the similarity calculation method of mathematical exercises mainly uses text information,ignoring mathematical expression information.However,mathematical exercises often contain a large number of mathematical expressions,which makes the existing similarity calculation methods not accurate.In order to improve the accuracy of recommending similar exercises,this paper proposes a method combining text and mathematical expression to calculate the similarity of mathematical exercises.The method uses tree code to calculate the similarity between mathematical expressions,and combines text information and expression information to calculate the similarity of mathematical exercises,so as to recommend exercises according to top-K.Comparing the proposed recommendation method with the text-based recommendation method,the experimental results show that the proposed method effectively improves the accuracy of recommendation and is a practical method.

关 键 词：数学表达式 树形码 相似度 相似数学题推荐 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]