高教程序代码作业抄袭检测的方法研究与实践

doi:10.3969/j.issn.0253-2778.2020.08.002

中国科学技术大学学报 ›› 2020, Vol. 50 ›› Issue (8): 1048-1057.DOI: 10.3969/j.issn.0253-2778.2020.08.002

高教程序代码作业抄袭检测的方法研究与实践

于俊，李雅洁，程礼磊，连顺，谭昶，丁德成，刘淇

1.中国科学技术大学计算机科学与技术学院，安徽合肥 230027;2.科大讯飞股份有限公司，安徽合肥 230088；

收稿日期:2020-06-05 修回日期:2020-06-24 接受日期:2020-06-24 出版日期:2020-08-31 发布日期:2020-06-24
通讯作者: 刘淇
作者简介:于俊，男，1981年生，博士生/工程师. 研究方向：数据挖掘、用户画像、知识图谱. E-mail: ustcyujun@163.com
基金资助:
国家自然科学基金(61922073)，中央高校基本科研业务费专项(WK2150110021)资助.

Research and practice of plagiarism detection in program code assignments by college students

YU Jun, LI Yajie, CHENG Lilei, LIAN Shun, TAN Chang, DING Decheng, Liu Qi

1. School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China; 2. USTC iFLYTEK Co., Ltd., Hefei 230088， China； 3. Nanjing Qiancui Intelligent Technology Service Co., Ltd, Nanjing 210019, China

Received:2020-06-05 Revised:2020-06-24 Accepted:2020-06-24 Online:2020-08-31 Published:2020-06-24

摘要/Abstract

摘要： 学生的编程水平直接反映技术类课程的学习效果，因此教学考察中程序代码作业的比重也越来越大.由于程序代码作业抄袭成本低，导致抄袭现象不同程度地存在于各高校教学中，严重影响了学生能力的培养和教师教学的效果，打击学生学习的积极性乃至损坏学风.为此以智能且自动化方式找出学生作业的相似之处，分析学生抄袭的总体情况为目的，将人工智能算法和数据处理分析技术相结合，提出一种学生作业抄袭检测方法.首先，分析学生提交的程序代码作业的复杂情况，设计作业数据预处理流程.然后，具体提出了基于KR和Winnowing的程序代码作业相似度检测算法，与传统检测方法相比通过代码格式化等改进手段提升了学生作业相似检测的精准度，并在大批量作业检测实践中，研究优化算法增加了不同学生之间作业相似结果的区分度.为了验证相似度计算部分的有效性和实用性，进一步设计了相关的模拟实验流程（包括与JPlag检测系统的对比），给出在相同实验数据集上不同抄袭类型下的相似度计算结果.最后，依托于科大讯飞博思智慧在线学习平台对该研究进行了真实场景的实际应用.实验结果以及实际应用都表明，该程序代码作业抄袭检测方法，对高校学生程序代码作业相似度检测有效，具有很高的应用价值.

关键词: 程序代码抄袭检测, 相似度检测, 在线智慧教育

Abstract: The programming ability of students directly reflects the learning effect of technical courses. The proportion of program code assignments are increasing in teaching evaluation. The low cost of plagiarism of program code homework leads to the widespread plagiarism in colleges and universities, which seriously affects the cultivation of students’ ability and the effect of teaching. To this end, a method for homework plagiarism detection is proposed by combining the artificial intelligence algorithm with data processing analysis technology to detect similarities in students’ homework intelligently and automatically, and analyze the overall situation of plagiarism. First, the complex situation of the program code assignments submitted by students is analyzed, and the data pre-processing process is designed. Then, the similarity detection algorithm for program code assignments based on KR and Winnowing is specifically proposed. Compared with the traditional detection methods, the accuracy of similarity detection in students’ homework is improved by such means as code formatting. In the practice of large-scale homework detection, the research optimization algorithm increases the differentiation of similarity results in different students’ homework. To verify the validity and practicability of the core similarity calculation part of this paper, a relevant simulation experiment process (including the comparison with JPlag detection system), was designed and the similarity calculation results were given under different plagiarism types on the same experimental data set. Finally, based on iFLYTEK’s Bosi intelligent online learning platform, the research has been applied in real scenarios. The experimental results and practical application results show that the proposed detection method has high validity and application value in the detection of similarities in program code assignments by college students.

Key words: plagiarism detection for program code, similarity detection, online wisdom education

中图分类号:

TP391

于俊，李雅洁，程礼磊，连顺，谭昶，丁德成，刘淇. 高教程序代码作业抄袭检测的方法研究与实践[J]. 中国科学技术大学学报, 2020, 50(8): 1048-1057.

YU Jun, LI Yajie, CHENG Lilei, LIAN Shun, TAN Chang, DING Decheng, Liu Qi. Research and practice of plagiarism detection in program code assignments by college students[J]. Journal of University of Science and Technology of China, 2020, 50(8): 1048-1057.

参考文献

［1］
傅钢善. 教育技术发展轨迹探讨[J].电化教育研究,2005(09):22-26.
[2] HONG C M, CHEN C M, CHANG M H, et al. Intelligent web-based tutoring system with personalized learning path guidance[J]. Computers &Education, 2008, 51( 2) : 787-814.
[3] 韦琳,袁泉,霍剑青,等. E-learning非结构化数据管理系统的构建与实现[J].中国科学技术大学学报,2010,40(06):623-628.
[4] 黄振亚,苏喻,吴润泽,等. 一种面向教育评估的智能教育辅助平台[J].中国科学技术大学学报,2015,45(10):846-854.
[5] 韩冰. 基于FTP教学平台的代码相似度检测的研究[J]．计算机光盛软件与应用, 2012 (09):217-218.
[6] LECUN Y, BOTTOU L, BENGIO Y. Gradient -Based Learning Applied to Document Recognition[M]. Proceedings of the IEEE,1998.
[7] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM , 2012:60 (2):1-9.
[8] 殷丹平. 基于CNN的代码相似度检测研究与代码查重系统[D]. 北京:北京邮电大学,2018.
[9] BAXTER. Clone detection using abstract syntax trees[J]. International Conference on Software Maintenance 1998, 1998:368-377.
[10] KOSCHKE R. Clone detection using abstract syntax suffix trees[J]. Working Conference on Reverse Engineering 2006, 2006:253-262.
[11] SCHLEIMER S, WILKERSON D S, AIKEN A. Winnowing :Local algo-rithms for document fingerprinting[C]∥Proc of the 2003 ACM SIGMOD Int’ l Conf on Management of Data, 2003:76-85.
[12] KARP R M, RABIN M O. Efficient randomized pattern-matching algorithms[J]. IBM Journal of Research and Development, 1987:115-126.
[13] 苏德富, 钟诚. 计算机算法设计与分析[M] .北京:电子工业出版社, 2001.
[14] 张文典,任冬伟. 程序抄袭判定系统[J].小型微型计算机系统,1988(10):34-39.
[15] 朱江. 基于XML的程序设计自动批改的研究[D]. 湘潭:湘潭大学,2005.
[16] 王继远. 一种用于软件作业评判系统的程序结构分析算法的设计与实现[D]. 北京:北京邮电大学,2007.
[17] 赵长海,晏海华,金茂忠. 基于编译优化和反汇编的程序相似性检测方法[J].北京航空航天大学学报,2008(06):711-715.
[18] 张鹏,王国胤,陶春梅,等. 基于本体粗糙集的程序代码相似度度量方法[J].重庆邮电大学学报(自然科学版),2008,20(06):737-741.
[19] 熊浩,晏海华,赫建营,等. 一种基于静态词法树的程序相似性检测方法[J].计算机应用研究,2009,26(04):1316-1319+1326.
[20] 王春晖. 程序代码抄袭检测中串匹配算法的研究与实现[D]. 内蒙古呼和浩特:内蒙古师范大学,2008.
[21] VERCO K L, WISE M J. Software for detecting suspected plagiarism: Comparing structure and attribute-counting systems[C]. Australasian Conference on Computer Science Education, 1996: 81-88.
[22] KOSCHKE R, FALKE R, FRENZEL P, et al. Clone Detection Using Abstract Syntax Suffix Trees[C]. Working Conference on Reverse Engineering, 2006: 253-262.
[23] KAMIYA T, KUSUMOTO S, INOUE K, et al. CCFinder: A multilinguistic token-based code clone detection system for large scale source code[J]. IEEE Transactions on Software Engineering, 2002, 28(7): 654-670.
[24] ELMATARAWY A, ELRAMLY M, BAHGAT R, et al. Code clone detection using sequential pattern mining[J].International Journal of Computer Applications, 2015, 127(2): 10-18.
[25] BAKER B S. Parameterized duplication in strings: Algorithms and an application to software maintenance[J]. SIAM Journal on Computing, 1997, 26(5): 1343-1362.
[26] Wise M J. Running karp-rabin matching and greedy string tiling[J]. Software - Practice and Experience,1993.
[27] PRECHELT L, MALPOHL G, PHILIPPSEN M. Finding plagiarisms among a set of programs with JPlag[J]. Universal Computer Science, 2000, 8(11):1016-1038.
[28] GRANVILLE A. Detecting Plagiarism in Java Code[J]. Supervisor Yorick Wilks, 2002.
[29] RAGKHITWETSAGUL C, KRINKE J, MARNETTE B, et al. A picture is worth a thousand words: Code clone detection based on image similarity[C]. International Workshop on Software Clones, 2018: 44-50.
[30] 牛永洁,张成. 多种字符串相似度算法的比较研究[J].计算机与数字工程,2012,40(03):14-17.
[31] MYLES G, COLBERG C. Detecting Software Theft via Whole Program Path Birthmarks[M]. Springer Berlin Heidelberg, 2004.
[32] XIE X, LIU F L, LU B, et al. A software birthmark based on weighted k-gram [C]//2010 IEEE International Conference on Intelligent Computing and Intelligent Systems. IEEE, 2010.
[33] MATHEWS B W. Comparison of the predicted and observed secondary structure of T4 phnge lysozyme [J]. Biochim Biophys Acta, 1975, 405(2):442-451.

()
()

[1]	占永昆, 杨文飞, 张天柱. 基于关系建模的弱监督时序动作定位[J]. 中国科学技术大学学报, 2021, 51(10): 753-765.
[2]	梁启鹏, 朱巧慧, 康宇, 赵云波. 基于估计的无线网络化控制系统逼近控制策略[J]. 中国科学技术大学学报, 2021, 51(4): 327-334.
[3]	李慧聪, 傅孝明∗ . 基于局部等距嵌入的各向异性曲面网格生成[J]. 中国科学技术大学学报, 2020, 50(12): 1460-1471.
[4]	张文静，班志杰. 基于全局的引文网络影响力最大化算法[J]. 中国科学技术大学学报, 2020, 50(8): 1058-1063.
[5]	任敏，许玲，王峰，吴超. 基于知识推荐的校园百科平台研究[J]. 中国科学技术大学学报, 2020, 50(8): 1072-1076.
[6]	孙磊，张义宁，薛艳芳，乔立山，张丽梅. 自适应功能连接网络学习及其在脑疾病识别中的应用[J]. 中国科学技术大学学报, 2020, 50(8): 1102-1109.
[7]	白江波，杨阳，张文生. 基于改进CycleGAN的合成孔径雷达图像仿真[J]. 中国科学技术大学学报, 2020, 50(8): 1181-1186.
[8]	辛守宇，郑蕊蕊，周瑜，刘文鹏，贺建军. 训练过程中使用支持集信息的单样本学习算法[J]. 中国科学技术大学学报, 2020, 50(8): 1187-1192.
[9]	汪志华，康红梅. 使用三角网格上的样条求解带有非齐次边界的PDE[J]. 中国科学技术大学学报, 2020, 50(7): 901-905.
[10]	龚乐君，周佘海，程逸飞，高志宏，李华康. 单细胞RNA序列数据的PBMC相关细胞的识别[J]. 中国科学技术大学学报, 2020, 50(7): 1013-1018.
[11]	杜淑颖，杜鹏，丁世飞. 基于CNN的假冒域名识别方法研究[J]. 中国科学技术大学学报, 2020, 50(7): 1019-1025.
[12]	李永军，曹为华，凌强. 基于特征点轨迹的多目标跟踪算法[J]. 中国科学技术大学学报, 2020, 50(6): 726-732.
[13]	江琦，刘建宏，关勇，白浩波，刘刚，田扬超. 一种针对不完善数据的基于全变分约束的相干衍射算法[J]. 中国科学技术大学学报, 2020, 50(4): 418-427.
[14]	王旭辉，燕明叶，吴梦. 适用于等几何分析退化光滑插值曲面片构造[J]. 中国科学技术大学学报, 2020, 50(3): 335-342.
[15]	祁鹏，匡森. 基于抽样学习的开放量子系综时间最优控制[J]. 中国科学技术大学学报, 2019, 49(10): 775-780.

高教程序代码作业抄袭检测的方法研究与实践

Research and practice of plagiarism detection in program code assignments by college students

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价