为了有效地抑制VB程序代码抄袭现象,提出一个基于N-gram的VB源代码抄袭检测方法,利用N-gram来表示VB代码文件,以提高检测准确率。同时采用基于Fork-Join框架的并行计算技术来提高算法效率。通过与MOSS系统的对比实验,证明基于N-gram的VB源代码抄袭检测方法检测准确率高于MOSS系统,并具有处理大规模数据的能力。%With the rapid development text, the text plagiarism becomes more of information networks and the widespread use of electronic serious. In order to effectively curb the plagiarism phenome- gram to represent the VB source code files to improve the detection accuracy, and using the parallel computing technology based on Fork-Join to improve the efficiency of the algorithm. The experiment results showed our code plagiarism detection method achieves higher accuracy than the MOSS system, and has the ability to handle large-scale data.
展开▼