从抄袭的定义和法律规定出发,在分析比较国内外主要的论文抄袭判定方法基础上,提出存在的问题和改进策略,最后给出一种基于段落相似度的论文抄袭判定算法。此算法可以检测出抄袭者将论文的段落顺序打乱或者将段落文字打乱重新组合的情况,并将确认抄袭和疑似抄袭的抄袭论文和原论文的相应内容输出,方便用户进一步审查。
Based on the definition of plagiarism and the law, we put forwards the existent problems and strategies for improvement by analyzing the main methods to deal with plagiarism judgment both at home and abroad, and give a method to judge plagiarism according to the similarity between paragraphs. In this way we can find out the cases in which plagiarists reform the articles by rearranging the order of paragraphs or the words of one paragraph, and output the papers which are confirmed or suspected as plagiarisms and the corresponding content in the original in order to make it convenient for users to check.