Electronic text document plagiarism recognition method based on similar string matching distance

Abstract

The invention relates to a method for identifying plagiarism of an electronic text document. The method mainly identifies the plagiarism through the approximate string matching distance of a subparagraph. The method to identify whether a document A plagiarizes a document B comprises the following specific steps: firstly, the approximate string matching distance and an approximate matching segmentof each paragraph of the document A in the document B are calculated; secondly, according to the approximate matching segment, the retroversion number and the forward jumping number are calculated; theretroversion number refers to the number of generation that the head part of the next approximate matching segment is positioned before the tail part of the last approximate matching segment or theto tal number of passing segments; the forward jumping number refers to the number of generation that the next approximate matching segment is behind the last approximate matching segment and at leasthasdistance of one segment with the last approximate matching segment or the total number of the alternate segments; and finally, the sum of the approximate string matching distance, the retroversionnum ber and the forward jumping number are summed; the sum is taken as the plagiarism distance of the document A to the document; and if the distance is less than certain threshold value, the documentA issuspected of plagiarizing the document B.

Description

technical field [0001] The invention belongs to the field of intelligent information processing and computer technology, in particular to a method for identifying plagiarism of electronic text documents by using a computer system. Background technique [0002] The use of electronic documents is becoming more and more common, such as students submitting experimental reports, computer programs, and electronic homework, unit employees submit work summaries, political learning experience, and scientific researchers write papers and reports. Since the plagiarism of electronic documents has the characteristics of convenience and speed, no trace of copying, and no need to submit in person, the problem of plagiarism has become more and more prominent in today's popularization of computer networks and office automation software, and it is easy to occur electronic plagiarism. Completion, misconduct in scientific research, coping with higher-level tasks, etc. The identification of pla...

AI Technical Summary

Problems solved by technology

The advantage of the statistical model is that it has strong anti-noise ability, but the disadvantage is that it is easy to misjudge and fail to recognize non-uniform plagiarism actions

The advantage of the matching model is that it has a strong ability to identify structural plagiarism and high recognition accuracy. The disadvantage is that it is sensitive to local features and requires a large amount of calculation.

Images