基于Simhash算法的作业查重系统设计

为了减少大学生完成作业过程中的抄袭问题,提高大学课程教学的过程性考核效果。基于自然语言处理中常用的Simhash算法,设计开发了作业查重系统。该系统以Spring、SpringMVC、MyBatis(SSM)为开发框架,前端开发采用Bootstrap技术。先采用IKAnalyzer分词器对输入的作业文本进行分词处理,再使用Simhash算法计算文档的签名,最后通过计算汉明距离得到作业的查重结果。该系统能够对学生提交的作业进行查重,帮助教师客观地评价学生的作业完成情况,有效防止作业抄袭现象,从而营造良好的学风环境,促进学生的健康发展。

Design of Course Assignment Duplicate Checking System Based on Simhash Algorithm

In order to reduce the plagiarism problem in students’ homework and improve the process quality of teaching in universities, we design and develop a course assignment duplicate checking system based on the Simhash algorithm that is commonly used in natual language processing. The system is designed and developed based on Spring, Spring MVC, and MyBatis (SSM) framework, while the user interface is designed using Bootstrap. Ikanalyzer is firstly used to segment the input text, and then Simhash algorithm is used to calculate the signature of the document. Finally, the duplicate check result of the course assignment is obtained by calculating the Hamming distance. The system can check the homework submitted by students, which helps the teachers to evaluate students’ homework accurately, and to prevent the phenomenon of homework plagiarism effectively. As a result, it will help us to create a good learning environment and promote the healthy development of students.