【摘要】 随着作业数据的电子化,为了能够更好地监督学生的抄袭行为,本文研究了电子作业相似性检测的相关技术,分析了作业检测的流程,给出了文本内容提取、中文分词、文本特征提取和文本相似性计算4个部分的关键技术和实现算法,并在此基础上开发了一个作业相似性检测系统,实现了对作业文档的对比和检测,系统的实现为将来作业电子化进一步发展提供了技术指导和理论依据。更多还原

【Abstract】 With the electronic of student homework, in order to better monitor the students’ copying behavior, this paper studied the related technologies of similarity detection in electronic work, analyzed the work flow of electronic homework similarity detection, and presented the key technologies of text content extraction, Chinese word segmentation, text feature extraction and text similarity calculation. On the basis of this, a homework similarity detection system was developed to implement the comparison and detection of the homework documents, the realization of the system provided the technical guidance and theoretical basis for the better development of the electronic homework in the future.更多还原