基于特征融合的主观题智能阅卷算法研究

Research on Subjective Intelligent Marking Algorithm Based on Feature Fusion

为了实现主观题智能阅卷,本文提出了一个基于多特征融合的主观题智能阅卷算法。首先,分别设计两种算法:关键词相似度算法和语义相似度算法,计算学生答案和标准答案之间的关键词相似度和语义相似度;然后,以题目的题型和科目作为特征值,分别计算出两相似度的权值,并利用权值计算出学生答案的得分实验表明,本文提出的算法,能有效主观题智能阅卷算法的准确性,具有较好的应用前景。

In order to realize intelligent marking of subjective questions,this paper proposes an intelligent marking algorithm for subjective questions based on multi-feature fusion.First,two algorithms are designed respectively:keyword similarity algorithm and semantic similarity algorithm,to calculate the keyword similarity and semantic similarity between students'answers and standard answers.Then,using the question type and subject as the eigenvalue,calculate the weight of the two similarities respectively,and the final scores of students'answers were calculated by using the two weights.The experiment shows that the intelligent marking algorithm proposed in this paper is effective and accurate,and has a good application prospect.