基于机器学习的自动阅卷关键技术研究

Research on key technologies of automatic scoring based on machine learning

当今,随着人工智能、云计算、物联网、大数据等高新技术的迅速崛起,传统的教育理念、教学方式、教学生态正在被机器学习、教育大数据、智慧教育等新理念不断地改变,这也促使教育现代化向着教育信息化深度发展。而教育教学活动中非常重要的一个环节就是考试,这是老师了解学生在某一阶段学习过程中对所学知识掌握程度的重要检验,阅卷则成为该过程中必不可少的组成部分。传统的人工阅卷不仅工作量大而且效率相对较低,某些情况下受阅卷老师主观因素影响,难免出现评分偏差。提出了新型基于机器学习的自动阅卷系统架构模型,并通过运用机器学习、自然语言处理、图像识别等技术实现了计算机自动阅卷的功能。

Nowadays,with the rapid rise of high and new technologies such as artificial intelligence,cloud computing,Internet of Things,and big data.Traditional education concepts,teaching methods,and teaching ecology are constantly being changed by new concepts such as machine learning,educational big data,and wisdom education.This also promotes the in-depth development of educational modernization towards educational informatization.Examination is a very important link in education and teaching activities,which is an important test for teachers to understand the degree of students’mastery of the knowledge in a certain stage of learning process,and paper marking becomes an indispensable part of the process.The traditional manual marking is not only heavy in workload but also relatively low in efficiency.In some cases,it will inevitably be affected by the subjective influence of the marking teacher.A new machine learning based automatic grading system architecture model has been proposed through research,and realizes the function of automatic marking by using machine learning,natural language processing,image recognition and other technologies.