Fine Arts College, Shenyang University, Shenyang 110044, China.
Comput Intell Neurosci. 2022 Jul 1;2022:4709146. doi: 10.1155/2022/4709146. eCollection 2022.
With the popularity of the Internet and the advancement of information technology, more and more people are accepting the teaching and sharing of knowledge through the digitalization of information. The widespread adoption of 5G technology has pushed online learning even further into the mainstream. However, because online teaching does not have the drawback of being intuitive like classroom teaching, teachers' assessments of students' learning situations are less accurate. As a result, how to effectively evaluate students' academic performance in the context of 5G wireless network technology is a pressing issue that must be investigated. By processing these heterogeneous large-scale learning records and integrating multiple perspectives to analyze this learning record information to identify students' learning behaviors, this study proposes an integrated analysis algorithm based on artificial intelligence information technology. The possible learning outcomes of students are predicted based on their current learning situation, so teachers can provide auxiliary teaching strategies to students who may have learning difficulties based on the predicted information. The method proposed in this article uses information technology to predict students' grades, and the analysis shows that the method is very effective. In this article, different grades of classification methods are used to analyze and predict the whole students. All grade classification methods are effective in describing decision rules. No matter what grades classification method is used, the error rate of students' grades distribution is predicted to be below 40%.
随着互联网的普及和信息技术的进步,越来越多的人通过信息数字化来接受教学和知识分享。5G 技术的广泛采用甚至进一步将在线学习推向主流。然而,由于在线教学不像课堂教学那样直观,教师对学生学习情况的评估就不太准确。因此,如何在 5G 无线网络技术环境下有效地评估学生的学业成绩,是一个亟待研究的问题。本研究通过处理这些异构的大规模学习记录,并整合多个角度来分析这些学习记录信息,以识别学生的学习行为,提出了一种基于人工智能信息技术的综合分析算法。该算法根据学生当前的学习情况预测学生可能的学习成果,以便教师可以根据预测信息为可能有学习困难的学生提供辅助教学策略。本文提出的方法使用信息技术来预测学生的成绩,分析表明该方法非常有效。本文使用不同的成绩分类方法对全体学生进行分析和预测。所有的成绩分类方法都有效地描述了决策规则。无论使用哪种成绩分类方法,对学生成绩分布的错误率预测都低于 40%。