基于CNN-LSTM神经网络的在校大学生教育成果预测

A Study on the Prediction of College Students’Educational Achievements Based on the CNN-LSTM Neural Network

当下,人工智能正积极应用于教育领域,但对于高校教育成果的预测研究仍存在一定的空白。为了使因材施教的实施更加合理,实现培养学生核心素养的目标,本实验应用问卷调查法,对学生过去一学年的情况进行收集,评价问卷的效度与信度,保证问卷的正确与有效性,并将质性评价适当转换为量化评价,将质性与量化研究相结合,进而建立神经网络模型,实现对学生未来取得成果的预测,辅助高校实现教育的可预测性,及时把控教育成果,适当进行相应的教育措施调整。

At present,artificial intelligence is being actively applied in the field of education,but there is still a gap in researches on the prediction of educational achievements in colleges and universities.In order to make the implementation of teaching students in accordance with their aptitude more reasonable and achieve the goal of cultivating students’core literacy,this experiment uses questionnaires to collect their situation in the past academic year,evaluate the validity and reliability of the questionnaires,and ensure the correctness and effectiveness of them.In addition,the qualitative evaluation is appropriately converted into the quantitative evaluation,and qualitative and quantitative researches are combined to establish a neural network model.Then,students’future achievements can be predicted to assist colleges and universities in realizing the predictability of education.Meanwhile,educational achievements can be controlled in time for possible corresponding adjustment of educational measures.