Research on the Cultivation and Promotion of College Students’ Legal Quality and Legal Knowledge Based on Deep Learning

Abstract

Under the new situation, it is urgent to strengthen the cultivation of the legal consciousness of young college students, which makes the research on the cultivation and promotion of college students’ legal quality and legal knowledge become very important. This article is aimed at studying the cultivation and promotion of college students’ legal quality and legal knowledge based on deep learning. This article first analyzes the legal quality and legal knowledge level of college students by proposing a questionnaire survey method, interview method, and interdisciplinary research method and establishes an explanatory structure model of the factors affecting the legal quality of college students; secondly, it introduces the basic theories of deep learning and explains its practical application; finally, the training rules of neural network are constructed through experiments, and the stage method of legal quality training based on BP neural network is introduced in detail. Considering that virtual reality technology has recently penetrated into the game industry and other fields, we have reason to believe that it will find ways to enter the legal knowledge training industry. The experimental results of this article show that the cultivation and improvement of college students’ legal quality and legal knowledge based on deep learning can reduce the momentary confusion and impulsiveness of college students. Among them, more than 80% of college students who know a little about the Constitution account for more than 80%, which also shows the importance of cultivating and improving the laws and regulations of college students. The results show that the method is accurate and fast.

Applications of Artificial Intelligence to Popularize Legal Knowledge and Publicize the Impact on Adolescents' Mental Health Status

“…Here, the proposed technique is used to predict the mental health status of legal students. Our proposed technique is performed and also matched with other standard techniques such as BP-neural network ( 34 ), ANOVA ( 35 ), and Bayesian-BP branch ( 36 ), and VGG-19 ( 32 ). The metrics mentioned above are determined with both the proposed and standard techniques.…”