Optimization of Balanced Distribution of Online and Offline Biochemistry Teaching Resources Utilizing Machine Learning Algorithms and Big Data

Abstract

Utilizing machine learning algorithms, the current conventional optimization methods for balanced allocation of teaching resources are enhanced. These methods primarily focus on predicting the current network resource load capacity without calculating the adaptation factor, often leading to suboptimal allocation outcomes. To address this issue, we propose a balanced allocation optimization approach for online and offline biochemistry education resources, taking into account the importance degree and big data. This approach calculates the probabilistic importance of teaching resources and the user delay in distinct modes to identify the optimal balanced allocation of teaching resources. Our experimental results comfirm that this approach achieves a higher resource utilization rate and a more desirable allocation effect compared to previous methods.