Artificial intelligence and cognitive diagnosis based teaching resource recommendation algorithm

In the realm of advanced technology, deep learning capabilities are harnessed to analyze and predict novel data, once it has absorbed existing information. When applied to the sphere of education, this transformative technology becomes a catalyst for innovation and reform, leading to advancements in teaching modes, methodologies, and curricula. In light of these possibilities, the application of deep learning technology to teaching resource recommendations is explored in this article. Within the context of the study, a bespoke recommendation algorithm for teaching resources is devised, drawing upon the integration of deep learning and cognitive diagnosis (ADCF). This intricately constructed model consists of two core elements: the Multi-layer Perceptron (MLP) and the Generalized Matrix Factorization (GMF), operating cohesively through stages of linear representation and nonlinear learning of the interaction function. The empirical analysis reveals that the ADCF model achieves 0.626 and 0.339 in the hits ratio (HR) and the Normalized Discounted Cumulative Gain (NDCG) respectively due to the traditional model, signifying its potential to add significant value to the domain of teaching resource recommendations.