In order to meet the needs of the digital media industry and the development needs of all sectors of society, this study improves the traditional digital media talent training model. This paper proposes an interdisciplinary talent cultivation model in digital media based on resource recommendation system, researches on recommendation algorithms of learning resources, researches on collaborative filtering algorithms based on user’s similar interest preferences as the goal, and further constructs learner models. Finally, we take the graduate students of digital media art majoring in digital media art in an art college as an empirical study to analyze the effect of the application of learning resource recommendation system in the talent cultivation of digital media art majors. The main conclusions drawn in this paper are that the P-value is greater than 0.05 in the five questions about the learning interest of learning digital media art majoring in digital media art, and the P-value is less than 0.05 in the five questions about the learning interest of learning digital media art, indicating that there is no significant difference between the experimental group and the control group in the learning interest of learning digital media art, and that the experimental group and the control group in the learning interest of learning digital media art majoring in digital media art after the experiments There is a significant difference in the learning interest of digital media art between the experimental group and the control group. The proportion of the experimental class was higher than that of the control class in terms of creative ability and open-mindedness and in terms of the improvement of self-confidence, which were 12 percentage points and 9 percentage points, respectively.