Data-Driven Artificial Intelligence Recommendation Mechanism in Online Learning Resources

Abstract

This study attempts to reveal the intelligent recommendation mechanism of online learning resources. The “multimodal data fusion” aspect is adopted, illustrating online learning resource modeling, learning preference modeling, learning preference evolution, and referral engine smart design. Multimodal learning resources are key constituents of multidimensional intelligent recommendation services. The learner model that integrates multimodal preference data is the key to implementing smart recommendations. Learning preference evolution is a key factor in sustaining learner model robustness. The intelligent recommendation engine is the technical guarantee for developing an intelligent recommendation. Providing learning resources is an important part of online learning services, which mediate online learning processes. Intelligent recommendation, as an effective personalized servicing strategy, recommends differentiated, personalized, and precise learning resources to learners, thereby promoting the effectiveness of online learning performance. This study constructs a framework that reveals an intelligent recommendation mechanism for online learning resources.

Keywords

• data-driven
• online learning resource
• intelligent recommendation