Course recommendation system based on a heterogeneous information network and deep learning

Abstract

The invention relates to a course recommendation system based on a heterogeneous information network and deep learning. The course recommendation system comprises a course heterogeneous information network node vectorization module, an effective sub-network extraction module and a deep learning course recommendation module based on an effective sub-network, According to the course recommendation system based on the heterogeneous information network and deep learning provided by the invention, on the basis of the DeepFM deep learning model, effective sub-network information in the heterogeneousinformation network is introduced, and an independent system structure is designed for the effective sub-network, so that the recommendation effect of the course recommendation system is better and more accurate.

Description

technical field [0001] The invention relates to a course recommendation system based on heterogeneous information network and deep learning, which belongs to the field of computer artificial intelligence. Background technique [0002] With the popularity and rapid development of the Internet, the Internet has become the most important channel for people to obtain information. The Internet can break the limitations of time and space, enabling people to obtain information more efficiently, and online education meets the needs of people to obtain knowledge efficiently from the Internet, and learners can access the educational resources they are interested in without leaving home. Due to the surge in the number of courses caused by the development of online education, online education platforms are also facing information overload. When choosing courses, learners can feel overwhelmed by the sheer number of courses. Therefore, how to help learners choose appropriate courses to ...

AI Technical Summary

Problems solved by technology

[0007] The technical solution of the present invention solves the problem of insufficient use of auxiliary information by traditional recommendation systems and how to effectively model auxiliary information, and provides a course rec...

Images