Knowledge point recommendation method and device and storage medium

Abstract

The invention provides a knowledge point recommendation method and related equipment, which comprehensively considers the preference of a user for knowledge points and the cognitive state of the user for the knowledge points, and further recommends the knowledge points which are more suitable for the learning level of the user and conform to the preference of the user to the user. The method comprises the following steps: determining a user embedding vector corresponding to a target user, knowledge point embedding vectors corresponding to N knowledge points and exercise question embedding vectors corresponding to M exercise questions; determining the interest preference of the target user to each knowledge point in the N knowledge points according to the user embedding vector and the knowledge point embedding vector; determining a cognitive state of the target user for each knowledge point in the N knowledge points according to the user embedding vector and the exercise question embedding vector; determining a knowledge point recommendation degree corresponding to each knowledge point in the N knowledge points according to the interest preference of each knowledge point and the cognitive state of each knowledge point; and recommending the knowledge points to the target user according to the knowledge point recommendation degree corresponding to each knowledge point in the N knowledge points.

Description

【Technical field】 [0001] The present application belongs to the recommendation field, and in particular relates to a knowledge point recommendation method, device and storage medium. 【Background technique】 [0002] Online learning is gradually on the rise, and the Chinese MOOC platform has gradually become the main way of online learning. Users can freely choose the courses and knowledge they are interested in to learn on the MOOC platform. The online MOOC platform applies personalized course recommendation technology, but it mainly recommends courses that users may be interested in based on the user's historical learning records. [0003] Most of the existing knowledge point recommendation technologies are based on the user's historical behavior, focusing on the accuracy of the recommendation results, mainly based on the user's feature representation and knowledge point feature representation to predict a specific user's preference for a specific knowledge point. Recommen...

AI Technical Summary

Problems solved by technology

[0004] However, just recommending knowledge points to users based on their preference will lead to the recommended knowledge points often exceeding the user's learning ability, which cannot well meet the user's learning needs.

Images