The invention discloses a
learning resource recommendation method and device, equipment and a storage medium, and belongs to the technical field of Internet. According to the method, recommendation can be carried out under the condition that no historical user exists, namely, the problem of
cold start is solved. In detail, according to the method, a
knowledge graph and an evaluation index are constructed respectively; according to the knowledge map, on one hand, learning resources are associated through courses, course labels, knowledge points and teacher users, on the other hand, examination and learning resources are associated through knowledge points contained in examination and courses, and the knowledge map rich in content is formed; the knowledge mastering condition of the training object can be evaluated through the constructed evaluation index, and the knowledge
weakness item of the training object is analyzed according to the knowledge mastering condition. When the method is used for recommendation, not only is the
knowledge graph combined, but also the course learning
record, the assessment
record and the knowledge weak item of the training object are considered, so that the accuracy and comprehensiveness of the recommended content can be greatly improved, and the recommendation effect is good.