A SYSTEM FOR TRACKING USER KNOWLEDGE BASED ON ARTIFICIAL INTELLIGENCE LEARNING AND METHOD THEREOF

摘要

The present specification provides a user knowledge tracking method of a user knowledge tracking system, comprising: inputting problem information to a kth encoder neural network, and generating attention information based on the problem information; inputting response information to a kth decoder neural network, and generating query data, which is information about a problem for which a user wants to predict a correct probability, based on the response information; and wherein the attention information is divided into a key and a value value, and is used as a weight for the query data to learn the user knowledge tracking system, wherein the user knowledge tracking system includes a plurality of encoder neural networks and a plurality of decoders. It may include a neural network.