METHOD OF RECOMMENDING DIAGNOSTIC TEST FOR USER EVALUATION
The present disclosure relates to a method of recommending a diagnostic test question for user evaluation by an electronic device, including: generating a first matrix indicating whether users answer all questions correctly; generating a second matrix based on the first matrix using knowledge tracing (KT); and selecting the diagnostic test question using Lasso regression based on the second matrix.
1 . A method of recommending a diagnostic test question for user evaluation by an electronic device, the method comprising:
generating a first matrix indicating whether users answer all questions correctly;
generating a second matrix based on the first matrix using knowledge tracing (KT); and
selecting the diagnostic test question using Lasso regression based on the second matrix.
2 . The method of claim 1 , wherein the first matrix is a sparse matrix, and the second matrix is a dense matrix.
3 . The method of claim 2 , further comprising training a model for predicting a user’s score using linear regression based on the diagnostic test question.
4 . The method of claim 3 , further comprising correcting a model for predicting the user’s score by using a time value taken for the user to solve the questions as a weight.
5 . The method of claim 4 , wherein the time value is an average value of times taken to solve questions for each part of the questions.
6 . The method of claim 5 , wherein the time value is a ranking value of the user compared to an average value of other users based on the average value.
7 . An electronic device for recommending a diagnostic test question for user evaluation, the electronic device comprising:
a communication module configured to communicate with a terminal;
a memory;
an artificial intelligence (AI) processor; and
a diagnostic test selection unit,
wherein the AI processor generates, through the memory, a first matrix indicating whether users answer all questions correctly, and
the diagnostic test selection unit uses knowledge tracing (KT) to generate a second matrix based on the first matrix, and selects the diagnostic test question using Lasso regression based on the second matrix.
8 . The electronic device of claim 7 , wherein the first matrix is a sparse matrix, and
the second matrix is a dense matrix.
9 . The electronic device of claim 8 , wherein the AI processor trains a model for predicting a user’s score using linear regression based on the diagnostic test question.
10 . The electronic device of claim 9 , wherein the AI processor corrects a model for predicting the user’s score by using a time value taken for the user to solve the questions as a weight.
11 . The electronic device of claim 10 , wherein the time value is an average value of times taken to solve questions for each part of the questions.
12 . The electronic device of claim 11 , wherein the time value is a ranking value of the user compared to an average value of other users based on the average value.