The choice of textbooks and other resources that correspond to the age and scientific potential of schoolchildren in the education system is one of the urgent issues today. In this article, with the help of the "School corpus", at the level of lexical similarity of texts on the example of primary school, we are talking about the problem of determining the compatibility of educational materials recommended for schoolchildren with the intellectual potential of the student. Of course, there are different approaches to solving the problem. The article highlights a method for solving
the problem based on TF-IDF.Firstly, TF-IDF of texts is identified, then, they are converted into a vector representation, and the corresponding class of the given educational material "School corpus" is compared using the cosine text similarity algorithm. Based on the results of the calculation, it is determined whether the given educational material is suitable or not for the student's educational potential. The issue considered in the article is fully resolved on the example of primary school students.