The article presents a system capable of generating new ontologies or supplementing existing ones based on articles in Ukrainian. Ontologies are described and an algorithm suitable for automated concept extraction from natural language texts is presented.Ontology as a technology has become an increasingly important topic in contemporary research. Since the creation of the Semantic Web, ontology has become a solution to many problems of understanding natural language by computers. If an ontology existed and was used to analyze documents, then we would have systems that could answer very complex queries in natural language. Google’s success showed that loading HTML pages is much easier than marking everything with semantic markup, wasting human intellectual resources. To find a solution to this problem, a new direction in the ontological field, called ontological engineering, has appeared. This direction began to study ways of automating the generation of knowledge, which would be consolidated by an ontology from the text.Humanity generates more data every day than yesterday. One of the main levers today in the choice of technologies for the implementation of new projects is whether it can cope with this flow of data, which will increase every day. Because of this, some technologies come to the fore, such as machine learning, while others recede to the periphery, due to the impossibility or lack of time to adapt to modern needs, as happened with ontologies. The main reason for the decrease in the popularity of ontologies was the need to hire experts for its construction and the lack of methods for automated construction of ontologies.This article considers the problem of automated ontology generation using articles from the Ukrainian Wikipedia, and geometry was taken as an example of the subject area. A system was built that collects data, analyzes it, and forms an ontology from it.