Abstract:
The modern labor market demands that educational institutions prepare specialists capable of
effectively responding to rapidly changing professional standards and technologies. In this regard, the use
of innovative approaches to adapt educational programs has become a key factor. This study is dedicated to
developing a methodology for using heterogeneous knowledge graphs to create a recommendation system
aimed at bridging the gap between existing educational courses and the dynamically changing requirements
of the labor market. The central element of the study is the use of knowledge graphs to aggregate and analyze
diverse data on skills, job vacancies, and educational courses. Knowledge graphs not only structure large
volumes of information but also visualize complex connections between various educational modules and
professional requirements. This approach fosters a deeper understanding of how educational programs can
be adjusted to match the market specifics. An important aspect of the study is the application of multilingual
semantic similarity algorithms to analyze and match skills. These algorithms play a key role in determining
the degree of correspondence between the skills listed in educational programs and courses, and those
required for specific job vacancies. The use of natural language processing techniques allows not only
capturing explicit keyword matches, but also recognizing deep semantic connections, which is an integral
part of accurate matching in educational and professional domains. The results of the study demonstrate that
the proposed methodology can effectively analyze the multilingual relationships between educational and
professional skills, which improves personalized courses and job recommendations. Our study contributes to
the literature by proposing a new methodology for building recommendations that improves the accuracy of
personalized educational and career recommendations, and facilitates the adaptation of educational programs
to dynamic changes in the labor market.
