semantic search

Summary. Automation of database indexing is a crucial component of modern database management systems that enhances search performance, scalability, and relevance in large-scale data environments. This paper explores the application of deep learning algorithms for building and optimizing vector indexes capable of automatic adaptation to changes in data structure and query patterns. An experimental comparison was conducted between traditional indexing methods (B-Tree, GIN in PostgreSQL) and vector-based indexing using Sentence-BERT embeddings implemented in FAISS and Milvus systems.

In modern conditions of society development, increasing degree and pace of integration of information technology achievements in the field of human life, traditional approaches to building information systems become too cumbersome or cease to be effective. One of the ways to solve this problem is to develop knowledge-based systems. The work is devoted to ontological modeling of a new subject area "travel organization". The ontology is considered in the context of knowledge exchange. The created travel ontology is quite modern and relevant today.

This paper describes the semantic search and storage of data of scientific and technical information system. The proposals of semantic structuring of the content of scientific and technical information system with explicitly structured representation of semantic relations between information objects contained in the system have been presented. The main components of the mathematical model of ontology of scientific and technical information system for semantic search and storage of scientific and technical information resource have been determined.