A.Yu. Novikov, M.G. Stolyarov

One of the most sought-after procedures in the field of automated text processing, formation of arrays is the full-text search. The basis for the construction of full-text search method is to develop a way of presenting the image of the title of document in a search query and how to determine the information value of a text document in accordance with the request. Used in existing methods of finding simplified conceptual model of the text focused on lexical semantics, the interpretation suggested search query as a set of words that define the desired concept. Determining the value of the information document in this case is reduced to some form of accounting numbers and the «weight» of words in a text document. It is clear that this approach cannot account for the relationship between the concepts of the subject area that is objectively present in the text, which does not improve the accuracy of search results. In this paper we propose a method for determining the value of a text document on the basis of its initial semantic analysis which allows to take into account the relationship between the concepts of the applied domain described in the text.