The paper considers the method of processing information in natural language latent-semantic analysis, which analyzes the relationship between the collection of documents and the words they meet. The analysis of the user request was made in Yandex and Google systems. The term frequency parameters are considered - an indicator of the frequency or density of occurrences of a term in a specific document, as well as an indicator of the ratio between the use of the term and the total number of words in the document and the inverse document frequency - the inverse frequency of the document with respect to the query, that is the ratio of the entire collection of documents in the search database to those, that contain a given term.