METHOD FOR AUTOMATED IDENTIFICATION OF LANGUAGE OR LINGUISTIC GROUP OF TEXT Russian patent published in 2017 - IPC G06F17/27 

FIELD: data processing.

SUBSTANCE: invention relates to automated identification of a language or a linguistic group (for example, Roman, German, Celtic, Slavic, etc.), which the analyzed text language belongs to. Method for automated identification of a language or a linguistic group of a text involves creating a set of identifying elements from a group of the most common verbs of each identified language or linguistic group and saving it on a data medium. Herewith the identifying elements used are grammatical forms and semantically significant parts of the verbs (roots or stems) of each identified language. Each identifying element of the set is compared with elements of the analyzed text. If matches of elements are observed, the language is identified by belonging of the matched elements to a certain language of the set.

EFFECT: technical result is providing the possibility of operation with multilingual texts and accurate identification of all the languages used in the analyzed text in case it includes forms of verbs from a set of identifying elements.

1 cl, 1 dwg