METHOD OF RECOGNIZING NATURE OF TEXT CONTENT Russian patent published in 2024 - IPC G06N3/00 G06F17/40 

FIELD: machine learning.

SUBSTANCE: invention relates to a method of recognizing the nature of text content. Method comprises steps of: generating an initial set of text data sources containing content of a predetermined subject, wherein each source is assigned at least one content nature mark and at least one content subject mark; automatically performing parsing of each source in the set of sources to identify the author of the source and identify links to third-party sources, wherein sources not included in available set of sources are considered as third-party sources, wherein links to third-party sources are the names of third-party sources and url-links to third-party sources; searching for said third-party sources by identified links; searching for third-party sources by identified authors; selecting sources from found third-party sources, subject of which is close to at least one of the content subjects of the initial set of sources; automatically assigning to selected sources corresponding content subject labels; forming an additional set of sources from the selected sources; each source from the additional set of sources is automatically assigned at least one content character label by comparing this source with sources from the initial set, having the same subject matter as this source; and generating a training set of sources by combining the initial set of sources and the marked additional set of sources.

EFFECT: high accuracy and speed of obtaining the end result.

4 cl