METHOD OF AUTOMATIC CLASSIFICATION OF CONFIDENTIAL FORMALIZED DOCUMENTS IN ELECTRONIC DOCUMENT MANAGEMENT SYSTEM Russian patent published in 2018 - IPC G06F17/30 G06F17/21 

FIELD: information technology.

SUBSTANCE: method of automatic classification of confidential formal documents in electronic document management system consists in allocation and analysis of formal part of received document (requisites), conversion of informative part of the document into natural language text, transforming the words of transformed document into basic word forms, discarding insignificant words, implementation of words weight calculation in the document in accordance with the frequency of their appearance, and thus the formation of document characteristics. At the training stage, predicate systems for identifying the characteristics of the text of received document are formed by a set of manually classified documents and are stored in database. When classifying a document on the basis of classification characteristics obtained, a decision on the relevance of the document to each of information fields is made with the help of database and corresponding confidentiality label is determined for it.

EFFECT: automation of confidential formalized documents classification in the electronic document management system by areas of information responsibility and by confidentiality labels.

1 dwg