Research indexJournal article
МоделюваннЯ сИстемИ розпізнаваннЯ тА аналізУ текстовиХ даниХ
Пількевич, Лобанчикова, Shulga and 1 other
1 Jan 2013
NobleIDark:/48914/w1/20260521/83D04EFDDOI10.15587/1729-4061.2013.16388
МоделюваннЯ сИстемИ розпізнаваннЯ тА аналізУ текстовиХ даниХ
Пількевич, Лобанчикова, Shulga and 1 other · 2013 · Subscription
NobleIDark:/48914/w1/20260521/83D04EFDDOI10.15587/1729-4061.2013.16388
The full text is at the publisher
You can read the abstract here, or open it at the publisher.
Abstract
Modern innovative technologies led to the active development of electronic information resources. Large storages of electronic data created in information and communication systems require their protection from unauthorized access. One of the ways of information protection is recognizing and identifying confidential information in text documents. Classification of documents according to their significance is necessary for identifying the type of information, and, depending on the degree of significance, determining the level of its availability for corresponding categories of users. The text information recognition system occupied a prominent place among the systems of information and communication structures protection. The purpose of the research is developing an automated system for detecting the confidential information in text documents for automation of the experts’ work at recognition and analysis of the text data. The paper gives the automated system for detecting the confidential information in text documents, and the software that allows uploading of the text or text document for its further analysis and determining the degree of its significance. Microsoft Visual C # 2010 was used as the software programming environment. In the proposed program the total account of all and hazardous (key) words has been made, the database has been applied and the text itself with further evaluation of its confidentiality has been analyzed