The NTI Competence Center Develops a Solution for the Intellectual Analysis of Large Arrays of Texts


In the NTI Competence Center based on Moscow State University in the direction of "Technologies for storing and analyzing big data", together with the Institute for Artificial Intelligence Problems of the Federal Information Center "Informatics and Management" of the Russian Academy of Sciences and Systems Analysis Technologies, LLC, a text analytics platform based on intelligent text collection and processing systems was developed in Russian and English languages. The project is the world's first industrial solution with cross-language analytics capabilities.

The developed solution can analyze and process any type of information presented in text form in Russian, English, Belarusian, Kazakh, and Tatar languages. The advantage of the project is the possibility of cross-language analysis of texts: it does not require a repeated search for the same information presented in documents in different languages and described in terms of different languages. The implementation of the solution will significantly simplify the work of specialists working with the analysis of large volumes of texts, and significantly increase the effectiveness of patent and research searches.

The solution allows the analysis of large volumes of scientific and technical information, the analysis of social networks to identify materials of undesirable topics, deviant behavior, the study of the psychological state of users and social tension of layers of society. Besides, the solution can perform the tasks of extracting information, analyzing medical documents, technical procurement information to translate large semi-structured arrays of texts in the form of structured data.

In the future, research centers, research and educational organizations, enterprises providing intellectual property protection services, and state corporations may become consumers of the development. Regulatory legal reference systems and consulting bureaus may also become potential consumers.

Ilya Sochenkov, Project Manager, researcher at the Center for Competence of the NTI based on Moscow State University for Big Data.
The symbiosis of several scientific approaches proposed by the President of the Russian Academy of Social Sciences, Doctor of Philosophy, Professor G.V. Osipov, makes it possible to describe the theme of documents through phrases and analyze the meaning of individual statements in the form of heterogeneous semantic networks. With modern methods of computer linguistics, distributive semantics, and machine learning, the created solution makes it possible to achieve higher accuracy and completeness in the tasks of text analytics.

The solution has already passed the stage of pilot implementations in such organizations as INFRA-M, NCR Rukont, NTIIM, Directorate of scientific and technical programs, Ministry of Education of the Russian Federation, which made it possible to collect a database of technological requests from customers in the field of text analytics.

The cost of developing and implementing a ready-made solution varies from 5 to 25 million roubles in each case, depending on the customer's need for integration services, customization, and deep software customization.


The NTI competence centers are divisions created on the basis of educational or scientific organizations. The centers conduct research and educational activities in consortium with leading technology companies in the interest of developing "end-to-end technologies". Among these technologies are big data, artificial intelligence, quantum technologies, new and portable energy sources, wireless communication technologies, and virtual and augmented reality technologies. A total of 14 such centers have been created. By 2021, the Centers' state funding in the amount of 10.3 billion roubles had been provided for. The operator of the NTI Competence Center project is RVC.

Search by name:

Search by date:

Select date in calendar
Select date in calendar