• Products
  • Projects
  • Free software
  • R&D
  • About us
Automation of enterprise business processes and workflow with E1 Evfrat.
With a throughput rate of 30 waybills, 50 invoices, or 100 insurance policies per minute, our robot Cognitive Forms is able to recognize, read, and transmit over 80 types of documents.
From requirements to results: purchase requisitions, sourcing event schedules, tenders, contracts in the modular suite Cognitive Lot.
Integrated solutions for nomenclature systems, directories and classification hierarchies — from statement of objectives to loading of data into your ERP.
Able to read and recognize passports with MRZ and without, driver's licences, images and copies thereof — within only 2 seconds with 99% quality. It works faster with NVIDIA CUBA and can be embedded in any system as a .NET component.
Everything in its place. Documents, power point presentations, video and audio — quick and secure deployment on MS SQL and Oracle in full conformity with the State Standards of archival storage.
Intelligent text recognition system. Program for optical recognition of printed text and its conversion into editable form.
Back

Cognitive Technologies
117312, Russia, Moscow
Pr. 60-letiya Octyabrya, 9, office 709

  • +7 (495) 956-90-06
  • +7 (499) 135-5088 (phone/fax)
  • +7 (499) 135-5510 (phone)
  • +7 (499) 135-8968 (phone)
Feedback
Cancel
Send
Menu

Sector

Industry

Year

2000

Objective

To increase the efficiency of expert work on issues relating to the R&D and technological development of the enterprise, in particular to expand the scope of data gathering and enhance their quality

Customer

Norilsk Mining Company, JSC

Area

Analytics

Products and technologies involved

The following products and technological solutions underlay the functions of the system:

  • the Astarta Information & Analytics system;
  • a technology for recognizing documents' metadata "on the run" as they are entered;
  • a technology for indexing and normalizing text;
  • a patent analysis technology which harnesses the method of Morphological classifier;
  • an interface for integration with external statistical suites for implementing low-level statistical methods.
  • Results

    There was designed and introduced a Data Mining & Analytics Suite that provided decision support services for decision-making on the enterprise's R&D programs and technological development. The solutions and technologies obtained in the course of this project male up a technological base for designing information systems of that class for large enterprises.

    Methods

    Development of a usable and effective toolkit for the gathering, processing, storage, and analysis of information (in the first instance on patents granted) describing various aspects of the operation of Norilsk Mining Company from estimating the prospects of new technological solutions finding industrial application to devising marketing tactics and strategy.

Cognitive Technologies' major products enable faster processing of large volumes of data
Anton Emelyanov
CEO
Cognitive Technologies

Norilsk Mining Company

Development and introduction of a Data Mining & Analytics Suite for Norilsk Mining Company, JSC

About the customer

Besides being the world's largest producer of nickel, palladium, platinum, and copper, Norilsk Nickel also produces cobalt, rhodium, silver, gold, iridium, ruthenium, as well as selenium, tellurium, and sulfur. The core specializations of the group of enterprises are the exploration, mining, and processing of minerals, and the production, marketing, and sale of non-ferrous and precious metals.

About the project

The Data Mining & Analytics Suite provides the following capabilities:

  • gathering of data for subsequent analysis and their preliminary processing, which includes the following operations:
    • entry of paper documents (with recognition of the entire text or only some fragments by the method of drag & drop recognition "on the run," i.e., by dragging a selected text fragment into the text field for it to be recognized automatically);
    • import of streams of documents from websites (e.g., news feeds, documents from designated websites);
    • extraction of documents from external databases (e.g., electronic libraries operated on external media);
    • attributive indexing of documents entered;
    • categorization of news feeds.
  • analytic functions and low-level groups of functions:
    • the search, selection, and filtering of patents and documents of other types located on the Internet or in a local storage (wildcard search, right and left truncation, composite queries involving the use of logical operators and factoring in the morphology of the Russian and English languages);
    • methods of statistical analysis (e.g., AR, SMA, ARIMA adjusted for seasonality and interventions, correlation analysis).
  • high-level group of functions:
    • dynamic analysis of a data object (e.g., choosing aspects of development, searching for alternatives for each aspect, modelling and forecasting, evaluating results);
    • statistical analysis of a data object (e.g., identification of patenting patterns for a data object in terms of firms, countries, etc. using the International Patent Classification).
  • functionality for presenting the results of analysis:
    • automatic generation of summary figures: tables, 2-D and 3-D charts, diagrams, pie charts, etc.;
    • export of figures into the word processor;
    • automatic generation of reports preconfigured using a template.

Fig. Chart of the Data Mining & Analytics Suite

The results achieved

The Data Mining & Analytics Suite allowed the client to automate the following operations:

  • analysis and forecasting aimed at estimating the development prospects of technologies and technological solutions using the methods of patent analysis;
  • employees' exercise of access, within their access rights, to operational documents they require, e.g., internal standards, patents, project specifications;
  • entry of documents by means of batch scanning and import from designated websites.