Digital scientific platform “Aggregator of unstructured geological and field data”: architecture and basic models of data extraction

Abstract

The article describes the project being developed for the digital scientific platform “Aggregator of unstructured geological and field data”, which could potentially be important for the oil and gas industry. The use of new intelligent technologies within the framework of this project will significantly improve the efficiency of processing, storage and use of geological and field information contained in various text sources, mainly in field reports.The main goal of developing a digital scientific platform is to integrate heterogeneous information about the objects of subsurface exploration, which is extracted from reports on deposits of the Republic of Tatarstan. This will create a consolidated database that will become the basis for making informed decisions in the oil and gas sector. The project of the digital scientific platform includes the development of architecture, algorithms and software solutions based on modern methods of text processing and data mining.

Keywords

• data collection and analysis
• field reports
• database
• automation
• big data
• text data processing
• unstructured data
• information extraction