Oil & gas contractor

Data Analytics for an Oil & Gas contractor

HomeCASESOil & gas contractor

[OUTSTAFFING | NOWAY]

Overview:

An Oil & Gas contractor needed to replace a heavy, manual workflow for extracting engineering tag numbers from a massive archive of technical PDFs.

Project in numbers

Industry: Oil & Gas
Location: Oslo, Norway
Time period: 2023-2024

TEAM

1 FTE:Data analytics
0.5 FTE:Project Manager

KEY TECHNOLOGY

Core Language & Performance:Python 3.12, concurrent.futures
Document & PDF Parsing:PyMuPDF, Camelot
Image & Text Processing:Tesseract OCR, Pillow
Data Manipulation & Export:pandas, openpyxl

01CHALLENGE

The customer is an Oil & Gas contracting company. They have accumulated a large number of PDF documents with various technical data. Engineering tag numbers had to be extracted from these documents. The initial solution was rather heavy and required much manual effort.

02SOLUTION

What we delivered

Modular architecture
Performance optimization with PyMuPDF and multiprocessing
Intelligent ENS tag recognition, OCR correction, slash expansion and master tag validation
Improved Excel output with formatting, hyperlinks, deduplication and missing-tag highlighting.

Our Data Analyst has helped the customer develop an end-to-end pipeline to automate the extraction. This solution ensures accurate identification of tag references and their association with corresponding documents and predefined actions.

03Results

Execution time reduced, scalable architecture, improved tag accuracy, structured Excel output, easier maintenance.

Do you have a different challenge?

Get a free expert advice from us

Collaboration AI Assistant

Answers based on our experience and solved cases