Skip links

Uncover Hidden Insights with The Power of Structured Data

dStill is an advanced data extraction platform that unlocks structured data from unstructured documents, providing businesses with high-quality data rapidly. With the power of human-assisted machine learning, it enables the capture of structured data from various document types, processes natural language and tabular data, creates searchable documents, and delivers data in any desired format. By combining technology with human expertise, dStill empowers businesses to extract valuable insights from large volumes of unstructured data, revolutionizing how they leverage information.

0 +
ML models with +90% F-score to predict and expedite data extraction
0 M+
Disparate images spanning decades
0 x
annual reduction in CAPEX for data processing
0 %
Increase efficiency by capturing more content per document and improve overall quality
0 %
Speed improvement in title abstract production

Landmen

Don't let image-based data hold you back. dStill unlocks the power of courthouse and proprietary records, transforming them into actionable insights for understanding liabilities and seizing opportunities.

Geologists

“If I have seen further than others, it is by standing upon the shoulders of giants.” Every great exploration idea is a derivative of an imprint from our past. That imprint is in a 1952 spacing order. Mud log. Exhibit. dStill structures unstructured data and surfaces valuable insights “hidden in plain sight.”

Mineral Buyers

Hey, Unit Declarations containing names, addresses, and ownership decimals - let’s structure them at scale.

Brokers

Document classification and “related documents” are at the heart of creating run sheets and title opinions. Lease provisions are integral to HBP analysis and pughed out acreage analyses. Put the robots to work for you to get the details out of the documents.

Analysts

There’s no place for you here. Joking. Not joking.

Engineers

AFEs are a proxy to LOE and IRR. AFEs are not standardized within companies, let alone across companies. AFEs and documents like them can be structured at scale to give you information that you may not have in your OBO or wells files.

Our online cloud-based data extraction platform, dStill, empowers you with:

Structured Data Extraction

Capture structured data from various unstructured document types, including TIFF, JPG, and PDF.

Document Processing

Process natural language documents, such as contracts, and tabular data, like forms and tables.

Searchable Magic

Create "Google-like" searchable documents for easy access and analysis.

Data Integration Mastery

Deliver data in any desired format or integrate it into your existing applications to support thorough analysis.

Revolutionary Unstructured Data Extraction

dStill is a game-changer in the field of structured data extraction. Born out of our determination to overcome skepticism, we have developed a scalable solution to unlock valuable insights from unstructured PDF and TIFF files. By aggregating data from diverse sources, our robust infrastructure automates the processing and extraction of structured data, empowering businesses with unparalleled intelligence.

Combining the power of artificial intelligence with human expertise, we have overcome challenges and achieved exceptional scalability and cost-effectiveness. With millions invested in the platform, dStill transforms vast amounts of public image data into structured formats, enabling businesses to harness the true potential of their data. Experience the revolution of data extraction with dStill by Oseberg.

How It Works

unstructure

Source Data

• Source data is ingested into dStill

OCR1

Image Processing

• Image preparation (rotation correction, size resampling, etc.) to ensure OCR quality.
• OCR extracts text from a document image and inserts it into a new searchable PDF document version of the original

dataextract

Data Extraction

• Document classification
• Supervised ML Models (select domains)
• Technology-assisted data extraction

structure

Data Export

• Save to database
• Exportable to Excel format for easy viewing
• Data can be delivered in any format or integrated directly into applications

Source Data

• Source data is ingested into dStill

Image Processing

• Image preparation (rotation correction, size resampling, etc.) to ensure OCR quality.

• OCR extracts text from a document image and inserts it into a new searchable PDF document version of the original

Data Extraction

• Document classification

• Supervised ML Models (select domains)

• Technology-assisted data extraction

Data Export

• Save to database

• Exportable to Excel format for easy viewing

• Data can be delivered in any format or integrated directly into applications