Well Completion Selection Using NLP and Historical Schematics

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The current well completion design process is inefficient and not scalable due to manual selection from thousands of equipment variations, leading to sub-optimal designs and requiring months to finalize, with historical data access being cumbersome.

Innovation Solution

A system utilizing machine learning and natural language processing to classify, convert, and cluster unstructured well completion documents, generating structured data for informed design decisions, leveraging a cloud-based workflow management system for efficient equipment selection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual selection from thousands of equipment variations is used, then equipment selection can be made based on local knowledge, but the process becomes inefficient and time-consuming

Engineering Contradiction:
Improveequipment selection qualityVSAvoiddesign finalization time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of equipment selection with an automated computer-based system that uses machine learning models and natural language processing to analyze historical data and generate completion design recommendations, thereby reducing design time while maintaining or improving selection quality

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces a computer-based workflow management system as an intermediary between historical completion data and engineers, using NLP to extract insights from unstructured documents and ML models to generate recommendations, facilitating efficient equipment selection without direct manual review of all variations

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If historical data is manually researched and accessed, then relevant insights can be obtained, but the process becomes cumbersome and inefficient

Engineering Contradiction:
Improvehistorical data insightsVSAvoiddata access process
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent enables the system to automatically access, process, and extract insights from historical completion data without requiring manual research by engineers. The NLP and ML components self-service the data retrieval and analysis functions, making historical insights readily available

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of researching and accessing historical data with an automated computer-based system that uses NLP to parse unstructured documents and ML models to extract relevant insights, dramatically improving ease of operation

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If traditional document exchange workflow is used, then collaboration between engineers can be maintained, but the process becomes inefficient and not scalable

Engineering Contradiction:
Improvecross-domain collaborationVSAvoiddesign process efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent creates a universal computer-based workflow management system that handles multiple functions including data storage, NLP processing, ML analysis, and collaboration tools, replacing the need for separate document exchange processes and improving both collaboration and productivity

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent replaces the mechanical document exchange workflow with an automated digital system that uses NLP and ML to process information across domains, enabling scalable collaboration without the inefficiencies of manual document sharing

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4413488B1Well completion selection and design using data insights
Publication Date: 2026.03.11 SERVICES PETROLIERS SCHLUMBERGER SA
  • EP4413488B1 patent drawingFigure 1
  • EP4413488B1 patent drawingFigure 2A
  • EP4413488B1 patent drawingFigure 2B

AI summary

Methods and systems are provided for automating well completion selection and design using machine learning and natural language processing. The present disclosure describes a method for designing a well completion, comprising: i) collecting and storing a historical dataset comprising unstructured data related to prior well completions; ii) identifying a plurality of unstructured schematic documents related to prior well completions that are a part of the historical dataset of i); iii) processing each given unstructured schematic document of the plurality of unstructured schematic documents of ii) to generate structured data corresponding to text of the given unstructured schematic document; iv) associating the structured data corresponding to text of the respective unstructured schematic documents of iii) with different well contexts as part of a database; and v) presenting a graphical user interface to a user for designing a well completion, wherein the graphical user interface presents structured data stored in the database of iv) for insight in designing the well completion.