Geological Knowledge Consolidation via Confidence Scoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The petroleum geology domain faces challenges in accurately consolidating evidence from multiple sources due to conflicting results and inaccuracies in knowledge extraction, leading to misvaluation of hydrocarbon reservoirs and inefficient resource allocation.

Innovation Solution

A system that automatically detects inconsistencies and contradictions in geological descriptions, generates confidence levels for consistent matches, and reduces reliance on experienced geologists by using keyword pattern matching and geological relation inference to merge and update geological resource database entries.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If knowledge extraction techniques are applied to consolidate evidence from multiple sources, then information consolidation is achieved, but conflicts and inconsistencies are introduced

Engineering Contradiction:

Improveinformation consolidation efficiencyVSAvoiddata accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent introduces an intermediary confidence scoring mechanism that mediates between multiple knowledge sources. Each piece of extracted knowledge is assigned a confidence score based on source reliability, consistency with existing knowledge, and extraction quality metrics. This intermediary scoring system resolves conflicts by quantitatively weighing evidence from different sources rather than简单地 accepting or rejecting contradictory information.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback loops where extraction results are continuously evaluated against existing geological knowledge bases. When conflicts are detected, the system adjusts extraction parameters, re-evaluates confidence scores, and iteratively refines the consolidation process. This feedback mechanism ensures that productivity gains from automated extraction do not compromise data reliability.

Inventive Principle:

Principle #23Feedback

2Extent of automation

If automated knowledge extraction is used, then reliance on experienced geologists is reduced, but conflicting results and contradictions increase

Engineering Contradiction:

Improveautomation levelVSAvoidinformation accuracy

Core Design Contradiction:

Extent of automationVSLoss of information

Solution Approach 1:

The patent replaces the mechanical system of manual geological analysis with an automated extraction and validation system. Natural language processing algorithms automatically extract geological knowledge from unstructured text, while confidence scoring mechanisms and consistency checks replace human expert judgment. This substitution maintains information accuracy by implementing multiple validation layers that mimic and enhance human expert review processes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a composite knowledge representation that combines structured data from multiple sources with confidence scores and validation metadata. This composite structure integrates diverse information types (geological reports, sensor data, literature) while maintaining traceability to original sources and enabling automated conflict detection and resolution.

Inventive Principle:

Principle #40Composite materials

3Quantity of substance

If multiple information sources are consolidated, then comprehensive knowledge is achieved, but conflicts and contradictions among sources increase

Engineering Contradiction:

Improveknowledge volumeVSAvoidknowledge consistency

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The patent merges multiple information sources into a unified knowledge representation framework that preserves source identity and reliability characteristics. The confidence scoring system combines evidence from diverse sources (geological surveys, sensor data, literature) while weighting each source according to its proven reliability. This merging process achieves comprehensive knowledge coverage while maintaining consistency through quantitative confidence evaluation.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS11163751B2Resource exploitation management system, method and program product

Publication Date: 2021.11.02 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A resource exploitation management system, method and a computer program product therefor. A description of new geological evidence for a geological resource is received, e.g., as one or more triples describing the evidence. Keywords in the description are matched against keywords in representations in a geological resource database. Geological relations are inferred from the descriptions and matched against predefined geological relations from the geological resource database. Consistent triple matches are merged with the geological resource database. The confidence level for merged matches is updated in the geological resource database.