Knowledge Base Concept Conflict Resolution via Graph Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current medical diagnosis, patient health management, and patient treatment recommendation systems suffer from concept conflicts due to aggregated data sources using specific terms, leading to noisy synonyms, ambiguous abbreviations, and incorrect relationships, resulting in erroneous results and degrading the quality of these systems.

Innovation Solution

A method is implemented to automatically detect and cleanse erroneous concepts in an aggregated knowledge base by generating a graph data structure representing a selected concept, analyzing for concept conflicts, and splitting distinct concepts within the knowledge base, using natural language processing to identify canonical names and synonyms, and applying graph analysis to resolve conflicts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data is aggregated from multiple sources to improve system functionality, then the quantity and variety of information increases, but concept conflicts and data quality deteriorate

Engineering Contradiction:

Improvequantity of informationVSAvoiddata quality

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The patent segments the aggregated data into individual concept entities and represents them as separate nodes in a graph data structure. This allows each concept to be independently analyzed and processed, enabling the system to identify and resolve concept conflicts while maintaining the overall aggregated knowledge base.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary processing layer that uses graph analysis and natural language processing to mediate between the aggregated data sources and the final output. This intermediary analyzes relationships between concepts, identifies conflicts, and resolves ambiguities before presenting results to users.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If manual construction of knowledge bases is used to ensure accuracy, then data quality improves, but system complexity and development time increase

Engineering Contradiction:

Improvedata qualityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements self-service mechanisms where the system automatically detects concept conflicts, analyzes relationships between concepts using graph analysis, and resolves ambiguities without manual intervention. The natural language processing capabilities enable the system to self-correct and maintain data quality autonomously.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent incorporates feedback loops where the analysis results are used to continuously improve the knowledge base. The system monitors concept relationships, identifies conflicts, and automatically adjusts the knowledge structure to prevent future conflicts, creating a self-improving system.

Inventive Principle:

Principle #23Feedback

3Productivity

If automatic processing is implemented to reduce manual effort, then productivity increases, but detection precision of concept conflicts decreases

Engineering Contradiction:

Improveprocessing efficiencyVSAvoiddetection precision

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent transforms the concept analysis problem into a different dimension by representing concepts as nodes and relationships as edges in a graph data structure. This dimensional transformation enables the use of graph analysis algorithms that can automatically detect concept conflicts with high precision while maintaining processing efficiency.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent replaces manual mechanical analysis with automated computational methods using natural language processing and graph analysis algorithms. These computational approaches maintain high detection precision by systematically analyzing concept relationships without human error or fatigue.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10331659B2Automatic detection and cleansing of erroneous concepts in an aggregated knowledge base

Publication Date: 2019.06.25 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A mechanism is provided for automatically detecting and cleansing erroneous concepts in an aggregated knowledge base. A graph data structure representing the concept present in a portion of the natural language content is generated. The graph data structure is analyzed to determine whether or not the graph data structure comprises one or more concept conflicts in association with a set of nodes in the graph data structure, the one or more concept conflicts are associated with the set of nodes if two or more nodes represent separate and distinct concepts. Responsive to determining that there are one or more concept conflicts due to there being two or more nodes representing separate and distinct concepts, the two or more nodes are split into separate distinct concepts within the knowledge base.