Automated Ontology Link Grading for Intelligence Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current intelligence gathering and analysis processes rely heavily on manual identification and evaluation of ontological relationships, which are time-consuming and inefficient, especially when dealing with complex information concepts and the need to determine hypothetical relationships lacking direct evidence.
Innovation Solution
A Question Answering (QA) system is enhanced to automatically identify and evaluate hypothetical ontological relationships by analyzing evidential support from various data sources, using machine learning techniques to generate questions, score confidence, and update ontologies with evidence-based links.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual identification and evaluation of ontological relationships is used, then reliability of analysis can be maintained through human judgment, but productivity decreases due to time-consuming processes
Solution Approach 1:
The patent replaces manual human evaluation of ontological relationships with an automated QA system that uses machine learning models to identify and verify hypothetical ontological links. The system automatically retrieves evidence from knowledge bases, evaluates relationships, and updates ontologies without requiring manual analysis, thereby resolving the contradiction between maintaining reliability and improving productivity.
2Productivity
If automated QA system is used to evaluate evidential statements, then productivity increases through automation, but measurement precision may decrease due to automated evaluation limitations
Solution Approach 1:
The patent implements feedback mechanisms where the QA system continuously refines its evaluations by analyzing confidence levels of automated determinations and adjusting its machine learning models accordingly. The system also allows for human review and correction of low-confidence evaluations, creating a feedback loop that maintains measurement precision while preserving productivity benefits of automation.
Solution Approach 2:
The system dynamically adjusts evaluation parameters and confidence thresholds based on the complexity and nature of each evidential statement. For simple statements, automated evaluation with standard precision thresholds is applied, while complex statements trigger enhanced evaluation protocols with adjusted parameters, allowing the system to maintain precision across diverse evaluation scenarios without sacrificing productivity.
3Measurement precision
If source grading measurement values are applied to evaluate reliability, then measurement precision improves through standardized grading, but device complexity increases due to additional evaluation dimensions
Solution Approach 1:
The patent segments the source reliability evaluation into distinct, manageable components including source identification, grading measurement value assignment, confidence level determination, and evidence retrieval. This segmentation allows the complex evaluation process to be broken down into modular functions that can be independently optimized and maintained, reducing overall system complexity while preserving measurement precision through standardized grading criteria.
Data Source
AI summary
Mechanisms for evaluating an evidential statement in a corpus of evidence are provided. An evidential statement is received for determining a level of confidence in a hypothetical ontological link of an ontology. A source of the evidential statement is identified and a grading of the source of the evidential statement is determined based on a source grading measurement value indicative of a degree of reliability and credibility of the source. An indication of trustworthiness of the evidential statement is generated based on the source grading measurement value. A representation of the indication of trustworthiness of the evidential statement is output in association with the evidential statement.