AI Assurance Case Assessment for Faster Software Certification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional software certification processes in aerospace and other safety-critical industries are costly, labor-intensive, and lack flexibility, particularly when integrating emerging technologies like AI and ML, leading to inefficiencies and scalability issues due to complex assurance cases and subjective arguments.

Innovation Solution

An AI-assisted certification system using hierarchical contract networks (HCNs) and confidence networks to automatically synthesize, validate, and assess assurance cases, providing probabilistic reasoning and quantified confidence levels, along with user interfaces for informed decision-making.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional manual software certification processes are used, then comprehensive safety evaluation can be achieved, but the process becomes costly, labor-intensive, and time-consuming

Engineering Contradiction:

Improvesafety evaluation qualityVSAvoidcertification time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical certification processes with an automated computer-based system that uses AI/ML models, natural language processing, and automated reasoning engines to evaluate assurance cases, thereby reducing certification time while maintaining or improving evaluation quality

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary automated assurance case evaluation system that acts as a mediator between developers and regulators, using standardized assurance case formats and automated reasoning to bridge the gap between manual processes and efficient automation

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If traditional manual software certification processes are used, then comprehensive safety evaluation can be achieved, but the process becomes costly and labor-intensive

Engineering Contradiction:

Improvesafety evaluation qualityVSAvoidcertification cost

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The patent replaces expensive manual expert review processes with automated AI/ML-based evaluation systems that can process assurance cases at lower marginal costs, reducing overall certification expenses while maintaining evaluation rigor

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses standardized assurance case templates and reusable evaluation models that can be copied and applied across multiple certification projects, reducing the need for custom manual analysis in each case and lowering costs

Inventive Principle:

Principle #26Copying

3Reliability

If traditional software certification processes are used, then thorough assessment can be performed, but flexibility is reduced when integrating emerging technologies like AI and ML

Engineering Contradiction:

Improveassessment thoroughnessVSAvoidflexibility for emerging technologies

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic assurance case evaluation system that can adapt its reasoning models and evaluation criteria based on the specific characteristics of emerging technologies being certified, allowing thorough assessment while maintaining flexibility for new technology types

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent creates a universal assurance case framework that can handle both traditional software and emerging technologies like AI/ML systems using the same standardized processes, thereby maintaining assessment thoroughness while improving adaptability

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Reliability

If complex assurance cases with subjective arguments are used, then comprehensive evaluation can be achieved, but scalability is reduced

Engineering Contradiction:

Improveevaluation comprehensivenessVSAvoidcertification scalability

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces subjective human argument evaluation with automated reasoning engines and AI/ML models that can objectively analyze assurance cases at scale, maintaining comprehensive evaluation while enabling scalability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms subjective qualitative arguments into quantifiable parameters and metrics that can be processed automatically by computers, enabling comprehensive evaluation to be performed at scale through automated parameter analysis

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12518017B2Artificial-intelligence-assisted certification system

Publication Date: 2026.01.06 ROCKWELL COLLINS INC

AI summary

An artificial-intelligence-assisted (AI-assisted) certification system includes an argumentation processor and an assurance case processor. The argumentation processor is configured to generate an argumentation pattern. The assurance case processor is configured to obtain the argumentation pattern from the argumentation processor, to automatically generate an assurance case based on one or more argumentation patterns, to determine evidence indicative of premises in the argumentation pattern, and to automatically assess the assurance case based on the evidence.