AI Specification Extraction From DUT Documentation for Test Planning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Test engineers face high overhead costs in time, training, and expertise due to the need to interact with multiple disparate software systems and documentations for developing test processes for devices under test (DUTs), leading to extended time to market for products.

Innovation Solution

A generative Artificial Intelligence (AI) system, such as large language models (LLMs), processes DUT documentation to generate test cases and refine specifications, summarizing and generating technical descriptions, and guiding users from documentation to test plans, supporting a specification-to-test platform.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If test engineers interact with multiple disparate software systems and documentations to develop test processes, then test process completeness and accuracy are improved, but overhead costs in time, training, and expertise increase

Engineering Contradiction:

Improvetest process completenessVSAvoidtime to market

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent combines multiple disparate software systems and documentation sources into a single integrated system. The system ingests documentation from various sources (word processing documents, PDFs, spreadsheets, presentations, 3D models, 2D models, images, videos) and processes them through a unified AI-based architecture that generates test cases, test procedures, and test specifications in one consolidated workflow, eliminating the need to switch between multiple tools.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an AI-based intermediary system that acts as a mediator between the input documentation and the output test artifacts. This intermediary uses natural language processing and generative AI to automatically extract requirements, generate test cases, and create test procedures, reducing the need for manual intervention and expertise across multiple specialized tools.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

Engineering Contradiction:

Improvetest process accuracyVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a universal system that performs multiple functions within a single platform. The system can ingest various documentation formats (word processing documents, PDFs, spreadsheets, presentations, 3D models, 2D models, images, videos), process them through AI analysis, generate test cases, create test procedures, and produce test specifications - all within one multi-functional system that replaces multiple specialized tools.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system provides self-service capabilities by automatically generating test artifacts from documentation without requiring extensive manual intervention. The AI-based system autonomously extracts requirements, identifies test scenarios, creates test cases, and generates test procedures, reducing the need for highly specialized expertise and extensive training.

Inventive Principle:

Principle #25Self-service

3Reliability

If manual test case development from documentation is performed, then test coverage is improved, but productivity decreases

Engineering Contradiction:

Improvetest coverageVSAvoidtest development speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent performs preliminary actions by automatically analyzing documentation and pre-generating test cases, test procedures, and test specifications before actual testing begins. The AI system processes the documentation in advance, extracts all necessary requirements, and prepares comprehensive test artifacts that ensure complete test coverage without manual effort during the execution phase.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical manual process of reading documentation and manually creating test cases with an AI-based automated system. The generative AI model substitutes human engineers' manual analysis and documentation work with automated natural language processing, significantly increasing productivity while maintaining or improving test coverage through comprehensive automated analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250356128A1Conversion from device documentation to technical specifications

Publication Date: 2025.11.20 NATIONAL INSTRUMENTS CORP

AI summary

Apparatuses, systems, and methods for one or more models (e.g., generative Artificial Intelligence (AI) and/or large language model(s)) to determine technical specifications based on input documentation of a device under test (DUT). The model(s) may divide the documentation into portions, iteratively identify technical specifications in the portions, format the specifications, and/or identify duplicative or related specifications for removal or consolidation.