AI-Guided Test System Specification from RFQ Documents

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 to develop a test system specification for a device under test, leading to extended time to market.

Innovation Solution

A generative AI-based system, such as a Large Language Model (LLM), assists in converting a request for quote into a test system specification by summarizing documents, interacting with users through question-answer sessions, and generating assets like code and diagrams to refine the specification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If test engineers use multiple disparate software systems to develop test system specifications, then comprehensive test development capabilities are achieved, but overhead costs in time, training, and expertise increase significantly

Engineering Contradiction:

Improvetest development capabilitiesVSAvoidoverhead costs in time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent combines multiple disparate software systems into a single integrated system that can handle various test development tasks (specification generation, test case creation, test sequence development, measurement abstraction) through a unified interface, eliminating the need for engineers to switch between multiple tools

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The integrated system provides multi-functional capabilities that previously required separate specialized tools, allowing a single system to perform specification generation, test case development, test sequence creation, and measurement abstraction tasks across different test engineering roles

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If test engineers interact with multiple disparate software systems, then comprehensive test development is achieved, but training and expertise requirements increase

Engineering Contradiction:

Improvetest development capabilitiesVSAvoidtraining and expertise requirements

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges multiple specialized software systems into one unified platform, reducing the complexity of learning and mastering multiple disparate tools while maintaining comprehensive test development capabilities through integrated functionality

Inventive Principle:

Principle #5Merging (Combining)

3Adaptability or versatility

If multiple disparate software systems are used for test development, then various test engineering roles can be supported, but time to market extends

Engineering Contradiction:

Improvesupport for test engineering rolesVSAvoidtime to market

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent integrates multiple software systems that support different test engineering roles (design engineer, test architect, validation engineer, production test engineer) into a single unified system, enabling seamless workflows and eliminating time losses from context switching between tools

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary actions by automatically generating test specifications, test cases, and test sequences from requirements, reducing the manual effort and time required for test development across all engineering roles

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250355790A1Converting a Request for Quote into a Specification for a Test System

Publication Date: 2025.11.20 NATIONAL INSTRUMENTS CORP

AI summary

Apparatuses, systems, and methods for generative Artificial Intelligence (AI)/Large Language Model (LMM) assisted test system specification based on an initial input of a request for quote (RFQ) or request for information (RFI). An RFQ/RFI document can be provided as input to the AI/LLM model. The AI/LLM model can also receive selection and detection criteria and user-provided input associated with the RFQ/RFI document as guidance for the generative AI/LLM process. The AI/LLM model generate a test system specification from the RFQ/RFI document, with the test system specification fulfilling one or more criteria identified from the RFQ/RFI document.