Automated Technical Requirements Generation via NLP

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

There is a technical challenge in efficiently generating technical requirements documents from business requirements documents without the need for expert human intervention, which hinders the streamlined development of software applications and other technologies.

Innovation Solution

A computer-implemented method that extracts section headers and content from business requirements documents, uses entities detection and topic modeling to map entities to technical terms, and employs machine learning to generate a summary arranged by key topics, thereby creating a technical requirements document automatically.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual expert analysis is used to convert business requirements to technical requirements, then accuracy and quality are improved, but time consumption and cost increase significantly

Engineering Contradiction:

Improveaccuracy of requirements conversionVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an intermediary system comprising NLP models, entity detection models, and topic modeling algorithms that act as a mediator between business requirements and technical requirements. This intermediary automatically extracts entities, identifies key topics, and generates technical requirements from business requirements documents, eliminating the need for direct manual expert analysis while maintaining conversion quality

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical system of manual expert analysis with an automated computational system using machine learning models. The entity detection model, topic modeling algorithm, and technical term mapping system substitute human experts' cognitive processes, enabling automatic conversion of business requirements to technical requirements without manual intervention

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated processing is used to convert business requirements to technical requirements, then productivity and speed are improved, but accuracy and quality may deteriorate

Engineering Contradiction:

Improveconversion speedVSAvoidaccuracy of requirements conversion

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent implements feedback mechanisms where the system continuously refines its entity detection and topic modeling based on the structure and content of business requirements documents. The technical term mapping uses feedback from identified key topics and entities to accurately generate technical requirements, ensuring that automated processing maintains high accuracy while achieving fast conversion speeds

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary actions by pre-training entity detection models and topic modeling algorithms on domain-specific data before actual conversion tasks. The system pre-establishes mappings between business terminology and technical terminology, enabling accurate and rapid conversion without compromising quality during the actual processing phase

Inventive Principle:

Principle #10Preliminary action

3Reliability

If expert human intervention is required for requirements conversion, then quality is improved, but device complexity and operational difficulty increase

Engineering Contradiction:

Improvequality of technical requirementsVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent enables the system to serve itself by implementing self-contained entity detection, automatic topic identification, and autonomous technical term mapping capabilities. The system processes business requirements documents independently without requiring external expert intervention, maintaining high quality through automated decision-making algorithms while reducing operational complexity

Inventive Principle:

Principle #25Self-service

4Adaptability or versatility

If manual processes are used for requirements conversion, then adaptability to complex scenarios is improved, but productivity and efficiency decrease

Engineering Contradiction:

Improvehandling complex requirementsVSAvoidconversion efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements dynamic processing where the entity detection model and topic modeling algorithm adapt their parameters and thresholds based on the complexity and characteristics of each business requirements document. The system dynamically adjusts its processing depth and detail level to handle complex scenarios effectively while maintaining high conversion efficiency through automated operations

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20240338659A1Machine learning systems and methods for automated generation of technical requirements documents

Publication Date: 2024.10.10 OPEN WEAVER INC

AI summary

A computer-implemented method for generating a technical requirements document from a business requirements document includes extracting section headers and section content from the business requirements document, extracting entities from the section content using an entities detection model, mapping the entities to technical terms using a master data dictionary, identifying key topics using topic modelling based on the section content, generating a summary of the section content by using the technical terms and section content as inputs to a machine learning model, and arranging the summary based on the key topics to generate the technical requirements document.