Learning Requirement Generation for ICT Systems

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing learning-type system automatic design technology for ICT systems requires a large amount of manual effort from engineers to generate learning requirements, as it necessitates a large number of system requirements for AI to acquire design knowledge, leading to a significant man-hour burden.

Innovation Solution

A learning requirement generation apparatus and method that automates the process by storing system requirements, acquiring and modifying them to generate learning requirements through addition or replacement of components, reducing the manual interpretation and preparation of case data needed for AI training.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a large number of learning requirements are prepared for AI to acquire design knowledge, then the reliability of design knowledge acquisition is improved, but the man-hour burden on engineers increases significantly

Engineering Contradiction:

Improvereliability of design knowledge acquisitionVSAvoidman-hour burden on engineers

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the learning requirement generation apparatus to automatically create learning requirements from actual case data without requiring manual interpretation and conversion by engineers. The apparatus autonomously processes the data transformation from actual cases to required learning data formats, eliminating the need for engineer intervention in this process.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual process of interpreting actual case data and converting it to requirement data format with an automated information processing system. The learning requirement generation apparatus uses computational algorithms to automatically transform data, substituting the manual mechanical work of engineers with automated digital processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If manual interpretation and conversion of actual case data is performed, then the accuracy of learning requirements is improved, but the productivity of the design process decreases

Engineering Contradiction:

Improveaccuracy of learning requirementsVSAvoidproductivity of design process

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The patent replaces manual interpretation and conversion processes with automated information processing. The learning requirement generation apparatus uses computational algorithms to accurately transform actual case data into learning requirements, maintaining precision while dramatically improving productivity by eliminating manual labor.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates copies of actual case data and automatically transforms these copies into learning requirements. By working with data copies rather than original cases, the system can perform multiple transformations and validations automatically, maintaining accuracy while increasing throughput and productivity.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20220366306A1Learning requirement generation apparatus, learning requirement generation method, and non-transitory computer readable medium

Publication Date: 2022.11.17 NEC CORP

AI summary

A learning requirement generation apparatus according to the present disclosure includes: a storage unit configured to store a system requirement group; a requirement acquisition unit configured to acquire the system requirement group from the storage unit and add the acquired system requirement group to an acquisition requirement group; and a learning requirement generation unit configured to generate a learning requirement by adding or replacing of a component on each of acquisition requirements that compose the acquisition requirement group.