Infrastructure Bill of Materials Generation From Application Terms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating and ordering computer infrastructure require manual processes that rely on expert knowledge, which can be time-consuming and less accurate due to reliance on past experiences, lacking automation and precision in translating user application-level requirements into hardware bills of materials.
Innovation Solution
Implementing a machine learning-based system using a generative adversarial network (GAN) to automate the translation of user application-level requirements into infrastructure bills of materials, utilizing a discriminator and generator neural networks to ensure accuracy and efficiency in determining the necessary hardware and connectivity needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual processes relying on expert knowledge are used to translate application-level requirements into hardware bills of materials, then expert knowledge and past experiences can be leveraged, but the process becomes time-consuming and less accurate
Solution Approach 1:
The patent replaces manual expert analysis with an automated machine learning system comprising a generator neural network and a discriminator neural network. The generator translates application-level requirements into hardware bills of materials, while the discriminator validates the outputs, substituting the mechanical expert review process with an automated computational system that operates faster and with consistent accuracy.
2Extent of automation
If manual expert processes are used for translating requirements into bills of materials, then flexibility in handling complex cases is maintained, but automation and precision are reduced
Solution Approach 1:
The patent implements a feedback mechanism where the discriminator neural network evaluates the outputs of the generator neural network and provides feedback signals. This feedback loop allows the system to learn from validation results and improve its translations, achieving both high automation and precision through iterative refinement driven by the discriminator's assessments.
3Adaptability or versatility
If manual processes are used, then adaptability to past experiences is maintained, but the ability to adapt to changes in infrastructure capabilities is reduced
Solution Approach 1:
The patent employs dynamic neural network models that can adapt to changing infrastructure capabilities through continuous training and learning. The generator and discriminator networks are designed to learn from new data and evolving infrastructure specifications, enabling the system to maintain high productivity while adapting to changes in hardware capabilities and technological advancements.
Data Source
AI summary
A system can train a generator neural network to produce a trained generator neural network of a generative adversarial network, wherein the trained generator neural network is configured to output a bill of materials in response to receiving functional requirements for a computer system. The system can train a discriminator neural network to produce a trained discriminator neural network of the generative adversarial network, wherein the trained discriminator neural network is configured to output whether the bill of materials received from the trained generator neural network satisfies the functional requirements for the computer system. The system can produce an output bill of materials from the generative adversarial network based on the functional requirements. The system can store the output bill of materials in the system.