System Design Learning Device Iterative Rule Application
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing system design technologies face challenges in deriving concrete system configurations due to the variability in conversion rules and their application order, leading to inconsistent results and potential system design failures, especially when dealing with undefined parts and diverse system configurations.
Innovation Solution
A system design learning device and method that iteratively applies conversion rules to components of a design target system, evaluates the results, and learns from the evaluation values to select appropriate conversion rules, ensuring successful system design by determining evaluation values for each component and optimizing the selection of conversion rules based on learning data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conversion rules are applied to derive concrete system configuration, then system design capability is improved, but result consistency deteriorates due to variability in rule selection and application order
Solution Approach 1:
The patent introduces a feedback mechanism where the system evaluates the results of applying conversion rules and uses this evaluation information to guide subsequent rule applications. The evaluation value calculation and learning process create a closed-loop system that adjusts rule selection based on past performance, thereby improving both success rate and result consistency.
Solution Approach 2:
The patent changes the parameter of rule selection from static/random to dynamic/adaptive by introducing evaluation values and learning mechanisms. The system modifies which conversion rules are applied and in what order based on learned patterns from previous design attempts, making the process adaptive rather than fixed.
2Adaptability or versatility
If diverse system configurations are used during learning, then learning coverage is improved, but learning validity deteriorates when target system differs from learning configuration
Solution Approach 1:
The patent segments the system configuration into individual components and learns conversion rules for each component separately. By determining evaluation values for each component's conversion independently, the system can generalize component-level knowledge across different system configurations, maintaining learning validity even when the overall system structure varies.
Solution Approach 2:
The patent creates universal learning data structures that can apply to diverse system configurations. The evaluation value determination mechanism is designed to be configuration-agnostic, learning patterns that are applicable across different system types and structures, thereby achieving both broad coverage and maintained validity.
Data Source
AI summary
A system design learning device includes: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to: perform, with respect to a design target system whose system requirement is shown, system design in which application of a conversion rule to a component of the design target system is iterated until a design result of the system design is obtained; determine an evaluation value for the system design based on the design result; determine an evaluation value related to conversion of each component in the system design based on the evaluation value for the system design; and learn about selection of a component to which the conversion rule is applied based on learning data including the evaluation value related to the conversion of each component.