Automated Design Ranking for Generative Exploration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Generative design processes are hindered by the time-consuming manual evaluation of vast numbers of designs, leading to the omission of potentially preferred designs and selection of non-optimal options due to the prohibitive effort required to explore the design space.
Innovation Solution
A computer-implemented method for automatically ranking designs based on user preferences, using a ranking subsystem that determines positive and negative examples, computes scores, and generates a ranked list to facilitate efficient exploration of the design space through a graphical user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the number of designs generated by the generative design application is increased to provide a more comprehensive design space, then the completeness of the design space is improved, but the time required for manual evaluation increases prohibitively
Solution Approach 1:
The patent replaces the manual mechanical evaluation process with an automated computer-based ranking system. The system uses algorithms to automatically score and rank designs based on user preferences, substituting human manual scrutiny with computational evaluation that can process thousands of designs efficiently without proportional time increases.
Solution Approach 2:
The system enables self-service evaluation where the computer automatically performs the evaluation and ranking of designs without requiring user intervention for each design. The automated ranking system independently assesses designs against user preferences and generates ordered results, freeing users from the time-consuming manual evaluation task.
2Loss of time
If the number of designs is limited to reduce evaluation time, then the evaluation time is reduced, but the design space becomes incomplete and may omit preferred designs
Solution Approach 1:
The automated ranking system replaces manual evaluation, enabling comprehensive assessment of large design spaces without time penalties. This substitution allows the system to maintain complete design spaces while avoiding the prohibitive time costs of manual review by using efficient computational scoring methods.
3Manufacturing precision
If manual evaluation of designs is performed to ensure selection of optimal designs, then the quality of design selection is improved, but the complexity and time consumption of the process increases
Solution Approach 1:
The patent replaces complex manual evaluation processes with automated computational ranking systems. These systems use algorithms to objectively score designs based on user preferences, eliminating the complexity and subjectivity of manual assessment while maintaining or improving selection quality through consistent, repeatable evaluation criteria.
Solution Approach 2:
The system transforms the evaluation process by changing from qualitative manual judgment to quantitative automated scoring. Designs are assigned numerical scores based on user preferences, converting subjective evaluation into objective parameter-based ranking that simplifies the selection process while improving consistency and quality.
Data Source
AI summary
In various embodiments, a ranking application automatically ranks designs included in a design space based on user preference(s). The ranking application determines that a first design included in the design space is a first positive example of user preference(s). The ranking application then computes a score associated with a second design that is also included in the design space based on a first attribute value and a second attribute value. The first attribute value is associated with both the first design and an attribute and the second value is associated with both the second design and the attribute. Subsequently, the ranking application orders the designs based on the first score and a second score associated with the second design to generate a ranked list of designs. The ranking application then displays the ranked list of designs via a graphical user interface to facilitate exploration of the design space.