Weighted Measure Evaluation Space for Fewer Pairwise Comparisons
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating measures require excessive user effort in pairwise comparisons, making it impractical to gather sufficient data for accurate goodness distributions.
Innovation Solution
A system that plots measures on an evaluation value space, applies user-defined weights to coordinate axes, extracts dissimilar measure pairs, and conducts a relative evaluation questionnaire to generate a goodness distribution chart, reducing the number of required comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pairwise comparison method is used to estimate goodness distribution, then measurement precision of evaluation is improved, but user effort and time required increase excessively
Solution Approach 1:
The patent extracts only the essential information needed for goodness distribution estimation by using utility function evaluations at specific points rather than requiring complete pairwise comparisons. This selective extraction approach maintains measurement precision while significantly reducing the quantity of user input required.
Solution Approach 2:
The patent introduces a utility function as an intermediary mathematical model that translates sparse user evaluations into comprehensive goodness distribution estimates. This intermediary allows the system to infer overall measure quality from limited direct user feedback, eliminating the need for exhaustive pairwise comparisons.
2Reliability
If pairwise comparison method is used to gather evaluation data, then reliability of evaluation results is improved, but device complexity and operational difficulty increase
Solution Approach 1:
The patent enables the evaluation system to serve itself by automatically generating and presenting utility function evaluations that users can quickly assess. The system handles the complex data processing and goodness distribution calculation autonomously, requiring users only to provide simple utility evaluations without needing to understand or perform complex pairwise comparisons.
3Adaptability or versatility
If multiple evaluation items are considered to achieve balanced solutions, then adaptability of evaluation is improved, but complexity of evaluation space increases
Solution Approach 1:
The patent transforms the complex multi-dimensional evaluation space into a simplified utility function parameter space. By changing the representation from multiple separate evaluation items to a unified utility function with scalar outputs, the system maintains comprehensive evaluation capability across multiple dimensions while reducing the perceived and actual complexity of navigating the evaluation space.
Data Source
AI summary
A measure evaluation assistance method includes plotting results of evaluation of measures by evaluation items on a first evaluation value space having the evaluation items as coordinate axes, setting weights for respective evaluation items based on a degree to which a user emphasizes each of the evaluation items, and generating a second evaluation value space by reflecting the weight on each of the coordinate axes of the first evaluation value space, extracting combinations of measures based on degrees of similarities of the measures in the second evaluation value space, and creating a distribution chart indicating a range in which evaluation by the user is high and a range in which the evaluation by the user is low in the first evaluation value space, based on a result of relative evaluation by the user of goodness or badness between measures included in each of extracted combinations, and outputting the distribution chart.