Genetic Algorithm Visualization Fitness Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing software visualization systems rely on predefined rules created by subject matter experts, which limits their adaptability to nuanced business needs and is resource-intensive for frequent rule creation, as each set of rules is specific to a predefined scenario and lacks the ability to automatically generate predictive models for assessing candidate visualizations.

Innovation Solution

A system and method that utilizes genetic algorithms and a training system to collect expert data, generating predictive models based on historical visualization data to assess the fitness of candidate visualizations, allowing for automatic adaptation to various business scenarios and reducing the burden on user resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If predefined rules created by subject matter experts are used to assess candidate visualizations, then the system can provide structured evaluation, but the adaptability to nuanced business needs deteriorates and resource consumption increases

Engineering Contradiction:

Improveevaluation consistencyVSAvoidadaptability to business needs

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system enables self-service by allowing the visualization assessment system to automatically learn and adapt to specific business scenarios through genetic algorithms and predictive modeling, eliminating the need for manual rule creation by experts while maintaining evaluation quality

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes parameters by transitioning from static predefined rules to dynamic predictive models that adapt their parameters based on scenario characteristics, business needs, and historical performance data

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If predefined rules are created for each specific scenario, then the evaluation can be tailored to that scenario, but the resource intensity increases for frequent rule creation

Engineering Contradiction:

Improvescenario-specific tailoringVSAvoidrule creation efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system replaces the mechanical process of manual rule creation with an automated computational system using genetic algorithms and machine learning models that generate and optimize assessment rules automatically

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs preliminary action by pre-training predictive models on historical visualization data and scenario characteristics, so that when new scenarios arise, the system can quickly adapt without starting from scratch

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If genetic algorithms are used to search through candidate visualizations, then the search capability is enhanced, but the computational complexity increases

Engineering Contradiction:

Improvesearch capabilityVSAvoidcomputational complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the complex search space by decomposing visualization assessments into multiple independent criteria (aesthetic quality, information effectiveness, technical feasibility) that can be evaluated separately and combined, reducing the complexity of the overall search

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11651233B2Candidate visualization techniques for use with genetic algorithms

Publication Date: 2023.05.16 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

According to one embodiment, a method for generating a plurality of candidate visualizations. The method may include receiving a scenario description. The method may also include collecting a plurality of expert data using a training system based on the received scenario description. The method may further include generating at least one predictive model based on the collected plurality of expert data in order to execute the at least one generated predictive model during an application of a plurality of genetic algorithms.