GUI Rule Conformance With ML-Guided Usability Tuning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Web page designers often adjust graphical user interface (GUI) attributes at their discretion, leading to potential usability issues and resource consumption due to inefficient design, particularly when they lack familiarity with design guidelines, causing slow navigation and interpretation by users.
Innovation Solution
A GUI design management server uses a machine learning model to generate proposed GUIs that conform to design rules and enhance usability by receiving inputs from designers, incorporating user demographics, and adjusting attributes to improve conformance and usability scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If web page designers adjust GUI attributes at their discretion without familiarity with design guidelines, then design flexibility is improved, but usability and conformance to design rules deteriorate
Solution Approach 1:
The system implements automated feedback by evaluating GUI designs against design rules and usability criteria, then providing recommendations to designers. This feedback loop maintains design flexibility while ensuring usability standards are met, resolving the contradiction between designer discretion and usability reliability.
Solution Approach 2:
An intermediary evaluation system acts as a mediator between designer intent and usability requirements. This system automatically assesses designs against multiple criteria and provides guided recommendations, allowing designers to maintain flexibility while achieving usable outcomes through the intermediary's structured guidance.
2Reliability
If web page designers iteratively adjust GUI designs to achieve usability, then usability is improved, but resource consumption and time increase
Solution Approach 1:
The system performs preliminary evaluation of GUI designs against design rules and usability criteria before final implementation. By automatically assessing multiple design aspects in advance and providing targeted recommendations, it reduces the need for extensive iterative adjustments, thereby improving usability while minimizing design time and resource consumption.
Solution Approach 2:
The system efficiently evaluates multiple design parameters simultaneously (layout, color, typography, spacing) and identifies optimal adjustments. By analyzing and recommending changes to multiple parameters in one evaluation cycle rather than sequential iteration, it achieves usability improvements more quickly with less time and computational resources.
3Reliability
If complex iterative design processes are used to achieve usable GUIs, then usability is improved, but device and server resource consumption increases
Solution Approach 1:
The system implements self-service evaluation where the GUI design automatically undergoes assessment against design rules and usability criteria without requiring manual intervention or complex iterative processes. This automated self-evaluation reduces the computational resources and energy required compared to human-driven iterative design, while still achieving usable outcomes through systematic criterion-based assessment.
Data Source
AI summary
Some implementations described herein provide apparatuses and techniques related to graphical user interface design conformance and useability. The apparatuses and techniques include a graphical user interface design management server including a graphical user interface design conformance and a measure of useability application. The graphical user interface design management server may receive one or more attribute changes related to a design of a graphical user interface. The graphical user interface design management server may then access a storage device containing graphical user interface design rules and determine a degree of conformance of a graphical user interface generated using the attribute changes to the graphical user interface design rules. Further, and using machine learning techniques, the graphical user interface design management server may determine one or more additional changes to the attributes that improve the measure of useability of the graphical user interface for anticipated users of the graphical user interface.


