Automated Digital Asset Sizing via Polynomial Regression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual sizing of digital assets for consistent display in user interfaces is tedious and labor-intensive, requiring extensive time and resources, especially when dealing with large collections of assets with varying aspect ratios, leading to user confusion and inefficient layout design.
Innovation Solution
An automated system using polynomial regression analysis to adjust the size of digital assets based on predetermined height or width, creating training data structures and applying a polynomial equation to calculate optimal sizes for aesthetically pleasing and consistent layouts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual sizing of digital assets is performed to achieve consistent display, then aesthetic quality and consistency are improved, but time consumption and labor requirements increase significantly
Solution Approach 1:
The patent replaces the manual mechanical process of adding padding to digital assets with an automated computer vision system. The system uses machine learning models to automatically analyze assets, determine appropriate padding, and generate sized versions without human intervention, thus eliminating the trade-off between consistency quality and time investment
Solution Approach 2:
The system enables digital assets to size themselves automatically through self-learning algorithms. The machine learning model continuously improves its sizing capabilities by learning from processed assets, allowing the system to serve itself and eliminate the need for manual intervention while maintaining high display consistency
2Manufacturing precision
If manual padding is added to each digital asset to ensure consistent rendering, then layout aesthetic quality is improved, but device complexity and operational difficulty increase
Solution Approach 1:
The patent extracts the complex decision-making process of determining appropriate padding from the manual design process and encapsulates it within an automated machine learning system. This separates the complexity from the user操作流程, presenting a simple automated service that maintains high layout consistency without requiring users to understand the underlying complexity
Solution Approach 2:
The system creates a universal automated sizing solution that handles various types of digital assets (logos, images, graphics) with different formats and requirements through a single unified platform. This multi-functional system replaces multiple manual processes with one automated service, reducing operational complexity while maintaining consistency across diverse assets
3Manufacturing precision
If extensive manual preparation is performed on large collections of digital assets, then display consistency is achieved, but productivity and efficiency decrease
Solution Approach 1:
The system performs preliminary automated analysis and sizing of digital assets before they are deployed or displayed. By pre-processing assets through the machine learning model, the system ensures consistency is established upfront, eliminating the need for subsequent manual adjustments and significantly improving overall processing efficiency for large asset collections
Solution Approach 2:
The machine learning system operates continuously to process digital assets, maintaining a steady flow of automated sizing and preparation. This continuous operation eliminates interruptions and manual batch processing, sustaining high productivity levels while ensuring consistent output quality across all processed assets
Data Source
AI summary
Systems, methods, and storage media for automatically sizing one or more digital assets in a display rendered on a computing device are disclosed. Exemplary implementations may: select examples of digital assets to be displayed; create a set of training data structures; each train data structure including an aspect ratio of each digital asset and the predetermined height or width corresponding to the aspect ratio for that digital asset; perform polynomial regression analysis on the set of training data to determine a best fitted trend line and a corresponding polynomial equation; and apply the polynomial equation to at least one specific digital asset data structure to be displayed to thereby automatically calculate a size of the at least one specific digital asset as displayed.