Machine Learning UI Ranking for Wearable Screen Space Constraints

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Mobile electronic devices have limited screen space, making it difficult for users to find relevant information quickly, as existing solutions do not effectively prioritize and recommend relevant user interface elements based on user interactions and environmental data.

Innovation Solution

A system using a locally stored machine learning model on wearable devices to rank user interface elements by relevance, incorporating user behavior data and environmental signals to provide personalized recommendations, leveraging APIs from third-party applications to gather and curate data for relevance scoring and UI element display.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If all available information is displayed on the mobile device screen, then the user has access to complete information, but the screen space is insufficient and the user cannot quickly find relevant information

Engineering Contradiction:
Improveinformation completenessVSAvoidscreen space
Core Design Contradiction:
Loss of informationVSArea of stationary object

Solution Approach 1:

The system extracts only the most relevant information and UI elements from the complete set of available data, displaying them on the limited screen space. The machine learning model identifies and extracts high-priority elements based on user context, ensuring information completeness is maintained through selective extraction rather than displaying all information.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies different quality levels of information presentation to different screen regions. High-relevance UI elements receive prominent display with detailed information, while lower-relevance elements are summarized or omitted. This local quality differentiation optimizes the use of limited screen real estate while maintaining overall information completeness.

Inventive Principle:
Principle #3Local quality

2Loss of information

If the user manually searches for relevant information, then the user can find needed information, but the time required increases significantly

Engineering Contradiction:
Improveinformation accessibilityVSAvoidsearch time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing and ranking UI elements before the user needs them. The machine learning model continuously analyzes user context, behavior patterns, and environmental data to pre-identify relevant information, so when the user views the screen, the most relevant elements are already positioned for immediate access, eliminating manual search time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback loops where user interactions with displayed elements are continuously monitored and fed back to the machine learning model. This feedback refines the relevance ranking in real-time, improving information accessibility with each interaction while reducing the time needed to locate relevant elements as the system learns user preferences.

Inventive Principle:
Principle #23Feedback

3Ease of manufacture

If generic UI elements are displayed without personalization, then the system is simple to implement, but the user experience and interaction efficiency decrease

Engineering Contradiction:
Improvesystem complexityVSAvoidinteraction efficiency
Core Design Contradiction:
Ease of manufactureVSProductivity

Solution Approach 1:

The system changes key parameters of UI element display based on user-specific data. Instead of static generic elements, the machine learning model dynamically adjusts display parameters such as element priority, positioning, and visibility based on user behavior patterns, environmental context, and interaction history. This parameter customization dramatically improves interaction efficiency while building upon a standard UI framework.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The UI element ranking system is designed to be dynamic rather than static. The machine learning model continuously updates element relevance scores as user context changes, allowing the UI to adapt in real-time to different situations, times of day, locations, and user states. This dynamic adaptation improves productivity without requiring complete system redesign.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3756078B1Determining relevant information based on third party information and user interactions
Publication Date: 2024.02.28 APPLE INC
  • EP3756078B1 patent drawingFigure 1
  • EP3756078B1 patent drawingFigure 2
  • EP3756078B1 patent drawingFigure 3

AI summary

A system for determining relevant information based on user interactions may include a processor configured to receive application data from one or more applications, the application data including features related to user activity from the one or more applications, the one or more application including applications local to the device that are stored in the memory and applications external to the device. The processor may be further configured to provide, using a machine learning (ML) model, a relevance score for each of one or more user interface (UI) elements based on each of the features. The processor may be further configured to sort one or more UI elements based on a ranking of the relevance scores. The processor may be further configured to provide, as output, the one or more UI elements based at least in part on the ranking.