Machine-Learned Haptic Feedback for UI Object Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing haptic feedback systems require manual configuration by developers lacking expertise, necessitating a more efficient and automated method for optimizing haptic responses in graphical user interfaces.

Innovation Solution

Utilizing machine-learning models, such as convolutional neural networks, to automatically classify and localize objects in user interfaces, enabling personalized haptic feedback configurations based on object detection and sound classification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual configuration by developers is used, then haptic feedback can be customized, but the process requires extensive time and expertise

Engineering Contradiction:
Improvehaptic feedback optimizationVSAvoidconfiguration time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system automatically analyzes UI screenshots and generates haptic feedback configurations without requiring developer intervention. The machine learning model performs the optimization task autonomously, transforming a manual expert-driven process into an automated self-service system that eliminates time-consuming manual configuration while maintaining high-quality results

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual developer configuration with an automated machine learning-based system. Instead of developers manually analyzing UI elements and configuring haptic parameters, the system uses computer vision and deep learning algorithms to automatically detect UI components and generate optimized haptic feedback configurations, substituting human expert work with automated intelligent processing

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual configuration by developers is used, then haptic feedback can be customized, but developer expertise is required

Engineering Contradiction:
Improvehaptic feedback optimizationVSAvoidconfiguration ease
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system empowers UI designers to independently configure haptic feedback by automatically analyzing their UI designs and generating appropriate configurations. This self-service capability eliminates the need for developers' expertise, allowing designers to work autonomously without requiring specialized knowledge of haptic programming or optimization

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The machine learning system acts as an intermediary between UI designers and haptic feedback mechanisms. Instead of requiring designers to directly understand and configure complex haptic parameters, the intermediary automatically translates UI design intent into optimized haptic configurations, bridging the gap between design and implementation while eliminating the need for developer expertise

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If automated machine-learning method is used, then configuration time is reduced, but system complexity increases

Engineering Contradiction:
Improveconfiguration speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent extracts the complex machine learning and automated analysis functionality into a separate, dedicated system component. By isolating the sophisticated image recognition and haptic optimization algorithms into a standalone service or module, the main application remains simple while benefiting from advanced automated capabilities, effectively removing complexity from the core workflow

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4553616B1Haptic feedback using machine-learning
Publication Date: 2026.03.04 AITO
  • EP4553616B1 patent drawingFigure 1
  • EP4553616B1 patent drawingFigure 2A
  • EP4553616B1 patent drawingFigure 2B

AI summary

Various example embodiments relate to determining a haptic feedback configuration based on user interface elements using machine-learning. A method may comprise: obtaining a first data, the first data comprising information of a UI; based on the first data, providing the first data to at least one machine-learning model; based on the providing the first data to the at least one machine-learning model, obtaining a second data, the second data comprising at least one classification of at least one object; determining a sensing and haptic configuration based on the second data; and based on the sensing and haptic configuration, providing a haptic feedback.