Touch Classifier for Unintended Mobile Screen Interaction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Touch screens are prone to unintentional interactions due to accidental activation, leading to embarrassing, costly, and inconvenient situations, such as unintended text messages, calls, or purchases, especially when devices are placed in pockets or purses and interacted with by body parts or small children.

Innovation Solution

A system and method that utilizes a Touch Classifier to analyze touch data and determine whether inputs are intentional or unintentional by considering historical patterns, logical UI elements, and thresholds, prompting users to verify the intent of inputs deemed unintentional, and potentially reversing or blocking such interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If touch screens are made responsive and intuitive, then user interaction flexibility is improved, but accidental interaction increases

Engineering Contradiction:
Improveuser interaction flexibilityVSAvoidaccidental interaction prevention
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary analysis of touch patterns before executing actions. It evaluates multiple parameters (touch duration, pressure, location, sequence) in advance to determine whether the input is intentional, and only then allows the action to proceed. This preliminary verification prevents accidental interactions while maintaining responsive operation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system provides feedback by analyzing touch patterns and comparing them against predefined criteria for intentional interaction. When a touch sequence does not match expected user behavior patterns, the system feedbacks by blocking the action or requiring additional verification, thus preventing accidental operations while maintaining ease of use for legitimate inputs.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If touch screens require verification for accidental inputs, then interaction accuracy is improved, but user convenience deteriorates

Engineering Contradiction:
Improveinput intent accuracyVSAvoiduser convenience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system applies different verification thresholds and analysis depths to different touch scenarios. For example, short taps on icons may have lower verification thresholds than prolonged presses or complex gesture sequences. This localized quality assessment ensures high accuracy for difficult-to-distinguish inputs while maintaining convenience for obvious user actions.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system dynamically adjusts verification parameters based on the touch context. By monitoring parameters such as touch duration, pressure level, location on screen, and sequence of actions, the system changes its verification stringency adaptively. This allows high precision when needed while maintaining user convenience for typical interactions.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS10318072B2Intelligent prevention of unintended mobile touch screen interaction
Publication Date: 2019.06.11 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10318072B2 patent drawing
  • US10318072B2 patent drawing
  • US10318072B2 patent drawing

AI summary

Method and system for detecting unintentional touch screen interaction. The method and system includes receiving touch data specifying information about a plurality of inputs on a touch screen, wherein the touch screen comprises a graphical user interface (GUI) comprising a first plurality of logical user interface (UI) elements. The method and system also include determining that the plurality of inputs was unintentional, based on a second plurality of logical UI elements that the plurality of inputs touch. The method and system conclude by prompting a user to verify that the plurality of inputs is intentional.