Pressure-Based Gesture Typing for Graphical Keyboards

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing gesture keyboards that follow a one-gesture-for-one-word model can lead to user fatigue and input errors when entering long words, as they require continuous contact and do not effectively differentiate between single and multiple word inputs.

Innovation Solution

A computing device that uses pressure information to determine whether a continuous gesture input corresponds to a single or multiple words, allowing for non-continuous gestures to be combined to form a word, thereby reducing user fatigue and improving input accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a one-gesture-for-one-word model is used, then input simplicity is maintained, but user fatigue increases and input accuracy decreases for long words

Engineering Contradiction:
Improveinput simplicityVSAvoidinput accuracy
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent divides a single word input into multiple separate gestures, allowing users to input long words in chunks rather than requiring one continuous gesture. This segmentation reduces user fatigue and improves accuracy while maintaining the simplicity of gesture-based input.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically determines whether to combine multiple gestures into a single word or treat them as separate words based on pressure information. This dynamic adaptation allows the system to optimize between continuity and accuracy based on real-time input characteristics.

Inventive Principle:
Principle #15Dynamics

2Productivity

If continuous contact is required for entire long words, then input speed may be maintained, but user fatigue increases and cognitive difficulty increases

Engineering Contradiction:
Improveinput speedVSAvoiduser fatigue
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

By allowing long words to be segmented into multiple gestures, users can take breaks between gesture segments, reducing physical fatigue while still achieving relatively fast input speeds through the combination of these segments into complete words.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system accepts partial gestures that don't complete a full word in one motion, allowing users to perform smaller, more manageable gesture actions that accumulate to form complete words, reducing the excessive physical demand of single continuous gestures.

Inventive Principle:
Principle #16Partial or excessive action

3Ease of operation

If multiple gestures are allowed for one word, then user fatigue is reduced, but device complexity increases

Engineering Contradiction:
Improveuser fatigueVSAvoidgesture recognition complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system uses pressure information as an additional parameter to determine gesture boundaries and word formation. This parameter-based approach provides a clear, objective criterion for the system to automatically determine when to combine or separate gestures, managing complexity through well-defined rules.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system provides feedback through candidate word display, allowing users to see potential word combinations formed from their gestures. This feedback mechanism helps users understand how their multiple gestures are being interpreted and allows for correction, effectively managing the complexity of multi-gesture recognition.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3485361B1Pressure-based gesture typing for a graphical keyboard
Publication Date: 2023.11.22 GOOGLE LLC
  • EP3485361B1 patent drawingFigure 1
  • EP3485361B1 patent drawingFigure 2
  • EP3485361B1 patent drawingFigure 3

AI summary

A computing device is described that outputs, for display, a graphical keyboard comprising a plurality of keys. The computing device receives an indication of a first gesture selecting a first sequence of one or more keys from the plurality of keys, and an indication of a second gesture selecting a second sequence of one or more keys from the plurality of keys. The computing device determines, based on pressure information associated with the indication of the second gesture, a candidate word that includes a combination of the first sequence of one or more keys from the plurality of keys and the second sequence of one or more keys from the plurality of keys. The computing device further outputs, for display, the candidate word that includes the combination of the first sequence of one or more keys and the second sequence of one or more keys.