Predictive Multi-Region Keyboard for Low-Precision Input

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional input interfaces struggle with low precision inputs, leading to errors or inoperability, particularly for users with limited dexterity or devices with constrained input interfaces, such as smartphones, smartwatches, and televisions.

Innovation Solution

A multi-region graphical keyboard interface with larger regions and prediction techniques that group symbols into different areas, using machine-learned models to suggest words or phrases based on region selections, improving input confidence and reducing keystrokes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a conventional input interface with numerous input options is used, then the device provides comprehensive functionality, but low precision inputs lead to errors or inoperability

Engineering Contradiction:
Improvecomprehensive functionalityVSAvoidinput accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The keyboard interface is segmented into multiple distinct regions (e.g., letter region, number region, symbol region), where each region contains a subset of input options. When a user inputs a region selection, the system displays only the symbols within that region, effectively filtering the comprehensive set of input options into manageable subsets. This segmentation reduces the cognitive load and improves input accuracy by preventing confusion among numerous input options while preserving comprehensive functionality through region navigation.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If individual keys are made smaller to fit more options, then the device maintains compact size, but users with limited dexterity experience difficulty with precision input

Engineering Contradiction:
Improvenumber of input optionsVSAvoidinput difficulty
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The interface transitions from a two-dimensional grid of small keys to a hierarchical structure that adds a third dimension of interaction: region selection followed by symbol selection. Instead of requiring precise direct key presses, users first select a broader region (easier, less precise input) and then choose from a filtered subset of symbols (more precise but fewer options). This dimensional change allows compact device size while maintaining ease of operation through multi-stage input.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Reliability

If a multi-region graphical keyboard interface is used, then input robustness and accessibility are enhanced, but the interface complexity increases

Engineering Contradiction:
Improveinput robustnessVSAvoidinterface complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-organizing all keyboard symbols into distinct regions before user interaction. When a user selects a region, the system has already prepared and filtered the relevant subset of symbols for display, eliminating the need for real-time complex processing. This preliminary organization simplifies the runtime interface while maintaining input robustness, as the multi-region structure is established in advance rather than computed during interaction.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4386493B1Predictive input interface having improved robustness for processing low precision inputs
Publication Date: 2025.10.29 GOOGLE LLC
  • EP4386493B1 patent drawingFigure 1A
  • EP4386493B1 patent drawingFigure 1B
  • EP4386493B1 patent drawingFigure 1C

AI summary

The present disclosure is directed to prediction and assistive techniques using a multi-region graphical keyboard interface. In particular, the system can present, on a display of a computing device, a graphical keyboard having a plurality of key regions. The plurality of key regions can include a first key region having a first set of keys and a second key region having a second set of keys. Additionally, the system can receive a first input selecting a first selected region from the plurality of key regions. Moreover, the system can determine, based at least in part on the first input, a first suggestion and a second suggestion. Furthermore, in response to the first input, the system can present, on the display of the computing device, an updated graphical keyboard having the plurality of key regions and a suggestion region. The suggestion region includes the first suggestion and the second suggestion.