Virtual Keyboard Subregion Segmentation for Input Precision

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Touch screen devices with virtual keyboards face challenges in accurately detecting intended input locations, especially when using objects with large surface areas like fingers, due to limited space and precision issues.

Innovation Solution

The implementation of a text prediction algorithm in electronic devices with a touch screen display, which includes a microprocessor, touch screen display, and memory with an input determination module to identify subregions on the virtual keyboard and provide characters or symbols to the algorithm for predicting intended input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If a virtual keyboard is used on a touch screen display, then the device portability and space utilization are improved, but the input precision and accuracy are worsened

Engineering Contradiction:
Improvespace utilizationVSAvoidinput precision
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The virtual keyboard is divided into multiple subregions within each key area. When a touch is detected, the system determines which subregion was touched to identify the intended character or symbol. This segmentation allows for more precise input detection even when the overall keyboard area is limited, resolving the contradiction between compact space utilization and input precision.

Inventive Principle:
Principle #1Segmentation

2Productivity

If the virtual keyboard keys are made smaller to fit more on the screen, then the space utilization is improved, but the detection accuracy of intended input is worsened

Engineering Contradiction:
Improvetyping speedVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system introduces a second dimension of discrimination by dividing each key into multiple subregions. Instead of relying solely on the position of the touch within the overall key area, the subregion detection provides an additional layer of precision. This allows smaller keys to maintain or even improve detection accuracy by utilizing the subregion information to disambiguate touches that might otherwise be indistinguishable.

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

3Ease of operation

If a finger with large surface area is used to touch the screen, then the ease of operation is improved, but the precision of detecting the intended location is worsened

Engineering Contradiction:
Improveease of useVSAvoidlocation detection precision
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

By dividing each key into multiple subregions, the system can more precisely determine which character or symbol the user intended to select, even when the finger covers a large area. The subregion analysis helps to pinpoint the intended target within the broader touch area, maintaining high precision despite the use of large-contact input methods.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9043718B2System and method for applying a text prediction algorithm to a virtual keyboard
Publication Date: 2015.05.26 MALIKIE INNOVATIONS LTD
  • US9043718B2 patent drawing
  • US9043718B2 patent drawing
  • US9043718B2 patent drawing

AI summary

An electronic device for text prediction in a virtual keyboard. The device includes a memory including an input determination module for execution by the microprocessor, the input determination module being configured to: receive signals representing input at the virtual keyboard, the virtual keyboard being divided into a plurality of subregions, the plurality of subregions including at least one subregion being associated with two or more characters and/or symbols of the virtual keyboard; identify a subregion on the virtual keyboard corresponding to the input; determine any character or symbol associated with the identified subregion; and if there is at least one determined character or symbol, provide the at least one determined character or symbol to a text prediction algorithm.