Browse Prior Art Database

A system and method to dynamically correct user input on virtual keyboard of mobile device.

IP.com Disclosure Number: IPCOM000235957D
Publication Date: 2014-Apr-01
Document File: 4 page(s) / 162K

Publishing Venue

The IP.com Prior Art Database

Abstract

The invention dynamically adjusts available stroke area to correct user input on mobile virtual keyboard based on word prediction.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 53% of the total text.

Page 01 of 4

A system and method to dynamically correct user input on virtual keyboard of mobile device

A system and method to dynamically correct user input on virtual keyboard of mobile device. .

.

The invention dynamically adjusts available stroke area (call it as response area) based on word prediction. User's each input can result in adjustment of response area for next possible characters. The adjusted response area can tolerant user's imprecise input and recognize it as a right input.

Advantages:

1. The invention can effectively correct wrong input and increase typing speed

Virtual keyboard is widely used on mobile device. When user types a word, he may sometimes input a wrong character. Existing solutions normally show character/word predictions. The problem is once user strokes on an incorrect area, such as space around the character or even on the edge of other nearby characters, incorrect character will be selected.

This disclosure proposes a way to dynamically correct user input

.

.

2. The adjustment of response area is invisible to end user. The real size and position of each key in virtual keyboard will not be changed

      So looking and feel of the virtual keyboard keeps the original theme. This will avoid annoying key jumping like zoom in/zoom out or move.

Terminology definition in this article:

Response area- The area user strokes on virtual keyboard.

Normal

Normal/

//Min

Min

Min/

//Max response area

Max response area- The size of response area as figure 1 shows.

Next probable character- The next probable character predicted by word prediction. For example, 'a, e, i, o, u, y' can be next probable character when user types 'h'.

Probability of next probable character- The percentage of probability for next probable character. For example, the probability of 'a, e, i, o, u, y' might be 23%, 18%, 18%, 18%, 18%, 5%.

Threshold- A threshold to classify the next character. The threshold is a configurable constraint.

It classifies characters into 'active', 'negative' or 'other'. For example, if threshold is defined as '10%', then the probability more than 10% is marked as 'active' while those less than 10% or equal 10% is marked as 'negative', other characters not listed in the probable character list are marked as 'other'.

1



Page 02 of 4

Figure 1

Mechanism

All characters will be classified into three types - 'active', 'negative' and 'other' based on the probability and threshold.

The higher the probability, the further the 'separation line' away from...