Reduced Keyboard Disambiguation with Integrated Spell Checking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Handheld electronic devices with reduced keyboards face challenges in text entry due to ambiguous inputs, as existing disambiguation systems often result in poor spell checking performance, either requiring excessive processing power or providing unacceptably poor results.

Innovation Solution

A handheld electronic device with a reduced QWERTY keyboard layout and a disambiguation function that uses a combination of N-gram objects, frequency data, and a learning method to provide accurate spell checking, allowing users to enter text with ease by suggesting alternate interpretations and learning from user corrections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Volume of moving object

If a reduced keyboard with multiple letters assigned to each key is used, then the device becomes more compact and portable, but the input becomes ambiguous and requires disambiguation processing

Engineering Contradiction:

Improvedevice sizeVSAvoidinput disambiguation complexity

Core Design Contradiction:

Volume of moving objectVSDevice complexity

Solution Approach 1:

The keyboard is segmented into reduced keys, each containing multiple letters (e.g., key '2' contains 'A', 'B', and 'C'). This segmentation allows the physical keyboard to be compact while the software handles the ambiguity through segmented input processing, where each key press is processed as a separate unit that can be combined in different ways to form complete words.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

N-gram objects serve as an intermediary data structure between the ambiguous key presses and the final word output. The disambiguation function uses N-gram objects to store and process sequences of letters, matching them against frequency data to determine the intended word, thus mediating between the reduced keyboard input and the required unambiguous text output.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If spell checking is performed on ambiguous input from reduced keyboard, then text entry accuracy improves, but processing power requirements increase significantly

Engineering Contradiction:

Improvespell checking accuracyVSAvoidprocessing power

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

Frequency data about word usage patterns is pre-calculated and stored before the user actually types anything. This preliminary preparation allows the disambiguation function to quickly reference pre-computed statistics during text entry, avoiding the need for complex real-time analysis and reducing processing power requirements while maintaining high accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of performing complex spell checking on every possible ambiguous input combination, the system creates simplified representations (copies) of the input as N-gram objects and matches these against pre-stored frequency data. This copying approach maintains the essential information needed for accurate spell checking while dramatically reducing the computational complexity required to perform the check.

Inventive Principle:

Principle #26Copying

3Ease of operation

If existing disambiguation systems are used, then text entry is enabled on reduced keyboard, but spell checking performance becomes unacceptably poor

Engineering Contradiction:

Improvetext entry capabilityVSAvoidspell checking performance

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system incorporates feedback by continuously monitoring user corrections to misspelled words and using this information to improve future disambiguation decisions. When a user corrects a spelling error, the system learns from this feedback and adjusts its frequency data and N-gram matching algorithms, progressively improving spell checking performance while maintaining the ease of operation provided by the reduced keyboard.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system dynamically changes the parameters used for disambiguation based on context and user behavior. By adjusting frequency thresholds, N-gram lengths, and matching criteria in response to user input patterns, the system adapts to improve spell checking accuracy without requiring changes to the reduced keyboard hardware or fundamental input method, thus maintaining ease of operation while improving performance.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS8890806B2Handheld electronic device and method for performing spell checking during text entry and for integrating the output from such spell checking into the output from disambiguation

Publication Date: 2014.11.18 MALIKIE INNOVATIONS LTD

AI summary

A handheld electronic device includes a reduced QWERTY keyboard and is enabled with a disambiguation routine that is operable to disambiguate text input. In addition to identifying and outputting representations of language objects that are stored in the memory and that correspond with a text input, the device is able to perform a spell check routine during input of a text entry, with the output from the spell check routine being visually integrated into the output from the disambiguation routine.