Reduced QWERTY Text Disambiguation With Low-Probability Variant Suppression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Handheld electronic devices with reduced keyboards face challenges in efficient text entry due to ambiguous inputs, as multiple letters, digits, and symbols are assigned to a single key, requiring complex keystroke interpretation systems that can be cumbersome and inefficient.
Innovation Solution
A handheld electronic device with a reduced QWERTY keyboard layout and a compound text input disambiguation function that uses a processor, memory, and input apparatus to provide a user-friendly text entry experience by displaying alternative inputs and learning frequently used words, allowing for easy selection and customization of inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Volume of moving object
If a reduced keyboard is used to provide numerous letters in a small space, then the device form factor is reduced, but the input becomes ambiguous requiring complex disambiguation
Solution Approach 1:
The system performs self-service by automatically analyzing ambiguous inputs and generating predicted words without requiring user intervention. The processor autonomously evaluates multiple interpretations of the ambiguous input sequence and selects the most probable word, allowing the device to resolve its own input ambiguity internally.
Solution Approach 2:
The system implements feedback by displaying predicted words to the user based on their ambiguous input, allowing the user to see the system's interpretation and confirm or correct it. This feedback loop enables the user to verify whether the predicted word matches their intent, improving the overall input accuracy.
2Measurement precision
If multi-tap system is used to specify characters unambiguously, then input precision is improved, but the number of keystrokes increases
Solution Approach 1:
The system applies partial action by requiring only a single keystroke per character position rather than multiple taps. Instead of fully specifying each character through repeated key presses, the system partially specifies the input and completes the disambiguation automatically through prediction algorithms, reducing the total number of required actions.
Solution Approach 2:
The system performs preliminary action by pre-calculating and displaying predicted words before the user completes their input. The processor analyzes the ambiguous input sequence and prepares potential word matches in advance, allowing the user to quickly select from pre-computed options rather than manually constructing each character.
3Ease of operation
If software-based text disambiguation is used to predict intended input, then ease of operation is improved, but low probability artificial variants may be incorrectly suggested
Solution Approach 1:
The system changes parameters by dynamically adjusting the probability threshold for displaying predicted words. Instead of using a fixed threshold, the system adapts the criteria for what constitutes a valid prediction based on the specific input context, allowing it to filter out low-probability artificial variants while maintaining ease of operation for high-probability matches.
Solution Approach 2:
The system implements dynamics by making the disambiguation process adaptive rather than static. The prediction algorithm dynamically adjusts its behavior based on the input sequence, learning from usage patterns and adjusting probability calculations in real-time to improve accuracy while maintaining ease of operation.
Data Source
AI summary
A handheld electronic device includes a reduced QWERTY keyboard and is enabled with disambiguation software 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 generate artificial variants in certain circumstances. Each artificial variant is compared with N-gram data on the handheld electronic device and is suppressed from being output if the artificial variant is determined to have a low probability of being the input intended by a user.