Disambiguation Function for Reduced Keyboard Text Entry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Handheld electronic devices with reduced keyboards face challenges in accurate text entry due to ambiguous inputs, as keys often serve multiple functions, leading to erroneous outputs that do not resemble the intended input.
Innovation Solution
A handheld electronic device with a disambiguation function that uses a processor, memory, and a reduced QWERTY keyboard layout, where the disambiguation function generates permutations of key actuations and consults a database to identify the most likely intended word, providing both a default and alternate proposed outputs to the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Volume of moving object
If a reduced keyboard is used to enable text entry in a compact device, then the device form factor is reduced, but text input accuracy deteriorates due to ambiguous inputs
Solution Approach 1:
The patent introduces a software-based text disambiguation function as an intermediary between the reduced keyboard input and the final text output. This disambiguation software analyzes the sequence of key presses, generates multiple possible interpretations, and selects the most likely intended input based on language models and context, thereby resolving the ambiguity caused by the reduced keyboard layout without requiring a larger physical device
Solution Approach 2:
The system implements feedback by providing the user with multiple disambiguated options displayed on the screen after a sequence of key presses. The user can review these options and select the correct one if the automatic disambiguation is incorrect, creating a feedback loop that improves text input accuracy while maintaining the compact reduced keyboard form factor
2Area of stationary object
If multiple letters and symbols are assigned to a single key to reduce keyboard size, then the device becomes more compact, but input ambiguity increases
Solution Approach 1:
The system performs preliminary action by pre-calculating and storing multiple possible interpretations of key press sequences in a language model database before actual text input occurs. When the user presses a sequence of keys on the reduced keyboard, the system has already prepared multiple disambiguated options based on linguistic patterns, allowing for rapid and accurate interpretation without losing input clarity
Solution Approach 2:
The disambiguation software acts as an intermediary that translates the ambiguous physical key presses into clear textual meaning. It processes the raw input data, applies language modeling to generate multiple possible interpretations, and presents the most likely intended input to the user, thereby recovering the lost input clarity despite the condensed keyboard layout
3Ease of operation
If traditional text disambiguation systems are used on reduced keyboards, then text entry is enabled, but erroneous keying produces output that bears no similarity to the intended input
Solution Approach 1:
The system applies dynamics by implementing a learning function that adapts to the user's typing patterns and preferences over time. The disambiguation algorithm dynamically adjusts its parameters based on observed user behavior, such as preferred word choices and common typing errors, thereby improving reliability and ensuring that the output remains similar to the intended input even when erroneous keying occurs
Solution Approach 2:
The learning function utilizes feedback from user corrections and selections to continuously improve text entry accuracy. When the user selects a disambiguated option or corrects an error, this feedback is used to refine the language model and adjust disambiguation parameters, making the system progressively more reliable in producing output that matches the user's intended input
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 provides a learning function which facilitates providing proposed corrected output by the device in certain circumstances of erroneous input.