Text Correction via Lazy Evaluation and Space Key Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current user interface systems for touch-sensitive devices face challenges in accurately mapping user touches to intended keys and correcting errors, particularly in sequences involving the 'space' key, leading to inefficiencies in auto-correction and auto-completion suggestions.
Innovation Solution
The system employs a combination of keyboard geometry and language models to initially map user inputs to candidate keys, with 'lazy' evaluation of candidate sequences and extended unigram analysis to detect and correct 'space' key errors by assigning probabilities based on the likelihood of intended key entries, optimizing processing by delaying refined scoring for less likely candidates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If extended unigram analysis is performed for all candidate sequences, then auto-correction accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs extended unigram analysis partially by applying it only to candidate sequences that include the space key, rather than analyzing all possible candidate sequences. This selective application maintains high accuracy for space-related corrections while significantly reducing overall processing time and computational resources.
Solution Approach 2:
The system uses keyboard geometry to preliminarily identify and filter candidate keys before performing the computationally intensive extended unigram analysis. By pre-filtering based on spatial proximity and likelihood, the system reduces the number of sequences requiring full analysis, thus optimizing the balance between accuracy and processing time.
2Measurement precision
If all candidate key sequences are evaluated with refined scoring, then mapping accuracy is improved, but processing efficiency deteriorates
Solution Approach 1:
The system applies refined scoring selectively only to candidate sequences that include the space key, rather than evaluating all candidate sequences with full refinement. This partial evaluation approach maintains high mapping accuracy for critical space-related inputs while improving overall processing efficiency by avoiding unnecessary computations on less likely candidates.
Solution Approach 2:
The system applies different evaluation qualities to different parts of the candidate sequence evaluation process. High-quality refined scoring is applied locally to sequences involving the space key where accuracy is most critical, while simpler evaluation methods are used for other sequences, optimizing the balance between local accuracy and overall efficiency.
Data Source
AI summary
Text correction processing is disclosed. An initial score is assigned to each of a plurality of candidate sequences of one or more characters, based at least in part on a keyboard geometry-based value associated with the received user input with respect to the candidate key. Further processing is performed with respect to a subset of the candidate sequences having the highest initial score(s) to determine for each candidate sequence in the subset a refined score. A candidate sequence is selected for inclusion in a result set based at least in part on a determination that a refined score of the selected candidate is higher than an initial score of one or more candidate sequences that are not included in the subset and with respect to which the further processing has not been performed.