Gesture Typing Error Correction via Alternative Hypotheses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture-based input methods on computing devices often fail to accurately determine the intended word due to erroneous selections, particularly with substitution, deletion, insertion, and transposition errors, leading to inefficiencies and incorrect word predictions.
Innovation Solution
The implementation of techniques that incrementally determine different groups of keys traversed by a gesture path, allowing for alternative hypotheses based on misspellings, and using spatial and language models to relax constraints on gesture input, enabling more accurate word prediction by considering phonetic and positional relationships between characters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If strict gesture alignment constraints are applied to determine word input, then measurement precision is improved, but reliability deteriorates due to erroneous selections from substitution, deletion, insertion, and transposition errors
Solution Approach 1:
The patent applies dynamics by making the gesture recognition system adaptive and flexible rather than rigid. The system dynamically adjusts the alignment constraints based on the confidence score calculated from the gesture path. When the confidence score indicates potential errors (substitution, deletion, insertion, or transposition), the system relaxes the alignment constraints to allow for alternative hypothesis generation, thereby maintaining reliability while preserving measurement precision for clear gestures.
Solution Approach 2:
The patent changes the parameter of alignment constraint strictness based on the calculated confidence score. Instead of using a fixed threshold, the system dynamically modifies the acceptable deviation parameters for gesture key traversal. When confidence is low, the system allows greater parameter flexibility to accommodate spelling errors, effectively resolving the contradiction between precision and reliability.
2Reliability
If alternative hypotheses based on misspellings are generated, then reliability of word determination is improved, but device complexity increases due to additional processing requirements
Solution Approach 1:
The patent applies segmentation by breaking down the complex gesture recognition process into distinct stages: initial gesture path extraction, confidence score calculation, error type identification (substitution, deletion, insertion, transposition), and selective alternative hypothesis generation. This segmented approach manages complexity by handling each aspect separately rather than simultaneously, reducing the overall computational burden while maintaining reliability.
Solution Approach 2:
The patent implements partial action by generating alternative hypotheses only when the confidence score indicates potential errors, rather than generating all possible alternatives for every gesture. This selective approach reduces unnecessary processing complexity while maintaining reliability for uncertain cases. The system performs exactly the amount of additional processing needed - no more, no less - based on the confidence assessment.
3Adaptability or versatility
If phonetic and positional relationships are considered for error correction, then adaptability of the gesture keyboard is improved, but difficulty of detecting and measuring increases
Solution Approach 1:
The patent applies preliminary action by pre-computing and storing phonetic relationships and positional information for keyboard characters before runtime processing. The system prepares lookup tables and data structures containing common spelling patterns, phonetic similarities, and key positions in advance. During gesture recognition, the system quickly queries these pre-prepared data structures rather than performing complex analyses in real-time, thereby improving adaptability while reducing detection difficulty.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In one example, a method may include outputting, by a computing device and for display, a graphical keyboard comprising a plurality of keys, and receiving an indication of a gesture. The method may include determining an alignment score that is based at least in part on a word prefix and an alignment point traversed by the gesture. The method may include determining at least one alternative character that is based at least in part on a misspelling that includes at least a portion of the word prefix. The method may include determining an alternative alignment score based at least in part on the alternative character; and outputting, by the computing device and for display, based at least in part on the alternative alignment score, a candidate word based at least in part on the alternative character.