Gesture Keyboard Precision Correction via Probability Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Continuous gesture graphical keyboards often result in inaccurate text entry due to imprecise gestures, leading to incorrect word selection and reduced interaction speed, as they fail to accurately determine the intended word based on imprecise finger movements over the presence-sensitive screen.
Innovation Solution
A method that outputs a graphical keyboard, receives gesture inputs, determines the precision of the gesture by analyzing features such as distance and curvature, and adjusts spatial model probabilities to improve key selection accuracy, allowing incremental determination and display of candidate words during the gesture, thereby enhancing precision and speed of text entry.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If continuous gesture graphical keyboard is used to allow users to trace words with finger, then input efficiency is improved, but text entry accuracy deteriorates due to imprecise gestures
Solution Approach 1:
The system performs preliminary actions by determining gesture precision metrics (straightness, curvature, length) before final word selection. These preliminary analyses of gesture characteristics enable the system to prepare appropriate correction strategies and candidate word lists in advance, resolving the contradiction between allowing free gesture input and maintaining accurate word recognition
Solution Approach 2:
The system implements feedback by continuously monitoring gesture precision metrics and using this information to dynamically adjust word selection. When imprecision is detected through analysis of gesture straightness and curvature, the system provides feedback by presenting corrected candidate words, thereby maintaining accuracy while preserving the efficiency benefits of continuous gesture input
2Measurement precision
If gesture precision is improved by stricter key location matching, then text entry accuracy is improved, but interaction speed deteriorates
Solution Approach 1:
The system applies dynamics by making the precision threshold adaptive rather than fixed. The precision requirements dynamically adjust based on the detected gesture characteristics and context, allowing faster, less precise gestures to be corrected automatically while maintaining high accuracy when the user takes their time, thus resolving the contradiction between speed and precision
Solution Approach 2:
The system changes parameters by modifying the precision threshold and correction probability based on gesture metrics. When gestures are detected as imprecise (low straightness score, high curvature), the system adjusts parameters to accept broader key region matches and apply stronger corrections, thereby maintaining both speed and accuracy without requiring consistently high precision input
3Ease of operation
If imprecise gestures are accepted with higher tolerance, then ease of operation is improved, but text entry accuracy deteriorates
Solution Approach 1:
The system introduces an intermediary correction mechanism that sits between the imprecise gesture input and the final word selection. This intermediary layer analyzes gesture precision metrics and applies intelligent corrections by suggesting alternative words, thereby maintaining ease of operation while compensating for accuracy losses from imprecise gestures
Solution Approach 2:
The system replaces the mechanical approach of strict geometric key matching with a computational approach using probability models and language understanding. Instead of relying solely on precise spatial correspondence, the system substitutes this with probabilistic word selection based on gesture patterns, context, and linguistic validity, thereby maintaining accuracy despite imprecise physical input
Data Source
AI summary
In one example, a method includes outputting, by a computing device and for display, a graphical keyboard comprising a plurality of keys. The method may also include receiving, by the computing device, an indication of a gesture detected at a presence-sensitive input device. The method may also include determining, by the computing device and based on a plurality of features associated with the gesture, a degree of precision of the gesture. The method may also include modifying, by the computing device and based at least in part on the degree of precision, a probability that the gesture indicates at least one key of the plurality of keys. The method may also include outputting, by the computing device and for display, a candidate word that is based at least in part on the probability that the gesture indicates at least one key of the plurality of keys.