Touch Keyboard Spatial Model Gesture Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Graphical keyboards on computing devices, such as smartphones and tablets, face challenges in accuracy and speed due to users' imprecise tap or sliding gestures, leading to incorrect character input and the need for frequent corrections.
Innovation Solution
A method that modifies a spatial model based on user input characteristics, such as gesture speed and location, in conjunction with a language model to predict and correct text input, allowing for more accurate and efficient text entry by adjusting the input zone and providing candidate words and predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If users perform rapid gestures to increase typing speed, then productivity improves, but measurement precision deteriorates leading to incorrect character input
Solution Approach 1:
The system provides feedback by analyzing gesture characteristics (speed, location, pressure) and comparing them against spatial models of key locations. The feedback mechanism allows the system to determine the most likely intended key even when the gesture is imprecise, thereby maintaining high typing speed while compensating for reduced gesture accuracy through computational correction
Solution Approach 2:
The system changes parameters by dynamically adjusting the spatial model based on gesture characteristics. By modifying the spatial relationships and probability distributions in the model according to observed gesture patterns, the system can accommodate faster, less precise gestures while still accurately determining intended input through parameter-based probabilistic matching
2Measurement precision
If the graphical keyboard requires precise tap gestures to ensure accurate character input, then measurement precision improves, but ease of operation deteriorates as users must pay close attention to accuracy
Solution Approach 1:
The system performs self-service by automatically analyzing gesture characteristics and correcting potential input errors without requiring user intervention. The spatial model and language model work together to self-correct imprecise gestures, determining the most likely intended character or word without requiring the user to review or confirm each input, thereby maintaining accuracy while preserving ease of operation
Solution Approach 2:
The system performs preliminary action by pre-computing spatial models of key locations and probability distributions before gestures are entered. This preliminary preparation allows the system to rapidly and accurately interpret gestures without requiring real-time complex calculations, thereby maintaining both precision and operational simplicity through pre-computed reference data
3Device complexity
If the system uses a fixed spatial model for gesture recognition, then device complexity remains low, but adaptability deteriorates as the system cannot adjust to variations in user gesture patterns
Solution Approach 1:
The system applies dynamics by making the spatial model adaptable and modifiable based on observed gesture patterns. Rather than using a completely fixed model, the system can adjust spatial relationships and probability distributions to accommodate variations in user behavior, thereby achieving adaptability while maintaining relatively simple model structures through dynamic parameter adjustment rather than structural complexity
Data Source
AI summary
A computing device outputs for display at a presence-sensitive display, a graphical keyboard comprising a plurality of keys, receives an indication of at least one gesture to select a group of keys of the plurality of keys, and determines at least one characteristic associated with the at least one gesture to select the group of keys of the plurality of keys. The computing device modifies a spatial model based at least in part on the at least one characteristic and determines a candidate word based at least in part on data provided by the spatial model and a language model, wherein the spatial model provides data based at least in part on the indication of the at least one gesture and wherein the language model provides data based at least in part on a lexicon. The computing device outputs for display at the presence-sensitive display, the candidate word.