Predictive Virtual Keyboard Probabilistic Spacebar
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Typing on virtual keyboards displayed on touch-sensitive devices is often slow and error-prone due to cramped key sizes and lack of tactile feedback, necessitating improved methods for interpreting user interactions.
Innovation Solution
A method that displays a virtual keyboard, detects contacts, and uses probabilistic models to predict intended words based on contact locations and sequences, allowing for predictive text correction and completion by determining if a subsequent contact is intended to select a virtual key, such as the spacebar, by analyzing the spatial location and candidate words generated from the contact sequence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If virtual keyboard keys are made smaller to fit more keys on the screen, then the number of available keys increases, but the ease of operation decreases due to cramped spacing and difficulty in accurate selection
Solution Approach 1:
The system performs preliminary word prediction based on the sequence of key contacts before the user completes typing. By predicting the intended word in advance and displaying it as a candidate, the system reduces the user's workload and allows for easier confirmation rather than requiring precise selection of each individual key in cramped conditions
Solution Approach 2:
The patent introduces an intermediate prediction interface between the virtual keyboard and the final text output. This prediction interface acts as a mediator that interprets the user's partial input sequence and presents predicted words, allowing users to confirm or correct predictions rather than directly selecting keys in the cramped virtual keyboard layout
2Device complexity
If the virtual keyboard provides no tactile feedback, then the device structure remains simple, but the reliability of input decreases due to lack of confirmation that a key was successfully selected
Solution Approach 1:
The system provides visual feedback by displaying predicted words and candidate lists in response to user input sequences. This feedback mechanism allows users to confirm whether their intended input was correctly interpreted, compensating for the lack of tactile feedback while maintaining simple device structure
Solution Approach 2:
The system performs preliminary validation and prediction of user input before final submission. By analyzing the contact sequence and predicting intended words in advance, the system can prompt users to confirm or correct their input, thereby improving reliability without adding complex tactile feedback mechanisms
3Measurement precision
If the system waits for complete word input before processing, then input precision can be verified, but the productivity decreases due to slower text entry speed
Solution Approach 1:
The system performs preliminary word prediction and presentation of candidate words during the typing process, before the user completes the full word. This allows the system to start processing and presenting predictions in advance, reducing the overall time required for text entry while maintaining accuracy through user confirmation of the predicted words
Solution Approach 2:
The system skips the traditional sequential processing model by predicting and presenting multiple candidate words simultaneously based on the partial input sequence. This allows the user to quickly scan and select from pre-computed candidates rather than typing out the complete word character by character, thereby increasing productivity while maintaining precision
Data Source
AI summary
In general, aspects of this disclosure are directed to techniques for predictive text correction and completion for text entry using virtual keyboards on touch-sensitive displays. A user may be able to type on a representation of a virtual keyboard displayed on touch-sensitive displays by contacting representations of virtual keys included in the virtual keyboard, and the word the user intended to type on the virtual keyboard may be predicted and displayed in place of characters associated with the virtual keys actually contacted by the user. In some examples of the present disclosure, a virtual spacebar key included in the virtual keyboard may be treated in a probabilistic fashion to determine whether a contact received by the touch-sensitive display is intended to select the virtual spacebar key to perform an autocorrect or autocomplete function.