Stroke Input Disambiguation for Omitted and Misordered Strokes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of inputting text using stroke sequences in languages like Chinese on electronic devices is often lengthy and frustrating due to errors in stroke input, such as omissions or incorrect sequences, which can lead to the user not finding the desired character in candidate lists, requiring repetitive retyping.
Innovation Solution
An electronic device with a stroke disambiguation module that applies disambiguation rules to correct invalid stroke inputs, such as adding missing strokes or correcting sequence errors, to generate an updated input sequence for improved text prediction and candidate list generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If text input is based on individual strokes that form a character, then the user can input text character by character, but the input process becomes long and complicated requiring the user to enter strokes in a given sequence
Solution Approach 1:
The system performs preliminary action by predicting candidate characters after each stroke is input, rather than waiting for the complete stroke sequence. This allows the user to see potential matches early and reduces the need to complete lengthy stroke sequences for characters that are already identifiable from partial input.
Solution Approach 2:
The system implements feedback by providing a candidate list to the user during the stroke input process, allowing the user to verify whether the predicted characters match their intent. This feedback mechanism enables early termination of stroke input when the desired character is found in the candidate list.
2Productivity
If a text prediction algorithm provides a candidate list based on input strokes, then the user can select from predicted characters, but the user may fail to find the desired character when strokes are omitted or entered in wrong sequence
Solution Approach 1:
The system applies partial action by generating candidate predictions based on partial stroke sequences rather than requiring complete stroke input. This allows the prediction algorithm to work with incomplete information and still provide useful candidate lists, reducing the need for users to retype entire sequences.
Solution Approach 2:
The system changes parameters by adjusting the flexibility of stroke matching, allowing for omitted or incorrectly sequenced strokes to still generate valid candidate predictions. This parameter adjustment enables the system to accommodate common user errors while maintaining prediction accuracy.
3Measurement precision
If the user has to retype the entire stroke sequence when the desired character is not found, then the user can attempt to correct input errors, but this process is time-consuming and frustrating
Solution Approach 1:
The system performs preliminary correction by automatically generating alternative candidate lists when the initial prediction fails, rather than requiring the user to retype. This preliminary action includes considering common stroke errors and omissions when generating alternative predictions.
Solution Approach 2:
The system implements self-service by automatically detecting and correcting common stroke input errors without user intervention. The prediction algorithm self-corrects for omitted strokes or incorrect sequences by generating alternative candidate lists based on probable user intent.
Data Source
AI summary
An electronic device for disambiguation of stroke input, the device comprising: an input device coupled to the microprocessor for accepting a stroke input; and a stroke disambiguation module resident in the memory for execution by the microprocessor. The device is configured to: receive a signal representing a stroke input sequence at the stroke disambiguation module; apply one or more stroke disambiguation rules to the stroke input sequence to generate an updated input sequence; and transmit a signal representing the updated input sequence.