Typing Error Correction via Substring Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional typing error correction methods require users to manually delete errors using backspace or precise cursor movement, which is inconvenient, especially for mobile devices, and auto-correction functions often fail due to limited libraries and inaccuracies when dealing with new words or languages like Korean, leading users to disable these features.
Innovation Solution
A method that calculates correlations between newly input characters and existing substrings to suggest correction candidates, allowing users to retyping corrections without using deletion keys and enabling cursor placement anywhere within a word for error correction, with a library-based system for word replacements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If conventional auto-correction function is used, then typing error correction is automated, but correction accuracy deteriorates due to limited library and inability to handle new words or Korean language properly
Solution Approach 1:
The patent changes the parameter of correction candidate selection from library-based word replacement to correlation-based substring matching. By calculating correlation values between newly input characters and existing substrings, the system can accurately identify and correct typing errors without relying on pre-registered word libraries, thereby improving correction accuracy for new words and Korean language while maintaining automation.
2Measurement precision
If manual deletion method is used, then correction precision is maintained, but operation convenience deteriorates due to need for backspace key and retyping
Solution Approach 1:
The patent implements self-service correction by automatically identifying typing errors through correlation calculation between newly input characters and existing substrings. The system serves itself by detecting and suggesting corrections without requiring user intervention with deletion keys or cursor movement, thereby improving operation convenience while maintaining correction precision through accurate correlation-based error detection.
3Measurement precision
If cursor movement method is used, then correction accuracy is maintained, but operation convenience deteriorates due to need for precise cursor placement and additional features
Solution Approach 1:
The patent replaces the mechanical system of cursor movement and manual deletion with an automated correlation-based correction system. Instead of requiring users to physically move cursors or press deletion keys, the system uses correlation calculation to automatically identify and suggest corrections, thereby improving operation convenience while maintaining correction accuracy through computational methods rather than mechanical input.
4Reliability
If library-based correction is used, then existing words can be corrected, but adaptability deteriorates for new words and abbreviations not in the library
Solution Approach 1:
The patent changes the fundamental parameter of correction from library-based word matching to correlation-based substring matching. This allows the system to adapt to new words and abbreviations by calculating correlations between newly input characters and existing substrings in real-time, rather than relying on pre-registered word libraries. The system can handle Korean language without spaces and newly coined terms by using correlation calculation to identify typing errors and suggest appropriate corrections.
Data Source
AI summary
A typing error correction method and a device implementing the same method are provided. A correction method includes the following: every time when a user inputs characters, a correlation between the newly input characters and the character substrings of the already input words having the same length as the newly input characters is calculated; in case the correlation exceeds a predetermined value, such character substring of already input word is registered in a correction candidate list; in case there is only one correction candidate in the list, the candidate substring in the list is replaced by the newly input characters according to correction command; in case there are more than one correction candidates in the list, a user's move command is input for selection, and the selected candidate substring is replaced by the newly input characters.