Chinese Text Error Detection via Character Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The complexity of the Chinese language, with many characters having similar pronunciations or appearances, leads to errors when typing Chinese articles on computers, as users often inadvertently use incorrect characters that resemble or sound like correct ones.
Innovation Solution
An error-detecting apparatus and method that subdivides erroneous Chinese character strings into subgroups, uses databases of correct character strings and indices to generate candidate sentences, and scores these sentences based on character, pronunciation, and language model similarities to identify and display the most likely correct text.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If users type Chinese characters using computers, then writing efficiency is improved, but errors occur due to similar-looking or similarly-pronounced characters
Solution Approach 1:
The patent segments the Chinese character string into multiple sub-strings (e.g., bigrams or trigrams) and processes each segment independently. By dividing the character sequence into smaller units and comparing them against a database of correct character combinations, the system can identify and correct errors more effectively while maintaining writing efficiency.
2Adaptability or versatility
If the Chinese language uses many characters with similar pronunciations or appearances, then language expressiveness is improved, but error detection becomes more difficult
Solution Approach 1:
The patent introduces an intermediary database containing correct Chinese character strings and their corresponding indices. This database acts as a mediator between the input text and the error detection process, enabling systematic comparison and identification of incorrect characters even when they have similar pronunciations or appearances.
Solution Approach 2:
The patent replaces manual error detection with an automated computational system that uses database matching and algorithmic comparison. This substitution of mechanical/manual processes with automated systems enables efficient error detection despite the complexity of Chinese characters with similar characteristics.
3Reliability
If users manually check each Chinese character for correctness, then character accuracy is improved, but writing speed decreases
Solution Approach 1:
The patent performs preliminary error detection and correction by processing Chinese character strings in real-time or near-real-time during the writing process. By implementing automated error detection that operates concurrently with or immediately after input, the system maintains writing speed while ensuring character accuracy through pre-computed database matching.
Data Source
AI summary
The invention discloses an error-detecting method for a Chinese article, handling a Chinese sentence including a first erroneous Chinese character string in a first location. The method includes subdividing the first erroneous Chinese character string into a plurality of first subgroups, wherein each of the first subgroups consists of two consecutive and non-consecutive Chinese characters out of the first erroneous Chinese character string. The method further includes providing a database containing a plurality of first correct Chinese character strings and a plurality of corresponding first correct indices, wherein the first correct indices consist of two consecutive and non-consecutive Chinese characters out of the first correct Chinese character strings. The method further includes acquiring one of the first correct indices according to the first subgroup, and one of the first correct Chinese character strings according to the acquired first correct index. The method further includes generating a best candidate sentence according to the acquired first correct Chinese character string, and showing the Chinese sentence and the best candidate sentence on a display device.