Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Method of Error Detection and Proofreading of Text Shapes and Near Characters

It is a kind of near-character and error detection technology, which is applied in the fields of electrical digital data processing, instruments, calculations, etc.

Active Publication Date: 2021-09-14
KUNMING UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a text error detection and proofreading method for similar characters, which is used to solve the problem of the dependence of text error detection on word segmentation and the low accuracy rate of error detection caused by inaccurate word segmentation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Method of Error Detection and Proofreading of Text Shapes and Near Characters
  • A Method of Error Detection and Proofreading of Text Shapes and Near Characters
  • A Method of Error Detection and Proofreading of Text Shapes and Near Characters

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Embodiment 1: as Figure 1-2 As shown, a kind of error detection and proofreading method of text shape near word, concrete steps are as follows:

[0029] Step0.1. Create a database, which includes font library X, corpus Y, commonly used font library Q, and disabled thesaurus T.

[0030] Step1, select the sample sentence A to be processed, such as 'I am a Tai student. '.

[0031] Step2, the sentence A is preprocessed, the punctuation marks in the sentence are removed, and a new character string is obtained, B='I am a Tai student' and n is the length of the character string B.

[0032] Step3, with each word in B='I am a student of Tai', in the shape near character library X, find out the similar shape near word {c n1 ,c n2 ... c nm} as c n Candidate word, with c n The degree of similarity decreases from left to right, we temporarily take m=3, that is, with c n The first three similar characters with the highest similarity, for example, the similar characters of 'I...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an error detection and proofreading method for text-like characters, belonging to the technical field of natural language processing. First, use the Chinese character library to find out the corresponding character in the input sentence, and form a candidate word vector with the original character; then use the commonly used character library to clean out the uncommon words in the vector, and convert all the candidate word vectors Form a candidate matrix; secondly, bind the adjacent vectors in the candidate matrix into words, compress the vectors that can be combined into words to form candidate word vectors, compare the vectors that cannot be formed into words with the inactive word library, and eliminate non-inactive words; finally Introduce the N-Gram language model to combine the above words, so that the keywords have a cohesive relationship between top and bottom, and form a sentence with the strongest connection relationship. Compare the sentence with the original sentence to find out the mistakes in the original sentence and give proofreading suggestions.

Description

technical field [0001] The invention relates to an error detection and proofreading method for text-like characters, belonging to the technical field of natural language processing. Background technique [0002] At present, due to the application of OCR text recognition technology, when translating paper texts into computer texts, some texts are often misrecognized as their similar characters, and manual proofreading is used in a large number of texts. Extremely inefficient. [0003] It is a common method to use the word segmentation tool to decompose the sentence into words, and then compare the words with the thesaurus to find the wrong position in the text. However, for word segmentation, the accuracy of word segmentation plays a decisive role in the error detection of the text. In the case of inaccurate word segmentation, the correct rate of error detection results is extremely low. Contents of the invention [0004] The technical problem to be solved by the present ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/232G06F40/205G06F40/216
CPCG06F40/205G06F40/216G06F40/232
Inventor 邵玉斌王林坪龙华杜庆治
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com