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

Automatic document checking method based on artificial intelligence

An automatic calibration and artificial intelligence technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as frequent rework, numerous project files, and low efficiency, so as to reduce work costs and improve processing efficiency , Improve the effect of work quality and efficiency

Pending Publication Date: 2022-03-01
国网新疆电力有限公司信息通信公司 +1
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Taking the power grid as an example, first, there are 14 types of commonly used official documents, with different file formats and review points. Each department needs to set up a clerical post to complete the daily review and circulation of official documents; Divided into five subcategories, each category of project contains 16-19 kinds of project data, the file volume is large, and the inspection work is heavy
The third is that various inspections are carried out continuously, daily document self-examination is heavy, and various inspection problems continue, rework occurs frequently, and the efficiency is low

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
  • Automatic document checking method based on artificial intelligence
  • Automatic document checking method based on artificial intelligence
  • Automatic document checking method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0018] as attached figure 1 As shown: the present invention includes four modules: text detection and recognition in an open scene, intelligent extraction of structured information, efficient intelligent document proofreading, document topic structure and key content extraction. The specific implementation of the model is as follows:

[0019] The text detection and recognition module in the open scene uses the neural network technology as a convolutional cyclic neural network (CRNN). The input of the network is the denoising image preprocessed by the traditional algorithm, and the output is digital text information. The overall flow chart is as follows: figure 2 , the detailed steps are as follows:

[0020] (1) Cell positioning is realized by traditional algorithms for data preprocessing. These include: encrypted file decryption, image orientation correction, format conversion, grayscale and binarization and other related operations;

[0021] (2) The preprocessed denoising...

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 the technical field of document checking, in particular to an automatic document checking method based on artificial intelligence, which comprises the following steps of: 1, detecting and identifying a text in an open scene; 2, intelligent extraction of structured information; 3, efficient and intelligent document proofreading; and 4, extracting a subject structure and key content of the document. According to the method, early-stage deposited document data in a company is utilized, a leading-edge machine learning and character intelligent recognition technology is utilized, a basic auditing rule is compiled and prefabricated, an intelligent document review model is constructed, and novel intelligent document processing functions such as character recognition, intelligent information extraction, intelligent document format character proofreading and key content recognition and extraction are achieved; according to the method, the standard and unified writing of daily internal files and documents is ensured, the document error problems such as character errors and inconsistency are effectively recognized, intelligent office is achieved, the file and document processing efficiency is improved, the working cost is reduced, and the quality and efficiency of transverse cooperation and up-down linkage work are effectively improved.

Description

technical field [0001] The invention relates to the technical field of document checking, and is an artificial intelligence-based automatic document checking method. Background technique [0002] With the rapid improvement of machine learning and text intelligent recognition technology, in order to support the construction of the service energy Internet, strengthen horizontal coordination, upper and lower linkages, and further implement the requirements of digital transformation, daily office efficiency urgently needs to be improved. Taking the power grid as an example, first, there are 14 types of commonly used official documents, with different file formats and review points. Each department needs to set up a clerical post to complete the daily review and circulation of official documents; It is divided into five subcategories, and each category of project contains 16-19 kinds of project materials. The volume of documents is relatively large, and the inspection work is hea...

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 Applications(China)
IPC IPC(8): G06V30/148G06K9/62G06N3/04G06N3/08G06V30/19G06V10/22
CPCG06N3/08G06N3/045G06F18/2415
Inventor 陈淑婷李雅洁马婉贞曹源明涛胡新苗舒斐胡美慧张腾郭江涛
Owner 国网新疆电力有限公司信息通信公司
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