Unlock instant, AI-driven research and patent intelligence for your innovation.

Archive management method based on deep learning

A technology of deep learning and file management, applied in the field of file management based on deep learning, can solve the problems of lower recognition quality and high recognition error rate, and achieve the effect of ensuring integrity, improving utilization, and improving the level of intelligent management of files

Pending Publication Date: 2021-07-30
云南电网有限责任公司信息中心
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In terms of image recognition, the archive data of the power grid industry usually scans the text in the archive through OCR to obtain unstructured data. Distorted text lines, skew, noise and other common defects in scanned images and digital photos in archive data may be Reduce the recognition quality, resulting in a higher recognition error rate

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0017] Embodiment 1: The file management method is realized in the following manner.

[0018] File collection: first create a configuration file in the terminal, read the configuration file when archiving, judge whether it has reached the maximum number of volumes, and retrieve the next file directory that does not reach the maximum number of volumes in order or automatically create a file directory, continue to complete Archiving operation, cooperate with external equipment including scanners, store paper archives in image format, first perform OCR text extraction on project information based on project text data, and perform regular preprocessing on this unstructured or semi-structured data , noise reduction preprocessing, and then input the data into the decision tree to analyze the data according to the specific business logic and obtain the analysis results. After manual intervention and comparison of the results, the parameters and weights are adjusted. Then a large amou...

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 belongs to the technical field of machine learning, and particularly relates to an archive management method based on deep learning, archive management is realized through the steps of archive collection, archive assembly, archive search and classification and archive value identification, and the method improves the archive resource utilization and archive intelligent management level, reduces the management cost, and ensures the integrity, authenticity, reliability and availability of the science and technology archives.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and specifically relates to a file management method based on deep learning. Background technique [0002] At present, there is no digital platform support in archives management, and the compliance inspection of archives is still carried out manually, and there are a large number of archives, which requires a lot of manpower and time, and its standardization and integrity cannot be well guaranteed. Unstructured data accounts for about 90% of archival data, and key information data and knowledge are usually hidden in these unstructured data. [0003] Deep learning (DL, Deep Learning) is a new research direction in the field of machine learning. By learning the internal laws and representation levels of unstructured data as sample data, the terminal device has the ability to analyze and learn, and can recognize text, images and data such as sound. Deep learning is a complex machine lear...

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): G06F16/11G06K9/20G06N3/08G06Q10/10G06F16/16
CPCG06F16/113G06N3/08G06F16/16G06Q10/103G06V10/22G06V30/10
Inventor 刘伊玲杨坤丽柯燕周琼凤吴冬梅
Owner 云南电网有限责任公司信息中心