OCR-based post-loan inspection system and method

An inspection method and inspection system technology, applied in the computer field, can solve problems such as inaccurate identification and captured content, and achieve the effect of improving accuracy

Pending Publication Date: 2020-10-30
重庆富民银行股份有限公司
View PDF13 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides an OCR-based post-loan inspection system and method, which solves the technical problem

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
  • OCR-based post-loan inspection system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] The embodiment of the OCR-based post-loan inspection system of the present invention is basically as attached figure 1 shown, including:

[0060] The input module is used to take and extract the text picture of the photocopy of customer information;

[0061] The character module is used to input the text image into the pre-trained text correction network model, and output the classification saliency map at the character level;

[0062] The correction module is used to correct the text picture and the classification salient map by using the strip region transformation algorithm, and output the corrected picture;

[0063] The recognition module is used to convert the printed characters in the corrected picture into a black and white dot matrix image file by using optical character recognition technology, convert the text in the image file into a text format, and output the recognized text;

[0064] The error correction module is used for associating and identifying the ...

Embodiment 2

[0085] The only difference from Embodiment 1 is that the error correction module also includes a confusing unit, which determines the confusing words corresponding to the wrong word segmentation, determines the degree of confusion of the confusing words corresponding to the wrong word segmentation; and based on the confusing words corresponding to the wrong word segmentation; For the degree of confusion of the confused word, the confusing word corresponding to the wrong word segmentation is selected according to the preset rules, and the selection result is used as the error correction word corresponding to the wrong word segmentation. In this embodiment, confusing words are collected in advance, such as "reservation", "reservation", "deposit" and "deposit". For identifying the wrong word segmentation in the text, based on the pre-collected data, determine the confusing word corresponding to the wrong word segmentation, and manually set the confusing degree of the confusing wor...

Embodiment 3

[0087] The only difference from Embodiment 2 is that it also includes a client, which is used to collect the behavior data related to the loan of the user in real time, analyze the behavior data, and judge whether the user is a high-quality customer with both repayment willingness and repayment ability . In this embodiment, the client is a bank APP, which is provided to the user for free for a period of time, and collects data related to the user's loan behavior in real time during the user's usage period.

[0088]Specifically, read the text messages received by the user every day, and conduct semantic analysis by extracting keywords in the text messages, so as to make a judgment on the user's repayment willingness and repayment ability. For example, the user's bank card text message may contain words such as "balance" and "arrears". At this time, semantic analysis is performed to determine whether the balance of the bank card is less than the arrears, and at the same time cou...

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 computers, in particular to an OCR-based post-loan inspection method. The method comprises the following steps: S1, shooting and extracting a text picture of a photocopy of customer data; S2, inputting the text picture into a pre-trained text correction network model; S3, correcting the text picture and the classification saliency map by utilizing astrip-shaped region transformation algorithm; S4, outputting an identification text by adopting an optical character identification technology; S5, determining an error correction word corresponding to an error segmentation word with an identification error in the identification text; S6, determining an error correction confidence degree corresponding to the error correction candidate text througha neural network model, and taking the error correction candidate text of which the error correction confidence degree is greater than a first threshold value as an error correction text; S7, performing information comparison according to the error correction text, judging whether the information comparison is consistent or not, and if not, prompting manual recheck. According to the invention, the technical problem that the content of a photoprint with poor photoprint quality is inaccurately identified and captured by using an OCR technology is solved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an OCR-based post-loan inspection system and method. Background technique [0002] At present, when it is necessary to apply for a loan, bank staff will review the authenticity of the information provided by the lender. In most cases, banks use manual review, that is, the staff reviews the materials provided by the lender one by one to determine whether the lender meets the conditions for lending by the bank. However, the manual review method is inefficient and has high labor costs; when the workload is heavy, it is easy to cause mistakes if the staff perform repeated work for a long time. [0003] In this regard, document CN109697665A discloses an artificial intelligence-based loan review method, device, equipment, and medium, including: obtaining a loan application request, the loan application request including an ID card image and user personal information; using OCR recog...

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
IPC IPC(8): G06Q40/02G06K9/00G06K9/32G06K9/62G06F40/232G06F40/284G06F40/289
CPCG06F40/232G06F40/284G06F40/289G06V30/413G06V20/62G06V30/10G06Q40/03G06F18/253
Inventor 何寒曦
Owner 重庆富民银行股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap