Intelligent extraction method and device for table cells of financial statements

An extraction method and technology for financial statements, applied in the field of intelligent extraction of financial statement cells, can solve problems such as high labor costs, fatigue, and low efficiency, and achieve the effects of improving work efficiency, reducing error rates, and reducing labor costs.

Inactive Publication Date: 2018-09-04
上海眼控科技股份有限公司
View PDF0 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional financial statement review is mainly through manual identification. This method has high labor costs and low efficiency, and...

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
  • Intelligent extraction method and device for table cells of financial statements
  • Intelligent extraction method and device for table cells of financial statements

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with the accompanying drawings.

[0041] The concrete implementation process of the present invention is as figure 1 As shown, an intelligent extraction method for financial statement cells includes the following steps:

[0042] S1. Download the target form image of the financial statement from the server;

[0043] S2. Perform image tilt correction on the target table image;

[0044] Among them, the specific method of image tilt correction is as follows:

[0045] S21. Using Gaussian blur to denoise the input image, and then using a histogram equalization algorithm and gamma transformation to perform contrast stretching on the denoised image to achieve image enhancement, and then using an adaptive binary method to obtain a binary image;

[0046] S22. Use the Hough straight line method to detect straight lines on the binary image obtained in S21, sort all detected straight lines according to their len...

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 discloses an intelligent extraction method and device for table cells of financial statements. The intelligent extraction method for table cells of financial statements includes the following steps: downloading a target table image of financial statements from a server; performing image tilt correction on the target table image; using a table outline border target detection model based on deep learning to detect the table area of the target table image, and obtaining a table area image; on the obtained table area image, using a table intersection point model based on depth learning to locate the table intersection points; and performing ordering, screening and regrouping on the coordinates of the table intersection points so as to obtain each table cell. The scheme of the intelligent extraction method and device for table cells of financial statements can accurately and quickly extract the table cells of financial statements, uses algorithms to realize accurate identification, can greatly improve the work efficiency of checking financial statements, can reduce the labor cost, and can reduce the error rate.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence judgment for financial statement review, in particular to an intelligent extraction method and device for financial statement cells. Background technique [0002] With the continuous development of social economy and the continuous improvement of people's living standards, banks have an increasing demand for identifying financial statements. The traditional financial statement review is mainly through manual identification. This method has high labor costs and low efficiency, and long-term repetitive verification operations are prone to fatigue, negligence and other bad states, which affect the accuracy of the verification. [0003] How to accurately and quickly extract the cells of the financial statement and use algorithmic identification to avoid the disadvantages of high cost, fatigue, and negligence of manual identification is an urgent technical problem that needs to be solve...

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): G06K9/00G06K9/36
CPCG06V30/412G06V10/247G06V10/20
Inventor 周康明
Owner 上海眼控科技股份有限公司
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