Invoice recognition method and system based on deep learning

A deep learning and invoicing technology, applied in neural learning methods, character recognition, character and pattern recognition, etc., can solve the problems of inaccurate OCR data acquisition of invoices and invoices, so as to solve the problem of slow recognition speed, ensure effectiveness, and ensure accuracy Effect

Inactive Publication Date: 2019-07-05
SUNING COM CO LTD
View PDF11 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide an invoice recognition method and system based on deep learning, which can solve the tech

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
  • Invoice recognition method and system based on deep learning
  • Invoice recognition method and system based on deep learning
  • Invoice recognition method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] see figure 1 and figure 2 , the present embodiment provides a deep learning-based invoice recognition method, including:

[0057] Step S1, obtain multiple sample reimbursement forms marked with invoice types and location coordinates, and construct training data sets and verification data sets; Step S3, use multiple pre-networks combined with the Faster-RCNN framework to train multiple invoices based on the training data set Detection model; step S4, check the performance of each invoice detection model through the verification data set, and select the optimal invoice detection model; step S5, use the optimal invoice detection model to detect the invoice reimbursement form, and identify the invoice reimbursement form Each invoice image and the corresponding invoice type and position coordinates; step S7, use the OCR model to perform text recognition on the invoice images corresponding to each position coordinates, and use the text recognition content, invoice type and / ...

Embodiment 2

[0071] see figure 1 and image 3 , this embodiment provides a deep learning-based invoice recognition system, including:

[0072] The sample construction unit 1 is used to obtain a plurality of sample reimbursement forms marked with invoice type and location coordinates, and construct a training data set and a verification data set;

[0073] Invoice detection model training unit 3, based on the training data set, using a combination of multiple pre-networks

[0074] The Faster-RCNN framework corresponds to training a variety of invoice detection models;

[0075] The invoice detection model screening unit 4 performs performance verification on each invoice detection model through the verification data set, and screens out the optimal invoice detection model;

[0076] The invoice detection unit 5 is used to detect the invoice reimbursement form by using the optimal invoice detection model, and identify each invoice image and the corresponding invoice type and position coordin...

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 invoice recognition method and system based on deep learning, relates to the technical field of invoice recognition, and solves the technical problem of inaccurate invoice OCR data acquisition caused by various invoice types and nonstandard invoice pasting in the prior art. The method comprises the following steps: obtaining a plurality of sample reimbursement lists marked with invoice types and position coordinates, and constructing a training data set and a verification data set; based on training data set, combining multiple front networks with a Faster-RCNN framework correspondingly trains a plurality of invoice detection models; carrying out performance verification on each invoice detection model through the verification data set, and screening out an optimal invoice detection model; detecting the invoice reimbursement list by utilizing the optimal invoice detection model, and identifying each invoice image in the invoice reimbursement list and corresponding invoice types and position coordinates; and carrying out character recognition on the invoice images corresponding to the position coordinates by using an OCR model, and packaging and outputtingthe character recognition content, the invoice type and/or the position coordinates of each invoice as invoice recognition results.

Description

technical field [0001] The present invention relates to the technical field of invoice identification, in particular to an invoice identification method and system based on deep learning. Background technique [0002] In recent years, with the rapid development of society and economy, economic activities have become more and more frequent. Both ordinary consumers and various types of enterprises have become more and more aware of the fact that consumption must be invoiced and reimbursed by ticket. In the process of expense reimbursement, enterprises will require employees to paste relevant invoices on paper for image collection. Since one expense reimbursement may contain multiple types of invoices, multiple different invoices are often pasted on one reimbursement form. Types of invoices, sometimes in order to save paper space, the invoices are pasted vertically or upside down. Therefore, based on the above-mentioned variety of invoice types and irregular pasting of invoices...

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): G06K9/34G06K9/20G06N3/04G06N3/08G07D7/20G07D7/202
CPCG06N3/08G07D7/2008G07D7/202G06V10/22G06V30/153G06V30/10G06N3/045
Inventor 郭近之杨现王云龙刘亚峰
Owner SUNING COM CO LTD
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