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

Bill identification method and device, electronic equipment and storage medium

An identification method and technology for bills, which are applied in the fields of bill identification methods, electronic equipment, storage media, and devices, and can solve problems such as time-consuming and labor-intensive, heavy work, and boring.

Active Publication Date: 2022-07-29
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, when entering bill information, it is usually necessary to train a certain number of manual entry personnel to reduce human errors when extracting structured information from bills (receipts), but manual entry is heavy, boring, and time-consuming. laborious

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
  • Bill identification method and device, electronic equipment and storage medium
  • Bill identification method and device, electronic equipment and storage medium
  • Bill identification method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

[0029] The bill identification method according to the embodiment of the present disclosure will be further introduced below.

[0030] figure 1 is a flow chart of a method for bill identification according to an embodiment of the present disclosure, such as figure 1 As shown, the method may include the following steps:

[0031] Step S102, acquiring a target bill ...

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 provides a bill recognition method and device, electronic equipment and a storage medium, and relates to the field of deep learning and pattern recognition, and the method comprises the steps: obtaining a to-be-recognized target bill; encoding the two-dimensional position information of the plurality of text blocks on the target bill to obtain a plurality of encoding results; performing graph convolution processing on the plurality of coding results to obtain a plurality of convolution results; each convolution result is identified based on a first conditional random field model to obtain a first prediction result of the text block level of the target bill, the first conditional random field model and a second conditional random field model are cooperatively trained, and the second conditional random field model is used for identifying each convolution result to obtain a second prediction result of the text block level of the target bill; and obtaining a second prediction result of the word level of the target bill. The segmentation error introduced by the second conditional random field model is avoided, and the prediction performance of the first conditional random field model is promoted while the performance of the second conditional random field model is improved.

Description

technical field [0001] The present disclosure relates to the fields of deep learning and OCR recognition, and in particular, to a method, device, electronic device and storage medium for bill recognition. Background technique [0002] At present, when entering bill information, it is usually necessary to train a certain number of manual entry personnel to reduce human errors when extracting structured information from bills (receipts). However, the manual entry method is heavy, boring and time-consuming. Effort. SUMMARY OF THE INVENTION [0003] The present disclosure provides a method, apparatus, electronic device and storage medium for bill identification. [0004] According to an aspect of the present disclosure, a bill identification method is provided, which includes: acquiring a target bill to be identified, wherein the target bill includes a plurality of text blocks; Encoding processing to obtain multiple encoding results, wherein the multiple encoding results are...

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): G06V30/40G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045G06F18/214G06V30/41G06V10/82G06N3/0464G06N3/042G06N3/0895G06N3/0442G06N7/01G06V30/19187G06V30/19147G06V30/1916G06T9/002
Inventor 何烩烩王佳阳向宇波
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD