Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Table recognition method, device and storage medium

A recognition method and table technology, which is applied in the computer field, can solve problems such as inability to accurately restore tables, and achieve the effects of easy optimization and analysis, improved accuracy, and a single task

Pending Publication Date: 2019-12-03
苏州美能华智能科技有限公司
View PDF10 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a form recognition method, device and storage medium, which can solve the problem that the form cannot be accurately restored in the existing solutions

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
  • Table recognition method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The specific implementation manners of the present application will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0042] First of all, for ease of understanding, the technical terms involved in the various embodiments of the present application are briefly described below.

[0043] The task of the image pre-training model is defined as outputting the vertex position of the table cell and the connection of each vertex, such as cross or T.

[0044] The frame model takes the sub-outer output (cross coding) of the image pre-training model and text semantics as the input of the frame model, and after transformation, new semantic codes and image codes are generated. In actual implementation, the framework model encapsulates image, semantic coding, and four sub-models. The four sub-models are: the model respo...

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 a table recognition method, a table recognition device and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: obtaining the structural information of a table in a target file according to a picture pre-training model, and the structural information comprises the vertex position of the table and the connection relation of vertexes; grouping the text contents in the table by taking cells as units through a grouping model; connecting the cells in the same table in the target file through a connection model; according to the structure information, the text groups obtained through division and the cells in the same table obtained through recognition, the layout of the cells is regenerated; combining the cells according to the layout of the regenerated cells and the content in the cells; and generating description information of the target file according to the merged cells and the content in each cell, wherein the description information comprises the number of tables in the target file and the positions of each cell in the tables. The problem that a table cannot be recognized in an existing scheme is solved.

Description

technical field [0001] The application relates to a table recognition method, device and storage medium, and belongs to the field of computer technology. Background technique [0002] At present, many electronic documents are stored in the form of pictures, scanned paper copies, or PDF (Portable Document Format, Portable Document Format), and it is often necessary to identify the content in the document. [0003] In existing schemes, extracting text / tables from electronic files and reconstructing texts and tables in the form of html (Hyper Text Markup Language, Hypertext Markup Language) is of great significance to downstream data processing. Text data has been successfully extracted through ocr (Optical Character Recognition) and pdf file formats, but it is still difficult to accurately restore the table layout. Contents of the invention [0004] The present application provides a form recognition method, device and storage medium, which can solve the problem that the fo...

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): G06K9/00
CPCG06V30/412G06V10/94
Inventor 侯绍东周以晴熊玉竹
Owner 苏州美能华智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com