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

An analysis method and device for line-changing and page-changing of tables

An analysis method and table technology, applied in the field of recognition, can solve problems such as difficult to judge line break or non-line break

Active Publication Date: 2022-06-17
上海犀语科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, when there is a page break or line break, it is difficult to judge the line break or non-line break simply by the separator line or simple rules
For the case of no table line, it is difficult for the computer to make an accurate judgment on whether two adjacent rows output the same cell

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
  • An analysis method and device for line-changing and page-changing of tables
  • An analysis method and device for line-changing and page-changing of tables

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] like figure 1 As shown, the present invention provides a method for analyzing form line feed and page feed, comprising the following steps:

[0027] Step 1. Determine the clear line feed and page feed situation through expert experience summarization rules.

[0028] In step 1, the clear line feed and form feed situation is judged by the left parenthesis contained above and the right parenthesis contained below the two paragraphs of text, and the entire date composed of the upper and lower paragraphs of text.

[0029] Step 2. Use a deep learning model to obtain annotated corpus.

[0030] In step 2, the acquired annotated corpus includes semantic information of the content of two adjacent lines and associated cell information in the table.

[0031] Step 3. Determine whether two adjacent cells can be merged according to the marked corpus and by training a deep learning language model.

[0032] Step 4. Check the merged cell information to improve the accuracy of judgment...

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 present invention provides an analysis method for line and page changes in tables, including: judging clear line and page changes through expert experience summary rules; using deep learning models to obtain marked corpus; judging relevant Whether two adjacent cells can be merged. The device for implementing the above method includes: a judging module for judging the clear line and page change situation through expert experience summary rules; a marked corpus acquisition module for using a deep learning model to obtain the marked corpus acquisition module ; A cell merging judging module for judging whether two adjacent cells can be merged according to the labeled corpus and by training a deep learning language model. The present invention uses a deep learning model to mine the semantic information contained in the table, and can accurately analyze whether two adjacent cells can be merged in the scene of changing lines or changing pages.

Description

technical field [0001] The present invention relates to an identification method, in particular to an analysis method and device for form wrapping and form wrapping. Background technique [0002] In recent years, deep learning technology has been widely used in natural language processing, graphics and images, automatic driving and other fields, and the performance is significantly better than traditional methods. [0003] In the field of natural language processing, deep learning technology can capture deep grammatical and semantic information by encoding text in high-dimensional space, thus providing a technical basis for further advanced applications in the field of natural language processing based on semantics. [0004] In textual information processing, there are a large number of tables of different styles. There are still many problems in the extraction of table information in the current technology. For example, when a page break occurs, it is difficult to determi...

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 Patents(China)
IPC IPC(8): G06V30/416G06V20/70G06N20/00
CPCG06V30/412
Inventor 李鹏辉竺晨曦邱锡鹏
Owner 上海犀语科技有限公司