Table extraction method and device, terminal and computer readable storage medium

An extraction method and table technology, applied in the field of data extraction, can solve the problem that the table extraction method cannot directly extract the table, etc.

Pending Publication Date: 2020-01-07
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a form extraction method, device, terminal and readable storage medium, aiming to solve the technical problem that the existing form extraction method cannot directly extract the required form

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 extraction method and device, terminal and computer readable storage medium
  • Table extraction method and device, terminal and computer readable storage medium
  • Table extraction method and device, terminal and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0081] Further, please refer to image 3 , image 3 It is a detailed schematic diagram of the process of identifying the word document and obtaining the table keywords corresponding to each table in the word document in the embodiment of the present invention. Based on the first embodiment, step S300 includes:

[0082] Step S310, identifying tables in the word document, and obtaining internal keywords of each table;

[0083] Specifically, a word document can be recognized through a java and / or python program, a separate table and text can be obtained, and the content in the table can be extracted as internal keywords. The internal keywords include the header of the first row and / or first column of the table.

[0084] Step S320: parse the document type of the word document;

[0085] Specifically, the description object between the table and its corresponding paragraph text is highly related. Some word documents have a fixed typesetting format, such as contracts, resumes, etc. The docume...

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 a table extraction method. The method comprises the steps of obtaining a query request and a word document to be extracted; obtaining a corresponding query keyword according tothe query request; identifying the word document, and obtaining a table keyword corresponding to each table in the word document; respectively carrying out similarity matching on the query keyword and the table keyword corresponding to each table to obtain the similarity between the query keyword and the table keyword corresponding to each table; and extracting a table corresponding to the presetnumber of table keywords with the highest similarity. The invention further provides a table extraction device, a terminal and a computer readable storage medium. According to the technical scheme provided by the invention, the form in the word is extracted based on data query, and the required target form can be directly extracted from the word document.

Description

Technical field [0001] The present invention relates to the technical field of data extraction, and in particular to a table extraction method, device, terminal and computer-readable storage medium. Background technique [0002] At present, the Table Iterator of POI (Apache POI) is usually used to obtain the data in the word table, but this will read the data set of all tables, and the user cannot tell which table this kind of table is from the information of the cells in a table. Therefore, users cannot directly extract the required form from multiple forms in the word document. [0003] Therefore, the existing table extraction method cannot directly extract the required table is a problem to be solved urgently. Summary of the invention [0004] The main purpose of the present invention is to provide a table extraction method, device, terminal and readable storage medium, aiming to solve the technical problem that the existing table extraction method cannot directly extract the re...

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): G06F16/33G06F16/383
CPCG06F16/334G06F16/383
Inventor刘翔佘昊天
OwnerPING AN TECH (SHENZHEN) CO LTD