Form information extraction method, system, apparatus, medium and program product
A technology of information extraction and tables, applied to neural learning methods, instruments, biological neural network models, etc., can solve problems such as cumbersome methods, difficult maintenance, and inability to deal with complex and diverse table structures, and achieve simple training rules and high accuracy Effect
Active Publication Date: 2022-07-12
ANHUI DIGITAL INTELLIGENT CONSTR RES INST CO LTD
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the current extraction methods based on deep learning are mostly rule-based methods that are cumbersome, require more rules to be defined, are difficult to maintain, cannot cope with complex and diverse table structures, and cannot meet the conditions of irregular tables. Requirements for Accurately Extracting Specified Content Information
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with some aspects of the invention as recited in the appended claims.
[0054] figure 1 is a flowchart of a method for extracting information from a table according to an exemplary embodiment, such as figure 1 shown, including:
[0055] In step S101, a table for information extraction to be performed is obtained.
[0056] Specifically, the user uploads the form for which information extraction needs to be performed according to his own needs, so as to obtain the table ...
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
Login to View More Abstract
The present disclosure relates to an information extraction method, system, device, medium and program product for a table, including: obtaining a table for information extraction; inputting the table into a pre-trained graph neural network, and obtaining the graph neural network from the table The content in the extracted target cell, wherein the graph neural network is pre-trained based on the following methods: obtaining table samples, labeling and classifying them according to the header cells and content cells of the table samples, and classifying the content of interest The corresponding header cells and content cells are labeled and classified; a graph structure is constructed according to the labeled table structure of the table sample, and the graph neural network is trained based on the graph structure and the training task. The present application uses a pre-trained graph neural network to extract the table to be subjected to information extraction, and can accurately extract the specified content information under the conditions of regular and irregular tables.
Description
technical field [0001] The present disclosure relates to the technical field of table information extraction, and in particular, to a table information extraction method, system, device, medium and program product. Background technique [0002] Tables are a very important and common semi-structured data widely used in documents and web pages. Tabular information is clear and easy to understand for humans. However, it is usually very tedious and time-consuming to manually extract the specified information from a large number of tables, so there is a method of automatically extracting the information in the table by a machine. [0003] In the related art, table-related research includes table recognition, table structure extraction, table understanding, etc., wherein table understanding is further divided into table-based information retrieval, table question and answer, and table content extraction. The extraction method of table content When faced with complex and diverse ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06V30/413G06V30/414G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 宋恒刘道学仇明清李亚楠耿天宝程维国孙朝福张志强
Owner ANHUI DIGITAL INTELLIGENT CONSTR RES INST CO LTD