A method and a terminal for creating paper document structured data based on a deep learning model

Abstract

The invention relates to a method and a terminal for creating paper document structured data based on a deep learning model. The method comprises the following steps: training a sample set through a preset document; wherein each sample in the document sample set comprises a paper document OCR recognition result and a labeled document corresponding to the paper document OCR recognition result; wherein the labeled document records position information and category information of each key field in the OCR recognition result of the paper document; training a preset first deep learning model by using the training sample set to obtain a second deep learning model; enabling the second deep learning model to analyze a first paper document OCR recognition result to obtain position information and category information of each key field in the first paper document OCR recognition result; and creating a structured document corresponding to the first paper document OCR recognition result accordingto the position information and the category information of each key field in the first paper document OCR recognition result. The accuracy of converting the OCR result of the paper document into thestructured document is improved.

Description

technical field [0001] The invention relates to a method and terminal for creating paper document structured data based on a deep learning model, and belongs to the field of artificial intelligence paper document identification data processing. Background technique [0002] Converting paper documents to structured data is a method of extracting key field information from a large amount of text information in the ORC recognition results of paper documents, such as the payer, payment date, and payee in the receipt, and according to certain The process of saving the structure. After a large number of paper documents identified by OCR are processed in a structured manner, efficient document retrieval, document analysis and other intelligent services can be provided. The key and main technical difficulty of structured data processing of paper documents is to extract key field information from a large amount of text, including determining the location of the required key fields i...

AI Technical Summary

Problems solved by technology

However, this document structure system is only effective when the positions of the fields to be intercepted are fixed in all documents, which limits the scope of use of the system

In actual application, if the invoice printing system sets different key field content printing position settings or the key field content length changes, the content information of these key fields will be offset and exceed the setting range, resulting in errors

For some bill recognition applications, a large number of bills are stored in the computer by scanning or taking pictures with mobile phones, which can easily cause the displacement of bills in the image, and different bills may have different formats, and the position of the same field in the image is not necessarily the same , these characteristics make the above-mentioned document structuring scheme not suitable for businesses such as bill identification

For the above-mentioned document structuring scheme, the accuracy of converting the ORC recognition results of paper documents into structured document nodes is low for application scenarios where position shifts are prone to occur.

Images