Document auditing method and device, computer equipment and storage medium

Abstract

The invention discloses a document auditing method and device, computer equipment and a storage medium. The document auditing method comprises the steps of obtaining a to-be-audited document image associated with a document auditing instruction; inputting the to-be-audited document image into a character string area recognition model, and obtaining at least three character string area images through a YOLO algorithm; inputting each character string area image into a trained lightweight character recognition model, and performing character feature extraction on the character string area imagesto obtain a recognition result; judging whether the receipt information is the same as the receipt number or not to obtain a first judgment result, judging whether the identity card information is thesame as the identity card number or not to obtain a second judgment result, and judging whether the bank card information is the same as the bank card number or not to obtain a third judgment result;and if the first judgment result, the second judgment result and the third judgment result are the same, determining that the auditing is passed. According to the document auditing method, the character string in the document is automatically identified and audited, and the effect of automatically auditing the document is achieved.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a document auditing method, device, computer equipment and storage medium. Background technique [0002] With the development of science and technology, there are more and more scenes that need to review various document images and document images. For example, in many scenarios, it is necessary to review and verify the images of various personnel's filled-in documents to determine whether the information in them is wrong. , the workload is huge, and handwritten characters often appear in the forms filled by various personnel. At present, for the recognition of handwritten characters, manual recognition is required, and there is a certain recognition error rate; OCR (Optical Character Recognition, Optical Character Recognition) technology recognizes document images. Since the existing OCR technology recognizes characters one by one, the response time for character (especially handw...

AI Technical Summary

Problems solved by technology

[0002] With the development of science and technology, there are more and more scenes that need to review various document images and document images. For example, in many scenarios, it is necessary to review and verify the images of various personnel's filled-in documents to determine whether the information in them is wrong. , the workload is huge, and handwritten characters often appear in the forms filled by various personnel. At present, for the recognition of handwritten characters, manual recognition is required, and there is a certain recognition erro

Images