Document file identification method and system

Abstract

The invention discloses a document file identification method and system. The method comprises the following steps: judging the type of an obtained unknown file, and screening out a document file; judging the authenticity of the document files, and screening out real document files; sequentially identifying important information and attribute information of the real document file to obtain complete information of the real document file. By means of the above manner, whether the unknown file to be recognized is the document file or not can be judged in advance, and the authenticity of the unknown file can be judged, so that the needed real document file is accurately screened out, complex processing on irrelevant files or non-real document files is prevented, and the recognition efficiencyis improved; according to the document file identification method and system, the document file is automatically identified, and important information and other attribute information in the real document file are automatically identified, so that tedious manual input is prevented, frequent updating and maintenance according to the change of the document file are not needed, accurate and efficientidentification of the document file is realized while the cost is saved, and the document file identification method and system have relatively high application value.

Description

technical field [0001] The invention relates to the technical field of document identification and processing, in particular to a document identification method and system thereof. Background technique [0002] Document documents refer to the written certificates obtained or filled in when economic business occurs, which specify the actual situation of transactions and matters. It is the original data and important basis for accounting and is a common document in economic business in various fields. For example, in the field of business foreign trade, from the inquiry form in the inquiry process, to the quotation list in the quotation process, to the proforma invoice issued after the intention is confirmed, and the official invoice, to the final receipt of payment, every stage There are different documents, and these documents are transmitted in the form of files by mail or instant messaging. It is an indispensable process to identify and process these documents. [0003] D...

AI Technical Summary

Problems solved by technology

However, this patent converts all kinds of receipt documents into pdf format and then uses the region growing algorithm to segment the region, which has a large amount of calculation and low recognition efficiency; and, in the actual application process, there are often Mixed with other types of documents, not all real document documents, the method provided by the patent not only cannot screen them out, but also consumes a lot of time and computation for the identification of such documents, resulting in the identification efficiency of the method provided by the patent Low, low accuracy, difficult to meet the needs of practical applications

Images