File process system and method

Abstract

The present invention discloses a document processing system and method. Said system includes the following several portions: template storage module, it is used for storing input template and output template; template matching module, it is used for receiving input document and utilizes format information of input document and / or specific information of input template to select correspondent input and / or output template from template storage module; and document automatic processing module, it is used for extracting information of input document according to the input template selected by template matching module and is used for storing the information of extracted input document by utilizing output module.

Description

technical field [0001] The invention relates to a document processing system and method, in particular to a system and a method for identifying documents and processing the identified documents. Background technique [0002] Document format recognition has always been a difficult problem in document automatic processing, because document formats vary and there is no fixed form at all. [0003] In real work and life, it is often encountered that documents in the same format need to be processed repeatedly, because documents in the same format are often used repeatedly by different people at different times, such as a company's job application form, different application forms, etc. Applicants always fill out the application form in the same format at different times. For repeated processing of documents in the same format (such as the application form mentioned above), the format of the document to be processed can be saved in advance. By saving the format information of the...

AI Technical Summary

Problems solved by technology

Although the efficiency of template creation can be improved by automatically creating templates, the main object of this processing is image files. At the same time, the automatically created template information is very limited, and the help for automatic document processing is very limited, and the output specified by the user cannot be completed. Format

[0005] The patent number is US6,785,420, and the title of the invention is "Method and apparatus for table recognition, apparatus for character recognition, and computer product (Method and apparatus for table recognition, apparatus for character recognition, and computer product)" of the invention, which discloses a method for table processing, Find the positions of tables, strings and lines through connected domain analysis, and then use these information for table recognition. However, the template information of the document is not used in this method

Images