Digital organization of printed documents according to extracted semantic information

An electronic device, comprising:

• one or more processors;
• and
• memory storing one or more programs for execution by the one or more processors, the one or more programs including instructions for:
• receiving one or more printed documents, each printed document including a respective one or more pages;
• for each printed document:
• for each page of the respective printed document:
• scanning the respective page to obtain an image file;
• applying one or more trained classifier models to the image file to determine a document class for the respective page, wherein the one or more trained classifier models are trained using documents of a plurality of document classes, each document class is associated with a semantic analyzer pipeline of a plurality of semantic analyzer pipelines, and each semantic analyzer pipeline includes (i) a preprocessing semantic analyzer to preprocess the respective page, and (ii) an optical character recognition (OCR)-based semantic analyzer to process output of the preprocessing semantic analyzer;
• determining, based on the document class, a respective semantic analyzer pipeline for analyzing the respective page;
• applying the preprocessing semantic analyzer to the image file to generate a preprocessed output page;
• and
• applying the OCR-based semantic analyzer to the preprocessed output page to extract semantic information corresponding to the respective page;
• determining a digital organization for the respective printed document based on the extracted semantic information and the document class corresponding to respective pages of the respective printed document.

A non-transitory computer-readable storage medium storing one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for:

• receiving one or more printed documents, each printed document including a respective one or more pages;
• for each printed document:
• for each page of the respective printed document:
• scanning the respective page to obtain an image file;
• applying one or more trained classifier models to the image file to determine a document class for the respective page, wherein the one or more trained classifier models are trained using documents of a plurality of document classes, each document class is associated with a semantic analyzer pipeline of a plurality of semantic analyzer pipelines, and each semantic analyzer pipeline includes (i) a preprocessing semantic analyzer to preprocess the respective page, and (ii) an optical character recognition (OCR)-based semantic analyzer to process output of the preprocessing semantic analyzer;
• determining, based on the document class, a respective semantic analyzer pipeline for analyzing the respective page;
• applying the preprocessing semantic analyzer to the image file to generate a preprocessed output page;
• and
• applying the OCR-based semantic analyzer to the preprocessed output page to extract semantic information corresponding to the respective page;
• determining a digital organization for the respective printed document based on the extracted semantic information and the document class corresponding to respective pages of the respective printed document.