Automatic development and enhancement of deep learning model for data extraction using feedback loop

A method comprising:

• storing, by one or more databases, one or more documents of a specified type of document together with data automatically extracted from each document via at least one extraction model for the specified type of document, the at least one extraction model comprising a machine learning (ML) model;
• generating, by at least one server, an interactive graphical user interface (GUI) on at least one user device, the interactive GUI configured to display, for a document of the one or more documents, said document together with one or more extracted data indications associated with the respective extracted data and user interaction tools to indicate any user correction information associated with the one or more extracted data indications, the at least one server being operatively coupled to the one or more databases, the at least one server comprising one or more processors and a memory storing computer-readable instructions executable by the one or more processors, the memory storing the at least one extraction model, the interactive GUI comprising an extraction region configured to display one or more fields of the extracted data, and a document region configured to display the document and bounding boxes used to define the extraction region;
• receiving, by the at least one server, via the user interaction tools of the interactive GUI, from the at least one user device, user correction information associated with at least one field among the one or more fields of the extraction region to form training data, the user correction information including:
• forming corrected bounding boxes by correcting one or more of the bounding boxes used to define the extraction region and forming corrected data by correcting the extracted data for at least one field among the one or more fields;
• storing, by the at least one server, in the one or more databases, the user correction information forming the training data received from the at least one user device via the user interaction tools of the interactive GUI for the one or more documents, such that each of the one or more documents, the respective extracted data and the corresponding user correction information form an extracted document dataset, each extracted document dataset being updated as corresponding new user correction information is received;
• monitoring, by the at least one server, in real-time, performance characteristics of the at least one extraction model based on the user correction information in each extracted document dataset, stored in the one or more databases;
• executing an automated extraction model update process, comprising:
• determining, by the at least one server, a status of a trigger for extraction model training, wherein the trigger is based on the performance characteristics of the at least one extraction model;
• augmenting, by the at least one server, the training data by correlating images from the specified type of document with the user correction information corresponding to the images from the specified type of document, and preprocessing both the images and the user correction information to form a labeled dataset having a format compatible with model training;
• determining, by the at least one server, that the labeled dataset is of a threshold quantity and of a predetermined data quality for extraction model training, wherein the determining that the labeled dataset is of the predetermined data quality comprises calculating a distance between the extracted data and the user correction information associated with the at least one field among the one or more fields of the extraction region, determining that the distance is within a threshold distance, and determining the labeled dataset includes a desired number of fields;
• and
• responsive to the status of the trigger indicating that the performance characteristics of the at least one extraction model are below a predefined threshold, and that the labeled dataset is of the threshold quantity and the predetermined data quality:
• extracting, by the at least one server, the labeled dataset of the specified type of document from the one or more databases, and
• automatically updating and training, by the at least one server, the at least one extraction model using the labeled dataset to form at least one new extraction model, the at least one new extraction model being used for executing subsequent data extraction operations for the specified type of document.