Methods and systems for artificial intelligence- assisted document annotation

A computer-implemented method for electronic document annotation comprising:

• displaying an electronic document, or a page therefrom, on an electronic display device;
• receiving a first input from a user indicating a selection of a label that may be applicable to categories of text within the electronic document;
• displaying a selection of text in the electronic document that may match a category of text corresponding to the user-selected label;
• receiving a second input from the user to confirm a match between the selection of text and the category of text corresponding to the user-selected label, thereby assigning the label to the selection of text;
• and
• storing the assigned label, the selection of text, and a location of the selected text for one or more instances of selected text within the electronic document as an annotated electronic document;
• wherein the annotated electronic document is used to train or retrain one or more term-based machine learning models, and wherein the one or more term-based models are used for document data extraction in a continuous learning-based document data extraction pipeline.

A system comprising:

• one or more processors;
• a memory;
• an electronic display device;
• and
• one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
• displaying an electronic document, or a page therefrom, on the electronic display device;
• receiving a first input from a user indicating a selection of a label that may be applicable to categories of text within the electronic document;
• displaying a selection of text that may match a category of text corresponding to the user-selected label, wherein the selection of text is based on an artificial intelligence-based prediction by the system;
• receiving a second input from the user to confirm a match between the selection of text and the category of text corresponding to the user-selected label, thereby assigning the label to the selection of text;
• and
• storing the assigned label, the selection of text, and a location of the selected text for one or more instances of selected text within the electronic document as an annotated electronic document;
• wherein the annotated electronic document is used to train or retrain one or more term-based machine learning models, and wherein the one or more term-based models are used for document data extraction in a continuous learning-based document data extraction pipeline.

A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, the instructions when executed by one or more processors of a computing platform, cause the computing platform to:

• display an electronic document, or a page therefrom, on an electronic display device;
• receive a first input from a user indicating a selection of a label that may be applicable to categories of text within the electronic document;
• display a selection of text that may match a category of text corresponding to the user-selected label, wherein the selection of text is based on an artificial intelligence-based prediction;
• receive a second input from the user to confirm a match between the selection of text and the category of text corresponding to the user-selected label, thereby assigning the label to the selection of text;
• and
• store the assigned label, the selection of text, and a location of the selected text for one or more instances of selected text within the electronic document as an annotated electronic document;
• wherein the annotated electronic document is used to train or retrain one or more term-based machine learning models, and wherein the one or more term-based models are used for document data extraction in a continuous learning-based document data extraction pipeline.