Techniques for targeted data extraction from unstructured sets of documents

A system for targeted data extraction, the system comprising:

• at least one memory configured to store computer-readable instructions;
• and
• at least one processor communicatively coupled with the at least one memory, and configured to execute the computer-readable instructions to:
• cause a display of a first view of a graphical user interface (GUI) displaying a plurality of graphical elements for selection, each graphical element of the plurality graphical elements corresponds with a respective document from a plurality of documents;
• detect a first input on the GUI selecting a first page view of a document from the plurality of documents, wherein the document is identified by selection of a respective graphical element associated with the document from among the plurality of documents;
• detect a second input identifying an area of the first page view of the document;
• determine coordinates of the area of the first page view;
• generate a visual box based on the coordinates;
• cause a display of the visual box in the document on the GUI;
• and
• preserve the visual box across an additional page, the additional page being one of remaining pages of the document or pages of remaining documents of the plurality of documents such that the display of the visual box persists in the additional page on the GUI.

One or more non-transitory computer-readable media comprising computer-readable instructions, which when executed by at least one processor of at least one computing device, cause the at least one computing device to:

• cause a display of a first view of a graphical user interface (GUI) displaying a plurality of graphical elements for selection, each graphical element of the plurality graphical elements corresponds with a respective document from a plurality of documents;
• detect a first input on the GUI selecting a first page view of a document from the plurality of documents, wherein the document is identified by selection of a respective graphical element associated with the document from among the plurality of documents;
• detect a second input identifying an area of the first page view of the document;
• determine coordinates of the area of the first page view;
• generate a visual box based on the coordinates;
• cause a display of the visual box in the document on the GUI;
• and
• preserve the visual box across an additional page, the additional page being one of remaining pages of the document or pages of remaining documents of the plurality of documents such that the display of the visual box persists in the additional page on the GUI.