US 12,259,984 B2
Distributed computer architecture for processing data
Pieter Luitjens, Toronto (CA); and Graham Miller, Toronto (CA)
Assigned to Private AI Inc., Toronto (CA)
Filed by Private AI Inc., Toronto (CA)
Filed on Apr. 12, 2024, as Appl. No. 18/634,032.
Claims priority of provisional application 63/496,228, filed on Apr. 14, 2023.
Prior Publication US 2024/0346162 A1, Oct. 17, 2024
Int. Cl. G06F 21/62 (2013.01)
CPC G06F 21/6209 (2013.01) 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by one or more processors, from a client device, a first input including a first plurality of data elements to be provided at least in part to a deep learning architecture;
parsing, by the one or more processors, the plurality of data elements of the first input to identify at least one first data element corresponding to an identifier type of a plurality of identifier types that satisfies a redaction condition;
generating, by the one or more processors, a second data element corresponding to the identifier type to replace the at least one first data element in the first input;
storing, by the one or more processors, in one or more data structures, an association between the at least one first data element and the second data element;
generating, by the one or more processors, a first output from the first input by replacing the at least one first data element with the second data element;
transmitting, by the one or more processors, the first output for provision to a deep learning architecture;
receiving, by the one or more processors, a second input comprising a model output comprising a third data element generated by the deep learning architecture based on the second data element of the first output;
determining, by the one or more processors, that the third data element is an altered form of the second data element;
identifying, by the one or more processors, the at least one first data element associated with the second data element, responsive to determining that the third data element is the altered form of the second data element;
generating, by the one or more processors, using the one or more data structures storing the association, a second output from the second input by replacing the third data element with the at least one first data element identified as associated with the second data element; and
transmitting, by the one or more processors, to the client device, the second output including the at least one first data element.