US 12,468,856 B2
AI-assisted compliance mapping
Abdulhamid Adebowale Adebayo, White plains, NY (US); Anca Sailer, Scarsdale, NY (US); Muhammed Fatih Bulut, West Greenwich, RI (US); and Daby Mousse Sow, Croton on Hudson, NY (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jan. 18, 2022, as Appl. No. 17/577,978.
Prior Publication US 2023/0229812 A1, Jul. 20, 2023
Int. Cl. G06F 21/64 (2013.01); G06N 20/00 (2019.01)
CPC G06F 21/64 (2013.01) [G06N 20/00 (2019.01)] 25 Claims
OG exemplary drawing
 
1. A system, comprising:
a memory that stores computer executable components; and
a processor that executes at least one of the computer executable components that:
trains a machine learning model to map compliance controls for target domains, wherein the training comprises:
receiving a plurality of context result data sets for a plurality of contexts, wherein each context result data set corresponds to a respective context of the plurality of contexts derived from a respective associate domain specific dependency for an associate domain among entities in a target domain;
for each context result data set, validating context result data of the context result data set to generate validation data representing semantic relationships within the respective context;
aggregating the validation data from the respective contexts to form an aggregated data set;
mapping, using the machine learning model and the aggregated data set, a compliance control to the respective contexts;
presenting, via a user interface, the mapping of the compliance control to the contexts;
receiving, via the user interface, feedback regarding the mapping; and
updating the mapping based on the feedback.