US 12,235,828 B2
Systems and methods for detection and correction of anomalies priority
Johannes Schleith, London (GB); Brian Kent Cechmanek, London (GB); and Revogatus Apolinary Tesha, Cambridge, MA (US)
Assigned to Thomson Reuters Enterprise Centre GmbH, Zug (CH)
Filed by Thomson Reuters Enterprise Centre GmbH, Zug (CH)
Filed on Dec. 16, 2022, as Appl. No. 18/083,469.
Claims priority of provisional application 63/290,105, filed on Dec. 16, 2021.
Prior Publication US 2023/0195715 A1, Jun. 22, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/23 (2019.01); G06F 16/28 (2019.01)
CPC G06F 16/2365 (2019.01) [G06F 16/285 (2019.01)] 12 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, by one or more processors, a dataset comprising transaction data stored in a plurality of data sources, wherein the plurality of data sources store portions of the dataset in a non-standardized format dependent on hardware and software associated with each data source;
converting, by the one or more processors, information of the dataset to a standardized format;
executing, by the one or more processors, one or more clustering algorithms against the dataset to generate a plurality of clusters, wherein at least one duster of the plurality of clusters corresponds to a portion of the dataset comprising an anomaly;
applying a classifier to a portion of the dataset associated with the anomaly, wherein the classifier is configured to determine a cause of the anomaly;
mapping portions of the dataset to data fields of a report based on mapping data;
populating the data fields of the report with the mapped portions of the dataset;
initiating, by the one or more processors, one or more actions to eliminate the anomaly based at least in part on the cause of the anomaly; and
outputting, by the one or more processors, data derived from the dataset subsequent to the one or more actions, wherein the data derived from the dataset comprises the report.