US 11,893,501 B2
Big data based predictive graph generation system
Harish Ragavan, W. Windsor, NJ (US); and Srinivasan Shanmugam, Highland Park, NJ (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Sep. 26, 2022, as Appl. No. 17/952,886.
Application 17/952,886 is a continuation of application No. 16/933,589, filed on Jul. 20, 2020, granted, now 11,526,771.
Application 16/933,589 is a continuation in part of application No. 15/094,636, filed on Apr. 8, 2016, granted, now 10,754,867, issued on Aug. 25, 2020.
Prior Publication US 2023/0007994 A1, Jan. 12, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/901 (2019.01); G06F 16/25 (2019.01); G06F 16/904 (2019.01); G06N 5/02 (2023.01); G06Q 50/00 (2012.01); G06Q 10/0635 (2023.01); G06F 16/23 (2019.01)
CPC G06N 5/02 (2013.01) [G06F 16/2379 (2019.01); G06F 16/258 (2019.01); G06F 16/904 (2019.01); G06F 16/9024 (2019.01); G06Q 10/0635 (2013.01); G06Q 50/01 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a data accumulation server communicatively coupled via a network to a data repository, wherein the data accumulation server comprises
a first processor; and
first non-transitory memory storing first computer-readable instructions that, when executed by the first processor, cause the data accumulation server to:
receive information from a plurality of data sources, wherein the plurality of data sources comprises two or more of business computing systems, social media networks, and user devices;
store the information received from the plurality of data sources in the data repository;
monitor the plurality of data sources for at least one data change event at one or more of the plurality of data sources; and
update, based on the data change event, the data stored in the data repository into an updated data set; and
a predictive graph processing system comprising:
a second processor;
second non-transitory memory storing second computer-readable instructions that, when executed by the second processor, cause the predictive graph processing system to:
retrieve information from the data repository;
transform, based on a predictive model, the information retrieved from the data repository into a predictive graph data set;
predict, based on an indication of the data change event and using the predictive model, a first relationship between a plurality of objects of an updated data set, wherein the first relationship between the plurality of objects of the updated data set comprises a semantic relationship;
store the predictive graph data set to a visualization data repository, wherein the predictive graph data set comprises the first relationship; and
cause display, based on a visualization request, a visualization of the predictive graph data set comprising an indication of the first relationship between the plurality of objects of the updated data set.