US 11,971,900 B2
Rule-based data transformation using edge computing architecture
Raja Arumugam Maharaja, Tamil Nadu (IN); and Khushbu Rani, Bokaro Steel (IN)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Feb. 4, 2022, as Appl. No. 17/592,712.
Prior Publication US 2023/0252040 A1, Aug. 10, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/25 (2019.01); G06F 18/2411 (2023.01); G06N 3/045 (2023.01); G06N 20/10 (2019.01)
CPC G06F 16/258 (2019.01) [G06F 16/254 (2019.01); G06F 18/2411 (2023.01); G06N 3/045 (2023.01); G06N 20/10 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for rule-based data processing, the system comprising:
a plurality of edge computing nodes, wherein each of the edge computing nodes is associated with a corresponding set of data transformation rules; and
a central computing node comprising:
a processor; and
memory storing computer-readable instructions that, when executed by the processor, cause the central computing node to:
receive a first data set;
determine, an edge computing node, among the plurality of edge computing nodes, for processing the first data set;
send, to the edge computing node, a subset of the first data set, wherein the subset of the first data set comprises one or more records that are randomly selected from the first data set, and wherein the sending the subset of the first data set causes generating a second data set at the edge computing node based on applying a first set of data transformation rules associated with the edge computing node to the subset of the first data set;
receive, from the edge computing node, the second data set;
determine, using a machine learning (ML) algorithm based on the subset of the first data set and the received second data set, a second set of data transformation rules;
generate a third data set based on applying the second set of data transformation rules to a remainder of the first data set, wherein the remainder of the first data set does not include the subset of the first data set; and
send, to the edge computing node, at least a subset of the third data set.