US 11,810,126 B2
System and method for implementing an intelligent customer service query management and routing system
Mike Dai, East Rutherford, NJ (US); Heidi V. Tumey, New Castle, DE (US); Fran Bocain, Holbrook, NY (US); Ramesha Narasappa, Jersey City, NJ (US); Rajesh Kalyanpur, Green Brook, NJ (US); Jignesh M. Patel, Iselin, NJ (US); and Keith Mascheroni, Brooklyn, NY (US)
Assigned to JPMORGAN CHASE BANK, N.A., New York, NY (US)
Filed by JPMorgan Chase Bank, N.A., New York, NY (US)
Filed on Apr. 4, 2019, as Appl. No. 16/374,888.
Claims priority of provisional application 62/652,452, filed on Apr. 4, 2018.
Prior Publication US 2019/0311374 A1, Oct. 10, 2019
Int. Cl. G06Q 30/016 (2023.01); G06F 40/205 (2020.01); G06F 40/279 (2020.01); G06N 5/02 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 30/016 (2013.01) [G06F 40/205 (2020.01); G06F 40/279 (2020.01); G06N 5/02 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system that implements an intelligent customer service query management and routing system, the system comprising:
one or more processors; and memory, wherein the memory stores computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to:
receive, via a communications server, a query from a client;
apply, via a predictive analytics engine, predictive analytics to the query, wherein the predictive analytics engine further applies data enrichment that fetches associated metadata;
provide, via a management platform dashboard, an interface for a customer service representative to provide feedback to the predictive analytics engine, wherein the management platform dashboard simultaneously comprises a plurality of icons, a plurality of links to contact information for various queries that each distinctly correspond to one of the plurality of links, a plurality of indications that display various statistics about queries that have been received, and a display of information about routing of the queries that have been received;
build, monitor, optimize and deploy, via a periodic model build processing component, one or more predictive models executed by the predictive analytics engine;
cache, via the memory, current training data to ensure that predictions are made in real-time;
phase out, via the memory, irrelevant training data;
receive, from the periodic model build processing component, a signal that indicates that the periodic model build processing component is ready to load the current training data;
retrieve the current training data from a cache of the memory;
use the current training data to retrain, via the periodic model build processing component, the one or more predictive models on a periodic basis; and
make, via the predictive analytics engine, real-time predictions by applying tags to the query, virtually immediately after receiving the query.