US 11,893,590 B2
Interpretation workflows for machine learning-enabled event tree-based diagnostic and customer problem resolution
James Fan, San Ramon, CA (US); Al Hooshiari, Alpharetta, GA (US); Dan Celenti, Holmdel, NJ (US); and Eric Forbes, Canton, GA (US)
Assigned to AT&T Intellectual Property I, L.P., Atlanta, GA (US)
Filed by AT&T Intellectual Property I, L.P., Atlanta, GA (US)
Filed on Jun. 2, 2021, as Appl. No. 17/336,396.
Prior Publication US 2022/0391917 A1, Dec. 8, 2022
Int. Cl. G06Q 10/00 (2023.01); G06Q 30/016 (2023.01); G06Q 10/0631 (2023.01); G06N 20/00 (2019.01); G06Q 10/0633 (2023.01); G06N 5/01 (2023.01)
CPC G06Q 30/016 (2013.01) [G06N 5/01 (2023.01); G06N 20/00 (2019.01); G06Q 10/0633 (2013.01); G06Q 10/06315 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a system comprising a processor, a workflow construction specification derived from a machine learning-enabled event tree, wherein the machine learning-enabled event tree is generated for use by a customer service agent to resolve a customer problem, and wherein the workflow construction specification comprises a plurality of objects, each of which represents a navigation path through the machine learning-enabled event tree;
traversing, by the system, the workflow construction specification and creating a set of workflow creation commands based upon at least one policy;
generating, by the system, a workflow visualization interpretation file based upon the set of workflow creation commands, wherein the workflow visualization interpretation file identifies how the machine learning-enabled event tree derived a root cause of the customer problem; and
presenting, by the system, the workflow visualization interpretation file to the customer service agent.