US 12,169,808 B2
System and method for predictive product quality assessment
Aravindan Krishnan, Bangalore (IN); Seema Chopra, Bangalore (IN); and Kirk A. Hoeppner, Everett, WA (US)
Assigned to The Boeing Company, Arlington, VA (US)
Filed by The Boeing Company, Chicago, IL (US)
Filed on May 11, 2022, as Appl. No. 17/662,984.
Prior Publication US 2023/0368115 A1, Nov. 16, 2023
Int. Cl. G06Q 10/00 (2023.01); G06Q 10/0639 (2023.01)
CPC G06Q 10/06395 (2013.01) 18 Claims
OG exemplary drawing
 
12. A computing system, comprising:
a processor; and
a memory storing instructions executable by the processor to,
during an initialization phase,
receive initialization product assessment data for a plurality of products, wherein the initialization product assessment data comprises, for each product of the plurality of products,
one or more events, and
for each of the one or more events, an amount of remediation time associated with the event, a reassessment status that indicates whether the event is likely to trigger an additional product assessment, and a recurring event status; and
use the initialization product assessment data to initialize a product readiness model to determine a product readiness score based upon run-time product assessment data, wherein initializing the product readiness model comprises training a machine learning model using the initialization product assessment data as unlabeled input and using at least, for the one or more events for each product, the amount of remediation time associated with each of the one or more events, the reassessment status that indicates whether the event is likely to trigger the additional product assessment, and the recurring event status; and
during a run-time phase,
receive the run-time product assessment data comprising, for a selected product, one or more run-time events;
obtain, for each of the one or more run-time events, a run-time reassessment status that indicates whether the run-time event is likely to trigger an additional product assessment and a run-time recurring event status;
determine, based upon historic remediation data, a run-time remediation time for each of the one or more run-time events;
input a total run-time remediation time for the selected product, the run-time reassessment status and the run-time recurring event status into the product readiness model;
utilize the trained machine learning model of the product readiness model to determine and output the product readiness score of the selected product based upon the run-time product assessment data;
perform feedback training of the trained machine learning model; and
after performing feedback training of the trained machine learning model, using the feedback trained machine learning model to output another product readiness score.