US 12,014,220 B2
Learning-based automatic selection of AI applications
Sun Young Park, San Diego, CA (US); Kourosh Jafari-Khouzani, Rego Park, NY (US); and Dustin Michael Sargent, San Diego, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Sep. 12, 2022, as Appl. No. 17/931,147.
Prior Publication US 2024/0086248 A1, Mar. 14, 2024
Int. Cl. G06F 9/50 (2006.01); G06F 11/34 (2006.01)
CPC G06F 9/5055 (2013.01) [G06F 11/3495 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-based method for learning-based automatic selection of artificial intelligence (AI) applications, the method comprising:
receiving a user request for an exam, the user request including exam information;
automatically identifying an exam type cluster corresponding to the received exam information;
automatically detecting applicable AI applications corresponding to the identified exam type cluster;
automatically running each applicable AI application on a series of relevant test sets to generate a score for each applicable AI application, wherein the series of relevant test sets comprise previously stored exams, each of the previously stored exams including a respective stored ground truth; and
automatically recommending to a user a highest-scoring applicable AI application based on the generated scores.