US 12,468,643 B2
System integrations based on intelligent monitoring
Debashis Upagupta Mishra, Jharsuguda (IN); Varun Jain, Foster City, CA (US); and Suraj Singh, Pleasanton, CA (US)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Feb. 9, 2024, as Appl. No. 18/437,403.
Prior Publication US 2025/0258788 A1, Aug. 14, 2025
Int. Cl. G06F 13/22 (2006.01)
CPC G06F 13/22 (2013.01) 20 Claims
OG exemplary drawing
 
1. One or more non-transitory computer readable media comprising instructions which, when executed by one or more hardware processors, cause performance of operations comprising:
obtaining historical data comprising:
characteristics of a first task;
a first execution time for the first task;
generating a training data set comprising the historical data;
training a machine learning model to compute execution times for tasks based on the training data set;
receiving a second task for execution;
applying the machine learning model to characteristics of the second task to predict a second execution time for the second task; and
generating a first polling configuration for requesting results based at least on the second execution time predicted by the machine learning model.
 
11. A method, comprising:
obtaining historical data comprising:
characteristics of a first task;
a first execution time for the first task;
generating a training data set comprising the historical data;
training a machine learning model to compute execution times for tasks based on the training data set;
receiving a second task for execution;
applying the machine learning model to characteristics of the second task to predict a second execution time for the second task;
generating a first polling configuration for requesting results based at least on the second execution time predicted by the machine learning model; and
wherein the method is performed by at least one device including a hardware processor.