US 11,886,907 B2
Analytic model execution engine with instrumentation for granular performance analysis for metrics and diagnostics for troubleshooting
Stuart Bailey, San Jose, CA (US); Matthew Mahowald, Chicago, IL (US); and Maksym Kharchenko, Kyiv (UA)
Assigned to ModelOp, Inc., Chicago, IL (US)
Filed by ModelOp, Inc., Chicago, IL (US)
Filed on Nov. 28, 2022, as Appl. No. 18/070,168.
Application 18/070,168 is a continuation of application No. 17/074,271, filed on Oct. 19, 2020, granted, now 11,544,099.
Application 17/074,271 is a continuation of application No. 16/782,904, filed on Feb. 5, 2020, granted, now 10,860,365, issued on Dec. 8, 2020.
Application 16/782,904 is a continuation of application No. 15/721,310, filed on Sep. 29, 2017, granted, now 10,599,460, issued on Mar. 24, 2020.
Claims priority of provisional application 62/542,218, filed on Aug. 7, 2017.
Prior Publication US 2023/0135164 A1, May 4, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 9/455 (2018.01); G06F 8/60 (2018.01); G06F 9/50 (2006.01); G06F 8/30 (2018.01); G06F 8/51 (2018.01); G06N 20/20 (2019.01); G06N 20/00 (2019.01); G06Q 10/067 (2023.01); G06N 5/01 (2023.01)
CPC G06F 9/45558 (2013.01) [G06F 8/31 (2013.01); G06F 8/51 (2013.01); G06F 8/60 (2013.01); G06F 9/455 (2013.01); G06F 9/45504 (2013.01); G06F 9/5077 (2013.01); G06F 8/30 (2013.01); G06N 5/01 (2023.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G06Q 10/067 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor configured to:
receive, at an interface of the system, an analytic model for processing an input data stream;
inspect the analytic model to determine a programming language of the analytic model, an action to be performed on the input data stream, a type of the input data stream, and a type of an output data stream;
generate a virtualized execution environment (VEE) for an analytic engine, wherein the VEE includes executable code to implement the analytic model for processing the input data stream, wherein the VEE binds the analytic model and a stream configuration descriptor based on a schema shared by the analytic model and the stream configuration descriptor;
translate the determined programming language of the analytic model to a first analytic model programming language, wherein the translation generates the executable code; and
route, based on the first analytic model programming language, the executable code to one runtime engine of a plurality of runtime engines of the VEE, wherein the VEE binds the analytic model with a model runner associated with the one runtime engine, wherein the one runtime engine supports the first analytic model programming language, and wherein the one runtime engine executes the executable code; and
a memory coupled to the processor and configured to provide the processor with instructions.