US 11,675,614 B2
Standardized model packaging and deployment
Eugene Von Niederhausern, Rosenberg, TX (US); Sreenivasa Gorti, Austin, TX (US); Kevin W. DiVincenzo, Pflugerville, TX (US); and Sridhar Sudarsan, Austin, TX (US)
Assigned to SPARKCOGNITION, INC., Austin, TX (US)
Filed by SPARKCOGNITION, INC., Austin, TX (US)
Filed on Feb. 16, 2021, as Appl. No. 17/176,889.
Claims priority of provisional application 62/976,965, filed on Feb. 14, 2020.
Prior Publication US 2021/0255839 A1, Aug. 19, 2021
Int. Cl. G06F 8/60 (2018.01); G06F 9/455 (2018.01); G06F 11/34 (2006.01); G06F 9/48 (2006.01); G06F 9/50 (2006.01); G06F 8/35 (2018.01); G06F 8/41 (2018.01); G06F 8/52 (2018.01); G06F 16/903 (2019.01); G06N 20/00 (2019.01); G06F 16/21 (2019.01); G06N 5/04 (2023.01)
CPC G06F 9/45558 (2013.01) [G06F 8/35 (2013.01); G06F 8/433 (2013.01); G06F 8/52 (2013.01); G06F 8/60 (2013.01); G06F 9/4881 (2013.01); G06F 9/5077 (2013.01); G06F 11/3447 (2013.01); G06F 16/211 (2019.01); G06F 16/90335 (2019.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06F 2009/4557 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method implemented by a computing device for standardized model packaging and deployment, the method comprising:
generating a model package comprising:
for a model, model definition data that includes a binding to a computer programming language, wherein the model is a trained machine learning model to generate prediction data, wherein the binding enables one or more functions written in the computer programming language to execute one or more portions of the model;
function code that facilitates execution of the model via the binding;
at least one interface for at least one operating system; and
wherein one or more of the model definition data or the function code access one or more runtime dependencies excluded from the model package.