US 11,880,749 B2
System and method for deploying and versioning machine learning models
Amit Deshpande, McKinney, TX (US); Jason Hoover, Grapevine, TX (US); Geoffrey Dagley, McKinney, TX (US); Qiaochu Tang, The Colony, TX (US); Stephen Wylie, Carrollton, TX (US); Micah Price, Plano, TX (US); and Sunil Vasisht, Flowermound, TX (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Apr. 9, 2020, as Appl. No. 16/844,399.
Application 16/844,399 is a continuation of application No. 15/916,032, filed on Mar. 8, 2018, granted, now 10,621,513.
Prior Publication US 2020/0234195 A1, Jul. 23, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a request from a remote computer for a pre-trained machine learning model;
receiving one or more parameters for the pre-trained machine learning model via a first application programming interface (API), the API being accessible by the remote computer via an application executing on the remote computer and wherein the one or more parameters comprises a machine learning model type for the pre-trained machine learning model and data to be analyzed by the pre-trained machine learning model;
retrieving from a library of a plurality of machine learning models the pre-trained machine learning model corresponding to a type of model specified in the one or more parameters;
generating a container image comprising the pre-trained machine learning model and the data to be analyzed by the pre-trained machine learning model; and
provisioning a container based on the container image, wherein the pre-trained machine learning model analyzes the data following provisioning.