US 12,223,403 B2
Machine learning model publishing systems and methods
Isidre Royo Bonnin, Terrassa (ES); and Mariano Fernandez Garrido, Seville (ES)
Assigned to OPEN TEXT SA ULC, Halifax (CA)
Filed by OPEN TEXT SA ULC, Halifax (CA)
Filed on Oct. 31, 2022, as Appl. No. 17/977,839.
Application 17/977,839 is a continuation of application No. 16/262,170, filed on Jan. 30, 2019, granted, now 11,514,356.
Prior Publication US 2023/0072862 A1, Mar. 9, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01); G06F 16/182 (2019.01)
CPC G06N 20/00 (2019.01) [G06F 16/182 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
responsive to an indication that a machine learning (ML) model has been trained and is ready for publication, generating, by a computer, a model publication request form or window within a ML modeling application on a user device, the ML model publication request form or window containing input fields and a publication button;
accessing, by the computer, a data structure in memory, the data structure containing an attribute used in training the ML model;
populating, by the computer, the input fields of the publication request form or window with a path to a repository location where the ML model is stored and with information from the data structure describing the attribute used in training the ML model;
receiving, by the computer, an indication that the publication button has been selected for single-click publication of the ML model; and
performing, by the computer, the single-click publication of the ML model to a target computing system, including providing the target computing system with the path to the repository location where the ML model is stored and the information describing the attribute used in training the ML model.