US 12,379,904 B2
No-coding machine learning pipeline
Jiaqi Guo, Cupertino, CA (US); and Pavel A. Dournov, Sammamish, WA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jul. 7, 2023, as Appl. No. 18/348,623.
Application 18/348,623 is a continuation of application No. 16/549,675, filed on Aug. 23, 2019, granted, now 12,045,585.
Prior Publication US 2023/0350648 A1, Nov. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/0482 (2013.01); G06F 8/34 (2018.01); G06F 9/451 (2018.01); G06N 20/00 (2019.01)
CPC G06F 8/34 (2013.01) [G06F 3/0482 (2013.01); G06N 20/00 (2019.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method that when executed on data processing hardware causes the data processing hardware to perform operations comprising:
receiving, at a graphical user interface (GUI) of a user device displaying a plurality of machine learning sub-routines, a first selection of one or more machine learning sub-routines from the plurality of machine learning sub-routines, each respective machine learning sub-routine of the plurality of machine learning sub-routines comprising a corresponding set of machine learning parameters;
displaying, by the GUI of the user device, the selected one or more machine learning sub-routines at an edit area of the GUI of the user device;
displaying, by the GUI of the user device, source code representing the selected one or more machine learning model sub-routines;
receiving, at the GUI of the user device, a second selection adjusting the source code for the corresponding set of machine learning parameters for a respective one of the selected one or more machine learning sub-routines displayed at the edit area;
generating a machine learning model using the selected one or more machine learning sub-routines and the adjusted source code for the corresponding set of machine learning parameters for the selected one or more machine learning sub-routines displayed at the edit area; and
training the machine learning model using a training dataset.