US 12,333,277 B2
Machine-learned models for generating code snippets with predicted placeholders for optimizing software development
Daniel Dun-ning Woo Johnson, Toronto (CA); Daniel Stefan Tarlow, Montréal (CA); Maxim Tabachnyk, Munich (DE); Marc Hatcher Rasi, Sunnyvale, CA (US); Jacob Austin, New York, NY (US); Hassan Abolhassani, Palo Alto, CA (US); and Jacob Hanson Hegna, Minneapolis, MN (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Mar. 27, 2024, as Appl. No. 18/618,371.
Application 18/618,371 is a continuation of application No. 17/832,199, filed on Jun. 3, 2022, granted, now 11,972,234.
Prior Publication US 2024/0231765 A1, Jul. 11, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 8/33 (2018.01)
CPC G06F 8/33 (2013.01) 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for machine-learned code segment prediction for optimizing software development, comprising:
obtaining, by a computing system comprising one or more computing devices, an incomplete segment of code;
processing, by the computing system, the incomplete segment of code with a machine-learned code prediction model to obtain a segment completion prediction, wherein the segment completion prediction comprises code that completes the incomplete segment of code and an input field, wherein the input field replaces a portion of the segment completion prediction associated with a degree of certainty less than a threshold degree of certainty; and
providing, by the computing system, the segment completion prediction for display to a user.