US 12,299,423 B2
Intent-based machine programming
Brian Cremeans, Hillsboro, OR (US); Marcos Emanuel Carranza, Portland, OR (US); Krishna Surya, Portland, OR (US); Mats Agerstam, Portland, OR (US); and Justin Gottschlich, Santa Clara, CA (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Mar. 7, 2022, as Appl. No. 17/688,524.
Application 17/688,524 is a continuation of application No. 16/455,125, filed on Jun. 27, 2019, granted, now 11,269,601.
Prior Publication US 2022/0197611 A1, Jun. 23, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 8/41 (2018.01); G06F 8/20 (2018.01); G06F 8/36 (2018.01); G06F 8/73 (2018.01); G06N 20/00 (2019.01)
CPC G06F 8/427 (2013.01) [G06F 8/22 (2013.01); G06F 8/36 (2013.01); G06F 8/73 (2013.01); G06N 20/00 (2019.01)] 21 Claims
OG exemplary drawing
 
1. A non-transitory computer readable storage medium comprising computer readable instructions to cause at least one processor circuit to, at least:
access text representative of a desired functionality of a function, a desired input to the function, and a desired output of the function;
generate a candidate response based on execution of a machine learning model using the text as a textual input to the machine learning model, the candidate response including executable program code;
identify a supplemental source code in response to at least one of the candidate response having an input that does not match the desired input, or the candidate response having an output that does not match the desired output, the supplemental source code to complete the candidate response with respect to the at least one of the desired input or the desired output; and
insert the candidate response and the supplemental source code into source code.