US 12,217,030 B2
Generating automations via natural language processing
José Luis Fernández Gorroño, Paris (FR); Lan Li, Bellevue, WA (US); Cédric Thierry Michel Bignon, Clamart (FR); Nicolas Chao Wei Ding, Issy-les-Moulineaux (FR); Cédric Bernard Jean Golmard, Plaisir (FR); Anand Mourouguessin, Bezons (FR); Jaime Enrique Reyes Salazar, Bellevue, WA (US); Shuktika Jain, Bellevue, WA (US); Dimitrios Leventis, Attica (GR); Yu Hu, Sammamish, WA (US); and Haoran Wei, Bellevue, WA (US)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 23, 2022, as Appl. No. 17/847,972.
Claims priority of provisional application 63/331,375, filed on Apr. 15, 2022.
Prior Publication US 2023/0333827 A1, Oct. 19, 2023
Int. Cl. G06F 8/41 (2018.01); G06F 8/10 (2018.01); G06F 8/38 (2018.01)
CPC G06F 8/42 (2013.01) [G06F 8/10 (2013.01); G06F 8/38 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a program memory that stores program code; and
a processing system, based on the program code to:
receive, at a machine learning model trained using natural language prompts and a second workflow definitional language that is derived from a first workflow definitional language, a natural language input from a first user interface;
output, by the machine learning model based on the natural language input, an output according to the second workflow definitional language;
convert the output into the first workflow definitional language to design an automation;
populate a graphical user interface with parameters for operations of the automation, the parameters derived from the natural language input; and
control, in response to an approval received via the graphical user interface, building of the automation based on the parameters.