US 12,236,195 B2
Systems and methods for generating names using machine-learned models
Victor Carbune, Winterthur (CH); and Alexandru-Marian Damian, Zürich (CH)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Feb. 9, 2023, as Appl. No. 18/166,525.
Application 18/166,525 is a continuation of application No. 16/552,253, filed on Aug. 27, 2019, granted, now 11,580,310.
Prior Publication US 2023/0186029 A1, Jun. 15, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/295 (2020.01); G06F 18/2132 (2023.01); G06F 18/23 (2023.01); G06F 18/24 (2023.01); G06F 40/56 (2020.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2023.01); G06N 3/088 (2023.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/30 (2022.01)
CPC G06F 40/295 (2020.01) [G06F 18/2132 (2023.01); G06F 18/23 (2023.01); G06F 18/24 (2023.01); G06F 40/56 (2020.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2013.01); G06N 3/088 (2013.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/30 (2022.01)] 21 Claims
OG exemplary drawing
 
1. A computing system comprising:
at least one processor;
one or more machine-learned models configured to receive context data that describes an entity to be named, and, in response to receipt of the context data, generate output data that includes a generated name for the entity; and
at least one tangible, non-transitory computer-readable medium that stores instructions that, when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
extracting at least a portion of the context data from a text body, wherein the context data indicates a property of the entity to be named;
inputting the context data into the one or more machine-learned models to generate the generated name based on the context data, the generated name being an anonymous name that is relevant for the property indicated by the context data;
receiving, as an output of the one or more machine-learned models, the output data that includes the generated name; and
processing the text body to identify a portion of the text body that should be replaced with the generated name.