US 11,983,909 B2
Responding to machine learning requests from multiple clients
David Murphy, Palo Alto, CA (US); Thomas da Silva Paula, Porto Alegre (BR); Wagston Tassoni Staehler, Porto Alegre (BR); Joao Edurado Carrion, Porto Alegre (BR); Alexandre Santos da Silva, Jr., Porto Alegre (BR); Juliano Cardoso Vacaro, Porto Alegre (BR); and Gabriel Rodrigo De Lima Paz, Porto Alegre (BR)
Assigned to Hewlett-Packard Development Company, L.P., Spring, TX (US)
Appl. No. 17/415,867
Filed by Hewlett-Packard Development Company, L.P., Spring, TX (US)
PCT Filed Mar. 14, 2019, PCT No. PCT/US2019/022217
§ 371(c)(1), (2) Date Jun. 18, 2021,
PCT Pub. No. WO2020/185233, PCT Pub. Date Sep. 17, 2020.
Prior Publication US 2022/0076084 A1, Mar. 10, 2022
Int. Cl. G06V 10/20 (2022.01); G06F 18/40 (2023.01); G06N 20/00 (2019.01); G06V 10/94 (2022.01)
CPC G06V 10/20 (2022.01) [G06F 18/40 (2023.01); G06N 20/00 (2019.01); G06V 10/95 (2022.01); G06F 2218/16 (2023.01)] 15 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, with a computing device, a first client request from a first client that identifies a machine learning model and a sensor, wherein the machine learning model is an object detection model and wherein the first client request is to identify an object based in part on a set of data from the sensor;
in response to the first client request, sending, with the computing device, a call to a model server to apply the identified machine learning model to the set of data from the sensor to identify an object, wherein the set of data comprises video frames;
receiving, with the computing device, a second client request from a second client that identifies a same machine learning model and sensor as the first client request, the second client different from the first client; and
sending, with the computing device, object response data from the identified machine learning model corresponding to the call to both the first client and the second client without sending an additional call to the model server in response to the second client request.