US 12,033,006 B1
Edge deployment of cloud-originated machine learning and artificial intelligence workloads
Pradeep Nair, Greebrae, CA (US); Pragyana K Mishra, Seattle, WA (US); Anish Swaminathan, Greebrae, CA (US); and Janardhan Prabhakara, Greebrae, CA (US)
Assigned to Armada Systems Inc., Greebrae, CA (US)
Filed by Armada Systems Inc., Greebrae, CA (US)
Filed on Sep. 5, 2023, as Appl. No. 18/461,476.
Int. Cl. G06F 9/50 (2006.01); G06N 20/00 (2019.01); H04B 7/185 (2006.01)
CPC G06F 9/5083 (2013.01) [G06N 20/00 (2019.01); H04B 7/18521 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
transmitting, from a containerized edge data center unit, a request corresponding to a pre-trained machine learning model;
receiving, from a cloud management platform and by the containerized edge data center unit, the pre-trained machine learning model, wherein the containerized edge data center unit is deployed to an edge location and configured to obtain one or more sensor data streams at the edge location;
transmitting, from the containerized edge data center unit, one or more batch uploads of information associated with inference performed by the containerized edge data center unit using the pre-trained machine learning model and the one or more sensor data streams, wherein the one or more batch uploads of information are transmitted to the cloud management platform;
receiving, by the containerized edge data center unit, an updated machine learning model generated by the cloud management platform responsive to the one or more batch uploads of information, wherein the updated machine learning model is based on retraining or finetuning of the pre-trained machine learning model with the one or more batch uploads of information; and
performing, by the containerized edge data center unit, localized instruction tuning of the updated machine learning model to a particular task of the inference performed by the containerized edge data center, wherein the instruction tuning is based on domain-specific information obtained from a local data store of the containerized edge data center unit.