US 11,750,469 B2
Edge-based artificial intelligence enablement
Ronald A Lewis, Montgomery, AL (US); Alison Grayson, Lone Tree, CO (US); and Carlos Santiago, Aurora, CO (US)
Assigned to CenturyLink Intellectuall Property LLC, Broomfield, CO (US)
Filed by CenturyLink Intellectual Property LLC, Broomfield, CO (US)
Filed on Dec. 9, 2022, as Appl. No. 18/78,680.
Application 18/078,680 is a continuation of application No. 17/649,731, filed on Feb. 2, 2022, granted, now 11,528,193.
Claims priority of provisional application 63/152,139, filed on Feb. 22, 2021.
Prior Publication US 2023/0107501 A1, Apr. 6, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 41/16 (2022.01); H04L 41/14 (2022.01)
CPC H04L 41/16 (2013.01) [H04L 41/145 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, at a first edge compute site of a telecommunications network, raw data from a first device over a first access network;
determining, by the first edge compute site, whether the raw data needs to be modified for consumption by a first model that is stored by one of the first edge compute site, the first device, or a second device connected to the first edge compute site;
when it is determined that the raw data needs to be modified for consumption by the first model, modifying the raw data to generate modified data;
determining, by the first edge compute site, whether to modify the first model at the first edge compute site using the modified data;
when it is determined to modify the first model at the first edge compute site, modifying the first model using the modified data to generate a modified first model;
determining, by the first edge compute site, whether to send the modified first model to at least one of the first device or the second device;
when it is determined to send the modified first model to at least one of the first device or the second device, sending the modified first model to at least one of the first device or the second device; and
using the modified first model to automatically affect operation of at least one of the first edge compute site, the first device, or the second device.