US 11,968,281 B2
Distributed machine-learning resource sharing and request routing
Philippe Klein, Jerusalem (IL); Gordon Yong Li, San Diego, CA (US); and Xuemin Chen, Rancho Santa Fe, CA (US)
Assigned to Avago Technologies International Sales Pte. Limited, Singapore (SG)
Filed by Avago Technologies International Sales Pte. Limited, Singapore (SG)
Filed on Sep. 13, 2022, as Appl. No. 17/944,007.
Application 17/944,007 is a continuation of application No. 17/155,780, filed on Jan. 22, 2021, granted, now 11,516,311.
Prior Publication US 2023/0020939 A1, Jan. 19, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 67/63 (2022.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); H04L 67/10 (2022.01)
CPC H04L 67/63 (2022.05) [G06N 5/04 (2013.01); G06N 20/00 (2019.01); H04L 67/10 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a client request to process data via one or more machine learning processes, the client request being associated with a client device;
comparing a first set of attributes associated with a first network device with a second set of attributes associated with a second network device, the first set of attributes and the second set of attributes include one or more computer resource characteristics of a respective network device and one or more machine learning processing capabilities of a respective network device, the one or more machine learning processing capabilities comprising at least one of a machine learning model type hosted on a respective network device, hyperparameters used in a respective machine learning model, output data post-processing functions, and data paths for input and output data flows;
based at least in part on the comparing, selecting the first network device to route the client request to and refraining from selecting the second network device;
based at least in part on the selecting, causing the first network device to process the client request, the first network device comprising a first machine learning core configured to enable end-to-end processing associated with an object, wherein the object represents any logical entity with a unique signature embedded in an ML input data; and
at least partially in response to the processing of the client request, causing a transmission of data to the client device.