US 11,941,543 B2
Inferencing endpoint discovery in computing systems
Hao Huang, Kenmore, WA (US); Zhenghua Yang, Sammamish, WA (US); Long Qiu, Kirkland, WA (US); Ashish Pinninti, Redmond, WA (US); Juan Diego Ferre, Seattle, WA (US); and Amit Anand Amleshwaram, Wynnewood, PA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Nov. 21, 2022, as Appl. No. 18/057,455.
Application 18/057,455 is a continuation of application No. 17/193,753, filed on Mar. 5, 2021, granted, now 11,551,122.
Prior Publication US 2023/0102510 A1, Mar. 30, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/04 (2023.01); G06F 16/24 (2019.01); G06F 16/29 (2019.01); G06N 20/00 (2019.01); H04L 67/10 (2022.01)
CPC G06N 5/04 (2013.01) [G06F 16/24 (2019.01); G06F 16/29 (2019.01); G06N 20/00 (2019.01); H04L 67/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of inferencing endpoint discovery in a distributed computing system, the method comprising:
receiving, by a server in the distributed computing system, a query associated with a user for inferencing endpoints in the distributed computing system, the query including:
data representing a target value corresponding to a performance characteristic of the inferencing endpoints, and
data identifying a geographical parameter associated with the user;
in response to receiving the query, conducting a search of a database that stores a plurality of endpoint records, wherein each endpoint record, in the plurality of endpoint records, corresponds to a respective inferencing endpoint deployed in the distributed computing system and has data representing a value of the performance characteristic corresponding to the respective inferencing endpoint;
based on the search, identifying a set of inferencing endpoints matching the target value;
for each individual inferencing endpoint in the set of inferencing endpoints, identifying a network location for the individual inferencing endpoint; and
providing a query result including the set of inferencing endpoints based on the geographical parameter relative to the network locations for the set of inferencing endpoints.