US 12,407,510 B2
Methods and systems for ranking a plurality of worker agents based on a user request
Mohammad Naanaa, Hillsborough, CA (US); Volodymyr Panchenko, Hillsborough, CA (US); Manav Mehra, Toronto (CA); and Ricardo Fornari, San Jose, CA (US)
Assigned to Portal AI Inc., Redwood City, CA (US)
Filed by Portal AI Inc., Redwood City, CA (US)
Filed on Mar. 19, 2025, as Appl. No. 19/083,971.
Application 19/083,971 is a continuation of application No. 18/882,284, filed on Sep. 11, 2024, granted, now 12,265,856.
Claims priority of provisional application 63/537,979, filed on Sep. 12, 2023.
Prior Publication US 2025/0219832 A1, Jul. 3, 2025
Int. Cl. G06F 9/30 (2018.01); G06F 9/50 (2006.01); G06F 9/54 (2006.01); G06F 16/335 (2019.01); G06F 16/34 (2019.01); G06F 21/60 (2013.01); G06F 21/62 (2013.01); G06F 21/64 (2013.01); G06F 40/205 (2020.01); G06F 40/295 (2020.01); G06Q 10/0631 (2023.01); G06Q 10/0639 (2023.01); H04L 9/32 (2006.01)
CPC H04L 9/32 (2013.01) [G06F 9/505 (2013.01); G06F 9/54 (2013.01); G06F 16/335 (2019.01); G06F 16/345 (2019.01); G06F 21/602 (2013.01); G06F 21/6227 (2013.01); G06F 21/64 (2013.01); G06F 40/205 (2020.01); G06F 40/295 (2020.01); G06Q 10/06311 (2013.01); G06Q 10/063112 (2013.01); G06Q 10/06393 (2013.01); G06F 2209/503 (2013.01); G06F 2209/505 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, performed by at least one computer processor executing computer program instructions stored on at least one non-transitory computer-readable medium, for ranking a plurality of worker agents based on a user request, the method comprising:
(A) receiving, by a user agent, a user request including a description of a task;
(B) generating, by the user agent using a first pre-trained large language model, an embedding of the user request;
(C) identifying, by the user agent in communication with a second pretrained large language model, a plurality of tasks to be performed to process the user request;
(D) for each of a plurality of worker agents, computing a corresponding value for each of a plurality of metrics, thereby computing a plurality of metric values for each of the plurality of worker agents, wherein each of the plurality of worker agents comprises at least one model that has been trained using machine learning; and
(E) generating, for each of the plurality of worker agents, a corresponding ranking, based on the metrics computed for the plurality of worker agents in (D), thereby generating a plurality of worker agent rankings, each of which corresponds to a distinct worker agent in the plurality of worker agents.