US 12,265,856 B1
Methods and systems for identification and semantic clustering of worker agents for processing requests
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 Sep. 11, 2024, as Appl. No. 18/882,284.
Claims priority of provisional application 63/537,979, filed on Sep. 12, 2023.
Int. Cl. G06F 9/50 (2006.01); G06F 9/54 (2006.01)
CPC G06F 9/505 (2013.01) [G06F 9/54 (2013.01); G06F 2209/503 (2013.01); G06F 2209/505 (2013.01)] 14 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 identifying and clustering worker agents suitable for processing a user request, comprising:
(A) receiving, by a core node, from a user agent, a user request, the user request including a description of at least one task;
(B) updating, by the core node, for each worker agent W in a plurality of worker agents, an availability status for the worker agent W, thereby producing a plurality of availability statuses for the plurality of worker agents;
(C) computing, by the core node, for each worker agent W in the plurality of worker agents, a value of a drift metric for the worker agent W, the computing comprising:
(C)(1) computing, for the worker agent W, a relevance score representing a relevance of a plurality of responses provided by the worker agent W to a plurality of user requests, thereby computing a plurality of relevance scores for the plurality of worker agents;
(C)(2) computing the value of the drift metric for the worker agent W based on the relevance score for the worker agent W; and
(C)(3) updating the availability status of the worker agent W to an “unavailable” status if the value of the drift metric for the worker agent W satisfies a predetermined criterion;
(D) clustering, by the core node, the plurality of worker agents to produce a plurality of clusters of worker agents, wherein each of the plurality of clusters contains worker agents that have similar semantic capabilities; and
(E) based on the user request, the plurality of availability statuses, the plurality of relevance scores, and the plurality of clusters, identifying, by the core node, a subset of the plurality of worker agents that are both available to process the user request and that are suitable for processing the user request.