公开(公告)号：US20250086510A1

公开(公告)日：2025-03-13

申请号：US18829449

申请日：2024-09-10

Applicant: CenturyLink Intellectual Property LLC

Inventor： Kevin M. McBride ,  Sotiri Terry Barbounis ,  Scott Brindamour ,  Charles Stallings ,  John R.B. Woodworth ,  Dean Ballew ,  Brian J. Strong ,  Frank Moss

IPC: G06N20/00

Abstract: Novel tools and techniques are provided for implementing Inference as a Service. In various embodiments, a computing system may receive a request to perform an AI/ML task on first data, the request including desired parameters, in some cases, without information regarding any of specific hardware, specific hardware type, specific location, or specific network for providing network services for performing the requested AI/ML task. The computing system may identify edge compute nodes within a network based on the desired parameters and/or unused processing capacity of each node. The computing system may identify AI/ML pipelines capable of performing the AI/ML task, the pipelines including neural networks utilizing pre-trained AI/ML models. The computing system may cause the identified nodes to run the identified pipelines to perform the AI/ML task. In response to receiving inference results from the identified pipelines, the computing system may send, store, and/or cause display of the received inference results.