公开(公告)号：US20230305899A1

公开(公告)日：2023-09-28

申请号：US18318246

申请日：2023-05-16

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jiafeng Zhu ,  Jie Shen ,  Liya Chen ,  Feng Ye

IPC: G06F9/50

CPC classification number: G06F9/5038 ,  G06F9/5072

Abstract: A method implemented by a multi-access edge computing (MEC) distributed controller includes receiving a MEC computing task request for execution of a service on MEC nodes controlled by the MEC distributed controller; obtaining mobile device geo-location information associated with the mobile device; determining an execution plan and a pool of MEC nodes, the execution plan and the pool of MEC nodes being for the execution of the service, the determining being in accordance with the mobile device geo-location information; scheduling the execution plan for the pool of MEC nodes; and deploying the scheduled execution plan.

公开(公告)号：US20210342694A1

公开(公告)日：2021-11-04

申请号：US17371590

申请日：2021-07-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jiafeng Zhu ,  Wei Wei ,  Jianle Chen ,  Wei Wang ,  Jie Shen

IPC: G06N3/08 ,  G06N3/04

Abstract: A first aspect relates to a computer-implemented method for performing model compression. The method includes compressing a machine learning (ML) network model comprising a multiple layer structure to produce a compressed ML network model. The compressed ML network model maintains the multiple layer structure of the ML network model. The method generates a model file for the compressed ML network model. The model file includes the compressed ML network model and decoding information for enabling the ML network model to be decompressed and executed layer-by-layer.

公开(公告)号：US12271819B2

公开(公告)日：2025-04-08

申请号：US17371590

申请日：2021-07-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jiafeng Zhu ,  Wei Wei ,  Jianle Chen ,  Wei Wang ,  Jie Shen

IPC: G06N3/082 ,  G06N3/04 ,  H03M7/30 ,  G06F11/34

Abstract: A first aspect relates to a computer-implemented method for performing model compression. The method includes compressing a machine learning (ML) network model comprising a multiple layer structure to produce a compressed ML network model. The compressed ML network model maintains the multiple layer structure of the ML network model. The method generates a model file for the compressed ML network model. The model file includes the compressed ML network model and decoding information for enabling the ML network model to be decompressed and executed layer-by-layer.