公开(公告)号：US20240046151A1

公开(公告)日：2024-02-08

申请号：US18305712

申请日：2023-04-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sukhdeep SINGH ,  Vivek SAPRU ,  Joseph THALIATH ,  Ganesh Kumar THANGAVEL ,  Ashish JAIN ,  Seungil YOON ,  Hoejoo LEE ,  Hunje YEON

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A system and/or method for automated ML model retraining by an electronic device. The system and/or method may include one or more of: running a first ML model and a second ML model, predicting an accuracy degradation of the first ML model using the second ML model, determining whether the predicted accuracy degradation meets a pre-defined threshold, and/or retraining the first ML model when the predicted accuracy degradation meets the pre-defined threshold.

公开(公告)号：US20230054483A1

公开(公告)日：2023-02-23

申请号：US17944831

申请日：2022-09-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minha LEE ,  Hoejoo LEE ,  Myeonggi JEONG

IPC: H04W28/02 ,  H04L47/2475 ,  H04W76/19

Abstract: In an electronic device and an operating method of the electronic device according to various embodiments, the electronic device may include: a radio access network (RAN) intelligent controller (RIC) connected to at least one E2 node. The RIC may include: an application, a plurality of E2 terminations connected between the at least one node and the application, and a traffic controller. The traffic controller may be configured to: receive a subscription request for the node from the application, select an E2 termination to be used for the application to perform subscription among the plurality of E2 terminations based on traffic information of data transmitted or received through the E2 termination, and control the application to receive data through the E2 node, through the selected E2 termination.

公开(公告)号：US20230067970A1

公开(公告)日：2023-03-02

申请号：US17891273

申请日：2022-08-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoejoo LEE ,  Youngcheol JANG

IPC: G06N5/02 ,  H04W24/02

Abstract: According to various embodiments, a method of operating an electronic device may include: storing at least one value corresponding to each of at least one parameter associated with a radio access network (RAN), and information associated with an operation performed by the RAN. A value corresponding to at least some parameters among the at least one parameter may be used when at least one operation determination model executed by the electronic device determines at least a part of the information associated with the operation. The method of the electronic device may further include: identifying a request for experience information for learning a first operation determination model from a first learning learner for learning the first operation determination model among the at least one operation determination model, identifying, from the at least one value, a value corresponding to at least one first parameter corresponding to the first operation determination model and information associated with an operation corresponding to the at least one first parameter, in response to the request, and providing at least some among the value corresponding to the at least one first parameter, the information associated with the operation corresponding to the at least one first parameter, and a reward value identified based on at least a part of the value corresponding to the at least one first parameter, to the first learning learner as the experience information.

公开(公告)号：US20230031470A1

公开(公告)日：2023-02-02

申请号：US17863576

申请日：2022-07-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sukhdeep SINGH ,  Joseph THALIATH ,  Vivek SAPRU ,  Sandeep Kumar JAISAWAL ,  Naman AGARWAL ,  Seungil YOON ,  Hoejoo LEE

IPC: H04L41/16 ,  G06N20/00 ,  H04L41/5006 ,  H04W48/18 ,  G06K9/62

Abstract: The embodiments herein disclose a method for managing machine learning (ML) services in a wireless communication network. The method includes: storing a plurality of ML packages, each executing a network service request; receiving a trigger based on the network service request from a server; determining a plurality of parameters corresponding to the network service request, on receiving the trigger from the server; determining an ML package based on the trigger and the plurality of parameters corresponding to the network service request; and deploying the determined at least one ML package for executing the network service request.