公开(公告)号：US20210385170A1

公开(公告)日：2021-12-09

申请号：US17410331

申请日：2021-08-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jyotirmoy KARJEE ,  Ashok Kumar Reddy CHAVVA ,  Shubhneet KHATTER ,  Raja Moses Manoj Kumar EDA ,  Venkatesh M ,  Diprotiv SARKAR ,  Hema Lakshman Chowdary TAMMINEEDI

IPC: H04L12/863 ,  H04L12/851 ,  H04L12/815

Abstract: A method of distributing throughput intelligently amongst a plurality of applications residing at a User Equipment (UE) is provided. The method includes receiving, at the UE, recommended bit rate (RBR) information from a network node, the RBR information indicating a throughput value allocated to the UE, allocating a codec rate from the allocated throughput value to at least one voice over internet protocol (VoIP) application from the plurality of applications, and allocating, from remaining throughput value of the allocated throughput value, a bit rate to each of a plurality of non-VoIP applications from the plurality of applications, based on corresponding throughput requirement associated with the plurality of non-VoIP applications.

公开(公告)号：US20230196207A1

公开(公告)日：2023-06-22

申请号：US18109042

申请日：2023-02-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Prasenjit CHAKRABORTY ,  Narasimha Rao THURLAPATI ,  Srinidhi N ,  Eric Ho Ching YIP ,  Jyotirmoy KARJEE ,  Jaskamal KAINTH ,  Ramesh Badu VENKAT DABBIRU

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Provided is a method for adaptively streaming an artificial intelligence (AI) model file, including determining a capability of a first electronic device and a capability of a second electronic device, network information associated with the first and second electronic devices, and AI model information associated with the AI model file; determining to adaptively stream the AI model file based on the determined capabilities and information; pre-processing the AI model file; and adaptively streaming the AI model.

公开(公告)号：US20250063528A1

公开(公告)日：2025-02-20

申请号：US18753521

申请日：2024-06-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jagadeesh GANDIKOTA ,  Koustav ROY ,  Danish Ehsan HASHMI ,  Arijit SEN ,  Jyotirmoy KARJEE ,  Lalith KUMAR

IPC: H04W60/04 ,  H04W40/22 ,  H04W48/18 ,  H04W84/04

Abstract: According to an example embodiment of the disclosure, a method for performing network slice reselection by a User Equipment (UE) is disclosed. The method comprises identifying allowed network slices within a first Network Slice Simultaneous Registration Group (NSSRG) for first applications at the UE. The method comprises receiving an initialization request from a second application at the UE. The method comprises determining one or more UE Route Selection Policy (URSP) rules for the second application. The method comprises determining whether the network slice required for the second application corresponds to one of the one or more allowed network slices within the first NSSRG. The method comprises transmitting, to a network, a second registration request for registration of the UE to a second NSSRG including the network slice required for the second application based on the URSP rules for the second application.

公开(公告)号：US20250013874A1

公开(公告)日：2025-01-09

申请号：US18891095

申请日：2024-09-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jyotirmoy KARJEE ,  Praveen Naik S ,  Srinidhi NAGARAJA RAO ,  Eric Ho Ching YIP ,  Prasenjit CHAKRABORTY ,  Ramesh Babu Venkat DABBIRU

IPC: G06N3/098

Abstract: Systems and methods for optimal split federated learning (O-SFL) in a wireless network, including: receiving, by a federal device in the wireless network, local split points associated with a deep neural network (DNN) model over a time period from at least one client device of a plurality of client devices, wherein the plurality of client devices are connected to an edge device for training the DNN model using split federated learning (SFL); determining, by the federal device, an average of the local split points; determining, by the federal device, a global split point for partitioning the DNN model between the at least one client device and the edge device based on the average of the local split points; and applying, by the federal device, the determined global split point to train the DNN model.

公开(公告)号：US20240155478A1

公开(公告)日：2024-05-09

申请号：US18412162

申请日：2024-01-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jagadeesh GANDIKOTA ,  Danish Ehsan HASHIMI ,  Jyotirmoy KARJEE ,  Ankur POONIYA

IPC: H04W48/18 ,  H04W28/24 ,  H04W76/10

CPC classification number: H04W48/18 ,  H04W28/24 ,  H04W76/10

Abstract: An apparatus for selecting network slices for servicing application requests, includes: a memory storing at least one instruction; and at least one processor operatively connected to the memory and configured to execute the at least one instruction to: receive an application request from an application for establishing a new protocol data unit (PDU) session with a network over a first network slice, wherein the application request comprises one or more PDU session requirements, identify a plurality of network slices other than the first network slice, based on the one or more PDU session requirements; select a second network slice from the plurality of network slices, based on a configuration related to the apparatus; and perform a service corresponding to the application request using the second network slice.

公开(公告)号：US20220383116A1

公开(公告)日：2022-12-01

申请号：US17824075

申请日：2022-05-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jyotirmoy KARJEE ,  Praveen Naik S ,  Vanamala Narasimha BHARGAV ,  Kartik ANAND ,  Srinidhi N ,  Ramesh Babu Venkat DABBIRU ,  Anshuman NIGAM

IPC: G06N3/08 ,  H04L67/12 ,  H04L41/0681 ,  G06F9/48

Abstract: A method and system of task management in an internet of things (IoT)-edge network may be provided. The method may include assigning at least one deep neural network (DNN) task from an IoT device to a first edge device; determining whether the first edge device satisfies one of a first predetermined criteria and a second predetermined criteria during execution of the at least one DNN task; triggering an alarm to the IoT device based on the determination; identifying a second edge device subsequent to the triggering of the alarm; determining whether to transfer the at least one DNN task to the second edge device or to execute the at least one DNN task on the first edge device, based on determining that the first device satisfies the second predetermined criteria; and transferring the at least one DNN task to the second edge device, based on determining that the first device satisfies the first predetermined criteria.

公开(公告)号：US20220311678A1

公开(公告)日：2022-09-29

申请号：US17703296

申请日：2022-03-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jyotirmoy KARJEE ,  Kartik ANAND ,  Vanamala Narasimha BHARGAV ,  Praveen Naik S ,  Ramesh Babu Venkat DABBIRU ,  Srinidhi N ,  Anshuman NIGAM ,  Rishabh Raj JHA

IPC: H04L41/16 ,  H04L67/10 ,  H04L43/0888

Abstract: A method and device for execution of deep neural network (DNN) in an internet of things (IoT) edge network are provided. In an embodiment, at least one edge device within communication range of an IoT device are selected. Further, a network for connecting the IoT device with the at least one selected edge device is identified. A split ratio is determined based on an inference time of the DNN and a transmission time required for transmitting output of each layer of DNN from the IoT device to the selected at least one edge device. Finally, a plurality of layers of the DNN are split into a first part and a second part based on the split ratio, and the second part is transmitted to the selected at least one edge device through the identified network. The first part is executed on the IoT device, and the second part is executed on the selected at least one edge device.