公开(公告)号：US20250045564A1

公开(公告)日：2025-02-06

申请号：US18922433

申请日：2024-10-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jungbae KIM ,  Euntaik LEE ,  Seungjin KIM ,  Hyeonsu LEE ,  Mooyoung KIM

IPC: G06N3/045

Abstract: A processor of an electronic device according to an embodiment may be configured to identify first graphs included in a first model on the basis of a request for driving the first model, wherein the first model is stored in non-volatile memory of the electronic device. The processor may be configured to identify at least one graph, corresponding to at least one of the first graphs, among second graphs included in one or more second models which are different from the first model and stored in volatile memory. The processor may be configured to obtain, on the basis of the at least one identified graph among the second graphs, an instance for controlling the first model. The processor may be configured to execute a function related to the first model on the basis of the instance.

公开(公告)号：US20210389973A1

公开(公告)日：2021-12-16

申请号：US17412595

申请日：2021-08-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hojung CHOI ,  Sangjun PARK ,  Hyeonsu LEE ,  Jongwoo KIM ,  Gilyoung NOH ,  Bohyung LEE ,  Junguk LEE ,  Jongkyu LEE ,  Jaekyong CHOI ,  Inhwan HWANG ,  Mooyoung KIM

IPC: G06F9/48 ,  H04W52/02 ,  G06F9/54

Abstract: A method and an apparatus for reducing power consumption of an electronic device are provided. The method includes executing an app in response to a first user input and switching the app to a background in response to a second user input. The method also includes confirming whether the app that has been switched to the background satisfies at least one condition and automatically limiting an operation of the app when the app that has been switched to the background satisfies the at least one condition. A result of the automatically limiting operation the operation of the app is displayed.

公开(公告)号：US20200266649A1

公开(公告)日：2020-08-20

申请号：US16793665

申请日：2020-02-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyeonsu LEE ,  Chunggeol KIM ,  Hojung CHOI ,  Jeongmin MOON ,  Gyusung CHO ,  Mooyoung KIM

IPC: H02J7/00 ,  G06F3/0484 ,  G06F1/3231

Abstract: An electronic device includes: a location measurement circuitry; a rechargeable battery; a memory configured to store instructions; and at least one processor. The at least one processor may be configured to execute the instructions to: monitor a usage pattern of the battery while the electronic device operates in a first power management state; acquire, based on determining that the usage pattern of the battery is different from a reference pattern derived from a model, information on a location in which the battery is estimated to be charged and information on a time at which the battery is estimated to be charged using the model; and switch, partially based on the information on the location and the information on the time, the first power management state to a second power management state based on a second maximum driving frequency lower than the first maximum driving frequency.

公开(公告)号：US20240289654A1

公开(公告)日：2024-08-29

申请号：US18599852

申请日：2024-03-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jungbae KIM ,  Mooyoung KIM ,  Seungjin KIM ,  Euntaik LEE ,  Jungeun LEE ,  Hyeonsu LEE

IPC: G06N5/04

CPC classification number: G06N5/04

Abstract: An electronic device is provided. The electronic device includes memory storing artificial intelligence models and one or more programs including instructions, and one or more processor, wherein the one or more programs including instructions, when executed by the one or more processors, cause the electronic device to load the artificial intelligence models stored in memory and execute a runtime engine of a framework, identify whether an operation function is supported on a target processor, identify whether a first node for executing an inference on the artificial intelligence models operate without errors based on supporting the operation function on the target processor, repeat the identification until a last node by adding one more nodes in case that the first node operates without errors, form a first group by creating a partition from the first node to an identified N−1st node based on the identification that an error occurred on an Nth node, and form a second group by creating a partition for the Nth node on which the error occurred.

公开(公告)号：US20240273474A1

公开(公告)日：2024-08-15

申请号：US18644988

申请日：2024-04-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyeonsu LEE ,  Jungbae KIM ,  Euntaik LEE ,  Jaeho KO ,  Hyesoo KIM ,  Hyeyoung MOON ,  Hyewon PARK ,  Sungchan BAE ,  Seungyong LEE ,  Hyeonseung LEE ,  Yookyung HAM

IPC: G06Q10/1093

CPC classification number: G06Q10/1093

Abstract: According to various embodiments, an electronic device may comprise a display module, a processor, and a memory operatively connected to the display module and the processor. The memory can store instructions that allow, when executed, in response to reception of at least one piece of content, the processor to identify whether an application corresponding to the at least one piece of content is an information-sharing application, extract schedule-related information based on the received at least one piece of content in response to identifying that the application is the information-sharing application, generate at least one piece of recommendation information based on the extracted schedule-related information in response to execution of a schedule-related application, and display the generated at least one piece of recommendation information through the display module. Various other embodiments are possible.

公开(公告)号：US20220351041A1

公开(公告)日：2022-11-03

申请号：US17864697

申请日：2022-07-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyeonsu LEE ,  Mooyoung KIM

IPC: G06N3/08 ,  G06F9/54

Abstract: An electronic device may map a target application to a machine learning model matched to a request of the target application among a plurality of machine learning models, may generate an inference result for sensing data corresponding to the machine learning model based on the sensing data being sensed by the at least one sensor, and may transfer the generated inference result to at least one of the target application and another application.