公开(公告)号：US20250014578A1

公开(公告)日：2025-01-09

申请号：US18795487

申请日：2024-08-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Vishwanath Pethri KAMATH ,  Sushant KUMAR

IPC: G10L15/22 ,  G10L15/18

Abstract: A method for handling voice input by voice assistant device are provided. The method includes receiving, by the voice assistant device, a voice input from a user; identifying, by the voice assistant device, at least one first user intent and a plurality of slots based on the voice input, wherein the plurality of slots may include at least one slot related to the at least one first user intent and at least one slot unrelated to the at least one first user intent; identifying, by the voice assistant device, at least one second user intent based on the voice input and the at least one slot unrelated to the at least one first user intent; and performing, by the voice assistant device, at least one first operation based on the at least one first user intent and at least one second operation based on the at least one second user intent.

公开(公告)号：US20210280186A1

公开(公告)日：2021-09-09

申请号：US17193828

申请日：2021-03-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sathwick MAHADEVA ,  Indira Preethi Jain GARGATTI AJITH ,  Vishwanath Pethri KAMATH ,  Bharath Kumar NATARAJAN ,  Madhushree SHREESURESH GOWDA ,  Vijetha Kannukere Vinaya PRASAD

IPC: G10L15/22 ,  G10L15/25 ,  G06F21/62 ,  G06K9/00 ,  G10L25/78

Abstract: A method and a voice assistant device for managing private data are provided. The voice assistant device includes a processor configured to detect a privacy triggering event while obtaining at least one voice input from a first user in a voice input mode, switch from the voice input mode to a non-voice input mode in response to the privacy triggering event, obtain a non-voice input from the first user in the non-voice input mode, and execute an operation of the voice assistant device corresponding to the non-voice input.

公开(公告)号：US20250006195A1

公开(公告)日：2025-01-02

申请号：US18883463

申请日：2024-09-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Manjunath Belgod LOKANATH ,  Vishwanath Pethri KAMATH ,  Rishabh SHUKLA

IPC: G10L15/22

Abstract: A method for waking up a device among a plurality of devices in in a multi-reality environment is provided. The method includes detecting a voice input from a user, receiving, based on the voice input, a first plurality of wakeup parameters associated with a plurality of real-world devices in the real-world and a second plurality of wakeup parameters associated with a plurality of virtual-world devices in a virtual world, feeding the first plurality of wakeup parameters and the second plurality of wakeup parameters into a pre-trained artificial intelligence (AI)-based model a correlation of one or more of a context of the user, a history a device state of each of the plurality of real-world devices and the plurality of virtual-world devices, a device wakeup operation information of each of the plurality of real-world devices and the plurality of virtual-world devices, a task execution information of each of the plurality of real-world devices and the plurality of virtual-world devices, and error information in wake-up of each of the plurality of real-world devices and the plurality of virtual-world devices, predicting, by the pre-trained AI-based model, a target device based on the first plurality of wakeup parameters, the second plurality of wakeup parameters, and sending a wake-up signal to the target device for turning the target device into a listening state.

公开(公告)号：US20230421611A1

公开(公告)日：2023-12-28

申请号：US18342500

申请日：2023-06-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Vishwanath Pethri KAMATH ,  Madhushree SURESHA GOWDA ,  Vaibhav ITTAN ,  Sushant KUMAR ,  Jayantha Gowda SARAPANAHALLI ,  Sudhansu Ranjan ACHARYA

IPC: H04L9/40

CPC classification number: H04L63/20 ,  H04L67/131

Abstract: An example method for handling a secure virtual event in a virtual environment by an electronic device includes receiving at least one input from a first user avatar to create at least one virtual event within the virtual environment. The method further includes identifying at least one second user avatar for participating the at least one created virtual event based on the received input from the first user avatar and a nature of the virtual event and determining at least one security policy corresponding to at least one action associated with the at least one second user avatar and at least one parameter within the at least one created virtual event.