公开(公告)号：US20170032143A1

公开(公告)日：2017-02-02

申请号：US14967229

申请日：2015-12-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Deguang Kong ,  Hongxia Jin

IPC: G06F21/62 ,  H04L12/24 ,  H04L12/26 ,  H04L29/08

CPC classification number: G06F21/6245 ,  G06F9/4451 ,  G06F17/30 ,  G06F21/552 ,  G06F21/577 ,  G06F21/604 ,  G06F21/6263 ,  H04L63/102 ,  H04L67/306

Abstract: A computing system includes: a control circuit configured to: determine a privacy baseline for controlling communication for a user, determine an application-specific privacy setting for controlling communication for a first executable program associated with the user, generate a user-specific privacy profile based on the privacy baseline and the application-specific privacy setting, the user-specific privacy profile for controlling an application set including a second executable program; and a storage circuit, coupled to the control circuit, configured to store the user-specific privacy profile.

Abstract translation: 计算系统包括：控制电路，其被配置为：确定用于控制用户的通信的隐私基准，确定用于控制与用户相关联的第一可执行程序的通信的特定于应用的隐私设置，生成基于用户的隐私简档 关于隐私基准和特定于应用的隐私设置，用于控制包括第二可执行程序的应用集的用户特定隐私简档; 以及耦合到所述控制电路的存储电路，被配置为存储所述用户特定的隐私简档。

公开(公告)号：US20160188902A1

公开(公告)日：2016-06-30

申请号：US14585985

申请日：2014-12-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hongxia Jin

IPC: G06F21/62 ,  G06F21/57 ,  H04L29/08 ,  G06Q50/00 ,  H04W12/02 ,  H04W4/02

CPC classification number: G06F21/6245 ,  G06F21/577 ,  G06F2221/034 ,  G06Q50/01 ,  H04L63/20 ,  H04L67/306 ,  H04W4/02 ,  H04W4/021 ,  H04W12/00 ,  H04W12/02

Abstract: A computing system includes a control unit configured to determine a usage context including a capability of a device, a usage time and a device location associated with the device, and a user context of one or more users with access to the device; analyze a privacy risk level of a resource based on a resource content included in the resource, a metadata concerning the resource, a collective input regarding the resource, and the usage context; and generate one or more options for sharing the resource with the device based on the privacy risk level and the usage context.

Abstract translation: 计算系统包括：控制单元，被配置为确定包括设备的能力，使用时间和与设备相关联的设备位置的使用上下文以及具有访问设备的一个或多个用户的用户上下文; 基于资源中包含的资源内容，关于资源的元数据，关于资源的集体输入和使用上下文来分析资源的隐私风险级别; 并且基于隐私风险级别和使用上下文生成用于与设备共享资源的一个或多个选项。

公开(公告)号：US20140281532A1

公开(公告)日：2014-09-18

申请号：US14021132

申请日：2013-09-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hongxia Jin ,  Alan Messer

IPC: H04L29/06

CPC classification number: H04L63/0428 ,  G06F21/31 ,  H04L63/0407 ,  H04L63/08

Abstract: An information delivery system includes: a control unit configured to: generate an anonymous identity for concealing client information of an anonymous client from a provider, generate a comparison result for determining whether a client encryption data of the anonymous identity matches with a provider encryption data of the provider, obtain a provider notification based on the comparison result of a match for displaying on a device, and a user interface, coupled to the control unit, configured to display the provider notification.

Abstract translation: 一种信息传递系统，包括：控制单元，被配置为：生成用于从提供者隐藏匿名客户端的客户端信息的匿名身份，生成用于确定匿名身份的客户端加密数据是否与提供者加密数据匹配的比较结果 所述提供者根据用于在设备上显示的匹配的比较结果获得提供者通知，以及耦合到所述控制单元的被配置为显示所述提供者通知的用户界面。

公开(公告)号：US20250094709A1

公开(公告)日：2025-03-20

申请号：US18827108

申请日：2024-09-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shikhar TULI ,  Chi-Heng Lin ,  Yen-Chang Hsu ,  Yilin Shen ,  Hongxia Jin

IPC: G06F40/284

Abstract: A method for performing multi-token prediction by an apparatus includes receiving, from an artificial intelligence (AI) assistance device, a request for an output token sequence that is subsequent to an input token sequence indicated by the request, predicting, by a trained machine learning model, a plurality of candidate output tokens, estimating joint probability distributions of one or more combinations of the plurality of candidate output tokens, calculating joint probabilities of the one or more combinations by masking the joint probability distributions with a co-occurrence weighted mask, determining, based on the joint probabilities, whether to reduce the number of candidate output tokens included in each combination of the one or more combinations, identifying, based on the joint probabilities, a combination of the one or more combinations as the output token sequence, and outputting, to the AI assistance device, a response to the request, the response comprising the output token sequence.

公开(公告)号：US12211486B2

公开(公告)日：2025-01-28

申请号：US17647499

申请日：2022-01-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Avik Ray ,  Yilin Shen ,  Hongxia Jin

IPC: G10L15/06 ,  G10L15/14 ,  G10L15/22

Abstract: A method includes identifying multiple tokens contained in an input utterance. The method also includes generating slot labels for at least some of the tokens contained in the input utterance using a trained machine learning model. The method further includes determining at least one action to be performed in response to the input utterance based on at least one of the slot labels. The trained machine learning model is trained to use attention distributions generated such that (i) the attention distributions associated with tokens having dissimilar slot labels are forced to be different and (ii) the attention distribution associated with each token is forced to not focus primarily on that token itself.

公开(公告)号：US20240377829A1

公开(公告)日：2024-11-14

申请号：US18501887

申请日：2023-11-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yilin Shen ,  Kaiwen Zhou ,  Hongxia Jin

IPC: G05D1/02 ,  G06F40/40 ,  G06T7/70 ,  G06V20/50

Abstract: A method includes determining a specified object to locate within a surrounding environment. The method also includes causing a robot to capture an image and a depth map of the surrounding environment. The method further includes using a scene understanding model, predicting one or more rooms and one or more objects captured in the image. The method also includes updating a second map of the surrounding environment based on the predicted rooms, the predicted objects, the depth map, and a location of the robot. The method further includes determining a likelihood of the specified object being in a candidate room and a likelihood of the specified object being near a candidate object using a pre-trained large language model. The method also includes causing the robot to move to a next location for the robot to search for the specified object, based on the likelihoods and the second map.

公开(公告)号：US20240331715A1

公开(公告)日：2024-10-03

申请号：US18457921

申请日：2023-08-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ching-Hua Lee ,  Chou-Chang Yang ,  Yilin Shen ,  Hongxia Jin

IPC: G10L21/0224

CPC classification number: G10L21/0224 ,  G10L2021/02166

Abstract: A method includes receiving, during a first time window, a set of noisy audio signals from a plurality of audio input devices. The method also includes generating a noisy time-frequency representation based on the set of noisy audio signals. The method further includes providing the noisy time-frequency representation as an input to a mask estimation model trained to output a mask used to predict a clean time-frequency representation of clean speech audio from the noisy time-frequency representation. The method also includes determining beamforming filter weights based on the mask. The method further includes applying the beamforming filter weights to the noisy time-frequency representation to isolate the clean speech audio from the set of noisy audio signals. In addition, the method includes outputting the clean speech audio.

公开(公告)号：US20240070955A1

公开(公告)日：2024-02-29

申请号：US18057117

申请日：2022-11-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wenbo Li ,  Yi Wei ,  Jing Zhu ,  Hongxia Jin

IPC: G06T13/80 ,  G06T7/246 ,  G06T7/70 ,  G06V10/82 ,  G06V40/16

CPC classification number: G06T13/80 ,  G06T7/246 ,  G06T7/70 ,  G06V10/82 ,  G06V40/171 ,  G06V40/176 ,  G06T2207/10016 ,  G06T2207/30201 ,  G06V2201/10

Abstract: A method includes obtaining a source image of a user and obtaining a driving video in which a face or a head of the user is moving. The method also includes generating metadata identifying animations to be applied to the source image so that the source image mimics at least some movements of the user's face or head in the driving video. The method further includes transmitting the source image and the metadata to an end user device configured to animate the source image based on the metadata. Generating the metadata includes suppressing one or more artifacts associated with one or more objects that temporarily occlude at least a portion of the user's head or body in the driving video or that temporarily appear in the driving video.

公开(公告)号：US11875231B2

公开(公告)日：2024-01-16

申请号：US16661827

申请日：2019-10-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Avik Ray ,  Yilin Shen ,  Hongxia Jin

IPC: G06F15/16 ,  G06F9/54 ,  H04L29/06 ,  G06N20/00 ,  G06N5/02

CPC classification number: G06N20/00 ,  G06N5/02

Abstract: An electronic device for complex task machine learning includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive an unknown command for performing a task and generate a prompt regarding the unknown command. The at least one processor is also configured to receive one or more instructions in response to the prompt, where each of the one or more instructions provides information on performing at least a portion of the task. The at least one processor is further configured to determine at least one action for each one of the one or more instructions. In addition, the at least one processor is configured to create a complex action for performing the task based on the at least one action for each one of the one or more instructions.

公开(公告)号：US11790895B2

公开(公告)日：2023-10-17

申请号：US16661581

申请日：2019-10-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Avik Ray ,  Hongxia Jin

IPC: G10L15/18 ,  G06N20/00 ,  G06F40/205 ,  G06F40/284

CPC classification number: G10L15/1815 ,  G06F40/205 ,  G06F40/284 ,  G06N20/00

Abstract: An electronic device for natural language understanding includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to process an utterance using a trained model. The at least one processor is also configured to replace a first portion of the utterance with a first token, where the first token represents a semantic role of the first portion of the utterance based on a slot vocabulary. The at least one processor is further configured to determine a slot value in the utterance based on the first token. In addition, the at least one processor is configured to perform a task corresponding to the utterance based on the determined slot value.