公开(公告)号：US12174995B2

公开(公告)日：2024-12-24

申请号：US17658968

申请日：2022-04-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Winston Chen ,  Laszlo Gombos

IPC: G06F21/62 ,  G06T11/60 ,  G06T19/00 ,  H04N13/30

Abstract: A method includes receiving, at an intermediary layer, from a camera of a head mounted display (HMD), image data of a real-world operating environment of the HMD at a first time. The method further includes identifying, at the intermediary layer, one or more objects in the image data, determining, at the intermediary layer, coordinates of a region comprising the one or more identified objects, determining a display permission for the one or more identified objects, modifying the image data in the region comprising the one or more identified objects according to the display permission and outputting the modified image data to an application executing outside of the intermediary layer.

公开(公告)号：US20220374543A1

公开(公告)日：2022-11-24

申请号：US17658968

申请日：2022-04-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Winston Chen ,  Laszlo Gombos

IPC: G06F21/62 ,  H04N13/30 ,  G06T19/00 ,  G06T11/60

Abstract: A method includes receiving, at an intermediary layer, from a camera of a head mounted display (HMD), image data of a real-world operating environment of the HMD at a first time. The method further includes identifying, at the intermediary layer, one or more objects in the image data, determining, at the intermediary layer, coordinates of a region comprising the one or more identified objects, determining a display permission for the one or more identified objects, modifying the image data in the region comprising the one or more identified objects according to the display permission and outputting the modified image data to an application executing outside of the intermediary layer.

公开(公告)号：US20240281663A1

公开(公告)日：2024-08-22

申请号：US18427400

申请日：2024-01-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Winston Chen ,  Laszlo Gombos

IPC: G06N3/0895

CPC classification number: G06N3/0895

Abstract: A method includes obtaining, using at least one processing device of an electronic device, information associated with a webpage presented to a user. The method also includes providing, using the at least one processing device, the information to an on-device machine learning model of the electronic device. The method further includes generating, using the on-device machine learning model, a prompt for a large language model based on the information. The prompt includes an action from a set of candidate actions that the large language model is able to perform and at least some of the information. The method also includes providing, using the at least one processing device, the prompt as input to the large language model and receiving, using the at least one processing device, a response from the large language model. In addition, the method includes presenting, using the at least one processing device, the response to the user.