公开(公告)号：US20240045916A1

公开(公告)日：2024-02-08

申请号：US18381519

申请日：2023-10-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Vinod Kumar MISHRA ,  Ashish Kumar TANWAR ,  Mohammad AZAM

IPC: G06F16/954 ,  G06F16/957 ,  G06F16/9535 ,  G06F40/205 ,  G06F40/143

CPC classification number: G06F16/954 ,  G06F16/9577 ,  G06F16/9535 ,  G06F40/205 ,  G06F40/143

Abstract: A method for personalized browsing by using a remote device, includes: displaying a page associated with at least one user; identifying one or more navigable elements on the displayed page; creating one or more categories of the one or more navigable elements; classifying the one or more navigable elements based on at least one category of the one or more categories; generating hybrid blocks based on a category of the one or more navigable elements and user profile data; performing a content similarity check between the hybrid blocks; creating a relevance matrix based on pre-defined context parameters and the content similarity check; and navigating to an element of interest based on the relevance matrix and the hybrid block.

公开(公告)号：US20220148580A1

公开(公告)日：2022-05-12

申请号：US17460598

申请日：2021-08-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Anil KUMAR ,  Teena SALHOTRA ,  Vinod Kumar MISHRA ,  Mohammad AZAM

IPC: G10L15/14 ,  G10L15/07 ,  G10L15/06 ,  G10L15/08 ,  G10L15/183 ,  G06K9/62 ,  G06N7/00

Abstract: A method to adaptively predict non-default actions against unstructured utterances by an automated assistant operating in a computing-system is provided. The method includes extracting voice-features based on receiving an input utterance from at-least one speaker by an automatic speech recognition (ASR) device, identifying the input utterance as an unstructured utterance based on the extracted voice-features and a mapping between the input utterance with one or more default actions as drawn by the ASR, obtaining at least one probable action to be performed in response to the unstructured utterance through a dynamic bayesian network (DBN). The method further includes providing the at least one probable action obtained by the DBN to the speaker in an order of the posterior probability with respect to each action.