公开(公告)号：US20250029005A1

公开(公告)日：2025-01-23

申请号：US18669413

申请日：2024-05-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ting Hua ,  Xiao Li ,  Shangqian Gao ,  Yen-Chang Hsu ,  Yilin Shen ,  Hongxia Jin

IPC: G06N20/00 ,  G10L15/18 ,  G10L15/26

Abstract: A method includes accessing a plurality of weight matrices of a machine learning model. The method also includes, for each weight matrix, decomposing the weight matrix into a U matrix, an S matrix, and a V matrix using singular value decomposition. The S matrix is a diagonal matrix, and a singular group corresponds to each element in the S matrix. The method further includes, for each weight matrix, determining an importance score of each singular group. The importance score of the singular group represents a change in loss if the singular group is removed from the machine learning model. The method also includes, for each weight matrix, ranking the singular groups across the plurality of weight matrices based on the importance scores. In addition, the method includes, for each weight matrix, identifying one or more of the singular groups to prune based on the ranking of the singular groups.

公开(公告)号：US11995564B2

公开(公告)日：2024-05-28

申请号：US16246775

申请日：2019-01-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Justin C. Martineau ,  Christian Koehler ,  Hongxia Jin

IPC: G06N5/04 ,  G06F16/901 ,  G06N20/00

CPC classification number: G06N5/04 ,  G06F16/9024 ,  G06N20/00

Abstract: A recommendation method includes determining one or more aspects of a first item based on at least one descriptive text of the first item. The recommendation method also includes updating a knowledge graph containing nodes that represent multiple items, multiple users, and multiple aspects. Updating the knowledge graph includes linking one or more nodes representing the one or more aspects of the first item to a node representing the first item with one or more first edges. Each of the one or more first edges identifies weights associated with (i) user sentiment about the associated aspect of the first item and (ii) an importance of the associated aspect to the first item. In addition, the recommendation method includes recommending a second item for a user with an explanation based on at least one aspect linked to the second item in the knowledge graph.

公开(公告)号：US20230177332A1

公开(公告)日：2023-06-08

申请号：US18061216

申请日：2022-12-02

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sima Behpour ,  Yilin Shen ,  Hongxia Jin

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method includes accessing, using at least one processor of an electronic device, a machine learning model. The machine learning model is trained by directing a gradient direction of gradients to one or more flat local minima and using a dynamic learning rate for one or more additional tasks. The method also includes receiving, using the at least one processor, an input from an input source. The method further includes providing, using the at least one processor, the input to the machine learning model. The method also includes receiving, using the at least one processor, an output from the machine learning model. In addition, the method includes instructing, using the at least one processor, at least one action based on the output from the machine learning model.

公开(公告)号：US11669746B2

公开(公告)日：2023-06-06

申请号：US16370542

申请日：2019-03-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yue Deng ,  Yilin Shen ,  Hongxia Jin

IPC: G06N3/08 ,  G06N3/088 ,  G06N20/00 ,  G06F18/22 ,  G06F18/214 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V20/70

CPC classification number: G06N3/088 ,  G06F18/214 ,  G06F18/22 ,  G06N20/00 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/82 ,  G06V20/70

Abstract: An electronic device for active 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 select one or more entries from a data set including unlabeled data based on a similarity between the one or more entries and labeled data. The at least one processor is further configured to cause the one or more entries to be labeled.

公开(公告)号：US11620737B2

公开(公告)日：2023-04-04

申请号：US17504221

申请日：2021-10-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wenbo Li ,  Hongxia Jin

IPC: G06K9/00 ,  G06T5/00 ,  G06K9/62 ,  G06V10/22 ,  G06V30/262

Abstract: An inpainting method includes obtaining image information at an electronic device, where the image information identifies an area corresponding to a removed object within an image. The method also includes reconstructing the area corresponding to the removed object by (i) applying a semantic mask and a surface normal map to identify and rank neighboring contexts of the area and (ii) sampling, using an attention mechanism, the ranked contexts to generate pixel information for the area. The method further includes rendering the image with the reconstructed area.

公开(公告)号：US20230055991A1

公开(公告)日：2023-02-23

申请号：US17674258

申请日：2022-02-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yu Wang ,  Vijay Srinivasan ,  Hongxia Jin

IPC: G06F16/33 ,  G06F40/126 ,  G06F40/20 ,  G06F40/166 ,  G06F40/35

Abstract: A method includes receiving natural-language input from a user. The method also includes receiving, from an information source, one or more candidate recommendations as potential responses to the natural-language input. The method further includes determining, based on a similarity between the natural-language input and a selected candidate recommendation among the one or more candidate recommendations, whether to respond to the natural-language input with natural-language output that includes (i) the selected candidate recommendation or (ii) a query for additional user input. In addition, the method includes providing, based on the determination, the natural-language output to the user.

公开(公告)号：US20220156896A1

公开(公告)日：2022-05-19

申请号：US17503169

申请日：2021-10-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wenbo Li ,  Hongxia Jin

IPC: G06T5/00 ,  G06T5/50

Abstract: An inpainting method includes obtaining an image including an object having a delicate shape and identifying a target region within the image, where the target region is adjacent to the object. The method also includes using a first mask to separate the image into a number of semantic categories and aggregating neighboring contexts for the target region based on the semantic categories. The method further includes restoring, based on the aggregated contexts, textures in the target region without affecting the delicate shape of the object. In addition, the method includes displaying a refined image including the restored textures in the target region and the object.

公开(公告)号：US11036926B2

公开(公告)日：2021-06-15

申请号：US16236886

申请日：2018-12-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yilin Shen ,  Avik Ray ,  Hongxia Jin

IPC: G06F40/169 ,  G06F40/40 ,  G06F40/30 ,  G06F40/20 ,  G06F16/332

Abstract: A system receives a phrase that includes at least one tagged object and generates instantiated phrases by instantiations of each tagged object in the phrase. The system generates lists of natural language phrases by corresponding paraphrases of each of the instantiated phrases. The system generates ordered lists of natural language phrases by ordering natural language phrases in each list of natural language phrases based on occurrences of each natural language phrase. The system generates annotated natural language phrases by using each tagged object in the phrase to annotate the ordered lists of natural language phrases or an enhanced set of natural language phrases that is based on the ordered lists of natural language phrases.

公开(公告)号：US20210004532A1

公开(公告)日：2021-01-07

申请号：US16946746

申请日：2020-07-02

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yilin Shen ,  Xiangyu Zeng ,  Hongxia Jin

IPC: G06F40/279

Abstract: A method includes obtaining, using at least one processor of an electronic device, a base model trained to perform natural language understanding. The method also includes generating, using the at least one processor, a first model expansion based on knowledge from the base model. The method further includes training, using the at least one processor, the first model expansion based on first utterances without modifying parameters of the base model. The method also includes receiving, using the at least one processor, an additional utterance from a user. In addition, the method includes determining, using the at least one processor, a meaning of the additional utterance using the base model and the first model expansion.

公开(公告)号：US20200312299A1

公开(公告)日：2020-10-01

申请号：US16370497

申请日：2019-03-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sandeep Nama ,  Hongxia Jin

IPC: G10L15/06 ,  G10L15/30 ,  G06F16/901

Abstract: A method includes receiving, at an electronic device, a command directed to a first application operated by the electronic device. Features presented by the first application in response to interactions with the first application are captured at the electronic device. Data communicated with the first application via the interactions with the first application are captured at the electronic device. A task is learned based on the captured features and communicated data.