-
公开(公告)号：US12127726B2
公开(公告)日：2024-10-29
申请号：US17231958
申请日：2021-04-15
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yu Wang , Yilin Shen , Hongxia Jin
IPC: G06V10/70 , A47L9/28 , A47L11/40 , G06F18/214 , G06V20/10
CPC classification number: A47L9/2805 , A47L11/40 , G06F18/214 , G06V10/768 , G06V20/10 , A47L2201/06
Abstract: A method includes obtaining, using at least one processor of an electronic device, an image-query understanding model. The method also includes obtaining, using the at least one processor, an image and a user query associated with the image, where the image includes a target image area and the user query includes a target phrase. The method further includes retraining, using the at least one processor, the image-query understanding model using a correlation between the target image area and the target phrase to obtain a retrained image-query understanding model.
-
12.发明公开公开(公告)号：US20240311693A1
公开(公告)日：2024-09-19
申请号：US18592250
申请日：2024-02-29
Applicant: Samsung Electronics Co., Ltd.
Inventor： James S. Smith , Yen-Chang Hsu , Yilin Shen , Hongxia Jin , Lingyu Zhang , Ting Hua
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A method includes obtaining input data associated with a new concept to be learned by a trained machine learning model. The method also includes identifying initial weights of the trained machine learning model and one or more previous weight deltas associated with the trained machine learning model. The method further includes identifying one or more additional weight deltas based on the input data and guided by the initial weights and the one or more previous weight deltas. In addition, the method includes integrating the one or more additional weight deltas into the trained machine learning model. The one or more additional weight deltas are integrated into the trained machine learning model by identifying updated weights for the trained machine learning model based on the initial weights, the one or more previous weight deltas, and the one or more additional weight deltas.
-
13.发明公开公开(公告)号：US20230289590A1
公开(公告)日：2023-09-14
申请号：US17940709
申请日：2022-09-08
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Burak UZKENT , Vasili Ramanishka , Yilin Shen , Hongxia Jin
Abstract: A method of training a model includes configuring a first transformer for visual learning with a first set of weights, configuring a second transformer for textual learning with a second set of weights, adjusting at least the second set of weights based on minimizing a weight difference between the first set of weights and the second set of weights, replacing the first set of weights for the first transformer with the adjusted second set of weights, and updating the first transformer based on the adjusted second set of weights.
-
公开(公告)号：US11741307B2
公开(公告)日：2023-08-29
申请号：US17075353
申请日：2020-10-20
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Hongxia Jin
IPC: G06F40/30 , G10L15/14 , G10L15/22 , G10L15/18 , G06F18/214 , G06N7/01 , G06F40/216 , G06F40/295 , G10L15/16 , G06F40/279 , G10L25/30
CPC classification number: G06F40/30 , G06F18/214 , G06N7/01 , G10L15/14 , G10L15/1822 , G10L15/22 , G06F40/216 , G06F40/279 , G06F40/295 , G10L15/16 , G10L25/30
Abstract: A method includes applying, by at least one processor, a natural language understanding (NLU) model to an input utterance in order to obtain initial slot probability distributions. The method also includes performing, by the at least one processor, a confidence calibration by applying a calibration probability distribution to the initial slot probability distributions in order to generate calibrated slot probability distributions. The calibration probability distribution has a higher number of dimensions than the initial slot probability distributions. The method further includes identifying, by the at least one processor, uncertainties associated with words in the input utterance based on the calibrated slot probability distributions. In addition, the method includes identifying, by the at least one processor, a new concept contained in the input utterance that is not recognized by the NLU model based on the identified uncertainties.
-
公开(公告)号：US11681923B2
公开(公告)日：2023-06-20
申请号：US16728987
申请日：2019-12-27
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Yu Wang , Yilin Shen , Yue Deng , Hongxia Jin
IPC: G06N3/084 , G06N20/20 , G06F18/241 , G06N3/045 , G06V10/764 , G06V10/778 , G06V10/94
CPC classification number: G06N3/084 , G06F18/241 , G06N3/045 , G06N20/20 , G06V10/764 , G06V10/7784 , G06V10/94
Abstract: Intent determination based on one or more multi-model structures can include generating an output from each of a plurality of domain-specific models in response to a received input. The domain-specific models can comprise simultaneously trained machine learning models that are trained using a corresponding local loss metric for each domain-specific model and a global loss metric for the plurality of domain-specific models. The presence or absence of an intent corresponding to one or more domain-specific models can be determined by classifying the output of each domain-specific model.
-
Patent Agency Ranking
公开(公告)号：US20230075862A1
公开(公告)日：2023-03-09
申请号：US17899118
申请日：2022-08-30
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Burak UZKENT , Vasili Ramanishka , Yilin Shen , Hongxia Jin
Abstract: A method of training a neural network model includes generating a positive image based on an original image, generating a positive text corresponding to the positive image based on an original text corresponding to the original image, the positive text referring to an object in the positive image, constructing a positive image-text pair for the object based on the positive image and the positive text, constructing a negative image-text pair for the object based on the original image and a negative text, the negative text not referring to the object, training the neural network model based on the positive image-text pair and the negative image-text pair to output features representing an input image-text pair, and identifying the object in the original image based on the features representing the input image-text pair.
-
公开(公告)号：US20220005464A1
公开(公告)日：2022-01-06
申请号：US17075353
申请日：2020-10-20
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Hongxia Jin
Abstract: A method includes applying, by at least one processor, a natural language understanding (NLU) model to an input utterance in order to obtain initial slot probability distributions. The method also includes performing, by the at least one processor, a confidence calibration by applying a calibration probability distribution to the initial slot probability distributions in order to generate calibrated slot probability distributions. The calibration probability distribution has a higher number of dimensions than the initial slot probability distributions. The method further includes identifying, by the at least one processor, uncertainties associated with words in the input utterance based on the calibrated slot probability distributions. In addition, the method includes identifying, by the at least one processor, a new concept contained in the input utterance that is not recognized by the NLU model based on the identified uncertainties.
-
18.发明申请公开(公告)号：US20210027020A1
公开(公告)日：2021-01-28
申请号：US16947258
申请日：2020-07-24
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Hongxia Jin
IPC: G06F40/30 , G06F40/279 , G06N3/08
Abstract: A method includes obtaining, using at least one processor of an electronic device, a base natural language understanding (NLU) model that includes a word embedding layer, where the word embedding layer is associated with at least one training utterance. The method also includes calculating, using the at least one processor, a regularization loss value for use in a determination of an intent detection loss, where the regularization loss value reveals an effect of word embeddings on intent determination of the training utterance. The method further includes retraining, using the at least one processor, the word embedding layer of the base NLU model using the intent detection loss to obtain a retrained NLU model.
-
公开(公告)号：US10902211B2
公开(公告)日：2021-01-26
申请号：US16390241
申请日：2019-04-22
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yu Wang , Yilin Shen , Hongxia Jin
Abstract: A system determines intent values based on an object in a received phrase, and detail values based on the object in the received phrase. The system determines intent state values based on the intent values and the detail values, and detail state values and an intent detail value based on the intent values and the detail values. The system determines other intent values based on the intent values and another object in the received phrase, and other detail values based on the detail values and the other object in the received phrase. The system determines a general intent value based on the other intent values, the other detail values, and the intent state values, and another intent detail value based on the other intent values, the other detail values, and the detail state values.
-
公开(公告)号：US09697381B2
公开(公告)日：2017-07-04
申请号：US14186438
申请日：2014-02-21
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yilin Shen , Fenjiao Wang , Hongxia Jin
CPC classification number: G06F21/6254 , G06Q50/01
Abstract: A computing system includes: a communication unit configured to access a target account including a feature; a control unit, coupled to the communication unit, configured to: calculate a comparison result based on the feature, determine an anonymity threshold for conforming the target account with a comparison account, and determine the feature for the target account based on the comparison result and the anonymity threshold for displaying on a device.
-
-
-
-
-
-
-
-
-
Search Results
74
records
(took 0.03 seconds)
