知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

132 records (took 0.035 seconds)

    Deep reinforcement learning-based multi-step question answering systems
    51.
    发明授权
    Deep reinforcement learning-based multi-step question answering systems 有权

    公开(公告)号：US11573991B2

    公开(公告)日：2023-02-07

    申请号：US16695641

    申请日：2019-11-26

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yu Wang ,  Hongxia Jin

    IPC: G06F16/33 ,  G06F16/338 ,  G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06F16/35

    Abstract: A method includes receiving a user query and performing, using at least one processor, multiple rounds of an answer generation process. Each round of the answer generation process includes selecting one of multiple functions to be performed based on an input state. The input state for each round includes an embedding of the user query in a feature space. The input state for at least one round also includes an embedding of information to be used to identify an answer to the user query in the feature space. Each round of the answer generation process also includes performing the selected function. The multiple functions include (i) an answer generation function that produces the answer to the user query and (ii) at least one additional function that updates the input state for a current round for use during a subsequent round. In addition, the method includes providing the answer to the user.

    APPARATUS AND METHOD FOR COMPOSITIONAL SPOKEN LANGUAGE UNDERSTANDING
    52.
    发明申请
    APPARATUS AND METHOD FOR COMPOSITIONAL SPOKEN LANGUAGE UNDERSTANDING 有权

    公开(公告)号：US20220375457A1

    公开(公告)日：2022-11-24

    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 ,  G10L15/22 ,  G10L15/14

    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.

    METHOD AND APPARATUS FOR CLASSIFYING IMAGES USING AN ARTIFICIAL INTELLIGENCE MODEL
    53.
    发明申请
    METHOD AND APPARATUS FOR CLASSIFYING IMAGES USING AN ARTIFICIAL INTELLIGENCE MODEL 有权

    公开(公告)号：US20220309774A1

    公开(公告)日：2022-09-29

    申请号：US17701209

    申请日：2022-03-22

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Burak Uzkent ,  Vasili Ramanishka ,  Yilin Shen ,  Hongxia Jin

    IPC: G06V10/82 ,  G06V10/764

    Abstract: An apparatus for performing image processing, may include at least one processor configured to: input an image to a vision transformer comprising a plurality of encoders that correspond to at least one fixed encoder and a plurality of adaptive encoders; process the image via the at least one fixed encoder to obtain image representations; determine one or more layers of the plurality of adaptive encoders to drop, by inputting the image representations to a policy network configured to determine layer dropout actions for the plurality of adaptive encoders; and obtain a class of the input image using remaining layers of the plurality of adaptive encoders other than the dropped one or more layers.

    Method to learn personalized intents
    55.
    发明授权
    Method to learn personalized intents 有权

    公开(公告)号：US11182565B2

    公开(公告)日：2021-11-23

    申请号：US15904203

    申请日：2018-02-23

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Avik Ray ,  Yilin Shen ,  Hongxia Jin

    IPC: G06F40/35 ,  G10L15/18 ,  G06F3/16 ,  G06F40/30 ,  G06F40/247 ,  G06F40/295 ,  G10L15/07 ,  G06F40/216

    Abstract: A method includes retrieving, at an electronic device, a first natural language (NL) input. An intent of the first NL input is undetermined by both a generic parser and a personal parser. A paraphrase of the first NL input is retrieved at the electronic device. An intent of the paraphrase of the first NL input is determined using at least one of: the generic parser, the personal parser, or a combination thereof. A new personal intent for the first NL input is generated based on the determined intent. The personal parser is trained using existing personal intents and the new personal intent.

    Method and system for learning and enabling commands via user demonstration
    57.
    发明授权
    Method and system for learning and enabling commands via user demonstration 有权

    公开(公告)号：US11093715B2

    公开(公告)日：2021-08-17

    申请号：US16370411

    申请日：2019-03-29

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Sandeep Nama ,  Hongxia Jin

    IPC: G06F40/30 ,  G10L15/18 ,  G06F3/16 ,  G06F40/205 ,  G06F40/289 ,  G10L15/08

    Abstract: A method for learning a task includes capturing first information associated with at least one application executed by an electronic device. A sequence of user interface interactions for the at least one application is recorded. Second information are extracted from the sequence of user interface interactions. Events, action or a combination thereof are filtered from the second information using the first information. Recognition is performed on each element from the first information to generate a semantic ontology. An executable sequential event task bytecode is generated from each element of the semantic ontology and the filtered second information.

    System and method to enable privacy-preserving real time services against inference attacks
    58.
    发明授权
    System and method to enable privacy-preserving real time services against inference attacks 有权

    公开(公告)号：US11087024B2

    公开(公告)日：2021-08-10

    申请号：US15011368

    申请日：2016-01-29

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yilin Shen ,  Hongxia Jin

    IPC: G06F21/62 ,  H04W12/00 ,  H04W12/02 ,  H04L29/06

    Abstract: One embodiment provides a method comprising receiving general private data identifying at least one type of privacy-sensitive data to protect, collecting at least one type of real-time data, and determining an inference privacy risk level associated with transmitting the at least one type of real-time data to a second device. The inference privacy risk level indicates a degree of risk of inferring the general private data from transmitting the at least one type of real-time data. The method further comprises distorting at least a portion of the at least one type of real-time data based on the inference privacy risk level before transmitting the at least one type of real-time data to the second device.

    SYSTEM AND METHOD FOR DEEP MEMORY NETWORK
    60.
    发明申请
    SYSTEM AND METHOD FOR DEEP MEMORY NETWORK 审中-公开

    公开(公告)号：US20200050934A1

    公开(公告)日：2020-02-13

    申请号：US16535380

    申请日：2019-08-08

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yilin Shen ,  Yue Deng ,  Avik Ray ,  Hongxia Jin

    IPC: G06N3/08 ,  G06F3/06 ,  G06N5/04

    Abstract: An electronic device including a deep memory model 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 input data to the deep memory model. The at least one processor is also configured to extract a history state of an external memory coupled to the deep memory model based on the input data. The at least one processor is further configured to update the history state of the external memory based on the input data. In addition, the at least one processor is configured to output a prediction based on the extracted history state of the external memory.

Patent Agency Ranking