中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.018 seconds)

    Training encoder model and/or using trained encoder model to determine responsive action(s) for natural language input
    1.
    发明授权
    Training encoder model and/or using trained encoder model to determine responsive action(s) for natural language input 有权

    公开(公告)号：US10783456B2

    公开(公告)日：2020-09-22

    申请号：US16611725

    申请日：2018-12-14

    Applicant: Google LLC

    Inventor： Brian Strope ,  Yun-hsuan Sung ,  Wangqing Yuan

    IPC: G06N20/00 ,  G06F16/35 ,  G06F16/332 ,  G06F16/33 ,  G06N5/04

    Abstract: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.

    COOPERATIVELY TRAINING AND/OR USING SEPARATE INPUT AND SUBSEQUENT CONTENT NEURAL NETWORKS FOR INFORMATION RETRIEVAL
    2.
    发明申请
    COOPERATIVELY TRAINING AND/OR USING SEPARATE INPUT AND SUBSEQUENT CONTENT NEURAL NETWORKS FOR INFORMATION RETRIEVAL 有权

    公开(公告)号：US20250068913A1

    公开(公告)日：2025-02-27

    申请号：US18828690

    申请日：2024-09-09

    Applicant: GOOGLE LLC

    Inventor： Brian Strope ,  Yun-Hsuan Sung ,  Matthew Henderson ,  Rami Al-Rfou' ,  Raymond Kurzweil

    IPC: G06N3/084 ,  G06F16/00 ,  G06F16/335 ,  G06N3/044 ,  G06N3/045 ,  G06N5/04

    Abstract: Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

    Speech recognition with parallel recognition tasks
    3.
    发明授权
    Speech recognition with parallel recognition tasks 有权

    公开(公告)号：US11527248B2

    公开(公告)日：2022-12-13

    申请号：US16885116

    申请日：2020-05-27

    Applicant: Google LLC

    Inventor： Brian Strope ,  Francoise Beaufays ,  Olivier Siohan

    IPC: G10L15/32 ,  G10L15/00 ,  G10L15/26 ,  G10L15/01

    Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving an audio signal and initiating speech recognition tasks by a plurality of speech recognition systems (SRS's). Each SRS is configured to generate a recognition result specifying possible speech included in the audio signal and a confidence value indicating a confidence in a correctness of the speech result. The method also includes completing a portion of the speech recognition tasks including generating one or more recognition results and one or more confidence values for the one or more recognition results, determining whether the one or more confidence values meets a confidence threshold, aborting a remaining portion of the speech recognition tasks for SRS's that have not generated a recognition result, and outputting a final recognition result based on at least one of the generated one or more speech results.

    Personal directory service
    4.
    发明授权
    Personal directory service 有权

    公开(公告)号：US10679624B2

    公开(公告)日：2020-06-09

    申请号：US16036662

    申请日：2018-07-16

    Applicant: GOOGLE LLC

    Inventor： Brian Strope ,  Francoise Beaufays ,  William J. Byrne

    IPC: G06F16/9535 ,  G10L15/22 ,  G10L15/26 ,  G06Q30/02 ,  G06F16/29 ,  G06F16/951 ,  G06F16/9537 ,  G10L15/18 ,  G10L15/197 ,  G10L15/30

    Abstract: A method of providing a personal directory service includes receiving, over the Internet, from a user terminal, a query spoken by a user, where the query spoken by the user includes a speech utterance representing a category of persons. The method also includes determining a geographic location of the user terminal, recognizing the category of persons with the speech recognition engine based on the speech utterance representing the category of persons a listing of persons within or near the determined geographic location matching the query to select persons responsive to the query spoken by the user, and sending to the user terminal information related to at least some of the responsive persons.

    TRAINING ENCODER MODEL AND/OR USING TRAINED ENCODER MODEL TO DETERMINE RESPONSIVE ACTION(S) FOR NATURAL LANGUAGE INPUT
    5.
    发明申请
    TRAINING ENCODER MODEL AND/OR USING TRAINED ENCODER MODEL TO DETERMINE RESPONSIVE ACTION(S) FOR NATURAL LANGUAGE INPUT 审中-公开

    公开(公告)号：US20200104746A1

    公开(公告)日：2020-04-02

    申请号：US16611725

    申请日：2018-12-14

    Applicant: Google LLC

    Inventor： Brian Strope ,  Yun-hsuan Sung ,  Wangqing Yuan

    IPC: G06N20/00 ,  G06F16/33 ,  G06F16/35 ,  G06F16/332 ,  G06N5/04

    Abstract: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.

Patent Agency Ranking