中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

58 records (took 0.025 seconds)

    SYSTEM(S) AND METHOD(S) FOR IMPLEMENTING A PERSONALIZED CHATBOT
    35.
    发明公开
    SYSTEM(S) AND METHOD(S) FOR IMPLEMENTING A PERSONALIZED CHATBOT 审中-公开

    公开(公告)号：US20240205332A1

    公开(公告)日：2024-06-20

    申请号：US18082424

    申请日：2022-12-15

    Applicant: GOOGLE LLC

    Inventor： Yoav Tzur ,  Yaniv Leviathan ,  Yossi Matias ,  Jan Jedrzejowicz

    IPC: H04M3/493 ,  G06F40/35 ,  G10L13/02 ,  G10L15/18 ,  G10L15/22 ,  H04M3/527

    CPC classification number: H04M3/4936 ,  G06F40/35 ,  G10L13/02 ,  G10L15/1815 ,  G10L15/22 ,  H04M3/527 ,  G10L2015/223

    Abstract: Processor(s) of a client device of a user can receive a telephone call that is initiated by an additional user, and, in response to receiving the telephone call, identify an entity that is associated with the additional user, and determine, based on the entity that is associated with the additional user, whether to (1) fully automate the telephone call, or (2) partially automate the telephone call. In fully automating the telephone call, the processor(s) can cause a chatbot to engage in a corresponding conversation with the additional user and without prompting the user for any input. In partially automating the telephone call, the processor(s) can cause the chatbot to engage in a corresponding conversation with the additional user but with prompting the user for input(s) via suggestion chip(s). In some implementations, the processor(s) can further determine whether to (3) refrain from automating the telephone call entirely.

    REDUCING TELEPHONE NETWORK TRAFFIC THROUGH UTILIZATION OF PRE-CALL INFORMATION
    36.
    发明公开
    REDUCING TELEPHONE NETWORK TRAFFIC THROUGH UTILIZATION OF PRE-CALL INFORMATION 审中-公开

    公开(公告)号：US20240205331A1

    公开(公告)日：2024-06-20

    申请号：US18082403

    申请日：2022-12-15

    Applicant: GOOGLE LLC

    Inventor： Yoav Tzur ,  Yaniv Leviathan ,  Yossi Matias ,  Eyal Segalis

    IPC: H04M3/493 ,  G10L15/22 ,  G10L15/30

    CPC classification number: H04M3/493 ,  G10L15/22 ,  G10L15/30 ,  G10L15/1815 ,  G10L2015/223

    Abstract: Implementations receive, via a client device, user input to initiate a telephone call with an entity, and, in response to receiving the user input to initiate the telephone call with the entity and prior to initiating the telephone call with the entity: obtain pre-call information that is stored in association with the entity, and cause the pre-call information that is stored in association with the entity to be provided for presentation to the user via the client device. The pre-call information may include any information that would be provided for presentation to a user subsequent to initiation of the telephone call with the entity. Further, implementations determine, based on user consumption of the pre-call information, whether to (1) proceed with initiating the telephone call with the entity, or (2) refrain from initiating the telephone call with the entity, and cause the client device to implement the appropriate action.

    Partially customized machine learning models for data de-identification
    37.
    发明申请
    Partially customized machine learning models for data de-identification 有权

    公开(公告)号：US20210303725A1

    公开(公告)日：2021-09-30

    申请号：US17216891

    申请日：2021-03-30

    Applicant: Google LLC

    Inventor： Tzvika Hartman ,  ltay Laish ,  Jiyang Chen ,  Kaveh Ketabchi ,  Gavin Bee ,  Rohit Talreja ,  Yossi Matias ,  Andrew Max

    IPC: G06F21/62 ,  G16H10/60 ,  G06N3/08 ,  G06K9/62

    Abstract: Apparatus and methods related to de-identifying data are provided. An example method includes receiving, by a computing device, input data comprising text. The method further includes applying a neural network to a tokenized representation of the input text, to generate an embedding based on contextual information associated with an entity. The method also includes predicting, by the neural network and based on the embedding, whether the input data comprises protected data in the text, wherein the neural network has been trained on a training dataset that has been partially customized based on the entity. The method further includes de-identifying the protected data in the text upon a determination that the input data comprises protected data in the text.

Patent Agency Ranking