中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

22711 records (took 0.046 seconds)

    VIRTUAL CONVERSATIONAL COMPANION
    2.
    发明申请
    VIRTUAL CONVERSATIONAL COMPANION 有权

    公开(公告)号：US20250157463A1

    公开(公告)日：2025-05-15

    申请号：US19017979

    申请日：2025-01-13

    Applicant: Amazon Technologies, Inc.

    Inventor： Taehwan Kim ,  Sanqiang Zhao ,  Robinson Piramuthu ,  Seokhwan Kim ,  Yang Liu ,  Gokhan Tur ,  Eshan Bhatnagar

    IPC: G10L15/18 ,  G06T13/20 ,  G06T13/40 ,  G06T13/80 ,  G10L13/08 ,  G10L15/22 ,  G10L25/57

    Abstract: Techniques for rendering visual content, in response to one or more utterances, are described. A device receives one or more utterances that define a parameter(s) for desired output content. A system (or the device) identifies natural language data corresponding to the desired content, and uses natural language generation processes to update the natural language data based on the parameter(s). The system (or the device) then generates an image based on the updated natural language data. The system (or the device) also generates video data of an avatar. The device displays the image and the avatar, and synchronizes movements of the avatar with output of synthesized speech of the updated natural language data. The device may also display subtitles of the updated natural language data, and cause a word of the subtitles to be emphasized when synthesized speech of the word is being output.

    WAKEWORD DETECTION USING A SECONDARY MICROPHONE
    3.
    发明申请
    WAKEWORD DETECTION USING A SECONDARY MICROPHONE 有权

    公开(公告)号：US20250157461A1

    公开(公告)日：2025-05-15

    申请号：US18985185

    申请日：2024-12-18

    Applicant: Amazon Technologies, Inc.

    Inventor： Andrew Mitchell ,  Gabor Nagy

    IPC: G10L15/08 ,  G10L15/22 ,  G10L15/30

    Abstract: Techniques for capturing spoken user inputs while a device is prevented from capturing such spoken user inputs are described. When a first device becomes incapable of capturing spoken user inputs intended for a system, a second device, for capturing such spoken user inputs, may be identified. The second device may be identified based on the second device being connected to a same vehicle computing system as the first device. The second device may be enabled to capture spoken user inputs, intended for the system, until the first device is again able to capture such spoken user inputs.

    Context data attachment for interface-based communication sessions
    4.
    发明授权
    Context data attachment for interface-based communication sessions 有权

    公开(公告)号：US12301758B1

    公开(公告)日：2025-05-13

    申请号：US18067381

    申请日：2022-12-16

    Applicant: Amazon Technologies, Inc.

    Inventor： Siddhartha Shankara Rao ,  Giridhar Kalpathy Narayanan ,  Ryan Steven McHarg ,  Abitha Padmanabhan ,  Curtis Gill Hartmann ,  John Joseph Dunne

    IPC: H04M3/51 ,  G06Q30/015 ,  H04M3/523

    Abstract: Context data may be received corresponding to a first communication session that includes a first user and a second user that joins the first communication session on behalf of a customer account. The context data may be provided to the first user and the second user. The context data may be stored in a searchable data storage that stores a communication session context history for the customer account. Search requests may be received, from the customer account, for searching the communication session context history. Responses may be provided based at least part on the context data. The context data may include second session information for joining a second communication session between the first user and the second user. Requests to join the second communication session may be received based on the second session information, and the second communication session may be established between the first user and the second user.

    Vehicle data stream subscription system
    7.
    发明授权
    Vehicle data stream subscription system 有权

    公开(公告)号：US12300041B2

    公开(公告)日：2025-05-13

    申请号：US17806434

    申请日：2022-06-10

    Applicant: Amazon Technologies, Inc.

    Inventor： Roland Mesde ,  Alex Bessonov ,  Nitin Giri ,  Kyle Daniel Halbach ,  Roie Hodara

    IPC: G06Q30/02 ,  G06F16/21 ,  G06F16/28 ,  G06V20/58 ,  G07C5/00

    Abstract: A vehicle data streaming service provides a curated catalog of vehicle attributes and allows a vehicle data stream source to register to the vehicle data streaming system and associate its data stream to a vehicle attribute of the attribute catalog. The vehicle data streaming service also allows vehicle data stream destinations to subscribe to the vehicle attribute in the vehicle catalog, receives streamed vehicle data from the data stream source, and sends streamed vehicle data conforming to registration requirements to the data stream destinations. Additionally, the vehicle data streaming service may allow management of the vehicle attribute catalog and may further manage the registration one or more sources and the subscriptions of one or more destinations.

    Synthetic image generation by manifold modification of a machine learning model
    8.
    发明授权
    Synthetic image generation by manifold modification of a machine learning model 有权

    公开(公告)号：US12299896B1

    公开(公告)日：2025-05-13

    申请号：US17702202

    申请日：2022-03-23

    Applicant: Amazon Technologies, Inc.

    Inventor： Qianli Feng ,  Raghu Deep Gadde ,  Pietro Perona ,  Aleix Margarit Martinez

    IPC: G06T3/14 ,  G06N3/045 ,  G06T7/187 ,  G06V10/74 ,  G06V10/774

    Abstract: Described herein is a computer-implemented method for generating a synthetic image. An input image can be received by a computing device. A representation of the input image on an image approximation manifold can be identified by inputting the input image into a machine learning model. The image approximation manifold can be defined by the machine learning model. A local region of the image approximation manifold can be modified relative to the first representation to generate a modified image approximation manifold. The modified image approximation manifold can include a second representation of the input image. A synthetic image can be generated based on the modified image approximation manifold. A rendering of the synthetic image can be caused on a display.

    Customized retail environments
    9.
    发明授权
    Customized retail environments 有权

    公开(公告)号：US12299630B1

    公开(公告)日：2025-05-13

    申请号：US17978006

    申请日：2022-10-31

    Applicant: Amazon Technologies, Inc.

    Inventor： Aaron M. McDaniel ,  Joel Stirling ,  Emily Marsden ,  Nirmal Doshi ,  Nathan P. O'Neill

    IPC: G06Q10/087 ,  G06K7/10 ,  G06N3/08 ,  G06Q20/08 ,  G06T7/70 ,  H04N7/18

    Abstract: This disclosure describes, in part, systems for enabling facilities to implement techniques to determine when users are in possession of items when located within and/or exiting the facilities. For instance, a system may use one or more sensors to determine locations of a user that navigated through a facility. Additionally, the system may use one or more sensors to determine locations of an item while the item was located within the facility. The system may then determine a probability that the user was in possession of the item when in the facility and/or when exiting the facility based at least in part on the locations of the user and the locations of the item. If the system determines that the user was in possession of the item when exiting the facility, the system may charge a payment instrument of the user for a price of the item.

    Techniques for generating a training data set for a machine-learning model
    10.
    发明授权
    Techniques for generating a training data set for a machine-learning model 有权

    公开(公告)号：US12299581B1

    公开(公告)日：2025-05-13

    申请号：US17214448

    申请日：2021-03-26

    Applicant: Amazon Technologies, Inc.

    Inventor： Patrick Ian Wilson ,  Dmitry Vladimir Zhiyanov ,  Lichao Wang ,  Jong Wan Kim ,  Srinivas K Yellala

    IPC: G06N20/00 ,  G06F7/24 ,  G06N3/088

    Abstract: Systems and methods are provided herein for generating a synthetic training data set that can be used to train a machine-learning model to identify when two addresses match (e.g., when a user-defined address and an authoritative address match). The addresses may each be tokenized. Each candidate address can be scored based on a number of common tokens it shares with the user-defined address. The highest-scored candidate address may be selected as a matching address for the user-defined address. In some embodiments, a number of the remaining candidate address can be selected as negative examples (e.g., candidate addresses that do not match the user-defined address) based on, for example, historical delivery information associated with the corresponding addresses. In this manner, an expansive training data set may be generated using addresses associated with user profiles of an online service provider and a set of authoritative addresses obtained from an authoritative source.

Patent Agency Ranking