中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.02 seconds)

    System, method and apparatus for scene recognition
    1.
    发明授权
    System, method and apparatus for scene recognition 有权

    公开(公告)号：US10019463B2

    公开(公告)日：2018-07-10

    申请号：US14747232

    申请日：2015-06-23

    Applicant: Amazon Technologies, Inc.

    Inventor： Yi Li ,  Tianqiang Liu ,  Hao Chen ,  Meng Wang

    IPC: G06F17/30 ,  G06K9/00 ,  G06K9/52 ,  G06K9/62

    Abstract: An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.

    Importance-based data storage verification
    2.
    发明授权
    Importance-based data storage verification 有权
    基于重要性的数据存储验证

    公开(公告)号：US09026869B1

    公开(公告)日：2015-05-05

    申请号：US13666855

    申请日：2012-11-01

    Applicant: Amazon Technologies, Inc.

    Inventor： Yi Li ,  Danny Wei ,  Kerry Quintin Lee ,  Mahmood Miah ,  Nandakumar Gopalakrishnan

    IPC: G06F11/10

    CPC classification number: G06F11/08 ,  G06F11/1004 ,  G06F11/1016 ,  G06F11/1032 ,  G06F11/106 ,  G11C29/38

    Abstract: Methods and systems for detecting error in data storage entities based at least in part on importance of data stored in the data storage entities. In an embodiment, multiple verification passes may be performed on a data storage entity comprising one or more data blocks. Each data block may be associated with a probability indicating the likelihood that the data block is to be selected for verification. During each verification pass, a subset of the data blocks may be selected based at least in part on the probabilities associated with the data blocks. The probabilities may be adjusted, for example, at the end of a verification pass, based on importance factors such as usage and verification information associated with the data blocks. The probabilities may be updated to facilitate timely detection of important data blocks. Additionally, error mitigation and/or correction routines may be performed in light of detected errors.

    Abstract translation: 至少部分地基于数据存储实体中存储的数据的重要性来检测数据存储实体中的错误的方法和系统。 在一个实施例中，可以对包括一个或多个数据块的数据存储实体执行多个验证遍。 每个数据块可以与指示数据块被选择用于验证的可能性的概率相关联。 在每次验证过程中，可以至少部分地基于与数据块相关联的概率来选择数据块的子集。 可以根据诸如与数据块相关联的使用和验证信息等重要性因素来调整概率，例如，在验证通过结束时。 可能更新概率以便于及时检测重要的数据块。 另外，可以根据检测到的错误来执行误差减轻和/或校正例程。

    Intelligent selection of images to create image narratives
    3.
    发明授权
    Intelligent selection of images to create image narratives 有权

    公开(公告)号：US11308155B2

    公开(公告)日：2022-04-19

    申请号：US16363955

    申请日：2019-03-25

    Applicant: Amazon Technologies, Inc.

    Inventor： Yi Li ,  Yuxin Wu ,  Yushan Chen ,  Meng Wang

    IPC: G06F16/58 ,  G06F16/9535 ,  G06F16/438 ,  G06V20/30 ,  G06V40/16

    Abstract: Images are intelligently selected to create image narratives. Instead of a user having to manually search and locate images to view, the images to associate with a particular image narrative are programmatically determined. Many different types of image narratives may be created. For example, one image narrative may show images that include both a first user and a second user over some period of time. Another image narrative may show images that relate to an activity that a first user enjoys or an event that included the user (e.g., a graduation). The tags and metadata associated with the images of the user are analyzed to determine the tags that are important to the user. For example, the importance might be determined based on the frequency of the tags within the images. After creation, the user may select one of the image narratives to view the associated images.

    INTELLIGENT SELECTION OF IMAGES TO CREATE IMAGE NARRATIVES
    5.
    发明申请
    INTELLIGENT SELECTION OF IMAGES TO CREATE IMAGE NARRATIVES 审中-公开

    公开(公告)号：US20190220483A1

    公开(公告)日：2019-07-18

    申请号：US16363955

    申请日：2019-03-25

    Applicant: Amazon Technologies, Inc.

    Inventor： Yi Li ,  Yuxin Wu ,  Yushan Chen ,  Meng Wang

    IPC: G06F16/58 ,  G06K9/00 ,  G06F16/9535

    CPC classification number: G06F16/5866 ,  G06F16/4393 ,  G06F16/9535 ,  G06K9/00288

    Abstract: Images are intelligently selected to create image narratives. Instead of a user having to manually search and locate images to view, the images to associate with a particular image narrative are programmatically determined. Many different types of image narratives may be created. For example, one image narrative may show images that include both a first user and a second user over some period of time. Another image narrative may show images that relate to an activity that a first user enjoys or an event that included the user (e.g., a graduation). The tags and metadata associated with the images of the user are analyzed to determine the tags that are important to the user. For example, the importance might be determined based on the frequency of the tags within the images. After creation, the user may select one of the image narratives to view the associated images.

    Importance-based data storage verification
    7.
    发明授权
    Importance-based data storage verification 有权

    公开(公告)号：US09430320B1

    公开(公告)日：2016-08-30

    申请号：US14703593

    申请日：2015-05-04

    Applicant: Amazon Technologies, Inc.

    Inventor： Yi Li ,  Danny Wei ,  Kerry Quintin Lee ,  Mahmood Miah ,  Nandakumar Gopalakrishnan

    IPC: G11C29/00 ,  G06F11/08 ,  G11C29/38

    CPC classification number: G06F11/08 ,  G06F11/1004 ,  G06F11/1016 ,  G06F11/1032 ,  G06F11/106 ,  G11C29/38

    Abstract: Methods and systems for detecting error in data storage entities based at least in part on importance of data stored in the data storage entities. In an embodiment, multiple verification passes may be performed on a data storage entity comprising one or more data blocks. Each data block may be associated with a probability indicating the likelihood that the data block is to be selected for verification. During each verification pass, a subset of the data blocks may be selected based at least in part on the probabilities associated with the data blocks. The probabilities may be adjusted, for example, at the end of a verification pass, based on importance factors such as usage and verification information associated with the data blocks. The probabilities may be updated to facilitate timely detection of important data blocks. Additionally, error mitigation and/or correction routines may be performed in light of detected errors.

    System, method and apparatus for scene recognition
    8.
    发明授权
    System, method and apparatus for scene recognition 有权

    公开(公告)号：US10176196B2

    公开(公告)日：2019-01-08

    申请号：US14747232

    申请日：2015-06-23

    Applicant: Amazon Technologies, Inc.

    Inventor： Yi Li ,  Tianqiang Liu ,  Hao Chen ,  Meng Wang

    IPC: G06F17/30 ,  G06K9/00 ,  G06K9/52 ,  G06K9/62

    Abstract: An image processing system for recognizing the scene type of an input image generates an image distance metric from a set of images. The image processing system further extracts image features from the input image and each image in the set of images. Based on the distance metric and the extracted image features, the image processing system computes image feature distances for selecting a subset of images. The image processing system derives a scene type from the scene type of the subset of images. In one embodiment, the image processing system is a cloud computing system.

    Identifying critical thermal conditions in multiple system-on-a-chip (SoC) systems
    10.
    发明授权
    Identifying critical thermal conditions in multiple system-on-a-chip (SoC) systems 有权

    公开(公告)号：US11126440B1

    公开(公告)日：2021-09-21

    申请号：US16911644

    申请日：2020-06-25

    Applicant: Amazon Technologies, Inc.

    Inventor： Lalithkumar Rajendran ,  Jun woo Park ,  Garrick Chow ,  Austin Bryant ,  Yi Li ,  Hua Wang

    IPC: G06F9/4401 ,  G01K3/00 ,  G06F13/10 ,  G06F13/42 ,  G01K7/22 ,  G06F1/20

    Abstract: Techniques for identifying thermal critical conditions in devices with multiple SoCs, and coordinating the resetting and rebooting of the SoCs to recover from the thermal critical conditions are described herein. A device may include a first SoC that monitors a first temperature sensor, and a second SoC that monitors a second temperature sensor, to determine whether temperatures in the device indicate thermal critical conditions. The second SoC may determine that a temperature determined using the second temperature sensor is above a threshold indicating a thermal critical condition, and may provide an indication to the first SoC that the temperature is above the threshold. The first SoC may detect the indication, and the first SoC and second SoC may each reset to allow the device to cool down. The first SoC and second SoC may then coordinate rebooting once the thermal critical condition is no longer detected in the device.

Patent Agency Ranking