知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.015 seconds)

    System management using natural language statements
    1.
    发明授权
    System management using natural language statements 有权

    公开(公告)号：US11100146B1

    公开(公告)日：2021-08-24

    申请号：US15933849

    申请日：2018-03-23

    Applicant: Amazon Technologies, Inc.

    Inventor： Jordan Barry Brest ,  Gunja Agrawal ,  Rahul Sharma ,  Venkata Keerthana Atchutuni ,  Vijay Dheeraj Reddy Mandadi

    IPC: G06F16/332 ,  G06F21/32 ,  G06F16/2457 ,  G06F40/205

    Abstract: Technologies are provided for managing computer system resources using natural language statements. A natural language statement can be received from a user computing device by a management service. The natural language statement can be analyzed to identify an executable command, and the command can be executed against one or more system resources. If the system resources are located in separate computing environments, different operations can be used to target the system resources in the separate computing environments. A script repository can be searched to identify an executable script containing the command referenced by the received natural language statement. A message can be transmitted to the user device, recommending execution of the identified script. In a different or further embodiment, if a given user is not authorized to execute a given command or script, a request for authorization can be sent to a supervisor of the given user.

    Identity management for coordinated devices in a networked environment
    4.
    发明授权
    Identity management for coordinated devices in a networked environment 有权

    公开(公告)号：US10979439B1

    公开(公告)日：2021-04-13

    申请号：US15910795

    申请日：2018-03-02

    Applicant: Amazon Technologies, Inc.

    Inventor： Rahul Sharma

    IPC: H04L29/06 ,  H04L12/24 ,  G06F21/34 ,  G06F21/44

    Abstract: Systems and methods are described for management of data transmitted between computing devices in a communication network. An administrative component can configure one or more devices in the communication path of messages to be exchanged by devices to interpret codes embedded in the communication messages. A receiving device can review incoming messages for one or more processing codes or instructions that are embedded in the portion of the communication typically utilized solely to identify the subject matter of the communication, generally referred to as the topic portion of the communication. The receiving devices can then process the embedded codes to determine how the communication message will be routed or otherwise processed.

    Custom labeling workflows in an active learning-based data labeling service
    5.
    发明授权
    Custom labeling workflows in an active learning-based data labeling service 有权

    公开(公告)号：US11481906B1

    公开(公告)日：2022-10-25

    申请号：US16370723

    申请日：2019-03-29

    Applicant: Amazon Technologies, Inc.

    Inventor： Hareesh Lakshmi Narayanan ,  Rahul Sharma ,  Arvind Jayasundar ,  Vikram Madan

    IPC: G06T7/187 ,  G06K9/62 ,  G06N20/00 ,  G06V30/414

    Abstract: Techniques for active learning-based data labeling are described. An active learning-based data labeling service enables a user to build and manage large, high accuracy datasets for use in various machine learning systems. Machine learning may be used to automate annotation and management of the datasets, increasing efficiency of labeling tasks and reducing the time required to perform labeling. Embodiments utilize active learning techniques to reduce the amount of a dataset that requires manual labeling. As subsets of the dataset are labeled, this label data is used to train a model which can then identify additional objects in the dataset without manual intervention. The process may continue iteratively until the model converges. This enables a dataset to be labeled without requiring each item in the data set to be individually and manually labeled by human labelers.

    Active learning loop-based data labeling service
    6.
    发明授权
    Active learning loop-based data labeling service 有权

    公开(公告)号：US11048979B1

    公开(公告)日：2021-06-29

    申请号：US16370706

    申请日：2019-03-29

    Applicant: Amazon Technologies, Inc.

    Inventor： Fedor Zhdanov ,  Siddharth Joshi ,  Sankalp Srivastava ,  Rahul Sharma ,  Pietro Perona ,  Sindhu Chejerla

    IPC: G06K9/00 ,  G06K9/62 ,  G06N20/00

    Abstract: Techniques for active learning-based data labeling are described. An active learning-based data labeling service enables a user to build and manage large, high accuracy datasets for use in various machine learning systems. Machine learning may be used to automate annotation and management of the datasets, increasing efficiency of labeling tasks and reducing the time required to perform labeling. Embodiments utilize active learning techniques to reduce the amount of a dataset that requires manual labeling. As subsets of the dataset are labeled, this label data is used to train a model which can then identify additional objects in the dataset without manual intervention. The process may continue iteratively until the model converges. This enables a dataset to be labeled without requiring each item in the dataset to be individually and manually labeled by human labelers.

    Machine learning based adaptive instructions for annotation
    7.
    发明授权
    Machine learning based adaptive instructions for annotation 有权

    公开(公告)号：US10977518B1

    公开(公告)日：2021-04-13

    申请号：US16355617

    申请日：2019-03-15

    Applicant: Amazon Technologies, Inc.

    Inventor： Rahul Sharma ,  Vikram Madan ,  James Robert Blair ,  Charles Bell

    IPC: G06K9/62 ,  G06N5/04 ,  G06N20/00

    Abstract: Techniques for generating and utilizing machine learning based adaptive instructions for annotation are described. An annotation service can use models to identify edge case data elements predicted to elicit differing annotations from annotators, “bad” data elements predicted to be difficult to annotate, and/or “good” data elements predicted to elicit matching or otherwise high-quality annotations from annotators. These sets of data elements can be automatically incorporated into annotation job instructions provided to annotators, resulting in improved overall annotation results via having efficiently and effectively “trained” the annotators how to perform the annotation task.

    Active learning-based data labeling service using an augmented manifest
    9.
    发明授权
    Active learning-based data labeling service using an augmented manifest 有权

    公开(公告)号：US11443232B1

    公开(公告)日：2022-09-13

    申请号：US16370733

    申请日：2019-03-29

    Applicant: Amazon Technologies, Inc.

    Inventor： Zahid Rahman ,  Wei Xiao ,  Stefano Stefani ,  Rahul Sharma ,  Siddharth Joshi

    IPC: G06F7/00 ,  G06N20/00 ,  G06F16/335 ,  G06F16/383 ,  H04L67/10 ,  G06F40/40

    Abstract: Techniques for active learning-based data labeling are described. An active learning-based data labeling service enables a user to build and manage large, high accuracy datasets for use in various machine learning systems. Machine learning may be used to automate annotation and management of the datasets, increasing efficiency of labeling tasks and reducing the time required to perform labeling. Embodiments utilize active learning techniques to reduce the amount of a dataset that requires manual labeling. As subsets of the dataset are labeled, this label data is used to train a model which can then identify additional objects in the dataset without manual intervention. The label data can be added to an augmented manifest, the augmented manifest can be used to filter the dataset to perform further labeling jobs on the same or different subsets of the dataset.

    Delivery confirmation using overlapping geo-fences
    10.
    发明授权
    Delivery confirmation using overlapping geo-fences 有权

    公开(公告)号：US10445685B2

    公开(公告)日：2019-10-15

    申请号：US15607980

    申请日：2017-05-30

    Applicant: Amazon Technologies, Inc.

    Inventor： Sandeep Bhatia ,  Kevin Lee Davenport, Jr. ,  Rahul Sharma ,  Vinoo Vasudevan ,  Beryl Tomay

    IPC: G06Q10/08 ,  H04W4/021 ,  H04W4/02 ,  G06F3/0481 ,  G06K19/06 ,  G06Q30/02 ,  H04W84/12

    Abstract: Disclosed are approaches for using overlapping geo-fences to confirm delivery of a shipment. A first client computing device and a second client computing device may be in data communication with a server computing device. The server computing device may receive a delivery notification from the first client computing device. The server computing device may receive a first position of the first client computing device and a second position of the second client computing device. The server computing device may then determine that the second position is within a threshold distance of the first position or vice versa. Finally, the server computing device may generate a delivery confirmation in response to a first determination that the second position is within a threshold distance of the first position and a second determination that the first position is within a threshold distance of the second position.

Patent Agency Ranking