知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.014 seconds)

    Machine learning-based program analysis using synthetically generated labeled data
    3.
    发明授权
    Machine learning-based program analysis using synthetically generated labeled data 有权

    公开(公告)号：US11593675B1

    公开(公告)日：2023-02-28

    申请号：US16699378

    申请日：2019-11-29

    Applicant: Amazon Technologies, Inc.

    Inventor： Pranav Garg ,  Srinivasan Sengamedu Hanumantha Rao

    IPC: G06F21/57 ,  G06N20/00 ,  G06N5/04 ,  G06F8/75

    Abstract: Techniques for performing machine learning-based program analysis using synthetically generated labeled data are described. A method of performing machine learning-based program analysis using synthetically generated labeled data may include receiving a request to perform program analysis on code, determining a first portion of the code associated with a first error type, sending the first portion of the code to an endpoint of a machine learning service associated with an error detection model to detect the first error type, the error detection model trained using synthetically generated labeled data, and receiving inference results from the error detection model identifying one or more errors of the first error type in the first portion of the code.

    Rule creation for code analysis
    5.
    发明授权
    Rule creation for code analysis 有权

    公开(公告)号：US12045609B1

    公开(公告)日：2024-07-23

    申请号：US17850583

    申请日：2022-06-27

    Applicant: Amazon Technologies, Inc.

    Inventor： Neela Sawant ,  Pranav Garg

    IPC: G06F8/75 ,  G06F8/71 ,  G06F40/20

    CPC classification number: G06F8/75 ,  G06F8/71 ,  G06F40/20

    Abstract: Techniques for generating custom rules are described. For example, a system to receive at least one request to create rules based on a policy and code repository files stored by the storage service; analyze the policy to generate a collection of rule candidates; analyze the code repository files to identify labeled code examples that either conform or do not conform to the rule candidates; receive a selection of the labeled code examples; and synthesize at least one rule that includes a precondition that specifies applicability to the selected labeled code examples and a postcondition that expresses a check to be performed contingent on the precondition being satisfied is at least described.

    Scoring events using noise-contrastive estimation for anomaly detection
    6.
    发明授权
    Scoring events using noise-contrastive estimation for anomaly detection 有权

    公开(公告)号：US11593639B1

    公开(公告)日：2023-02-28

    申请号：US16559393

    申请日：2019-09-03

    Applicant: Amazon Technologies, Inc.

    Inventor： Pranav Garg ,  Baris Coskun

    IPC: G06N3/00 ,  G06N3/08 ,  G06N3/04 ,  G06F21/31 ,  G06K9/62 ,  G06F17/16

    Abstract: Techniques for monitoring a computing environment for anomalous activity are presented. An example method includes receiving a request to invoke an action within the computing environment. An anomaly score is generated for the received request by applying a probabilistic model to properties of the request. The anomaly score generally indicates a likelihood that the properties of the request correspond to historical activity within the computing environment for a user associated with the request. The probabilistic model generally comprises a model having been trained using historical activity within the computing environment for a plurality of users, the historical activity including information identifying an action performed in the computing environment and contextual information about a historical request. Based on the generated anomaly score, one or more actions are taken to process the request such that execution of requests having anomaly scores indicative of unexpected activity may be blocked pending confirmation.

    Visual query language for code review rules
    7.
    发明授权
    Visual query language for code review rules 有权

    公开(公告)号：US12007877B1

    公开(公告)日：2024-06-11

    申请号：US17708269

    申请日：2022-03-30

    Applicant: Amazon Technologies, Inc.

    Inventor： Pranav Garg ,  Sengamedu Hanumantha Rao Srinivasan ,  Omer Tripp ,  Abhin Sharma

    IPC: G06F9/44 ,  G06F11/36

    CPC classification number: G06F11/3664 ,  G06F11/3688

    Abstract: Techniques for providing a visual code review editor are described. An electronic device is caused to display a graphical user interface including an editor portion to edit code review rules used by a code review service of a cloud provider network. The editor portion of the graphical user interface is caused to display a first graph associated with a first code review rule, the first graph including a first node, a second node, and a first edge connecting the first node and the second node. An indication that a third node has been added to the graph via the editor portion of the graphical user interface is received. The first code review rule is updated by the code review service to reflect the addition of the third node, the first code review rule is in a text format.

Patent Agency Ranking