公开(公告)号：WO2021247132A1

公开(公告)日：2021-12-09

申请号：PCT/US2021/025689

申请日：2021-04-05

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： YANG, Connie Qin ,  ROSOFF, Matthew Scott ,  ADAPA, Nithin ,  RINGER, Logan ,  LIM, Steve Ku ,  CHAI, Xiaoyu

IPC: G06F11/34 ,  G06F11/36 ,  G06F11/302 ,  G06F11/327 ,  G06F11/328 ,  G06F11/3452 ,  G06F11/3466 ,  G06F11/3616 ,  G06F11/3692 ,  G06K9/6282

Abstract: Systems and methods directed to generating a predicted quality metric are provided. Telemetry data may be received from a from a first group of devices executing first software. A quality metric for the first software may be generated based on the first telemetry data. Telemetry data from a second group of devices may be received, where the second group of devices is different from the first group of devices. Covariates impacting the quality metric based on features included in the first telemetry data and the second telemetry data may be identified, and a coarsened exact matching process may be performed utilizing the identified covariates to generate a predicted quality metric for the first software based on the second group of devices.

公开(公告)号：WO2022032021A1

公开(公告)日：2022-02-10

申请号：PCT/US2021/044833

申请日：2021-08-05

Applicant: NVIDIA CORPORATION

Inventor： LARSON, Alan Daniel ,  TODUR, Bipin Prabhakar ,  MILOVANOVIC, Marko ,  MCAULEY, Alexander Gordon ,  THAYER, Kevin Michael

IPC: G06F11/30 ,  G06F11/34 ,  H04L12/26 ,  G06F11/3006 ,  G06F11/3409 ,  G06F11/3452 ,  G06F11/3495 ,  G06F17/18 ,  G06F2201/865 ,  G06F2201/875 ,  H04L41/16 ,  H04L41/5009 ,  H04L43/0817 ,  H04L43/0894 ,  H04L67/02 ,  H04L67/22

Abstract: Apparatuses, systems, and techniques to identify a cause of a performance regression in a web-based service. In at least one embodiment, a cause of a performance regression is identified by comparing performance metrics associated with a first group of user interactions with a web-based service to performance metrics associated with a second group of user interactions with the web-based service.

公开(公告)号：WO2021133482A1

公开(公告)日：2021-07-01

申请号：PCT/US2020/060816

申请日：2020-11-17

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： SHMOUELY, Meir ,  SHAH, Rahul ,  FRANK, Alexander

IPC: G06F11/34 ,  G06F11/30 ,  G06F9/455 ,  G06F11/3006 ,  G06F11/3409 ,  G06F11/3428 ,  G06F11/3452 ,  G06F11/3457 ,  G06F11/3664 ,  G06F11/3688 ,  G06F11/3692 ,  G06F8/65 ,  G06N7/005 ,  H04L41/082 ,  H04L41/147 ,  H04L43/16 ,  H04L43/50 ,  H04L67/10 ,  H04L67/34

Abstract: A method for validation and prediction of cloud readiness is described. Method includes identifying a sample of components from a cloud infrastructure, wherein an update is applied to the sample to generate a treated sample and the treated sample is of a statistically sufficient scale and a relevant cloud-level diversity and identifying a control sample of components from the cloud infrastructure, wherein the control sample is statistically comparable to the treated sample. The method also includes executing a set of workloads on the treated sample and the control sample. Further, the method includes predicting an impact of the update on a user experience based on a comparison of telemetry captured during execution of the set of workloads on the treated sample and the control sample.

公开(公告)号：WO2022271290A1

公开(公告)日：2022-12-29

申请号：PCT/US2022/029082

申请日：2022-05-13

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： XUE, Xinjian ,  PAN, Bin ,  HARIBABU, Naveen Duddi ,  AHLUWALIA, Prashant Singh ,  GAO, Ryan Wang ,  LIN, Jong-Chin ,  VEGA ROMERO, Lea ,  RAMASUBRAMANIAM, Balaji ,  SIDDIQUI, Adeel Jamil ,  TUNA, Onur

IPC: G06F8/60 ,  G06F11/07 ,  G06F11/3452 ,  G06F2009/45595 ,  G06F8/65 ,  G06F9/45558

Abstract: Technologies related to predicting whether a requested change (deployment) in a cloud computing environment will fail are described herein. An exposomic feature value is computed based upon a time series of risk values, where the risk values represent risk of failure over several historic time intervals. A probabilistic model computes a likelihood that the requested deployment will fail during implementation of the requested deployment based upon the exposomic feature value and a contextual feature value, and a notification is transmitted to a computing device of a change manager to allow the change manager to take remedial action.

公开(公告)号：WO2021189904A1

公开(公告)日：2021-09-30

申请号：PCT/CN2020/131984

申请日：2020-11-27

Applicant: 平安科技（深圳）有限公司

Inventor： 邓悦 ,  郑立颖 ,  徐亮

IPC: G06F11/34 ,  G06F11/3452

Abstract: 一种数据异常检测方法、装置、电子设备以及计算机可读存储介质，该方法包括：获取包含缺失数据的标准训练数据集及包括变分下限函数的异常检测模型框架；利用所述缺失数据对所述变分下限函数进行调整，得到优化变分下限函数；利用所述标准训练数据集对异常检测模型框架进行训练，得到异常检测模型；利用所述异常检测模型对所述待检测数据集进行检测并得到待检测数据的重构概率；若存在重构概率大于等于重构阈值的目标待检测数据，则确定所述目标待检测数据为异常数据。该方法可以提高关键性能指标（KPI）异常检测的效率和准确率。

公开(公告)号：WO2023273224A1

公开(公告)日：2023-01-05

申请号：PCT/CN2021/140197

申请日：2021-12-21

Applicant: 天翼云科技有限公司

Inventor： 韩金涛 ,  李伟泽 ,  周济 ,  陈都 ,  王喜民 ,  焦利鹏

IPC: G06F11/34 ,  G06F11/3452

Abstract: 一种指标异常数据溯源方法、装置、设备及存储介质，涉及数据处理技术领域。该方法包括：获取多项指标中每两项指标之间的关联关系，多项指标包括指标数据发生异常的目标项指标；获取多项指标中发生异常的两项指标之间的异常发生时序关系，异常发生时序关系根据在指标采集周期内指标数据发生异常的概率获得；获取目标项指标的待溯源异常数据及其异常指示时间；根据待溯源异常数据的异常指示时间获得溯源终止时间；根据关联关系和异常发生时序关系在溯源终止时间之前从多项指标中对待溯源异常数据进行溯源，获得异常根源数据。该方法提高了指标异常数据溯源的准确性。

公开(公告)号：WO2021196943A1

公开(公告)日：2021-10-07

申请号：PCT/CN2021/078449

申请日：2021-03-01

Applicant: OPPO广东移动通信有限公司

Inventor： 柯卫卫

IPC: G06F11/32 ,  G06F11/3037 ,  G06F11/3051 ,  G06F11/3058 ,  G06F11/323 ,  G06F11/3452

Abstract: 本申请实施例公开了一种应用信息的显示方法，能够提高应用管理的效率，该方法包括：在锁屏状态或待机状态下，统计至少一个应用中每个应用的至少一个维度运行数据；基于至少一个维度运行数据，计算出每个应用对应的占用度，占用度表征每个应用对终端上至少一种系统资源的占用程度；根据每个应用对应的占用度，生成与每个应用对应的占用图标，占用图标用于显示每个应用对应的占用度；在锁屏界面的预设显示区域，显示每个应用对应的占用图标。

公开(公告)号：WO2021139253A1

公开(公告)日：2021-07-15

申请号：PCT/CN2020/118528

申请日：2020-09-28

Applicant: 平安科技（深圳）有限公司

Inventor： 邓悦 ,  郑立颖 ,  徐亮

IPC: G06F11/30 ,  G06F11/34 ,  G06F11/3051 ,  G06F11/3452 ,  G06K9/6215 ,  G06K9/6256

Abstract: 本申请涉及人工智能技术领域，应用于智慧城市中，提出的获取KPI异常数据样本的方法、装置、计算机设备和存储介质，其中方法包括：获取预设时间段的KPI数据；将KPI数据进行异常检测得到潜在异常数据点，以潜在异常数据点为终点，按时间顺序回溯截取一指定片段KPI数据作为候选KPI异常数据；对候选KPI异常数据与已知KPI异常数据进行调整，使两者时间长度一致，并将两者的对应数据点进行相似距离计算得到多个规整路径距离；依据各规整路径距离判断候选KPI异常数据是否为KPI异常数据；若是，则将候选KPI异常数据标记成KPI异常数据，以作为训练智能KPI异常识别模型的样本，通过少量已知的KPI异常数据样本即可得到大量的KPI异常数据样本，大大地降低运维成本。

公开(公告)号：WO2023072855A2

公开(公告)日：2023-05-04

申请号：PCT/EP2022/079638

申请日：2022-10-24

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED

Inventor： MANTRIPRAGADA, Kondala Rao Radha Ravi Shankara ,  VARADA, Sri Harsha ,  YAMALAPALLI, Ramesh Naidu ,  KARRI, Venkata Vara Prasad

IPC: G06F11/34 ,  G06F11/07 ,  G06F11/30 ,  G06F11/0793 ,  G06F11/3055 ,  G06F11/3058 ,  G06F11/3438 ,  G06F11/3447 ,  G06F11/3452 ,  G06F9/453 ,  G06Q30/016 ,  H04L67/535

Abstract: A system to provide increased visibility and insight into unexpected usage patterns for electronic devices is described. The utilization analysis system applies a utilization model to device utilization information. The utilization model is also used to determine one or more device usage patterns for the electronic device. These device usage patterns are used to determine an unexpected device utilization where the system responds to the unexpected device utilization with several hardware and software solution proposals to prevent damage to the electronic device and/or enhance the design and development of the electronic device.

公开(公告)号：WO2021189055A2

公开(公告)日：2021-09-23

申请号：PCT/US2021/023525

申请日：2021-03-22

Applicant: QUMULO, INC.

Inventor： BAI, Yuxi ,  ROTHSCHILDS, Thomas Gregory ,  MACLAREN, Jonathan Michael ,  NELSON, Noah Trent ,  FAIRHURST, Kimberly Alice

IPC: G06F16/185 ,  G06F11/0727 ,  G06F11/3058 ,  G06F11/3065 ,  G06F11/3409 ,  G06F11/3447 ,  G06F11/3452 ,  G06F11/3457 ,  G06F16/11 ,  G06F17/18

Abstract: Embodiments are directed to managing file systems over a network. A core specification that defines characteristics of a portion of a file system and parameters may be provided. The characteristics may include one or more storage device characteristics. And, the parameters may include one or more of a cluster size, or a protection level. File system models may be generated based on the core specification and the parameters. Each file system model may correspond to a file system that conforms to a core specification and specific values for the parameters. A simulation engine may be employed to provide simulation results based on the file system models. Deployment models may be generated based on the simulation results. The deployment models may be employed to provision file systems that conform to the file system performance characteristics associated with its corresponding deployment model.