Usage profile based recommendations

    公开(公告)号:US10963358B2

    公开(公告)日:2021-03-30

    申请号:US16776885

    申请日:2020-01-30

    摘要: A server may receive a device profile from a computing device. The device profile may identify a usage of at least software applications associated with the computing device. The server may perform a comparison of the device profile with other device profiles associated with other computing devices, determine a similarity index of the device profile with individual ones of the other device profiles, and select a subset of the other device profiles based on the similarity index to create a set of similar device profiles. The server may determine configuration differences between the device profile of the computing device and individual device profiles of the similar device profiles, determine recommendations based on the configuration differences, and send the recommendations to the computing device. Implementing one or more of the recommendations may cause the one or more tasks to execute faster or use less of one or more computing resources.

    Predicting a success rate of deploying a software bundle

    公开(公告)号:US10789057B2

    公开(公告)日:2020-09-29

    申请号:US16036102

    申请日:2018-07-16

    摘要: In some examples, a server may determine a plurality of variables associated with a software package. For example, the plurality of variables may include a size of the software package, a reboot variable associated with the software package indicating whether a reboot is to be performed after installing the software package, and an installation type indicating whether the software package is a first install or an upgrade. The server may execute a machine learning model to determine, based on the plurality of variables, a risk score predicting an installation success rate of the software package. The server may select a deployment strategy from a plurality of deployment strategies based at least in part on the risk score and the plurality of variables. The server may provide the software package to a plurality of computing devices in accordance with the deployment strategy.

    Usage profile based recommendations

    公开(公告)号:US10599538B2

    公开(公告)日:2020-03-24

    申请号:US15994406

    申请日:2018-05-31

    摘要: A server may receive a device profile from a computing device. The device profile may identify a usage of at least software applications associated with the computing device. The server may perform a comparison of the device profile with other device profiles associated with other computing devices, determine a similarity index of the device profile with individual ones of the other device profiles, and select a subset of the other device profiles based on the similarity index to create a set of similar device profiles. The server may determine configuration differences between the device profile of the computing device and individual device profiles of the similar device profiles, determine recommendations based on the configuration differences, and send the recommendations to the computing device. Implementing one or more of the recommendations may cause the one or more tasks to execute faster or use less of one or more computing resources.

    PREDICTING A SUCCESS RATE OF DEPLOYING A SOFTWARE BUNDLE

    公开(公告)号:US20200019393A1

    公开(公告)日:2020-01-16

    申请号:US16036102

    申请日:2018-07-16

    IPC分类号: G06F8/60 G06N99/00

    摘要: In some examples, a server may determine a plurality of variables associated with a software package. For example, the plurality of variables may include a size of the software package, a reboot variable associated with the software package indicating whether a reboot is to be performed after installing the software package, and an installation type indicating whether the software package is a first install or an upgrade. The server may execute a machine learning model to determine, based on the plurality of variables, a risk score predicting an installation success rate of the software package. The server may select a deployment strategy from a plurality of deployment strategies based at least in part on the risk score and the plurality of variables. The server may provide the software package to a plurality of computing devices in accordance with the deployment strategy.

    USAGE PROFILE BASED RECOMMENDATIONS
    5.
    发明申请

    公开(公告)号:US20190370139A1

    公开(公告)日:2019-12-05

    申请号:US15994406

    申请日:2018-05-31

    摘要: A server may receive a device profile from a computing device. The device profile may identify a usage of at least software applications associated with the computing device. The server may perform a comparison of the device profile with other device profiles associated with other computing devices, determine a similarity index of the device profile with individual ones of the other device profiles, and select a subset of the other device profiles based on the similarity index to create a set of similar device profiles. The server may determine configuration differences between the device profile of the computing device and individual device profiles of the similar device profiles, determine recommendations based on the configuration differences, and send the recommendations to the computing device. Implementing one or more of the recommendations may cause the one or more tasks to execute faster or use less of one or more computing resources.

    Determining a stability index associated with a software update

    公开(公告)号:US10732957B2

    公开(公告)日:2020-08-04

    申请号:US16048729

    申请日:2018-07-30

    摘要: In some examples, a server may receive telemetry data from a computing device. The server may determine based at least in part on the telemetry data, (1) a device (e.g., hardware and software) configuration associated with the computing device and (2) one or more events (e.g., an installation log, a memory dump, or the like) associated with installing a software package on the computing device. Based at least in part on the one or more events. the server may determine a stability index associated with the software package and associate the stability index with the device configuration. The stability index may indicate a probability of errors not occurring after the software package is installed. After determining that the stability index satisfies a predetermined threshold, the server may provide the software package and the associated stability index for download to one or more additional computing devices.

    CLASSIFYING TELEMETRY DATA TO IDENTIFY AND REMEDIATE ISSUES

    公开(公告)号:US20200005093A1

    公开(公告)日:2020-01-02

    申请号:US16021171

    申请日:2018-06-28

    IPC分类号: G06K9/62 H04Q9/02 G06F8/61

    摘要: In some examples, a server may receive, from a computing device, data identifying an event that occurred on the computing device. The server may determine a plurality of features associated with the event, determine a distance between individual features of the plurality of features and individual centroids of a plurality of clusters, and determine that a particular distance between a particular feature of the plurality of features and a centroid of a particular cluster of the plurality of clusters is a shorter distance than the distance between other features of the plurality of features and other centroids corresponding to other clusters of the plurality of clusters. The server may determine a classification of the event based on the particular cluster and determine that the classification is a remediable issue. Based on the classification, the server may select and perform a remediation action from a plurality of remediation actions.

    PROVIDING RECOMMENDATION(S) FOR A COMPUTING DEVICE EXECUTING A GAMING APPLICATION

    公开(公告)号:US20190391898A1

    公开(公告)日:2019-12-26

    申请号:US16016970

    申请日:2018-06-25

    摘要: In some examples, a server may receive, from a computing device, a device profile identifying a gaming application and metrics associated with execution of a gaming application. The server may compare the device profile with other device profiles associated with other computing devices, determine a similarity index of the device profile with the other device profiles, and select a subset of the other device profiles based at least in part on the similarity index. The server may determine configuration differences between the device profile of the computing device and individual device profiles of the subset of the other device profiles and send the configuration recommendations to the computing device. The recommendations may include at least one of (1) modifying settings of an operating system of the computing device, (2) modifying settings of the gaming application, (3) changing a hardware component or peripheral device associated with the computing device.

    DETERMINING A STABILITY INDEX ASSOCIATED WITH A SOFTWARE UPDATE

    公开(公告)号:US20200034133A1

    公开(公告)日:2020-01-30

    申请号:US16048729

    申请日:2018-07-30

    IPC分类号: G06F8/65

    摘要: In some examples, a server may receive telemetry data from a computing device. The server may determine based at least in part on the telemetry data, (1) a device (e.g., hardware and software) configuration associated with the computing device and (2) one or more events (e.g., an installation log, a memory dump, or the like) associated with installing a software package on the computing device. Based at least in part on the one or more events. the server may determine a stability index associated with the software package and associate the stability index with the device configuration. The stability index may indicate a probability of errors not occurring after the software package is installed. After determining that the stability index satisfies a predetermined threshold, the server may provide the software package and the associated stability index for download to one or more additional computing devices.

    Classifying telemetry data to identify and remediate issues

    公开(公告)号:US11106948B2

    公开(公告)日:2021-08-31

    申请号:US16021171

    申请日:2018-06-28

    摘要: In some examples, a server may receive, from a computing device, data identifying an event that occurred on the computing device. The server may determine a plurality of features associated with the event, determine a distance between individual features of the plurality of features and individual centroids of a plurality of clusters, and determine that a particular distance between a particular feature of the plurality of features and a centroid of a particular cluster of the plurality of clusters is a shorter distance than the distance between other features of the plurality of features and other centroids corresponding to other clusters of the plurality of clusters. The server may determine a classification of the event based on the particular cluster and determine that the classification is a remediable issue. Based on the classification, the server may select and perform a remediation action from a plurality of remediation actions.