Abstract: Automated order management techniques for order problem learning and mitigation in an order processing system are disclosed. For example, a method comprises obtaining historical order data associated with an order processing system. The method applies a reinforcement learning-based algorithm to the obtained historical order data to generate a state-based data structure that reflects successes and failures of actions associated with previous orders processed by the order processing system. The state-based data structure is utilized to identify one or more issues in a given pending order, and recommend one or more mitigating actions to remedy the one or more issues in the given pending order.

Abstract: A method for managing a client environment includes monitoring, by an upgrade management agent, the client environment for an application abstention by a plurality of client devices of the client environment, in response to the monitoring, obtaining device configuration information corresponding to each of the plurality of client devices, performing a text pre-processing on the device configuration information to obtain pre-processed information, applying a relational analysis to the pre-processed information to obtain a normalized context reference for application abstention corresponding to the plurality of client devices, and performing a clustering algorithm on the normalized context reference to generate a processed client intent dataset.

Abstract: A method for managing a client environment includes obtaining a notification for an application abstention by a client device, in response to the notification, performing an intent analysis on the client device using a processed client intent dataset to determine a set of reasons for the application abstention, comparing the set of reasons to an upgrade coverage dataset, identifying, based on the comparing, a set of solutions corresponding to the set of reasons, generating, based on the comparing, a specialized upgrade notification based on the set of solutions, and issuing the specialized upgrade notification to the client device.

Abstract: A method and system for version history based upgrade testing across simulated information technology (IT) environments. At least with respect to computing, an upgrade may entail the replacement of a product - in the form of hardware, software, and/or firmware - with a newer or better version, which may serve to bring the product up to date, improve the characteristic(s) of the product, and/or resolve any issue(s) inflicting the product. Further, through the process of upgrade testing, an upgrade may be assessed to determine its impact on an operability of varying environments following application of the upgrade thereon. The disclosed method and system, accordingly, propose a framework directed to conducting upgrade tests within simulated IT environments - each reflective of different computing resources and upgrade histories - where results of the simulations may be examined to ascertain which environment configurations (if any) may cause the tested upgrade to fail.

Abstract: A method for managing a client environment includes obtaining, by a remediation orchestrator, a remediation request associated with a failed application upgrade on an emulation of a client device; in response to the remediation request: obtaining a remediation policy associated with the application upgrade; obtaining application upgrade information associated with the application upgrade; identifying remediation steps to service the remediation request using the application upgrade information and the remediation policy; and initiating performance of the application upgrade and the remediation steps on the client device.

Abstract: A method for managing a client environment includes obtaining, by a predictor, a future state prediction request associated with an application upgrade on an emulation of a client device, wherein the application upgrade failed; in response to the future state prediction request: obtaining live data associated with the application upgrade; performing natural language processing on the live data to obtain processed live data; applying a future state prediction model to the processed live data to generate a future state prediction; and initiating the remediation of the application upgrade based on the future state prediction.

Abstract: A method for managing a client environment includes obtaining, by a state processor, a state prediction request associated with an application upgrade on an emulation of a client device; in response to the state prediction request: obtaining live data associated with the application upgrade; performing natural language processing on the live data to obtain processed live data; applying a state prediction model to the processed live data to generate a state prediction; making a first determination that the state prediction indicates that the application upgrade was not successful; and in response to the first determination: making a second determination that the state prediction indicates that the application upgrade is fixable; and in response to the second determination: initiating the remediation of the application upgrade.

Abstract: A method and system for machine learning based predictions of upgrade testing outcomes for information technology (IT) environments. At least with respect to computing, an upgrade may entail the replacement of a product—in the form of hardware, software, and/or firmware—with a newer or better version, which may serve to bring the product up to date, improve the characteristic(s) of the product, and/or resolve any issue(s) inflicting the product. Further, through the process of upgrade testing, an upgrade may be assessed to determine its impact on an operability of varying environments following application of the upgrade thereon. Moreover, each environment may reflect a different history of product upgrades that had been applied thereon prior to the upgrade being tested. The disclosed method and system, accordingly, propose a framework directed to ascertaining the post-upgrade outcomes of actual IT environments using machine learning applied to post-upgrade outcomes of simulated IT environments.

Abstract: A method and system for predicting post-upgrade outcomes in information technology environments through proactive upgrade issue testing. At least with respect to computing, an upgrade may entail the replacement of a product—in the form of hardware, software, and/or firmware—with a newer or better version, which may serve to bring the product up to date, improve the characteristic(s) of the product, and/or resolve any issue(s) inflicting the product. Further, the process of upgrading a product in view of an issue therein is often reactive—that is, it is often required that a customer experiences and reports an issue for a product to a vendor prior to the issuance of an upgrade to the customer that addresses the issue for the product by the vendor. Presently, what is lacking is a mechanism through which product upgrades may be presented to customers proactively in order to minimize product failure and/or downtime.

Abstract: An apparatus comprises a processing device configured to receive system state information corresponding to one or more devices, to predict a usage frequency of the system state information using one or more machine learning models, and to determine, based at least in part on the usage frequency, a compression level for storage of the system state information. The compression level is applied to the system state information to generate at least one compressed file for transmission to a database.

Abstract: An apparatus comprises a processing device configured to receive a request to boot a given computing device to a primary environment and, responsive to receiving the request, to obtain first inventory information for components of the given computing device utilizing a preinstallation environment of the given computing device. The processing device is also configured to analyze the first inventory information and second inventory information to determine whether there any changes in the components of the given computing device prior to booting the given computing device to the primary environment, the second inventory information being previously stored in a support environment of the given computing device. The processing device is further configured to generate notifications based at least in part on determining that there are one or more changes in the components of the given computing device, and to provide the notifications at a user interface of the given computing device.

Abstract: A method includes receiving data collected from a plurality of managed devices in a plurality of data collections. The data collections are performed using a plurality of collection protocols. A trigger that generated each of given ones of the data collections is determined. The method further includes identifying a collection protocol of the plurality of collection protocols used for each of the given ones of the data collections, and determining one or more attributes of a plurality of attributes of the plurality of managed devices that have been collected using given ones of the collection protocols. A mapping is generated between the triggers, the collection protocols and the attributes using one or more machine learning algorithms. The generated mapping is used to predict one or more collection protocols of the plurality of collection protocols to use to collect data from one or more of the managed devices.

Abstract: A method for managing a client environment includes obtaining, by an issue analyzing engine, a notification for an issue based on an application upgrade on a client device of the client environment, in response to the notification: applying an issue analyzing model to device configuration information associated with a client device to obtain a solution set, providing the solution set to client environment, obtaining a result from the client environment associated with the issue and the solution set, and updating the issue analyzing model based on the result to obtain an updated issue analyzing model.

Abstract: A method for managing a client environment includes obtaining, by a client environment watcher of a production host environment, a set of actions performed by the client environment operatively connected to the production host environment, in response to obtaining the set of actions: performing an action filtering on the set of actions to obtain a set of filtered actions, wherein the set of filtered actions is associated with an attempt to resolve an issue with performing an application upgrade on the client environment, determining, using the set of filtered actions, a client-applied action set, and initiating an update to an issue analyzer model to obtain an updated issue analyzer model.

Abstract: A disclosed method and system for allocating bandwidth among a plurality of virtual network ports assigned to a plurality of virtual machines accesses assignment information indicating which virtual network ports are assigned to which virtual machines. A network bandwidth manager (NBM) receives network utilization information indicating the network utilization of each virtual network port/The NBM further receives virtual machine priority information indicative of a derived priority for each of the plurality of virtual machines. The NBM configures bandwidth parameters for each of the virtual network ports based on the assignment information, network utilization information, and the virtual machine priority information.

Abstract: An apparatus comprises at least one processing device configured to detect one or more issues associated with execution of a first version of a microservice in one or more computing environments, to determine whether any of the detected issues correspond to one or more triggers of one or more predefined patterns in a knowledge base, and, responsive to determining that at least one of the detected issues corresponds to at least one of the triggers of at least one of the predefined patterns in the knowledge base, to utilize code modification data structures specified in the at least one predefined pattern to modify source code of the microservice. The processing device is further configured to generate at least one additional version of the microservice utilizing the modified source code, and to deploy the at least one additional version of the microservice in at least one of the computing environments.

Abstract: A method comprises receiving a notification of an issue with at least one component of a plurality of components in a computing environment. One or more machine learning algorithms are used to determine one or more components of the plurality of components impacted by the issue with the at least one component. The method further comprises collecting operational data for the at least one component and the one or more impacted components.

Abstract: Predictive techniques for issue impact management in a data center or other computing environment comprising a plurality of devices are disclosed. For example, a method comprises predicting an impact to a data center comprising a plurality of devices based on an issue associated with a given device of the plurality of devices within the data center, wherein the prediction utilizes at least one machine learning model. The method then causes one or more actions to be taken based on a result of the prediction.

Abstract: A method for managing a client environment includes obtaining, by a device emulation orchestration engine in an emulation system, an upgrade estimation time request associated with an application upgrade, in response to the upgrade estimation time request: performing a device emulation container analysis to determine a client device that requires the application upgrade, wherein the client device executes in the client environment, initiating an upgrade emulation using a device emulation container corresponding to the client device, obtaining, from a device emulation agent executing in the device emulation container, an upgrade estimation, and providing the upgrade estimation to the application upgrade monitoring agent.

Abstract: In general, embodiments relate to a method for managing a technical support session, comprising: generating a question path graph (QPG) based on a plurality of question sequences associated with technical support sessions, and displaying at least a portion of the QPG to a technical support person (TSP) during a technical support session.