Abstract: Technologies are disclosed herein for cross-correlating metrics for anomaly root cause detection. Primary and secondary metrics associated with an anomaly are cross-correlated by first using the derivative of an interpolant of data points of the primary metric to identify a time window for analysis. Impact scores for the secondary metrics can be then be generated by computing the standard deviation of a derivative of data points of the secondary metrics during the identified time window. The impact scores can be utilized to collect data relating to the secondary metrics most likely to have caused the anomaly. Remedial action can then be taken based upon the collected data in order to address the root cause of the anomaly.

Abstract: A method comprising the steps of responding to expiration of a timer, transmitting a signal from the timer to circuitry; responsive to receiving the signal, retrieving by the circuitry (i) first values stored in an analog array, and (ii) second values stored in a digital non-volatile memory; performing, by the circuitry, operations comprising a comparison of the first values and the second values; analyzing, by the circuitry, results of the comparison to determine whether an error is greater than or equal to a predefined threshold; responsive to determining the error is greater than or equal to the predefined threshold, initiating, by the circuitry, operations to reprogram the analog array with the second value is described.

Abstract: Described systems and techniques determine causal associations between events that occur within an information technology landscape. Individual situations that are likely to represent active occurrences requiring a response may be identified as causal event clusters, without requiring manual tuning to determine cluster boundaries. Consequently, it is possible to identify root causes, analyze effects, predict future events, and prevent undesired outcomes, even in complicated, dispersed, interconnected systems.

Abstract: Certain aspects of the present disclosure provide techniques for handling crash events in a software application using application-agnostic machine learning models. An example method generally includes receiving a data set of crash reports from a software application for analysis. Using a first neural network, a representation of each respective crash report in the data set is generated. The data set of crash reports and a mapping between functions in the software application and a multidimensional space are input into the first neural network. Each respective crash report in the data set is classified using a second neural network and the representation of each crash report in the data set. One or more actions are taken with respect to the software application based on the classifying each respective crash report in the data set.

Abstract: As described herein, a system, method, and computer program are provided for intelligent self-healing optimization for fallout reduction. A set of self-healing rules are stored that are configured to provide resolutions to failures detected in a computer process. Data associated with use of the self-healing rules is collected. The data is processed using a machine learning model to generate one or more recommendations for optimizing the set of self-healing rules. The one or more recommendations are output.

Abstract: A computer-implemented method to identify and remediate a failing sensor. The method includes identifying a set of sensors in an Internet of Things (IoT) system including a first sensor, where the IoT system is configured to perform at least one action, the IoT system includes one or more IoT devices, each sensor is correlated to one IoT device of the one or more IoT devices, and each sensor sends an output data feed to the IoT system including a first data feed for the first sensor. The method further includes predicting, by a generative adversarial network (GAN), an expected output of the first sensor. The method also includes determining that a difference between the expected output and an actual output of the first sensor exceeds a first threshold. The method includes replacing, in response the difference exceeding the first threshold, the first data feed with a first generated data feed.

Abstract: Systems and methods associated with incident prediction using machine learning techniques are disclosed. In one embodiment, an exemplary method may comprise obtaining current raw log data from at least one application log of at least one software application, converting the current raw log data into current tabular log data, applying one or more sampling techniques to the current tabular log data to form current balanced log data, the current balanced log data including incidents of failures, applying one or more machine learning techniques to the current balanced log data to generate an application failure predictive model, and predicting, based on future balanced log data, at least one future failure of the software application using the application failure predictive model.

Abstract: An example method includes receiving incident data for historical incidents of downtime or interrupted service. The incident data includes identification information about one or more first computing applications, devices, or services affected by the downtime or the interrupted service. The incident data further includes timing information relating to the historical incidents and version history information of the one or more first computing applications, devices, or services. The method further includes receiving root cause data indicating a cause of the historical incidents and receiving action data indicating a corrective or preventative action taken or to be taken in response to each of the historical incidents. The method further includes training a machine learning algorithm using the incident, root cause, and action data to create a trained model configured to determine a root cause and a new corrective or preventative action for a new incident.

Abstract: Various methods and systems for tracking incomplete purchases in correlation with application performance, such as application errors or crashes, are provided. In this regard, aspects of the invention facilitate monitoring transaction and application error events and analyzing data associated therewith to identify data indicating an impact of incomplete purchases in relation to an error(s) such that application performance can be improved. In various implementations, application data associated with an application installed on a mobile device is received. The application data is used to determine that an error that occurred in association with the application installed on the mobile device correlates with an incomplete monetary transaction initiated via the application. Based on the error correlating with the incomplete monetary transaction, a transaction attribute associated with the error is determined.

Abstract: Continuous value data redundancy, including: receiving, by a storage system, a dataset; determining, based on a data resiliency metric, an integer redundancy value for the dataset from among a plurality of redundancy values; and generating, based on the integer redundancy value for the dataset, data recovery information for the dataset, wherein the integer redundancy value for the dataset is different from at least one other integer redundancy value for another dataset stored within the storage system.

Abstract: A method for tracing an error of a logic system design includes obtaining an assertion failure of a combinational cone of the logic system design, the combinational cone including a plurality of sub-cones; and obtaining machine learning models of the sub-cones. Each sub-cone represents a sub-circuitry of the logic system design and has one or more input signals and an output signal. The assertion failure indicates an actual signal value of the combinational cone at a current clock cycle being different from an expected output value at the current clock cycle. The method also includes: performing backtracing on the sub-cones according to the assertion failure, the machine learning models of the sub-cones, and dynamic backtracing sensitivities corresponding to the sub-cones, to obtain a backtracing result; and outputting one or more target sub-cones as candidate root causes of the assertion failure according to the backtracing result.

Abstract: Some embodiments of the current disclosure disclose methods and systems for analyzing root causes of an incident disrupting information technology services such as cloud services. In some embodiments, a set of problem review board (PRB) documents including information about said incidents may be parsed using a natural language processing (NLP) neural model to extract structured PRB data from the unstructured investigative information contained in the PRB documents. The structured PRB data may include symptoms of the incident, root causes of the incident, resolutions of the incidents, etc., and a causal knowledge graph causally relating the symptoms, root causes, resolutions of the incidents may be generated.

Abstract: The present disclosure relates to a communication electronic control unit (ECU) provided in a vehicle to be used for exchange of a signal with an external device, the communication ECU including a bus interface configured to exchange signals with a plurality of slave ECUs in the vehicle, a primary processor configured to perform software cloning for at least one of the plurality of slave ECUs, and a secondary processor configured to determine whether to operate, based on whether overload is applied to the primary processor.

Abstract: Methods and systems for managing data processing systems based on indications of anomalous behaviors in logs are disclosed. A data processing system may include and depend on the operation of hardware and/or software components. To manage the operation of the data processing system, a data processing system manager may obtain logs for components of the data processing system that reflect the historical and/or current operation of these components. The logs may be used to identify the operational state of the data processing system, improving the context of the log information. Based on the identified state, inference models may be implemented to predict future infrastructure issues by detecting anomalous behaviors of the data processing system (e.g., behaviors that are unusual for the given state) recorded in the logs. Based on the predictions, the data processing system manager may take action to reduce the likelihood of the data processing system becoming impaired.

Abstract: On-the-fly point-in-time recovery operations are disclosed. During a recovery operation, the PiT being restored can be changed on-the-fly or during the existing recovery operation without restarting the recovery process from the beginning. In one example, this improves recovery time operation (RTO) and prevents aspects of the recovery operation to be avoided when changing to a different PiT.

Abstract: Various systems and methods may be used to implement a software defined industrial system. For example, an orchestrated system of distributed nodes may run an application, including modules implemented on the distributed nodes. The orchestrated system may include an orchestration server, a first node executing a first module, and a second node executing a second module. In response to the second node failing, the second module may be redeployed to a replacement node (e.g., the first node or a different node). The replacement mode may be determined by the first node or another node, for example based on connections to or from the second node.

Abstract: A method including receiving events from different data sources for a service automatically executing in an enterprise system. A first event is enriched by providing the first event with first metadata that associates the first event with a first application used by the service. The first event is assigned to a time slice associated with the first application. A second event is enriched in a similar manner. A correlation graph of nodes and edges is built using the enriched events, with nodes representing the events and edges indicating relationships between the edges. A third event indicating a fault in the first application associated with the first node is received. The source of the error for the third event is identified using the second updated correlation graph and the time slice. The source of error is then mitigated.

Abstract: A system for recordation and retrieval of incident resolution action information is provided. A recordation system processor is provided with a recordation application configured to receive a response action initiation instruction identifying an action taken to resolve an incident on a target system, The processor determines one or more responsible responders each having a responder data processor that displays a responder dashboard. The processor transmits a recordation instruction to the responder data processor of each responsible responder. The recordation instruction includes an instruction to begin recording responder dashboard information. The recordation application is also configured to receive a response action termination instruction and to transmit a recordation termination instruction to the responder data processor of each responsible responder. A data storage unit is configured for receiving, from the responder data processors, real-time responder dashboard information recordings.

Abstract: A data management and storage (DMS) cluster of peer DMS nodes manages migration of an application between a primary compute infrastructure and a secondary compute infrastructure. The secondary compute infrastructure may be a failover environment for the primary compute infrastructure. Primary snapshots of virtual machines of the application in the primary compute infrastructure are generated, and provided to the secondary compute infrastructure. During a failover, the primary snapshots are deployed in the secondary compute infrastructure as virtual machines. Secondary snapshots of the virtual machines are generated, where the secondary snapshots are incremental snapshots of the primary snapshots. In failback, the secondary snapshots are provided to the primary compute infrastructure, where they are combined with the primary snapshots into construct a current state of the application, and the application is deployed in the current state by deploying virtual machines on the primary compute infrastructure.

Abstract: A method to be performed by a processor includes determining whether an application software has called an application programming interface, upon determination that the application software has called the application programming interface, determining whether one or more floating-point errors are recorded in a floating-point status register, and upon determination that one or more floating-point errors are recorded in the floating-point status register, performing a predefined action for each type of floating-point error recorded in the floating-point status register.