Abstract: The disclosed technology relates identifying causes of an observed outcome. A system is configured to receive an indication of a user experience problem, wherein the user experience problem is associated with observed operations data including an observed outcome. The system generates, based on the observed operations data, a predicted outcome according to a model, determines that the observed outcome is within range of the predicted outcome, and identifies a set of candidate causes of the user experience problem when the observed outcome is within range of the predicted outcome.

Abstract: A failure prediction method of predicting a failure of a component of a robot including a robot arm having the component and a detection section that detects information on vibration characteristics when the robot arm moves, includes generating a failure prediction model for prediction of the failure of the component by machine learning based on the information on vibration characteristics, and predicting the failure of the component based on an estimated value of failure prediction output by the generated failure prediction model when the information on vibration characteristics is input to the generated failure prediction model.

Abstract: A system can include instructions for generating a machine-learning model, including accessing, from a memory device, training data including two or more first commands. The first commands can be manually generated in response to a utilization exceeding a preset threshold and two or more first conditions, including a date and time the utilization exceeded the preset threshold. The training data can also include second commands generated by the machine-learning model in response to the utilization exceeding the preset threshold. The system may train the machine-learning model using a machine-learning algorithm using the training data and the second commands. The system may receive an indication of a utilization exceeding a preset threshold and determine, using the machine-learning model, an action responsive to the utilization. A command can be outputted to execute the action responsive to the utilization.

Abstract: Systems and methods are disclosed herein for monitoring, detecting, and mitigating hardware and software failures. An error detection module monitors the execution of software processes and detects failures of the monitored processes. The error detection module may monitor reboot events and correlate reboot events with failures of the monitored software processes. If a monitored process fails, the error detection module may log the failure and its cause. If the same process has failed numerous times, causing the user device to experience a reboot loop, remedial action may be taken based on the cause of the failure.

Abstract: Various embodiments of the teachings herein include a fault processing method comprising: receiving two historical faults similar to a target fault; searching keywords in a description of the target fault and each historical fault, wherein the keywords are classified into N grades, and for each system component in a grade, the grade comprises at least one keyword for describing the component, wherein N is an integer no less than 2; for each of the N grades, counting a quantity of identical system components represented by the keywords in the text description of each historical fault and the target fault; and comparing a degree of similarity of each historical fault to the target fault according to the quantity of identical system components counted in each grade of the N different grades, wherein a historical fault relating to a larger number of high-grade identical system components has a higher degree of similarity to the target fault.

Abstract: A video playback method executed in a computer system includes measuring a bitrate in transport stream (TS) file units, and selecting the image quality of the next TS file in consideration of the bitrate and the amount of buffer that has already been loaded.

Abstract: A method for detecting and/or localizing keyboard accessibility failures (KAFs) in a web page is disclosed. A web page is rendered in a browser on a display portion of a computing system. A keyboard navigation flow graph based on based on keyboard-based navigation of a user with the web page. A second point-click navigation flow graph based on mouse-based navigation of the user with the web page. One or more KAFs are determined based on a comparison of the first graphical model with the second graphical model.

Abstract: A system configuration suitable for carrying out video recognition by machine learning in a video system including an imaging device and a video processing device is provided. One aspect of the video system according to the present invention includes an imaging device and a video processing device. The imaging device includes an imaging unit configured to generate video data by imaging, a front side NN unit including multiple layers of neural networks from an input layer to a predetermined intermediate hidden layer (hereinafter referred to as “intermediate hidden layer”) that are configured to perform recognition processing of the video data; and an imaging side control unit configured to transmit an output of the intermediate hidden layer of the front side NN unit (hereinafter referred to as “intermediate feature quantity”).

Abstract: System and techniques for computer vision assisted item search are described herein. A composite image, including visual data and depth data, may be obtained. The composite image may be filtered to isolate a clothing article represented in the composite image. A classifier may be applied to the depth data to produce a set of clothing attributes for the clothing article. The clothing attributes may then be provided to a remote device.

Abstract: Various embodiments of the teachings herein include an industrial network behavior analysis method. The method may include: defining a first time window for a target industrial control system, for the target industrial control system to perform a control behavior; respectively determining an execution probability deviation for each control instruction within the first time window and using the execution probability to characterize the ratio of the number of times the corresponding control instruction is executed within a time period to the total number of times the control instruction within the time period; defining a second time window according to the control instruction characterizing a time period when the system performs the corresponding control behavior, and the control behavior is the same as that performed in the first time window.

Abstract: Artificial Intelligence (AI) can rapidly evaluate a faulted message in 5G or 6G, calculate a likelihood that each message element is faulted, and optionally suggest a most probable corrected version for each of the likely faulted message elements. To do so, the AI takes in numerous factors besides the message itself, such as the modulation quality of each message element, the proximity and quality of a nearest demodulation reference, a signal-to-noise ratio of the message element, a measure of current electromagnetic noise during the message element, an expected format or expected codewords based on prior messages or convention, and other factors. The AI model can then provide guidance as to mitigation, such as choosing whether to request a retransmission or attempting to vary the likely faulted message elements. The AI model can be adapted to fixed-site computers or to the more limited computers of a mobile user device.

Abstract: A process for analyzing an incident includes setting up an alert for a high error rate on a particular endpoint. Once the alert is triggered, a set of traces for transactions exhibiting errors on the offending endpoint is queried. All traces for other services/operations that include errors on the offending endpoint are also enumerated. A set of baseline transactions that involve the offending endpoint, but do not result in error may be utilized to determine whether the errors are always present, or are distinctive for certain offending transactions. All traces are ranked based on a statistic. Once the traces have been ranked, they may be traced down to a deepest/most terminal error. A set of transactions that correlate to the terminal error may also be analyzed to determine infrastructure causes.

Abstract: In one embodiment, an issue analysis service obtains telemetry data from a plurality of devices in a network across a plurality of time intervals. The service detects a failure event in which a device in the network is in a failure state. The service clusters the telemetry data obtained prior to the failure event into rounds according to time intervals in which the telemetry data was collected. Each round corresponds to a particular time interval. The service applies a machine learning-based classifier to each one of the rounds of clustered telemetry data to identify one or more common traits appearing in the telemetry data for each round. The service generates a trait change report indicating a change in the one or more common traits appearing in the telemetry data across the rounds leading up to the failure event.

Abstract: A system and method to reduce weight storage bits for a deep-learning network includes a quantizing module and a cluster-number reduction module. The quantizing module quantizes neural weights of each quantization layer of the deep-learning network. The cluster-number reduction module reduces the predetermined number of clusters for a layer having a clustering error that is a minimum of the clustering errors of the plurality of quantization layers. The quantizing module requantizes the layer based on the reduced predetermined number of clusters for the layer and the cluster-number reduction module further determines another layer having a clustering error that is a minimum of the clustering errors of the plurality of quantized layers and reduces the predetermined number of clusters for the another layer until a recognition performance of the deep-learning network has been reduced by a predetermined threshold.

Abstract: An information processing system executes a series of processes. The information processing system includes a computer which manages, among multiple programs for executing the series of processes, a first program included in the information processing system and one or more second programs registered in the information processing system. The computer controls execution of the series of processes including a process executed by the second program and controls a virtual server for executing the second program.

Abstract: Embodiments of the present disclosure relate to a method for providing log information, an electronic device, and a computer program product.

Abstract: Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. At the sensor node, an indication is received to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment. After training is initiated, the sensor node automatically trains a model that resides on the sensor to detect anomalies in the environment, and such training is based on the sensor data. After the model is trained, the model to detect anomalies in the environment is executed by the sensor node.

Abstract: Storage management is performed. For example, a computing device may determine that a fault belongs to one of a plurality of predefined fault categories based on description information of the fault of a storage system. Then, the computing device may determine at least one fault cause associated with the fault category at a first level of a hierarchical structure of predetermined fault causes. Further, the computing device may determine a first fault cause that causes the fault among the at least one fault cause. After that, the computing device may determine a target fault cause at the deepest level that causes the fault based on the first fault cause. As a result, the root cause of a fault of a storage system may be accurately and efficiently determined, thereby providing the possibility of fundamentally eliminating the fault.

Abstract: Embodiments include a system, method, and a computer program product for notifying a technician when a repair task the technician is addressing may be negatively impacted by a nearby fault and/or if the technician is qualified to repair a nearby fault. The technician is qualified if the technician has the necessary skills, parts (e.g., materials), and/or equipment (test equipment) required to repair the nearby fault. In addition, embodiments include receiving and responding to queries from a technician to: determine whether any of the repair tasks associated with the technician's assigned tickets are futile tasks based on newly received faults or pending tickets; and determine whether the querying technician is qualified to address (e.g., repair) any newly received faults or pending tickets.

Abstract: Techniques for processing a request may include: providing tasks to a state machine framework, wherein the tasks perform processing of a workflow for servicing the request; generating, by the state machine framework, a state machine for processing the request, wherein the state machine includes states associated with the tasks, wherein generating the state machine may include automatically determining a first state transition of the state machine between a first and a second of the states; receiving the request; and responsive to receiving the request, performing first processing using the state machine to service the request. The framework may automatically generate triggers that drive the state machine to determine subsequent states in accordance with defined state transitions. State machine internal state information may be persistently stored and used in restoring the state machine to one of its states in connection processing of the command.

Abstract: Systems and methods are described identify a database metric value associated with a database instance storing a dataset associated with a user system. A database issue is detected in view of a determination that the database metric value satisfies a condition. In response to satisfaction of the condition, a set of user action metrics associated with the user system is collected from one or more data monitoring systems. At least one notification communication is generated including at least a portion of the set of user action metrics and information identifying the database issue. The at least one notification communication is transmitted to a remediation execution system configured to execute, using the at least a portion of the set of user action metrics and information identifying the database issue, a remedial action in response to the database issue.

Abstract: A security manager configured to generate a plurality of learned security policies and provide at least one learned security policy and a security agent to a client machine for enforcement of the at least one learned security policy by the security agent on the client machine. The security manager configured to receive alerts from the security agent indicating anomalous behavior on the client machine.

Abstract: An information processing apparatus includes a processor configured to execute a reset process for resetting a watchdog timer, execute a recovery process of the information processing apparatus, in a case where the watchdog timer is not able to be reset within a time limit, and sets the time limit to a longer time, in a case where an apparatus load which is at least one of a current processing load per unit time of the information processing apparatus or a processing amount of a processing request which is input to the information processing apparatus is large, as compared to a case where the apparatus load is small.

Abstract: Systems, methods, and computer-readable media for fault code aggregation across application-centric dimensions. In an example embodiment, a system obtains respective fault codes corresponding to one or more network devices in a network and maps the one or more network devices and/or the respective fault codes to respective logical policy entities defined in a logical policy model of the network, to yield fault code mappings. The system aggregates the one or more of the fault code mappings along respective logical policy dimensions in the network to yield an aggregation of fault codes across respective logical policy dimensions and, based on the aggregation, presents, for each of the respective logical policy dimensions, one or more hardware-level errors along the respective logical policy dimension.

Abstract: Computer implemented method for training a software infrastructure based on machine learning techniques and intended for analysis of data obtained from a three-dimensional tomographic inspection of objects of a predetermined type, such as logs, with the aim of determining information about internal characteristics of interest of the self-same objects, wherein, once a training set comprising a plurality of objects of the same predetermined type has been selected, for each object the software infrastructure is supplied with training input data and corresponding training output data, which are processed by the software infrastructure for setting internal processing parameters of the software infrastructure which correlate the training input data with the training output data; where the training input data comprise data obtained from a three-dimensional tomographic inspection of the object, and the training output data comprise information about internal characteristics of interest assessed at internal points of

Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

Abstract: An online system optimizes for longer attribution window conversions with an additive decomposition model by predicting the probability that a predefined action happens given an impression/click. The online system receives a content item from a content provider for display to a target user, and predicts a probability that a target user will convert given an interaction with the content item by the target user. The online system computes, by a first trained model, a short-term conversion probability of a conversion event happening within a first conversion window after the interaction. The online system computes, by a second trained model, a long-term conversion probability of the a conversion event happening within a second conversion window after the interaction, the second conversion window being longer than the first conversion window. The online system computes the conversion probability given the interaction based on the short-term conversion probability and the long-term conversion probability.

Abstract: A neural network system includes a primary input layer configured to acquire data in both a learning mode and an operation mode, an auxiliary input layer configured to acquire data solely in the learning mode, a first partial network configured to carry out learning using both an output of the primary input layer and an output of the auxiliary input layer and to subsequently carry out learning solely using the output of the primary input layer so as to produce a same calculation result as a calculation result produced using both the output of the primary input layer and the output of the auxiliary input layer, and a second partial network configured to carry out calculations in the learning mode and the operation mode upon receiving an output of the first partial network.

Abstract: Remote on-demand site link testing is provided. A site link tester (SLT) system includes an SLT connected to a customer's VoIP phone system. The SLT is configured to communicate with a front end client application operating remotely on a user's computing device. The packet-capture application receives instructions from the client application to perform a packet capture in association with the SLT's network interface and/or to operate as an emulated VoIP endpoint and conduct a test call (e.g., to confirm the customer's VoIP system's compliance with 911-associated legislation or to troubleshoot a VoIP issue). Results of the packet capture may be sent to the client application and analyzed for remotely diagnosing and troubleshooting VoIP-related problems. Using the SLT system, the technician is enabled to perform 911-associated legislation compliance and diagnose VoIP issues on-demand from a remote location, which can reduce or eliminate the need for a technician to be on-site.

Abstract: A device may receive information associated with media content that is capable of being provided by a first content delivery network and a second content delivery network. The first content delivery network may include a first host device and a second host device. The device may determine scores associated with the first content delivery network and the second content delivery network. The device may provide, based on the scores, information regarding the first content delivery to a user device to cause the user device to request the media content from the first content delivery network. The device may determine scores associated with the first host device and the second host device. The device may provide information regarding the first host device to a network device to cause the network device to route requests for the media content to the first host device.

Abstract: An issue tracking system configured to determine similarity between issue content in an issue request issue content in a previously submitted issue record. Based on the similarity, the issue tracking system may determine a likelihood that a given issue is related to at least one additional issue. In response to a determination that likelihood exceeds a threshold, data can be extracted from the related issue to provide the user with a suggested supplemental issue request to be submitted to the issue tracking system.

Abstract: A vehicle includes a data communication network, a serial data bus, and a plurality of electronic nodes in signal communication with the serial data bus. The vehicle further includes a node identification system configured to store a several different diagnostic tests, along with expected operating data corresponding to a given diagnostic test. The node identification system sorts the plurality of nodes into individual node groups in response to performing one or more diagnostic tests among the different available diagnostic tests.

Abstract: Methods, systems, and devices for analyzing vibration data to determine and mitigate an occurrence of an anomaly at an industrial asset. A device may obtain and preprocess vibration data, which may include grouping the vibration data according to respective time intervals, and the device may filter the grouped data to obtain the most recent measurement readings. The device may use an anomaly detection algorithm to detect outliers in the datasets for each group of vibration data and compare an amplitude of the outliers to a threshold for the respective group. The device may determine that the vibration data includes an anomaly based on quantities of outliers in first and second subsets of the vibration data that are within a detection window. The device may generate a report including an indication of the anomaly and transmit the report to an operator or engineer for the facility.

Abstract: Aspects of the subject disclosure may include, for example, a method in which a processing system collects information associated with trouble tickets each including a problem abstract and a log text. The method includes analyzing the log text to obtain a problem resolution for that ticket; defining ticket clusters according to the problem abstracts, and labeling the clusters. The processing system creates a library of the labeled clusters, each entry including a cluster label, a problem abstract for that cluster, and a resolution summary for that problem abstract, indicating a mapping of the problem abstract to the resolution summary for that cluster. The method includes training, based on the mapping, machine-learning applications for a predicted resolution summary for each cluster and for classifying a new ticket. The method includes assigning the new ticket to a cluster according to the classifying. Other embodiments are disclosed.

Abstract: An image of an object is received into an augmented reality (AR) device. Information is received for identifying the object or a component associated with the object. A database is accessed to retrieve data relating to the object or the component associated with the object, and a heat map is created as a function of the data relating to the object or the component associated with the object. The heat map is displayed on a computer display device.

Abstract: Disclosed here is a system to automatically predict and reduce hardware related outages. The system can obtain a performance indicator associated with a wireless telecommunication network including a system performance indicator or an application log, along with a machine learning model trained to predict and resolve a hardware error based on the performance indicator. The machine learning model can detect an anomaly associated with the performance indicator by detecting an infrequent occurrence in the performance indicator. The machine learning model can determine whether the anomaly is similar to a prior anomaly indicating a prior hardware error. Upon determining that the anomaly is similar to the prior hardware error, the machine learning model can predict an occurrence of the hardware error.

Abstract: Upon receiving a corrupted message in 5G or 6G, a receiver generally rejects the message or ignores it entirely, because determining which message elements are faulted is difficult and complex. AI-based procedures are provided for localizing faults in specific message elements, and for determining the corrected values when possible. AI inputs may include the amplitude or phase modulation quality of each message element, the measured SNR of each message element, the modulation quality of a preceding demodulation reference, and current backgrounds, among other factors. After training (adjusting according to measured network data), the AI model may then determine the most likely faulted message elements, and may also direct the search for the most likely corrected values. By recovering the original corrected message without an unnecessary retransmission, the system can save time, reduce transmission energy, and avoid generating backgrounds. Many additional aspects are disclosed.

Abstract: The example embodiments are directed to a system and method that applies knowledge developed by a subject matter expert with respect to a physical asset. In one example, the method includes receiving knowledge and issue resolution information developed of subject matter experts in association with historical issues for an asset, generating a plurality of data clusters for the asset based on the knowledge, wherein each historical issue of the asset is mapped to a cluster and includes a plurality of resolutions for the issue, receiving a new issue and new issue information, and processing the new issue by extracting keywords from the new issue information and assigning the new issue to a data cluster from among the plurality of data clusters based on the extracted keywords, and outputting, to a display, a cause of the new issue and potential solutions for the new issue.

Abstract: Techniques described herein relate to a method for performing testing operations for information handling systems.

Abstract: Some embodiments of the invention provide a method for defining code-based policies. The method generates a policy-builder first view of a policy for display in a graphical user interface (GUI) by processing a syntax tree that is generated from a code second view of the policy. The method receives, through the policy-builder first view, a modification to a portion of the policy. To reflect the modification, the method updates a portion of the syntax tree that corresponds to the portion of the policy that is affected by the modification. Based on the updating of the syntax tree, the method updates the code second view by modifying a portion of the code second view that corresponds to the updated portion of the syntax tree.

Abstract: Techniques perform storage management. In accordance with such techniques, in response to determining that there is an abnormal process in a process group of an application, and a first size of storage space occupied by the abnormal process exceeds a first threshold, an abnormal process is terminated. A second size of storage space occupied by other processes than the abnormal process in the process group after the abnormal process is terminated is determined. In response to the second size exceeding a second threshold, at least one process in the process group to reduce the second size is terminated, where the at least one process is different from the abnormal process.

Abstract: An automated method for determining a complexity of a task. The method includes extracting data from the plurality of historical support tickets to generate training data. The method trains a complexity model to predict a complexity value of a task associated with a support ticket using the training data. The method predicts, using the complexity model, the complexity value of a new task associated with a new support ticket.

Abstract: A model generation apparatus (2000) acquires component failure data in which a usage status is associated with a failure record of a component. The model generation apparatus (2000) generates, for each of a plurality of component groups, a prediction model for predicting the number of failures of each component included in the component group by using the component failure data relating to the component belonging to the component group. The prediction model computes a prediction value of the total number of failures of the components belonging to a corresponding component group from the usage status, and computes a prediction value of the number of failures of each component belonging to the component group from the computed prediction value of the total number of failures.

Abstract: An anomaly location identification device includes a determination unit configured to determine presence or absence of an anomaly by inputting part or all of information items output from a plurality of devices into an anomaly detection algorithm; a calculation unit configured to calculate, in response to a determination made by the determination unit that an anomaly is present, with respect to one of the information items, an index indicating a degree of contribution to the anomaly; and an identification unit configured to perform calculation by an analysis algorithm using a causal model receiving the index as input, to identify an anomalous device, to improve the precision and calculation speed related to identification of an anomaly location.

Abstract: An embodiment includes a method for use in managing a system comprising one or more computers, each computer comprising at least one hardware processor coupled to at least one memory. The method comprises a computer-implemented manager: detecting that the system is in an unhealthy state; determining a set of one or more possible actions to remedy the unhealthy state of the system; selecting at least one action of the set of one or more possible actions; and constructing a service request implementing the selected at least one action; wherein at least one of the detecting, determining, selecting, and constructing is based at least in part on applying a reinforcement learning algorithm.

Abstract: A system and method for connected vehicle cybersecurity. The method includes creating a normal behavior model based on a first set of data, the first set of data including at least one first event with respect to at least one connected vehicle, wherein the first set of data is collected from a plurality of data sources; detecting an anomaly based on the normal behavior model and a second set of data, the second set of data including a second event with respect to the at least one connected vehicle, wherein each of the first set of data and the second set of data includes vehicle data related to operation of the at least one connected vehicle, wherein each event represents a communication with the at least one connected vehicle; determining, based on the detected anomaly, at least one mitigation action; and causing implementation of the at least one mitigation action.

Abstract: Disclosed are various embodiments for managing the state of client devices using device-driven management workflows. A computing device can be evaluated to determine the current state of the computing device. Then, the current state of the computing device is compared to an expected state of the computing device. The expected state of the computing device may be based at least in part on a result of execution of at least one device-driven management workflow by the computing device. In response to a determination that the current state of the computing device fails to match the expected state of the computing device, the device-driven management workflow can be executed to resolve the discrepancy between the expected state and the current state.

Abstract: An operation data collection system comprises circuitry configured to: acquire, from an industrial device, configuration information on a connection destination device connected to the industrial device; execute a setting for collecting operation data on the connection destination device based on the configuration information; and collect the operation data from the industrial device based on the setting.

Abstract: A system and method for connected vehicle cybersecurity. The method includes creating a normal behavior model based on a first set of data, the first set of data including at least one first event with respect to at least one connected vehicle, wherein the first set of data is collected from a plurality of data sources; detecting an anomaly based on the normal behavior model and a second set of data, the second set of data including a second event with respect to the at least one connected vehicle, wherein each of the first set of data and the second set of data includes vehicle data related to operation of the at least one connected vehicle, wherein each event represents a communication with the at least one connected vehicle; determining, based on the detected anomaly, at least one mitigation action; and causing implementation of the at least one mitigation action.

Abstract: In an exemplary embodiment, computer circuitry determines term characterization values for terms in computer performance logs and generates vectors that indicate the term characterization values. The computer circuitry determines vector similarity scores for these vectors. The computer circuitry aggregates the computer performance logs into aggregated logs based on the vector similarity scores. The computer circuitry selects rare logs from these aggregated logs and obtains computer performance anomaly labels for the rare logs. The computer circuitry matches new computer performance logs with the rare logs to detect the labeled computer performance anomalies.