82results about "Detecting faulty hardware using expert systems" patented technology

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be used to generate citations for the outcome predictions to provide references to previous cases (e.g., historic data) from which the outcome predictions are based.

A method, system, and computer-readable storage media for anomaly detection on an Operational Technology (OT) network are disclosed. Input packets are obtained. Each of the input packets may represent a history of baseline packets. Based on the input packets, a foundation model is trained to generate corresponding recreated packets. The trained foundation model is optimized by minimizing a difference between the input packets and the corresponding generated recreated packets. Further, an incoming data packet is received on the OT network. Based upon the incoming data packet, a recreated data packet is generated using the trained and optimized foundation model. A difference between the recreated data packet and the incoming data packet is calculated. If the difference is above a predetermined threshold, a security protocol is triggered to a security system.

A method performed by a virtual environment-based vehicle ECU verification system comprises the steps of: receiving a control command from a user interface; reading, from a cooperative simulation middleware unit, at least one FMU model corresponding to the control command; performing a simulation on the basis of the read FMU model; transmitting a simulation operation signal, generated by performing the simulation, to an ECU interface via a virtual ECU wrapper (vECU wrapper) on the cooperative simulation middleware unit; and transmitting, via the ECU interface, the simulation operation signal to a virtual ECU corresponding to the simulation, so as to perform testing on the virtual ECU.

A method, computer program product, and computing system for generating a respective diagnostic history associated with each physical storage device of a plurality of physical storage devices. A subset of diagnostic history associated with a class of failing physical storage devices is identified from the diagnostic history associated with each physical storage device. The subset of diagnostic history associated with the class of failing physical storage devices is enhanced. A physical storage device failure event for a target physical storage device is forecast using a machine learning model and the enhanced subset of diagnostic history associated with the class of failing physical storage devices.

A method and device for predicting errors in a computing system are disclosed. The error prediction method includes: receiving log data generated by the computing system during operation of the computing system; tokenizing the log data into tokens; inputting the tokens to a discriminator model which generates scores of the respective tokens, each score corresponding to a probability that the corresponding token is an anomaly token; determining an anomaly score based on the scores; and determining a likelihood of future occurrence of an error in the computing system based on the anomaly score.

A method of operating a server is provided that includes providing, with the server, one or more services relating to network access control and management of a network, predicting a network configuration failure associated with the network with a failure prediction model, and generating a network configuration recommendation based on the predicted network configuration failure to avoid the predicted network configuration failure. The failure prediction model can be a machine-learning based network configuration failure prediction model that is trained on past network configuration failure events. Operated in this way, erroneous network configuration issues can be automatically identified and addressed in a timely fashion.

An example system includes a first memory that includes primary storage; a second memory that includes secondary storage; and a control system for predicting paths through a test program that will be taken during a planned execution of the test program, and for causing test data associated with the test program to be stored in the first memory or the second memory based on the paths predicted.

Components used during a video conference are managed during the video conference. A processing system associated with the video conference executes diagnostic software to test functionality of one or more components arranged in a physical space while the video conference is in progress, without interfering with operation of the video conference. Based on execution of the diagnostic software, the processing system determines a configuration of a component and compares the configuration to at least one parameter associated with the component to detect that the component is in a limited condition for use during the video conference. In response to detecting the limited condition, the processing system initiates, while the video conference is in progress, a response configured to change the limited condition of the component so as to increase functionality of the component during the video conference.

A bridging component is implemented as a computing unit that includes a first communications interface, a second communications interface, and a processor. The computing unit can receive, from one or more external systems that are communicatively coupled to the computing unit, test programs for testing DUTs that are communicatively coupled to the computing unit. The computing unit can also transmit commands for executing the test programs to the DUTs, can receive test results from the DUTs, and can transmit test results to the appropriate external system(s). Furthermore, the computing unit can determine, for each set of one or more of the DUTs, a respective type of DUTs in the set, associate a respective test program with the set, and issue commands for executing the respective test program to the DUT(s) in the set using an operating system that is compatible with the respective type of DUT(s) in the set.

The present application relates to memory subsystem analysis based on threshold distributions. A system is disclosed, comprising: a memory component having a plurality of memory cells capable of being in a plurality of states, each state in the plurality of states corresponding to a value stored by the memory cell; and a processing device operatively coupled to the memory component to perform operations comprising: obtaining a plurality of threshold voltage distributions for the plurality of memory cells, wherein each of the plurality of distributions corresponds to one of the plurality of states; classifying each of the plurality of distributions into one of a plurality of classifications; generating a vector comprising a plurality of components, wherein each of the plurality of components represents the class of a corresponding one of the plurality of distributions; and processing the generated vector using a classifier to determine a likelihood that the memory component will fail within a target time period.

In accordance with example embodiments of the invention, a user equipment receives or sends information to trigger model failure detection (MFD), wherein the trigger is based on a machine learning model or machine learning model functionality to initiate an MFD count in a medium access control layer, wherein MFD is using an MFD window in the medium access control layer and wherein one MFD count in the medium access control layer is determined by at least one model failure instances of the machine learning model or model functionality usage in a physical layer; and determining by the user equipment or a network the model failure for the machine learning model or machine learning model functionality when the MFD count in the medium access control layer is equal to or above a maximum model failure count prior to the end of the MFD window in the medium access control layer.

A computer-implemented method for determining a signature embedding vector for information technology events. The method including: receiving a current data object representing an occurrence of an information technology event associated with a configurable item; obtaining a graph database of logical associations of the configurable item; applying a clustering algorithm to the graph database to determine a subset of graphs; extracting associated data of the subset of graphs; applying an embedding model to the extracted associated data to determine an embedding vector for each subset of graphs; aggregating the embedding vector for each subset of graphs to determine a signature embedding vector; and utilizing the signature embedding vector to perform further analysis of the current data object.

A vehicle data verification apparatus includes a database (DB) and a processor connected with the DB. The processor is configured to: import at least one vehicle data set; identify whether the at least one vehicle data set is stored in the DB; verify pieces of vehicle data in the at least one vehicle data set upon identifying that the at least one vehicle data set is stored in the DB; and export a result of the verification of the pieces of vehicle data.

Techniques for collaboratively executing runbook sessions are disclosed. A system provides for collaborative completion of runbook operations by delegating runbook operations or by transferring ownership of a runbook from one user to another. A system identifies a first set of runbook operations capable of being completed by a first user. The system identifies a second set of runbook operations that are not capable of being completed by the first user. The system identifies a second user capable of completing the second set of runbook operations. Upon completion of the first set of runbook operations by the first user, the system determines whether to delegate the second set of runbook operations to the second user or to transfer ownership of the runbook session to the second user. The system determines that the runbook session is completed based on the combined results collaboratively generated by the initial user and the alternate user.

Techniques for collaboratively executing runbook sessions are disclosed. A system provides for collaborative completion of runbook operations by delegating runbook operations or by transferring ownership of a runbook from one user to another. A system identifies a first set of runbook operations capable of being completed by a first user. The system identifies a second set of runbook operations that are not capable of being completed by the first user. The system identifies a second user capable of completing the second set of runbook operations. Upon completion of the first set of runbook operations by the first user, the system determines whether to delegate the second set of runbook operations to the second user or to transfer ownership of the runbook session to the second user. The system determines that the runbook session is completed based on the combined results collaboratively generated by the initial user and the alternate user.

A processing system may execute diagnostic software to test the functionality of one or more components arranged in a physical space for use during a video conference. Functionality of the diagnostic software may include detecting that the component is in a limited condition for use during the video conference. The processing system may initiate a response, based on an output of the diagnostic software, to change the condition of the component to increase the functionality of the component.

A computer-implemented method for determining a signature embedding vector for information technology events. The method including: receiving a current data object representing an occurrence of an information technology event associated with a configurable item; obtaining a graph database of logical associations of the configurable item; applying a clustering algorithm to the graph database to determine a subset of graphs; extracting associated data of the subset of graphs; applying an embedding model to the extracted associated data to determine an embedding vector for each subset of graphs; aggregating the embedding vector for each subset of graphs to determine a signature embedding vector; and utilizing the signature embedding vector to perform further analysis of the current data object.

Methods, system, and non-transitory processor-readable storage medium for an Out of Memory test baseline system are provided herein. An example method includes executing a plurality of test cases on a system. A test score calculation module calculates a test case score for each of the executed test cases in a subset of the plurality of test cases. An Out of Memory (OOM) test baseline configuration system trains a machine learning system, using the subset test scores, to predict a baseline test score for an unexecuted test case. A test case score prediction module predicts the baseline test score for the unexecuted test case. A test case configuration tuning module tunes the unexecuted test case to determine a baseline configuration for the unexecuted test case, to identify OOM issues when the unexecuted test case is executed on a test system.

An example system includes a first memory that includes primary storage; a second memory that includes secondary storage; and a control system for predicting paths through a test program that will be taken during a planned execution of the test program, and for causing test data associated with the test program to be stored in the first memory or the second memory based on the paths predicted.

A test device according to an embodiment includes a first substrate including a data conversion module having a first connector for receiving data acquired from an external equipment, an FPGA (Field Programmable Gate Array) for converting the received data, and a second connector for outputting the converted data; a second substrate including a test module including a third connector connected to the second connector of the first substrate and receiving the converted data, a test unit for performing a test operation using the data received through the third connector, a communication unit for transmitting test result information according to a test operation result of the test unit to an outside, and a control unit for controlling the test unit and the communication unit; and a housing for accommodating the first substrate and the second substrate.

A neural processing unit (NPU) is capable of testing a component of the NPU in a running system, i.e., during runtime. The NPU includes a plurality of functional components, each of which includes an electronic circuit; at least one wrapper connected to at least one of the functional components; and an in-system component tester (ICT). The ICT performs a selection of one of the at least one functional component, in an idle state, as a component under test (CUT) and performs a test, via the at least one wrapper, of the selected functional component. The ICT may monitor states of the plurality of the functional components via the at least one wrapper, stop the test based on a detection of a collision due to an access to the selected functional component, and return a connection of the selected functional component to the at least one wrapper according to the stop.

A method of operating a network is provided that includes identifying a plurality of client devices connected to the network, categorizing the client devices into respective client groups based on device characteristics of each of the client devices, analyzing traffic patterns among the client groups and assigning the client groups to respective network segments based on the observed traffic patterns, and generating one or more network access policy for at least one of the network segments based on the traffic patterns or baseline behavior associated with a portion of the client devices belonging to the at least one of the network segments.

An example system includes a first memory that includes primary storage; a second memory that includes secondary storage; and a control system for predicting paths through a test program that will be taken during a planned execution of the test program, and for causing test data associated with the test program to be stored in the first memory or the second memory based on the paths predicted.

A processing system may execute diagnostic software to test the functionality of one or more components arranged in a physical space for use during a video conference. Functionality of the diagnostic software may include detecting that the component is in a limited condition for use during the video conference. The processing system may initiate a response, based on an output of the diagnostic software, to change the condition of the component to increase the functionality of the component.

The present disclosure relates to a method and system for screening CPU cores, receiving system data of a user computer to diagnose the computer, and based on the diagnosis results, accessing the system of the user computer to screen core combinations by excluding or executing certain cores. The method comprises the following steps: (a) receiving system data of a user computer; (b) diagnosing the user computer by comparing the received system data with an average performance value of the same model as the user computer; (c) screening the kernel combination so as to exclude or execute certain kernel operations by accessing the system of the user computer using the diagnostic data of the user computer to achieve the average performance value; (d) applying the screened kernel combination to the user computer and receiving system data of the user computer to which the screened kernel combination is applied; and (e) comparing the system data of the user computer with the average performance value to check whether the operation of the screened kernel combination is efficient.

The invention discloses a server performance grade evaluation method and device, and relates to the technical field of servers, and the method comprises the steps: carrying out the performance test of an accelerator card, and obtaining an accelerator card performance evaluation value; performing multi-class communication test on the plurality of interconnection types corresponding to each device to obtain a communication performance value; performing a video memory performance test on the video memory unit to obtain a video memory performance value; testing the reasoning process and expert partition performance of the model deployed on the server to obtain a first separation adaptive value and a second separation adaptive value of the server; determining a total evaluation value of the server according to the accelerator card performance evaluation value, the communication performance value, the video memory performance value, the first separation adaptive value, the second separation adaptive value and the corresponding target weight values; and according to the total evaluation value, determining the target performance grade of the server from the plurality of performance grades, so that the accuracy of server performance grade evaluation is improved.

The embodiment of the invention provides a fault positioning method, system and device of an eMMC and a medium, the eMMC comprises a first pin, and the method comprises the following steps: determining an operation stage of the eMMC; under the condition that the operation stage of the eMMC is a first type stage, configuring the first pin to be in a GPIO (General Purpose Input / Output) mode; respectively calling a first function at a plurality of function calling points of the first type stage, so that the first pin respectively outputs a waveform signal with a preset period number at each function calling point; obtaining the waveform signal output by the first pin through oscillographic equipment, and generating visual waveform data; and determining the fault position of the eMMC based on the visual waveform data, so as to quickly obtain the state information of the eMMC, thereby improving the efficiency of judging the fault position of the eMMC.

A method, computer program product, and computing system for generating a respective diagnostic history associated with each physical storage device of a plurality of physical storage devices. A subset of diagnostic history associated with a class of failing physical storage devices is identified from the diagnostic history associated with each physical storage device. The subset of diagnostic history associated with the class of failing physical storage devices is enhanced. A physical storage device failure event for a target physical storage device is forecast using a machine learning model and the enhanced subset of diagnostic history associated with the class of failing physical storage devices.

Existing Convolutional Dictionary Learning (CDL) based machine fault classification do not utilize label information while learning the dictionary, hence the representation learned are not class-discriminative. Method and system disclosed herein provide a label-consistent convolutional dictionary learning approach for machine fault classification. The approach involves generating a training data for a classifier, wherein coefficients forming a plurality of class-discriminative features form the training data. The training data is then used to train a classifier, which is then used to perform machine fault classification for a given test data.