58results about "Error identification" patented technology

A system and method for real-time detection of anomalies in high-dimensional systems. Various embodiments detect anomalies quickly and accurately to allow adequate time for appropriate countermeasures to be implemented. The sequential and multivariate anomaly detection method scales well to high-dimensional datasets using a nonparametric and semi-supervised approach that trains only on nominal data.

The current disclosure provides methods and systems that can manage the dynamic-uncertainty induced by resources of decentralized data networks, in order to ensure the stability and sustainability of task-oriented automated operations, such as operations conducted through intelligent agents. In contrast to the state-of-the-art object-based processing, the methods and systems enable object-aware processing, to ensure the establishment of stable and sustainable associations with physical and digital web-objects, while enabling those objects to be processed dynamically with full adaptability in response to contextual and structural alterations in real-time. Thus, the disclosure provides—both human and machine—users with the ability to develop and deploy modular systems capable of engaging any conceivable physical or digital interaction with the resources of a data network, such as dynamically linking and manipulating clusters of complex web-objects to execute complex tasks in complex and dynamic web environments—most importantly—stably and sustainably.

A method comprises analyzing, using one or more machine learning algorithms, parameters corresponding to at least one microservice operation processed by a first instance of a microservice, and predicting, based at least in part on the analyzing, whether the at least one microservice operation is anomalous. The first instance of the microservice is designated as being in an anomalous state responsive to predicting that the at least one microservice operation is anomalous. One or more requests for the microservice are routed to a second instance of the microservice responsive to the anomalous state designation. The method further comprises causing logging of information corresponding to operation of the second instance of the microservice to be enabled at a designated level of granularity.

In an embodiment, a computer generates a multi-sequence vector that contains a plurality of distinct sequences of distinct nodes of a parse tree of source logic. Based on the multi-sequence vector, the computer trains a logic encoder. After training and in a production environment, the logic encoder infers a fixed-size encoded logic from new source logic. Based on the fixed-size encoded logic, the new source logic is detected as anomalous by an anomaly detector. Both of the logic encoder and the anomaly detector are machine learning models and, herein, they may be separately trained. In an embodiment, the logic encoder is based on a natural language processing (NLP) language model architecture such as bidirectional encoder representations from transformers (BERT), or novel training herein may be self-supervised according to skip-gram for use with an unlabeled training corpus.

An aspect of behavior of an embedded system may be determined by (a) determining a baseline behavior of the embedded system from a sequence of patterns in real-time digital measurements extracted from the embedded system; (b) extracting, while the embedded system is operating, real-time digital measurements from the embedded system; (c) extracting features from the real-time digital measurements extracted from the embedded system while the embedded system was operating; and (d) determining the aspect of the behavior of the embedded system by analyzing the extracted features with respect to features of the baseline behavior determined.

Provided are a system and a method for maintaining task operation continuity. The system includes a server that communicatively coupled to a first computer device and a second computer device. The server is configured to monitor an operating status of each of the first computer device and the second computer device, in which each of the first computer device and the second computer device is at least deployed with a first task on Docker, and the first task is assigned to be run by the first computer device, and in response to determining that the first computer device cannot operate normally, assign the first task to the second computer device that is operating normally to run through a distributed architecture.

Noisy data parsed from raw data can be received. The noisy data indicates first transaction events determined to be noise in the raw data. Using the noisy data, a first detection model can be trained to assign anomaly event indicators to second transaction events. The first detection model can receive an anomaly record. The anomaly record can indicate at least a portion of anomalous transaction events identified in runtime data. The first detection mode can assign the anomaly event indicators to the anomalous transaction events. The anomaly event indicators can indicate levels of severity of the anomalous transaction events identified in the runtime data.

The embodiments of this specification provide a data processing method and device, wherein the data processing method includes: obtaining a set of page elements in a page to be processed; determining the page elements to be processed in the set of page elements based on a preset search strategy; determining the initial target page according to the interactive information of the page elements to be processed, and judging whether the initial target page is the target page; if so, determining the initial target page to be the target page; if not, treating the initial target page as a new page to be processed, and executing the step of obtaining the set of page elements in the page to be processed. The data processing method of this specification determines the page elements in the page to be processed, determines the next-level page of the page elements to be processed based on the interactive information of the page elements, and when determining that the next-level page is the target page, determines the path to the target page, so as to facilitate the subsequent path-based entry into the target page of the application and screenshot.

The invention discloses a management and education monitoring system based on deep learning, relates to the technical field of computers, and is used for solving the problem that a traditional management and education monitoring system usually depends on manual operation or simple automatic scripts and is difficult to deal with high-concurrency and high-reliability requirements in a complex linkage scene. Service actions are constructed into an atomic action graph, and graph rewriting and two-stage convergence batching are carried out in combination with a mutual exclusion matrix, so that the degree of parallelism is maximized, and resource contention is avoided; an idempotent token is generated by the plan fingerprint and only an outgoing box is added, so that first successful receipt reuse and at most one side effect semantics are realized; a main key set capable of being aligned is provided through rehearsal and a state transition diagram, so that the execution premise can be quickly verified; triple verification of an interface level, a state level and a side certificate level is taken as a decision mechanism, a side certificate is taken as a negative criterion, and loss can be stopped quickly when false success and late success occur.

A memory system includes a link having at least one signal line and a controller. The controller includes at least one transmitter coupled to the link to transmit first data, and a first error protection generator coupled to the transmitter. The first error protection generator dynamically adds an error detection code to at least a portion of the first data. At least one receiver is coupled to the link to receive second data. A first error detection logic determines if the second data received by the controller contains at least one error and, if an error is detected, asserts a first error condition. The system includes a memory device having at least one memory device transmitter coupled to the link to transmit the second data. A second error protection generator coupled to the memory device transmitter dynamically adds an error detection code to at least a portion of the second data.

A method comprises analyzing, using one or more machine learning algorithms, parameters corresponding to at least one microservice operation processed by a first instance of a microservice, and predicting, based at least in part on the analyzing, whether the at least one microservice operation is anomalous. The first instance of the microservice is designated as being in an anomalous state responsive to predicting that the at least one microservice operation is anomalous. One or more requests for the microservice are routed to a second instance of the microservice responsive to the anomalous state designation. The method further comprises causing logging of information corresponding to operation of the second instance of the microservice to be enabled at a designated level of granularity.

The invention relates to a method and a system for detecting a runtime error occurring during a data processing. According to the invention, each of two or more data processing devices processes the same input data in order to generate useful data for a receiver. In each case, the processing of the input data is monitored by one or more respective monitoring functions, the monitoring results of which form the basis for a calculation of data processing device-specific keys, which are used by all but one of the data processing devices to code via the respective self-calculated hash values via the self-calculated useful data. The data processing device which does not code the self-calculated hash value receives the coded hash values and decodes same on the basis of self-calculated reference keys which have been calculated under the assumption that the monitoring process carried out by the other data processing devices has not resulted in an error during the processing of the input data. The decoded hash values, the self-calculated hash value and the self-calculated useful data are sent, by said data processing device, to a receiver which checks the hash values against the useful data in order to detect a runtime error occurring during the data processing. The invention also relates to a computer program and to a machine-readable storage medium.

The embodiment of the invention provides an inspection method and device for communication equipment, equipment and a medium, and the method specifically comprises the steps: executing an inspection task instruction through a large language model and a logic processing model, so as to obtain result data corresponding to the inspection task instruction; generating an inspection result report according to the result data; the large language model reads a current instruction in the inspection task instructions; if the current instruction is the first instruction, obtaining a first instruction result corresponding to the first instruction from a log of a database; if the current instruction is a second instruction, the second instruction is sent to the PLC, so that the PLC sends the second instruction to a logic processing model, the logic processing model executes the second instruction to obtain a corresponding second instruction result, and the second instruction result transferred by the PLC is received; and fusing the first instruction result and the second instruction result to obtain result data corresponding to the inspection task instruction. According to the embodiment of the invention, the accuracy of the inspection result report can be improved.

An electronic device for detecting anomalies includes a processor and a memory storing instructions to cause the processor to input a normal input image to a pre-learned autoencoder, receive a normal output image from the autoencoder as an output related to the normal input image, and output the normal input image to the autoencoder. On the basis of a normal input image and a normal output image recognition threshold value, an input image to be determined is input to the automatic encoder, an output image to be determined is received from the automatic encoder as an output related to the input image to be determined, the input image to be determined is divided into a plurality of input regions, and the input regions are input to the automatic encoder. A determination target output image is divided into a plurality of output regions to respectively correspond to a plurality of input regions, first reconstruction errors associated with each of the corresponding input regions and each of the output regions are identified, and the determination target output image is determined on the basis of a comparison result between a threshold value and each of the first reconstruction errors. An abnormal region in each corresponding input region and each corresponding output region is identified.

The present invention provides a distributed system and a diagnosis method. The distributed system includes: an edge system that is an automatically operable mobile body or device, and a diagnostic data computer capable of communicating with the edge system. The edge system has a mechanism unit for operation, an in-edge controller that controls the mechanism unit, and a diagnostic controller capable of communicating with the in-edge controller via a vehicle network. The diagnostic controller acquires diagnostic data according to a first set of diagnostic sequences and sends the diagnostic data to the diagnostic data computer. The diagnostic data computer sends a diagnostic update notification updated to a second set of diagnostic sequences to the diagnostic controller based on the diagnostic data. The diagnostic controller performs an update from the first set of diagnostic sequences to the second set of diagnostic sequences.

The system obtains a first input indicating a machine experiencing an issue and one or more issues with the machine. Based on the first input, the system provides a first plurality of relevance indicators and a first plurality of troubleshooting procedures. The system receives a second input including a performed troubleshooting procedure among the first plurality of troubleshooting procedures. The system receives an indication of a result associated with the performed troubleshooting procedure. Based on the indication of the result associated with the performed troubleshooting procedure, the system generates a second plurality of relevance indicators associated with a second plurality of troubleshooting procedures, where the second plurality of relevance indicators indicates a second troubleshooting procedure to perform next.

The present embodiments relate to systems and methods to intelligently handle different types of concept drift scenarios in a machine learning operations framework with minimal / no down time or loss in processing data. Particularly, the present embodiments enable a system to generate Al model specific instructions from raw data automatically and use the generated instructions to generate code blocks through which the machine learning system can intelligently come up with challenges of Al Model quality drop scenarios. The present embodiments can solve the problem of automatic concept drift resolution in machine learning operations systems. For instance, the present embodiments can recommend the best possible code blocks for data pipelines and ML pipelines based on data distributions. Further, the embodiments can improve and maintain the Al model quality in a production environment, and also improve the code quality based on validation from an operator.

Systems and methods for automatically identifying and resolving problem instances in data service workloads are disclosed. In some embodiments, a disclosed method includes: identifying a problem instance for a workload associated with a plurality of data service platforms; determining, using at least one machine learning model, a problem solution based on the problem instance and a catalog of problem solutions; executing the problem solution including operations across the plurality of data service platforms; and recovering the workload in accordance with a determination that the problem instance is resolved by the problem solution.

A set of payload flip-flops receives an input instance of a payload, and outputs an output instance from which a first instance of an error check signal is generated. One or more error check flip-flops receive the first instance and output a second instance. The input payload instance is clocked into the payload flip-flops if a payload enable signal is asserted, and the first error-check signal instance is clocked into the error check flip-flops if an error check enable signal is asserted. The input payload instance is input to the set of payload flip-flops over two clock cycles, and the payload enable signal is asserted for the two clock cycles. The error check enable signal is asserted on the second cycle. The first instance of the error check signal is compared with the second instance and an error signal is asserted if they do not match.

Methods and systems for managing data processing systems based on indications of a failure 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. Inference models may be implemented to predict future system infrastructure issues (e.g., future component failures) using information recorded in the logs. The inference models may also predict times-to-failures associated with the future failures by assigning attribution scores to portions of logs. Further analysis of attribution scores may be performed to generate health scores for the data processing system, providing additional information for the determination of remedial actions that may reduce the likelihood of the data processing system becoming impaired.

The invention discloses an intelligent management system and method for a tablet personal computer, and relates to the field of intelligent management of the tablet personal computer, the intelligent management system comprises a data acquisition module, a hardware module, a user module, a verification module and a warning module, cache, micro-operation and branch prediction states of a processor are analyzed to obtain a state value of the tablet personal computer processor, and the state value of the tablet personal computer processor is analyzed; judging and analyzing a battery redox reaction state and a screen use state of the battery information and the screen information to obtain a battery screen positive value of the tablet computer, and analyzing a user interaction and sharing state of the user information to obtain a user state value of the tablet computer; according to the method, the state value of the tablet personal computer processor, the pool-screen-shaped positive value of the tablet personal computer and the state value of the tablet personal computer user are subjected to tablet personal computer comprehensive operation state analysis and compared with a set threshold value, a corresponding warning signal is obtained, warning operation is executed on the generated signal, and the use experience and the working efficiency of the user are guaranteed.

The invention provides an embedded system crash prediction method and device based on multi-source dynamic perception, and the method comprises the steps: carrying out the stack boundary monitoring and / or interruption storm detection of a system, and obtaining a detection result; performing deadlock probability calculation and / or memory leak trend analysis on the system to obtain an analysis result; and performing risk assessment on the detection result and the analysis result to obtain a crash risk value, comparing the crash risk value with a preset threshold value, and when the crash risk value exceeds the preset threshold value, judging that the system has a crash risk. According to the method, stack boundary monitoring and / or interruption storm detection are / is carried out on the system, deadlock probability calculation and / or memory leakage trend analysis are / is carried out on the system, a more comprehensive detection result and an analysis result are obtained, risk assessment is carried out on the basis, and a crash risk value is obtained; and the crash risk value is compared with the preset threshold value to predict the system crash in advance, so that the problems that the misjudgment rate is high and the crash cannot be prevented in the prior art are solved.

The present invention provides a real-time anomaly detection method and device for high-risk user instructions. The method includes: collecting instruction data used by a user from a production environment, and obtaining system error logs and automated test results of the instruction data; calculating a first high-risk score of the instruction data according to instruction sub-parameters of the instruction data, system error logs, and automated test results; calculating a second high-risk score of the instruction data based on word vectors of the instruction data; and obtaining an anomaly detection result of the instruction data according to the first high-risk score and the second high-risk score. The present invention reduces the difficulty of data access in a streaming data processing system and improves the throughput of the entire data processing system. By means of various factors such as instruction data, the corresponding number of system error logs, and automated test results, the present invention reduces the operation and maintenance difficulty of traditional abnormal instruction detection and improves the detection speed and accuracy of abnormal instructions.

The invention relates to the technical field of intelligent driving, and particularly discloses a black screen prevention control method for an intelligent cabin, which comprises the following steps: based on the black screen problem of the intelligent cabin, carrying out screen display link analysis on a black screen prevention system of the intelligent cabin from the source; and based on the link analysis, starting from the function safety requirement of preventing the black screen of the screen, obtaining the black screen prevention control strategy of the intelligent cabin. According to the black screen prevention control method for the intelligent cockpit, analysis of screen display links including the source of screen display content, the transmission path, the control logic, the final display and other links is carried out fundamentally, and detailed strategy disassembly and functional requirement decomposition are carried out on all system components in a cockpit controller. The black screen problem is avoided and solved, and smooth, stable and safe cabin screen use experience is provided for users.

Techniques for performing operation-based event suppression are described. In an example, a determination may be performed as to whether an event is to be suppressed if the event is received in response to performance of an operation. The determination may be performed based on at least one of number of actions triggered by the event, frequency of occurrence of the event in an event stream in response to performance of the operation, and frequency of occurrence of the event in the event stream without performance of the first operation.

The reset method, device, equipment and storage medium of the control panel status provided by the present invention call up a historical operation list in response to a reset operation instruction, wherein the reset operation instruction includes an undo operation instruction and a restore operation instruction; determine the legality of the reset operation instruction according to the historical operation list; when the reset operation instruction is legal, obtain the operation cache information in the historical operation list; reset the status of the control panel according to the operation cache information. By judging the legality of the instruction before executing the reset operation, system abnormalities or data loss caused by improper operation are avoided, and the safety of the operation is ensured. In addition, the user only needs to simply reset the operation instruction to quickly restore or revoke to the historical state, which improves the efficiency and convenience of the operation.

An imaging apparatus includes an image sensor, a controller, and an output interface. The image sensor captures a subject image to generate imaging data. The controller performs repair processing to generate a moving image file by sequentially analyzing information used for reproduction of a moving image from a corrupted file, the moving image file being capable of reproducing the moving image indicated by the imaging data, the corrupted file having a defect corrupted from the moving image file. The output interface outputs information to be presented to a user. The controller outputs a part of the moving image via the output interface, in a period from start of the repair processing on the corrupted file to completion of the repair processing, based on analyzed information in the repair processing in execution, the part of the moving image corresponding to the analyzed information.

A performance anomaly is detected in relation to a first data center equipment. An AI model is trained based on a plurality of anomaly patterns associated with a plurality of data center equipment and respective remediation processes associated with the anomaly patterns, to determine a remediation process that can resolve the detected performance anomaly associated with the first data center equipment. Upon execution of a machine-learning algorithm, the AI model compares real-time performance indicators recorded for the first data center equipment with performance indicators of the anomaly patterns and determines a matching anomaly pattern. The AI model determines a particular remediation process associated with the matching anomaly pattern. The remediation process is then implemented to resolve the performance anomaly associated with the first data center equipment.

The embodiments of the present invention disclose a method, device, computer equipment and computer-readable storage medium for judging faults. After the power bank is returned to the charging module, the status of the power bank is read through the ejector pin; if the status of the power bank is normal, the power bank is judged to be normal; if the status of the power bank is abnormal, a first status is obtained and a second status is determined, wherein the first status includes: the status of the power bank and / or the charging module before return, and the second status includes: the current status of the power bank and / or the charging module. Through the above-mentioned method, the embodiments of the present invention can change the past method of manually checking one by one, and by replacing different power banks on site, that is, by returning them multiple times, the system automatically determines whether the fault point exists in the charging module itself or in the power bank, and analyzes and records the fault type, and uploads the data to the server for subsequent big data analysis.

A method for managing data storage in a data grouping includes generating a data storage configuration specifying the data grouping comprising a first configuration identifying a set of storage resources presently allocated to the data grouping, and a second configuration identifying a set of storage resources previously allocated to the data grouping; storing, in a tracking list, one or more identifiers of storage resources in the first configuration that are eligible to transition to the second configuration; and performing one or more update operations on the first configuration using the tracking list.