Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

346 results about "Exception handling" patented technology

Exception handling is the process of responding to the occurrence, during computation, of exceptions – anomalous or exceptional conditions requiring special processing – often disrupting the normal flow of program execution. It is provided by specialized programming language constructs, computer hardware mechanisms like interrupts or operating system IPC facilities like signals.

Large model agent collaborative scheduling method and system oriented to complex tasks

The invention provides a large model agent collaborative scheduling method and system oriented to complex tasks, relates to the technical field of artificial intelligence, and comprises the steps of task decomposition, feature extraction, agent matching, dynamic scoring, scheduling scheme generation and optimization, execution monitoring, exception handling and the like to realize efficient collaboration of large model agents. According to the method, accurate matching can be carried out according to task characteristics and intelligent agent capabilities, the task completion efficiency and quality are improved, meanwhile, the dynamic adjustment capability is achieved, abnormal conditions in the execution process are effectively handled, and the system robustness is enhanced.
Owner:BEIJING YUANZHI STAR TECHNOLOGY CO LTD

Equipment abnormity self-closed-loop control system

The invention relates to the technical field of equipment abnormity control, and discloses an equipment abnormity self-closed-loop control system. An anomaly detection engine of the system collects operation state data of target equipment in real time, and performs preliminary anomaly marking according to a preset anomaly judgment rule; the dynamic analysis unit receives the preliminary anomaly marks, generates anomaly feature vectors in combination with historical operation data, and inputs the anomaly feature vectors into a multi-dimensional evaluation model to divide anomaly levels; a strategy generator is matched with a preset repair strategy library according to the abnormal grade division result, and a corresponding repair instruction sequence is generated; the execution control module analyzes the repair instruction sequence, and dispatches hardware resources to execute repair operation according to a preset execution priority; and the feedback verification unit collects the running state data again after restoration, and compares the running state data with the initial abnormal mark to generate a restoration verification result. The system realizes full-process automatic processing of equipment exceptions, and improves exception processing efficiency and equipment operation stability.
Owner:QUANZHOU INST OF INFORMATION ENG

Dynamic script compiling and hot updating system based on Grouping and implementation method of dynamic script compiling and hot updating system

PendingCN121029183AVersion controlCode compilationDynamic compilationDowntime
The invention discloses a dynamic script compiling and hot updating system based on Grouping and an implementation method of the dynamic script compiling and hot updating system. The system comprises a script source code management module, a dynamic compiling engine, an intelligent cache manager, an exception handling and recovery system and a hot update controller. And the script source code management module receives and preprocesses the Grouping script to generate a unique identifier for subsequent management. And the dynamic compilation engine executes compilation operation according to the identifier to ensure that a compilation result accords with a specification. And the intelligent cache manager efficiently stores and retrieves the compiling result, so that the repeated compiling cost is reduced. And the exception handling and recovery system monitors the execution state in real time, and automatically starts a recovery process in case of exception to guarantee stable operation of the system. The hot update controller realizes seamless update and version switching of scripts, and ensures service continuity. Through cooperative work of the modules, high-reliability, high-performance and zero-shutdown deployment is realized.
Owner:SICHUAN CHANGHONG JIAHUA INFORMATION PROD CO LTD

Multifunctional test tool and method for EUROMAP interface of injection molding machine

The invention relates to the field of industrial automation testing, discloses a multifunctional testing tool and method for an EUROMAP interface of an injection molding machine, and achieves the crossing from single function verification to system-level compliance evaluation. A test network is constructed through a controller, and deep compliance verification, coverage data interaction, exception handling and cross-layer response consistency are realized. The test tool integrates the functions of protocol analysis, signal simulation, fault injection and the like, supports dynamic generation of boundary value test scenes and abnormal injection of signal delay, CRC errors and the like, and verifies the time sequence / logic consistency of a protocol instruction and an execution mechanism response through a hardware-level timestamp alignment technology. According to the method, an evaluation report including compliance rating, fault diagnosis and optimization suggestions is automatically generated, the problems of single coverage dimension, insufficient abnormal simulation, cross-layer verification deficiency and the like of a traditional test are solved, the intelligence and standardization level of the injection molding machine interface test is remarkably improved, and the equipment interconnection and intercommunication performance is guaranteed.
Owner:KRAUSSMAFFEI MACHINERY ZHEJIANG CO LTD

Intelligent timed task configuration and multi-mode feedback system based on natural language interaction

The invention discloses an intelligent timed task configuration and multi-mode feedback system based on natural language interaction, and relates to the field of industrial automation control, enterprise-level task scheduling management and instant messaging. The system comprises a natural language interaction module, a user natural language instruction is converted into structured semantic information through a BERT + BiLSTM + CRF mixed architecture, and lightweight processing is achieved in combination with TinyBERT distillation; the dynamic task arrangement module completes task creation, modification and the like based on structured information, completes missing parameters through historical task mode matching, and supports multi-session real-time synchronization; the rich media report generation module generates a multi-mode report containing charts, tables and the like, and the RAG technology and large model interpretation are combined; and the multi-channel pushing adaptation module adapts multiple platforms by adopting a strategy and factory mode. According to the system, the task configuration efficiency and flexibility are improved, the feedback form is enriched, the information pushing accuracy is guaranteed, and the exception handling capacity is enhanced.
Owner:YIZHIWEISI (BEIJING) INTELLIGENT TECHNOLOGY CO LTD

Intelligent agent assisted test method and device, computer equipment and storage medium

The invention discloses an agent assisted testing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring demand information of a Web system to be tested; analyzing the demand information and generating a test case set; performing hierarchical labeling on the test case set to form a hierarchical case set containing the basic operation type case, the data verification type case and the complex logic type case; distributing the basic operation type use case to an execution module of the agent system, distributing the data verification type use case to an interface automation test module, and distributing the complex logic type use case to an artificial interaction terminal; and when the execution module or the interface automatic test module monitors that the case execution fails or the state is abnormal, an exception processing strategy is matched according to an exception type and an exception source, corresponding processing operation is executed, and feedback information used for optimizing the layered case set is generated. According to the method, the test tasks can be intelligently allocated and accurately executed, and automatic adaptation and optimization can be performed when an exception occurs, so that an efficient man-machine collaborative test is formed.
Owner:LESHUA TECH CO LTD

Interface automatic test management method and device, equipment and medium

The invention relates to an automatic interface test management method and device, equipment and a medium, and the method comprises the steps: obtaining an interface document of a to-be-tested interface, carrying out the analysis of the interface document, generating interface case data containing the primary configuration content of an interface case, and transmitting the interface case data to a server; performing execution grouping on the interface cases configured with the input parameter value set, generating a case execution group based on interface grouping information and a preset test execution strategy, setting an execution sequence and an exception handling rule for the case execution group, and generating a corresponding execution link at the same time; calling an execution link based on the trigger request to sequentially use each group of request content execution cases in the input parameter value set to execute the interface cases in the group, and generating corresponding case execution results; high automation and intelligentization are achieved in the whole interface test process, manual intervention is remarkably reduced, the test coverage rate is increased, the problem response speed is increased, and therefore the working efficiency of testers is effectively improved, and the human error risk is reduced.
Owner:BEIJING SHENZHOU EVERBRIGHT TECH CO LTD

Clock management method for power embedded RTOS (Real Time Operating System) and related equipment

The invention discloses a power embedded RTOS-oriented clock management method and related equipment, and the method comprises the steps: collecting the current clock data of a power embedded RTOS system, carrying out the feature extraction of the current clock data, constructing a clock feature library, and constructing a clock data model in a normal clock operation state, generating normal clock data according to the clock data model; the frequency stability, the clock jitter rate and the clock drift rate of the current clock data are calculated, and whether the deviation between the current clock data and the normal clock data exceeds a clock threshold value or not is judged; and when the deviation exceeds the clock threshold value, executing a corresponding exception handling flow according to the frequency stability, the clock jitter rate and the clock drift rate, and dynamically adjusting the range of the clock threshold value. According to the embodiment of the invention, combined judgment and dynamic adjustment can be carried out by combining drift, jitter and frequency stability thresholds, and accurate monitoring and anomaly detection of the clock are realized. The method can be widely applied to the technical field of clock management.
Owner:SOUTHERN POWER GRID DIGITAL GRID RESEARCH INSTITUTE CO LTD

Decision-making method for computing power balanced distribution between Internet of Things devices

The invention relates to the technical field of Internet of Things, in particular to a decision-making method for computing power balanced allocation between Internet of Things devices, which comprises a task allocation module, a resource management module, a dynamic adjustment module and a priority regulation and control module. The task distribution module decomposes tasks and generates a preliminary distribution scheme; the resource management module monitors equipment performance and classifies the equipment performance; the dynamic adjustment module optimizes an allocation strategy by using a particle swarm optimization algorithm; and the priority regulation and control module regulates the task sequence according to the weight and ensures the high-priority task resource demand. The system stability is enhanced through the exception handling unit and the load prediction unit, the computing power distribution efficiency and the resource utilization rate are improved, and efficient and flexible task execution is achieved.
Owner:SHANGHAI XIHENG NETWORK TECH CO LTD

Welding wire production control system and method based on visual feedback

The invention discloses a welding wire production control system and method based on visual feedback, and belongs to the technical field of precision machining. The system comprises a multi-mode intelligent sensing subsystem, a self-adaptive model prediction controller and a safety and exception handling subsystem, and a two-stage control architecture of a quality closed loop and an execution closed loop is constructed. According to the method, the microcosmic roughness, macroscopic geometry, defects and other multi-dimensional quality characteristics of the surface of the welding wire are obtained in real time through multi-modal sensing and fused into a comprehensive quality index; carrying out rolling optimization by adopting a model prediction control algorithm for updating parameters on line, and generating a control instruction; meanwhile, trend early warning based on statistical process control and sudden fault diagnosis based on model residual analysis are operated in parallel, and active safety protection is achieved. According to the method, the problems of unstable quality, control lag and passive safety caused by supplied material fluctuation and tool time variation in the welding wire flaking machining process are solved, and self-adaptive accurate control and intelligent safety protection in the machining process are achieved.
Owner:XIANGYANG YUNYE NEW MATERIAL CO LTD

Security authentication multi-start method for Linux system of development board

The invention discloses a development board Linux system security authentication multi-start method, which comprises the steps of 1, hardware trust root initialization and storage area division, 2, hardware trust root self-inspection and measurement, 3, starting item dynamic loading and multi-stage authentication, 4, security context establishment and system switching, and 5, multi-system isolation and collaboration. Step 6, performing security audit and exception handling; full-link authentication is realized by taking a hardware trust root as an anchor point, malicious mirror startup and inter-system data leakage are effectively resisted in combination with a storage and resource isolation mechanism, scenes such as on-demand dynamic switching, flexible adaptation debugging, upgrading and fault recovery of multiple systems can be realized, and the system reliability is improved by optimizing the lightweight design of an authentication algorithm and resource management. Limited computing power of the development board is adapted, the starting process and abnormal events can be completely recorded, and illegal operation can be traced conveniently.
Owner:BEIJING XUNWEI ELECTRONICS CO LTD

State machine management method based on layered architecture and dynamic trigger mechanism

The invention provides a state machine management method based on a hierarchical architecture and a dynamic trigger mechanism, which adopts a four-layer nested state hierarchical architecture and comprises the following steps: acquiring an equipment initial state signal and starting a state machine working process; switching from an initial state to a task state according to a trigger mechanism, and executing a task action; determining a state transition path according to a task state execution result, switching to a stable state and executing a resource synchronization operation if task execution succeeds, and switching to a fault state and executing an exception handling action if task execution fails; and determining whether to recover to a task state or enter a safety mode according to a fault state processing result. According to the technical scheme, the reliability and the operation efficiency of the electric energy meter equipment are effectively improved, and the fault recovery capability and the resource management capability of the system are enhanced.
Owner:JIANGSU LINYANG ENERGY CO LTD

Numerical model business operation method

The invention relates to the technical field of meteorological and ocean numerical forecasting, and aims to solve the problems of strong manual dependence, poor timeliness, high error risk and low resource utilization rate in coupling operation of a WRF atmosphere model and an ROMS ocean model. The method comprises the following steps of: storing an initial file into a date catalogue which is dynamically generated according to a YYYMMDD format after the initial file is subjected to integrity verification; the timed task checks nc.lock / nc.tone files every X minutes, a lock starting model is created when no lock exists and an initial file exists, and an ROMS needs to confirm nc.tone of a WRF result directory first; automatic exception processing is carried out when the model is overtime, and after completion of the automatic exception processing, a Done is created, a lock is deleted, resources are released, and computational nodes are dynamically allocated. According to the method, automatic scheduling is achieved through double-file marking, manual operation is shortened to be within one minute, model connection delay is shortened to be within five minutes, the failure rate is reduced, the resource utilization rate is improved, and a reliable scheme is provided for model business operation.
Owner:青岛国实信息科技有限公司

Dynamic configuration management method and system under single-machine lightweight scene

The invention relates to a dynamic configuration management method and system under a stand-alone lightweight scene, and the method comprises the steps: carrying out the unified description of a configuration file of an application program through the form of structured metadata, and obtaining a metadata configuration item, so as to achieve the decoupling of the configuration file and a business code; in the starting process of the application program, the metadata configuration items are detected and verified, and the metadata configuration items meeting preset requirements are cached in a key value hash table of a volatile memory; and after the application program is started, acquiring a configuration value corresponding to the metadata configuration item from the key value hash table of the volatile memory through the configuration item acquisition interface. Through the application, the configuration item is defined in the form of metadata to realize decoupling with the service code, the verification is configured in the application starting stage to realize timely abnormity, the operation and maintenance cost is effectively reduced, the hash table cache effectively reduces the access frequency of the configuration file in the disk, and the problem of how to improve the management efficiency of the configuration item of the application program is solved.
Owner:HUAXIN CONSULTATING CO LTD

Abnormity diagnosis and repair method and device for automatic process of robot and medium

The invention discloses an abnormality diagnosis and repair method and device for an automatic process of a robot and a medium, and relates to the technical field of artificial intelligence. The anomaly diagnosis and repair method for the automatic process of the robot comprises the following steps: acquiring RPA anomaly processing data; matching the RPA exception processing data with a target causal knowledge base to obtain an exception scene repair action; and according to the abnormal scene repair action and the large language model, generating a process repair script, and according to the process repair script, performing abnormal scene process repair. According to the technical scheme provided by the embodiment of the invention, the handling effect of the PRA in the exception handling scene can be greatly improved on the premise of low maintenance cost.
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA

Production line exception processing method and device, equipment and medium

The invention relates to the technical field of industrial automation, in particular to a production line exception handling method and device, computer equipment and a medium. The method comprises the following steps: in response to a production abnormal event of a production line, acquiring multi-dimensional state sensing data corresponding to the production abnormal event; according to the multi-dimensional state sensing data, constructing an exception handling decision tree corresponding to the production exception event; based on the exception processing decision tree, determining an optimal processing path for solving the production exception event; according to the method, the limitation of a traditional static mapping mechanism in coping with'same symptom and different cause 'and'multi-exception concurrence' scenes can be broken through, self-adaptive response and accurate disposal of complex exception scenes are realized, and the method is high in practicability and high in practicability. The intelligent level and response efficiency of production line exception handling are remarkably improved, and reliable guarantee is provided for stable operation of a production line.
Owner:SHENZHEN JIZHI INTELLIGENT TECH CO LTD

Ai exception interpreter

Example solutions for providing an artificial intelligence (AI) exception interpreter are disclosed. An exception interpreter receives an exception report from a software application, evaluates it (using AI), and generates a first exception handling response. This provides the benefit of learning over a large amount of exception handling data, which offers super performance over trial-and-error tactics by programmers who are either less experienced or unfamiliar with exceptions from third party resources. Some examples sanitize exception reports of sensitive information. Some examples track an exception event history, so that when the same exception is seen multiple times (meaning a prior response was not effective), a different exception handling response may be provided.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Rule engine and low-code dual-drive power grid digital graph fusion treatment platform and method

The invention discloses a rule engine and low-code dual-drive power grid digital graph fusion treatment platform and method. The platform comprises an infrastructure layer, a data layer, an algorithm engine layer and a business application layer. And the data layer is used for accessing and managing multi-source power grid data. And the algorithm engine layer comprises a rule engine module for configuring and executing data verification, digital graph association and exception handling rules, a data quality diagnosis algorithm module for performing data quality diagnosis to identify exceptions, and a digital graph fusion driving engine module for realizing bidirectional linkage between data and graphs. And the business application layer comprises a low-code arrangement platform for customizing a governance scene page and a work order process, a digital graph integrated display module for displaying multi-source power grid data on the same screen, and a closed-loop work order management module for automatically generating and distributing governance work orders. The method constructs a depth digital graph fusion system, improves the anomaly positioning and treatment efficiency, achieves automatic management and control and whole-course tracing, does not need a large amount of code development, and shortens the response period of a new business scene.
Owner:安徽明生恒卓科技有限公司

Structured information extraction method and system based on large language model

The invention discloses a structured information extraction method and system based on a large language model, and the method comprises the following steps: carrying out the modular cue word design and adaptive loading, so as to guide the large language model to carry out the content generation according to the expected structure and logic; inputting text type identification and task routing to ensure that each type of information can be processed by adopting the most appropriate model prompt strategy; automatic segmentation and concurrent processing are carried out to ensure information integrity and processing efficiency; semantic completion and key information enhancement are carried out to carry out semantic completion on the entity information; performing structured format conversion and standard packaging to output a standardized format; and performing exception processing and full-process log recording to perform real-time tracking and backtracking on the state of each processing task. According to the method, the key information in the text can be automatically recognized, extracted and output in a structured mode, and the information processing efficiency and accuracy are improved.
Owner:QIMING INFORMATION TECH

Root cause alarm analysis method and system based on time sequence correlation and multi-modal fusion

The invention discloses a root cause alarm analysis method and system based on time sequence association and multi-modal fusion, and the method comprises the steps: taking digital twin dynamic threshold cleaning as a core, fusing multi-source data time sequence alignment verification, and forming a multi-source data set of time sequence alignment and preliminary restoration through exception handling and cross-system time consistency verification; a cleaning threshold is optimized in combination with a working condition to filter noise, a label confidence weighting method is fused, confidence is given to a label through twin simulation, and a multi-modal data set with a multi-dimensional label is constructed. A learning model is constructed and trained, exclusive feature extraction branches are designed for multi-source data, a twin working condition adaptation enhancement module is introduced to strengthen core modal extraction, and the proportion of abnormal modals in fusion is reduced by means of a dynamic attention filtering mechanism. Based on the model and a twinning system, root cause penetration type positioning is completed through dynamic sequencing of root cause confidence in combination with a twinning reduction time sequence. And the root cause analysis efficiency and accuracy are improved.
Owner:东风设备制造有限公司

Automatic test method and test platform based on cloud computing

The invention discloses an automatic test method and test platform based on cloud computing, and belongs to the technical field of software testing, and the method comprises the steps: firstly constructing a dynamic elastic resource pool containing a virtualized test node cluster, a tool chain and a distributed data warehouse; after obtaining a performance test request, analyzing data to screen an optimal node combination and tool configuration, and generating a test case set covering a boundary scene and an abnormal path in combination with historical data and reinforcement learning; using an improved genetic algorithm and a load prediction model to disassemble the subtasks and intelligently distributing the subtasks; the progress is tracked in real time through a digital twinborn model, abnormity is recognized, and a multi-stage processing mechanism is activated; and after the test is finished, normalizing the processed data, and generating a panoramic report by means of the analysis model. According to the method, the intelligent level, the execution efficiency, the resource elasticity and the exception handling capacity of automatic testing are improved, and the high-performance testing requirement in a complex scene can be met.
Owner:BEIJING ZHONGCHAO WEIYE INFORMATION SECURITY TECH CO +1

Micro-service system exception handling method and system based on AI and storage medium

The invention discloses an AI-based micro-service system exception handling method and system and a storage medium, and belongs to the technical field of software exception monitoring. The method comprises the following steps: in an exception real-time capturing stage, deploying a global exception intercepting component at a micro-service gateway or each service framework layer, and generating an exception report; in the AI anomaly analysis stage, the anomaly report is analyzed, and a solution thought or a code repair suggestion is generated; an active alarm and notification stage: notifying development, operation and maintenance personnel according to an AI analysis result; meanwhile, all abnormal information is pushed to a monitoring panel; in the automatic repairing and deploying stage, exception handling is carried out, and dynamic deploying and system self-healing of exceptional patches are achieved; in the feedback learning and iterative optimization stage, exception processing results are collected, and the diagnosis accuracy and the repair suggestion quality are improved by continuously learning new exception cases and processing modes. According to the invention, abnormal information from different services is collected in a unified manner through a global interception mechanism, and the omission risk caused by decentralized processing is eliminated.
Owner:CHENGDU EACOM TECH

Galvanometer synchronous control and splicing error correction method and system in laser processing

The invention discloses a galvanometer synchronous control and splicing error correction method and system in laser processing, and relates to the technical field of laser processing control. Comprising the steps of system initialization and parameter configuration, machining path planning and region division, multi-galvanometer synchronous triggering and motion control, synchronous state monitoring and exception handling, splicing error correction and overall laser machining process execution in sequence. The system correspondingly comprises a parameter configuration and self-inspection module, a path planning and region division module, a synchronous control and motion driving module, a splicing error correction module and a processing execution and data management module, and a subunit is arranged below the synchronous control and splicing error correction module to realize the functions of clock synchronization, closed-loop feedback, offline calibration, dynamic compensation and the like. The method has the advantages that the synchronization precision is high, the error correction is comprehensive, the defects of the splicing area can be effectively avoided, and the large-format laser processing quality and stability are improved.
Owner:PRECISION SCAN INC

Interaction method and device based on order, computer equipment and storage medium

The invention relates to an order-based interaction method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: in a target time period when a target order is in a target state, when it is monitored that an order initiator of the target order is in an abnormal state, displaying a help receiving inquiry message used for inquiring the order initiator; in response to a help accepting agreement event for the help accepting inquiry message, displaying a notification message that seeking help from the target processing party is started; the target processing party is associated with at least one of the target order and the initiator position of the order initiator. By adopting the method, the exception handling efficiency can be improved.
Owner:TENCENT TECH (BEIJING) CO LTD

Service plan scheduling method and service plan scheduling system for mining machinery

The invention discloses a mining machinery service plan scheduling method and system, and belongs to the technical field of mining machinery, and the method comprises the steps: S1, carrying out the hierarchical data fusion, integrating the business data of a business system and the operation data of sensor equipment, and carrying out the exception processing of the data; s2, extracting spatio-temporal features to form a dynamic spatio-temporal feature fusion data set; s3, multi-task prediction is carried out by using deep learning, and fine-grained discrimination and increment correction of the effective working hours of the equipment are realized; and S4, dynamically adjusting and scheduling the service plan through data driving. The method has the advantages of integrating multi-source heterogeneous data in combination with spatial-temporal characteristics of a working place of the equipment, performing increment correction by using a deep learning algorithm, dynamically adjusting a service schedule, and ensuring good operation of the equipment.
Owner:XUZHOU XCMG MINING MACHINERY CO LTD

Online exception handling method for heavy truck transmission assembly production line

The invention discloses an online exception handling method for a heavy truck transmission assembly production line. The online exception handling method comprises the steps that 1, step types in the heavy truck transmission assembly process are configured in an AMS; 2, a station formula of each type of heavy truck transmission is compiled and stored in a TCM; step 3, carrying out equipment program debugging; the TCM issues station formulas corresponding to all machine type serial numbers to the AMS; 4, the AMS receives the work order and obtains a corresponding station formula according to the machine type serial number of the heavy truck transmission in the work order; 5, the AMS writes the station formula into the RIFD bar code of the workpiece tray; 6, the PLC reads the station formula in the RIFD bar code of the workpiece tray to control production; 7, the PLC feeds back a process step quality signal of the process step to the AMS, and the AMS triggers an exception handling process according to the signal; 8, the AMS sends all information in the exception handling process to the MES; and step 9, the tray leaves the station. According to the method, the processing flow is automatically triggered during online exception processing, and exception processing line control is achieved.
Owner:SHAANXI FAST GEAR CO LTD

Software test exception handling method and device, storage medium and electronic equipment

The invention relates to an exception handling method and device for software testing, a storage medium and electronic equipment. The method comprises the following steps: in response to a monitored abnormal event in a test process, obtaining abnormal information of the abnormal event; determining an exception type and associated service information of the exception event according to the exception information; generating at least one candidate processing operation based on a knowledge graph library according to the exception type and the associated service information; generating a target processing operation according to the at least one candidate processing operation; executing the target processing operation; and after executing the target processing operation, generating and outputting a diagnosis report corresponding to the abnormal event.
Owner:NEW ORIENTAL EDUCATION & TECH GRP CO LTD

Distributed training fault processing method and device, computer equipment, readable storage medium and program product

The invention relates to a distributed training fault processing method and device, computer equipment, a computer readable storage medium and a computer program product. A distributed training task is issued to the distributed training cluster, and training logs, task breakpoint data and model related information generated in the training process are shared and stored in real time; monitoring the training log in real time based on the fault detection large model, and generating and feeding back a model training progress, model verification precision and training suggestions to the deployment platform under the condition of judging that no abnormal information exists in the training log; when it is judged that the abnormal information exists in the training log, abnormal information and a processing scheme are generated according to the abnormal type and fed back to the deployment platform; and executing a corresponding processing operation based on an operable instruction in the processing scheme, and associating the exception information and the processing scheme with the task breakpoint data in the shared storage so as to provide data support during exception processing and task restarting. The method can improve the effective utilization rate of training resources.
Owner:CHINA TELECOM CLOUD TECH CO LTD

Abnormality processing method and system for power operation data

The invention discloses an exception handling method and system for power operation data. The method comprises the following steps: acquiring original operation data of a target power system; performing primary anomaly detection on the original operation data to obtain primary anomaly data; performing deep anomaly identification on the preliminary abnormal data to obtain each abnormal operation data in the original operation data and each corresponding anomaly type; respectively matching a repair strategy corresponding to each exception type so as to perform repair processing on each abnormal operation data, and integrating an exception repair processing result and non-abnormal operation data in the original operation data to obtain a repair data set; and inputting the repaired data set into the constructed data exception processing model to obtain processed target data corresponding to the original operation data. According to the method, the reliability of the power operation data is improved.
Owner:STATE GRID DIGITAL TECHNOLOGY HOLDING CO LTD +1

Data processing consistency verification method and system based on system internal enhancement verification

The invention provides a data processing consistency verification method and system based on system internal enhancement verification, and belongs to the technical field of computer system security and data integrity protection, and the method comprises the following steps: setting an enhancement verification enabling identifier for a data instance entering a system internal processing flow; generating an enhanced check value that fuses the data content, the initialized secret value, the runtime perturbation factor, the timing information, and the contextual information; verifying the enhanced verification value in the data processing process; and processing according to a pre-configured strategy when verification fails. The system comprises a management module, a check value generation module, a check value verification module, an exception handling module and a strategy configuration module. On the premise that an existing protocol and an existing system structure are not modified, the tamper-proof capacity of data in the system is improved, the data are prevented from being abnormally modified or replayed or subjected to cross-path error multiplexing, the system safety is enhanced, and meanwhile compatibility and good performance are kept.
Owner:HUNAN ZETIAN ZHIHANG ELECTRONIC TECH CO LTD