Operation and maintenance event processing method and device, electronic equipment and storage medium

Abstract

The invention discloses an operation and maintenance event processing method and device, electronic equipment and a storage medium. According to the operation and maintenance event processing method and device, due to the fact that multi-source heterogeneous operation and maintenance data are integrated through standardized processing to form unified context information, and event grading and processing suggestions with support evidence are generated based on a multi-step reasoning process; and then the output accuracy is ensured through logic consistency verification and a business rule correction mechanism, and finally automatic chemical order creation and feedback closed loop are realized, so that the technical problems of shutdown updating of a rule base, insufficient decision transparency, lack of flow closed loop and poor adaptability of complex scenes in the prior art can be solved; the technical effects of improving the operation and maintenance event processing efficiency, enhancing the decision reliability and meeting the minute-level response requirement are achieved.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method and apparatus for handling operation and maintenance events, electronic equipment, and storage medium. Background Technology

[0002] IT operations automation, as a core supporting technology for enterprise digital transformation, is widely used in industries with stringent business continuity requirements, such as finance and telecommunications. With the popularization of cloud-native architectures and microservice systems, operations events exhibit multi-source heterogeneous characteristics. Existing technical systems mainly rely on three types of solutions: rule engines, machine learning models, and large-scale model analysis. In existing operations event handling methods, manually maintained rule bases require downtime updates to adapt to business changes, resulting in significant deficiencies in decision transparency, process closure, and adaptability to complex scenarios. This makes it difficult to meet the business requirements for minute-level response times in terms of efficiency and reliability. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for handling maintenance events.

[0004] According to a first aspect of this disclosure, a method for handling operational and maintenance incidents is provided, comprising: Obtain operation and maintenance data from multiple data sources, and standardize the operation and maintenance data to form a unified set of context information; Based on the aforementioned set of contextual information, a predefined multi-step reasoning process is executed to generate event classification and processing allocation recommendations; wherein, each reasoning step of the multi-step reasoning process generates a logical output with supporting evidence; The event classification and the processing allocation suggestion are logically consistent. The abnormal reasoning results are corrected according to the preset business rules, and the verified final processing instructions are output. Based on the final processing instruction, the business management system interface is invoked to automatically create a processing work order, and the work order execution result is fed back.

[0005] Optionally, the step of executing a predefined multi-step reasoning process based on the context information set to generate event rating and processing allocation suggestions includes: Based on business topology relationships and pre-set core business identifiers, determine the scope of impact of operation and maintenance events and whether the operation and maintenance events involve critical business processes. When it is determined that the operation and maintenance event involves a critical business process, the impact of the operation and maintenance event is analyzed by combining performance index data and preset severity judgment criteria, and the judgment results related to the user's perceived impact are output.

[0006] Optionally, the step of logically verifying the consistency between the event classification and the processing allocation suggestion includes: Verify whether the event classification and processing allocation suggestions comply with the preset business rules constraints; wherein, the business rules constraints include that when the operation and maintenance event does not involve a critical business process, its classification shall not be higher than the preset level.

[0007] Optionally, the step of automatically creating a processing work order by calling the business management system interface based on the final processing instruction and feeding back the work order execution result includes: The actual rating results and processing time data generated during the work order execution process are encapsulated into structured feedback information and transmitted to the inference module; The parameters of the inference module are adjusted based on the structured feedback information to optimize the judgment logic in the multi-step inference process.

[0008] Optionally, before acquiring operational data from multiple data sources and standardizing the operational data to form a unified set of context information, the method further includes: By analyzing the changing characteristics of performance metrics and the repetitive patterns in log data, invalid operational events corresponding to temporary fluctuations can be identified and filtered.

[0009] According to a second aspect of this disclosure, an operation and maintenance event handling apparatus is provided, comprising: The acquisition unit is used to acquire operation and maintenance data from multiple data sources and to standardize the operation and maintenance data to form a unified set of context information. The generation unit is used to execute a predefined multi-step reasoning process based on the context information set to generate event classification and processing allocation suggestions; wherein each reasoning step of the multi-step reasoning process generates a logical output with supporting evidence; The verification unit is used to verify the logical consistency between the event classification and the processing allocation suggestion, correct the abnormal reasoning result according to the preset business rules, and output the verified final processing instruction. The feedback unit is used to automatically create a processing work order by calling the business management system interface according to the final processing instruction, and to feed back the work order execution result.

[0010] Optionally, the generation unit is further configured to: Based on business topology relationships and pre-set core business identifiers, determine the scope of impact of operation and maintenance events and whether the operation and maintenance events involve critical business processes. When it is determined that the operation and maintenance event involves a critical business process, the impact of the operation and maintenance event is analyzed by combining performance index data and preset severity judgment criteria, and the judgment results related to the user's perceived impact are output.

[0011] Optionally, the verification unit is further configured to: Verify whether the event classification and processing allocation suggestions comply with the preset business rules constraints; wherein, the business rules constraints include that when the operation and maintenance event does not involve a critical business process, its classification shall not be higher than the preset level.

[0012] Optionally, the feedback unit is further configured to: The actual rating results and processing time data generated during the work order execution process are encapsulated into structured feedback information and transmitted to the inference module; The parameters of the inference module are adjusted based on the structured feedback information to optimize the judgment logic in the multi-step inference process.

[0013] Optionally, the device further includes: The preprocessing unit is used to identify and filter invalid operation and maintenance events corresponding to temporary fluctuations by analyzing the change characteristics of performance indicators and the repetition patterns of log data before the acquisition unit acquires operation and maintenance data from multiple data sources and performs standardized processing on the operation and maintenance data to form a unified set of context information.

[0014] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0015] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0016] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0017] The operation and maintenance event handling method, apparatus, electronic device, and storage medium disclosed herein, through standardized processing to integrate multi-source heterogeneous operation and maintenance data to form unified context information, and generating event classification and handling suggestions with supporting evidence based on a multi-step reasoning process, and ensuring output accuracy through logical consistency verification and business rule correction mechanisms, ultimately achieves automated work order creation and feedback closed loop. Therefore, it can solve the technical problems of rule base requiring downtime for updates, insufficient decision transparency, lack of process closure, and poor adaptability to complex scenarios in the prior art, and achieve the technical effects of improving operation and maintenance event handling efficiency, enhancing decision reliability, and meeting minute-level response requirements.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0019] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is a flowchart illustrating a method for handling maintenance events provided in an embodiment of this disclosure. Figure 2 This is a schematic diagram of the structure of an operation and maintenance event handling device provided in an embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of an operation and maintenance event handling device provided in an embodiment of the present disclosure; Figure 4 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0020] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] The operation and maintenance event handling method, apparatus, electronic device, and storage medium of this disclosure are described below with reference to the accompanying drawings.

[0022] Figure 1 This is a flowchart illustrating a method for handling maintenance events provided in an embodiment of this disclosure.

[0023] like Figure 1 As shown, the method includes the following steps: Step 101: Obtain operation and maintenance data from multiple data sources, and standardize the operation and maintenance data to form a unified set of context information; The data acquisition module communicates with various external data sources (such as performance monitoring systems, log recording platforms, configuration management databases, etc.) through a unified access interface to pull raw operation and maintenance data in real time or near real time. Subsequently, the standardization processing unit uses predefined data models and transformation rules to convert the acquired multi-source heterogeneous data (including but not limited to indicator data, log fragments, change records, and topology information) into a standardized format with consistent structure and machine readability. This generates a contextual information set containing key fields (such as event identifiers, data content, timestamps, and relationships), providing a unified and complete data foundation for subsequent inference and analysis. For example, in a specific application scenario, the data acquisition module can support HTTP / HTTPS protocols to acquire data from tools such as Prometheus or ELK, while the standardization processing unit encapsulates data fields in JSON format to form a contextual information package containing elements such as "event ID," "alarm text," and "indicator list," serving as a feasible implementation method for this step.

[0024] It improves the efficiency and reliability of operation and maintenance data processing. Its multi-source dynamic data acquisition and standardization mechanism ensures the consistency and integrity of input data in subsequent reasoning stages, effectively reducing decision-making biases caused by data format differences or missing information, while also laying a solid foundation for the scalability and adaptability of the automated system.

[0025] Step 102: Based on the set of context information, execute a predefined multi-step reasoning process to generate event classification and processing allocation suggestions; wherein, each reasoning step of the multi-step reasoning process generates a logical output with supporting evidence; After forming a unified set of contextual information, this invention continues to execute a predefined multi-step reasoning process, generating event classification and handling allocation suggestions based on this set of contextual information. The core of this step lies in decomposing the complex event analysis task into multiple interrelated reasoning steps through a structured, sequential logical judgment process. Each step generates a logical output with supporting evidence, thereby constructing a transparent and traceable decision-making path. Specifically, the multi-step reasoning process is driven by a reasoning engine that receives standardized contextual information and performs analysis step-by-step according to a predefined business logic sequence. Each reasoning step is designed to perform a specific logical judgment task—for example, first assessing the scope of an event's impact, then analyzing its degree of impact—each task not only outputs a Boolean value or classification conclusion but also simultaneously generates key evidence data to support that conclusion. This evidence comes directly from the set of contextual information or the output of preceding reasoning steps. Finally, by combining the logical outputs and related evidence from multiple steps, the system comprehensively forms suggestions regarding event priority determination and handling team allocation. As one implementation method, this multi-step reasoning process can be executed by a large language model as the core reasoning engine. The steps can be specifically manifested as "impact scope judgment" and "impact degree assessment" performed sequentially. The judgment result of each step (such as "yes / no" impact on the core link) is accompanied by its reasoning basis (such as the specific performance index values ​​or business topology relationships involved), which together constitute a complete and interpretable rating and distribution recommendation.

[0026] By introducing a structured, evidence-driven, multi-step reasoning process, the transparency and credibility of event grading and distribution decisions are significantly improved. Its mechanism for progressively generating logical outputs and supporting evidence ensures that the final decision possesses good interpretability and auditability, effectively solving the problem of opaque decision-making processes in existing black-box models. Simultaneously, it provides operations and maintenance personnel with clear decision-making basis, enhancing their trust and acceptance of the automated system.

[0027] Step 103: Perform logical consistency verification between the event classification and the processing allocation suggestion, correct the abnormal reasoning result according to the preset business rules, and output the verified final processing instruction. By introducing an independent verification mechanism, the suggestions output by the aforementioned reasoning process are checked and corrected for business logic compliance, ensuring the accuracy and compliance of the final output instruction. Specifically, the verification module receives the event classification and processing allocation suggestions and compares and analyzes them with a pre-set business rule base. This rule base defines the constraints that should be met between event attributes and processing logic, such as certain types of events not being assigned excessively high priorities, or certain processing teams only being responsible for events within a specified scope. During the verification process, the system identifies anomalies in the suggestions that contradict or are inconsistent with these pre-set rules, and automatically adjusts them based on the explicit correction logic in the rule base, ultimately outputting a verified processing instruction that conforms to business specifications. For example, in a specific scenario, the verification module can be implemented based on the Drools rule engine. When an anomaly is found where "non-core link events are judged as the highest priority" conflicts with the "non-core links are prohibited from being classified as P1" rule in the rule base, the system will automatically correct the classification result to an appropriate lower priority, thereby outputting a logically consistent final processing instruction.

[0028] By introducing a rule-driven automatic verification and correction mechanism, the reliability and business compliance of the system output results are significantly improved. This effectively prevents operational errors caused by misjudgments or abnormal outputs from the inference model, ensuring that the final processing instructions remain consistent with the established business logic, thereby enhancing the robustness and reliability of the entire automated decision-making system.

[0029] Step 104: Based on the final processing instruction, call the business management system interface to automatically create a processing work order and feed back the work order execution result.

[0030] The final processing instructions are converted into executable operations of the business management system through an execution layer interface, and a result feedback mechanism is established to optimize system performance. Specifically, the system is equipped with an interface call module. This module receives the final processing instructions, maps the classification parameters, allocation objects, and event description information contained therein to standardized operation instructions supported by the downstream business management system, and automatically initiates an interface call to create the corresponding processing work order. Subsequently, the system continuously monitors the processing status of the work order through a closed-loop feedback module, collects execution data including actual classification confirmation, resolution time, and processing results, and sends this data back to the system's analysis and inference module as feedback information. For example, in a specific application scenario, the interface call module can be adapted to the ITSM system, converting instructions into API request parameters for creating work orders, while the feedback module periodically pulls work order status updates from the ITSM system to form training data for model optimization.

[0031] By automating the conversion of instructions into work orders and providing feedback on execution results, a complete closed loop for operation and maintenance event handling has been established. This significantly reduces manual intervention, greatly improves the efficiency of event response and handling, and provides a data foundation for the system's self-optimization of reasoning capabilities through continuous feedback data collection, thereby continuously enhancing the accuracy and adaptability of the entire automated processing system.

[0032] Optionally, the step of executing a predefined multi-step reasoning process based on the context information set to generate event rating and processing allocation suggestions includes: Based on business topology relationships and pre-set core business identifiers, determine the scope of impact of operation and maintenance events and whether the operation and maintenance events involve critical business processes. When it is determined that the operation and maintenance event involves a critical business process, the impact of the operation and maintenance event is analyzed by combining performance index data and preset severity judgment criteria, and the judgment results related to the user's perceived impact are output.

[0033] The inference engine first extracts business topology relationship data from the standardized context information set. This data originates from the configuration management database and includes dependencies between system components. Simultaneously, it loads a pre-set list of core business identifiers, stored in configurable JSON format, clearly marking unique identifiers for critical business paths such as "QH-001: API Gateway - QH Cluster → QH step1". The system performs pattern matching between the topology paths involved in the current maintenance event and the core business identifiers. If the component associated with the event exists in any core business path, it is determined to affect a critical business process, and a Boolean judgment result with specific matching path evidence is output. After determining the impact on critical business processes, the impact degree analysis step is performed as follows: The system filters key performance indicator data from the context information set, including response latency, error rate, and service success rate, and compares them with pre-set severity judgment criteria. These criteria are stored in the business rule base in the form of thresholds, for example, specifying that "a service success rate below 95% is considered a serious impact". By quantitatively calculating the deviation between the actual indicators and the thresholds, the system outputs a judgment conclusion on whether the user-perceived impact is serious, along with specific indicator numerical comparisons as evidence. In one specific embodiment, when processing the "API Gateway-QH Cluster High Latency" event, the system confirms that it belongs to the core business identifier "QH-001" by matching the topology path, and then calculates the severity threshold that the actual success rate is 80% lower than 95%, thereby outputting a judgment result that the user perceives the impact as severe.

[0034] Through precise topology matching and quantitative indicator analysis, the accuracy and objectivity of critical business impact assessment are ensured. Configurable core business identifiers and severity standards enable the system to flexibly adapt to the assessment needs of different business scenarios. Furthermore, by outputting assessment results with concrete evidence, it provides a reliable basis for subsequent grading decisions, effectively improving the accuracy and efficiency of operational event handling.

[0035] Optionally, the step of logically verifying the consistency between the event classification and the processing allocation suggestion includes: Verify whether the event classification and processing allocation suggestions comply with the preset business rules constraints; wherein, the business rules constraints include that when the operation and maintenance event does not involve a critical business process, its classification shall not be higher than the preset level.

[0036] The rules engine module loads a pre-built business rules library, which explicitly stipulates the constraint that "when an operational event does not involve a critical business process, its classification must not exceed the preset level P2." During the verification process, the rules engine receives output results from a multi-step inference process, including the impact scope determination conclusion and preliminary classification suggestion. The system will automatically trigger the check logic for this constraint based on whether the impact scope determination conclusion is "non-critical business process." If the event classification suggestion is also detected to be level P1, a rule conflict is identified. At this time, the rules engine will automatically adjust the classification result to an appropriate level not higher than P2 based on the pre-built correction strategy. In a specific embodiment, the rules engine is implemented using Drools. When it receives the input "impact scope: non-core link, classification suggestion: P1", the rules engine executes the corresponding correction rule in its rules library, automatically downgrades the classification result to P2, and generates detailed logs of the rule trigger as verification evidence.

[0037] By introducing explicit business rules and an automated conflict detection mechanism, the system effectively prevents the escalation of non-critical events. This ensures consistency between event classification results and business logic, avoids resource waste and priority mismatch, and reduces the need for manual intervention through automatic correction mechanisms, significantly improving the accuracy and efficiency of the event handling process.

[0038] Optionally, the step of automatically creating a processing work order by calling the business management system interface based on the final processing instruction and feeding back the work order execution result includes: The actual rating results and processing time data generated during the work order execution process are encapsulated into structured feedback information and transmitted to the inference module; The parameters of the inference module are adjusted based on the structured feedback information to optimize the judgment logic in the multi-step inference process.

[0039] This module continuously monitors the status changes of created work orders in the business management system. When a work order is marked as "resolved," it automatically collects key data, including the actual confirmed grading result, the total processing time from creation to resolution, and the final assigned processing team. This data is then encapsulated in a predefined structured format to form a JSON data packet containing the fields "actual_severity," "resolution_duration," and "assigned_team," which is transmitted to the large model module in the inference layer via an internal message queue or REST API interface. During the parameter optimization phase, the system periodically (e.g., weekly) compares the accumulated structured feedback information with the original inference records. Based on indicators such as the difference between the actual grading result and the original recommendation, and the deviation between the processing time and the expected standard, a training dataset containing positive and negative samples is constructed. These datasets are used to incrementally fine-tune the large model, specifically by adjusting the embedded judgment logic parameters, such as correcting the threshold sensitivity in the impact determination or optimizing the weight coefficients of business topology associations. This ensures that the judgment logic in the multi-step inference process continuously approximates the optimal decision-making mode for the actual business scenario.

[0040] By establishing a data-driven closed-loop optimization mechanism, the system can continuously learn and improve itself from actual processing results. This effectively improves the accuracy and business adaptability of multi-step reasoning processes, significantly reduces the false judgment rate, and reduces the workload of manual tuning through parameter self-adjustment mechanisms, ensuring the system's long-term intelligence level and processing efficiency.

[0041] Optionally, before acquiring operational data from multiple data sources and standardizing the operational data to form a unified set of context information, the method further includes: By analyzing the changing characteristics of performance metrics and the repetitive patterns in log data, invalid operational events corresponding to temporary fluctuations can be identified and filtered.

[0042] Before data acquisition and standardization, the system uses a pre-filtering module to identify the validity of raw operation and maintenance events. This module processes time-series metric data from the performance monitoring platform and text data from the log collection system in parallel. It uses a sliding window algorithm to analyze the changing characteristics of performance metrics, calculates the variance and short-term trend slope of metric values ​​within a specified time window, and marks metric fluctuations as temporary fluctuations when the fluctuation amplitude is below a preset threshold and shows rapid recovery characteristics. Simultaneously, it performs natural language processing and pattern matching on log data to identify log entries containing specific keywords such as "temporary interruption" and "network jitter," and uses a repetition pattern detection algorithm to identify identical error messages that appear repeatedly within a short period. When both the performance metric fluctuation characteristics and the log repetition pattern meet the invalid event criteria, the system marks the operation and maintenance event as invalid and filters it, preventing it from entering the subsequent standardization process. In one specific embodiment, the system sets a 60-second sliding window to monitor API latency metrics. When a latency peak duration of less than 30 seconds is detected and accompanied by a "network momentary interruption" log entry, the event is automatically classified as an invalid operation and maintenance event and discarded.

[0043] By effectively identifying and filtering temporary fluctuation events through multi-dimensional feature analysis, the system's processing load and false alarm rate are significantly reduced. This effectively prevents invalid events from entering subsequent analysis processes, thus avoiding resource waste and improving the efficiency and accuracy of the entire event processing pipeline. Simultaneously, it ensures that critical business events receive timely and focused processing resources.

[0044] Corresponding to the above-described operation and maintenance event handling method, this invention also proposes an operation and maintenance event handling device. Since the device embodiment of this invention corresponds to the above-described method embodiment, details not disclosed in the device embodiment can be referred to the above-described method embodiment, and will not be repeated here.

[0045] Figure 2 This is a schematic diagram of the structure of an operation and maintenance event handling device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: The acquisition unit 21 is used to acquire operation and maintenance data from multiple data sources and to standardize the operation and maintenance data to form a unified set of context information. The generation unit 22 is used to execute a predefined multi-step reasoning process based on the context information set to generate event classification and processing allocation suggestions; wherein each reasoning step of the multi-step reasoning process generates a logical output with supporting evidence; Verification unit 23 is used to perform logical consistency verification between the event classification and the processing allocation suggestion, correct the abnormal reasoning result according to the preset business rules, and output the verified final processing instruction. Feedback unit 24 is used to automatically create a processing work order by calling the business management system interface according to the final processing instruction, and to feed back the work order execution result.

[0046] Furthermore, in one possible implementation of this disclosure embodiment, the generation unit 22 is further configured to: Based on business topology relationships and pre-set core business identifiers, determine the scope of impact of operation and maintenance events and whether the operation and maintenance events involve critical business processes. When it is determined that the operation and maintenance event involves a critical business process, the impact of the operation and maintenance event is analyzed by combining performance index data and preset severity judgment criteria, and the judgment results related to the user's perceived impact are output.

[0047] Furthermore, in one possible implementation of this disclosure, the verification unit 23 is further configured to: Verify whether the event classification and processing allocation suggestions comply with the preset business rules constraints; wherein, the business rules constraints include that when the operation and maintenance event does not involve a critical business process, its classification shall not be higher than the preset level.

[0048] Furthermore, in one possible implementation of this disclosure, the feedback unit 24 is further configured to: The actual rating results and processing time data generated during the work order execution process are encapsulated into structured feedback information and transmitted to the inference module; The parameters of the inference module are adjusted based on the structured feedback information to optimize the judgment logic in the multi-step inference process.

[0049] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, the device further includes: The preprocessing unit 25 is used to identify and filter invalid operation and maintenance events corresponding to temporary fluctuations by analyzing the changing characteristics of performance indicators and the repetitive patterns of log data before the acquisition unit acquires operation and maintenance data from multiple data sources and performs standardized processing on the operation and maintenance data to form a unified set of context information.

[0050] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0051] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0052] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0053] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0054] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0055] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as maintenance event handling methods. For example, in some embodiments, the maintenance event handling method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned operation and maintenance event handling method by any other suitable means (e.g., by means of firmware).

[0056] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0057] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0058] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0059] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0060] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0061] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0062] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0063] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0064] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An operation and maintenance event processing method, characterized in that, The method comprises the following steps: obtaining operation and maintenance data from multiple data sources, and performing standardization processing on the operation and maintenance data to form a unified context information set; based on the context information set, a pre-defined multi-step reasoning process is executed to generate event grading and processing allocation suggestions; wherein each reasoning step of the multi-step reasoning process generates logical output with supporting evidence; logical consistency verification is performed on the event grading and the processing allocation suggestions, abnormal reasoning results are corrected according to pre-set business rules, and a final processing instruction is outputted after verification; a business management system interface is called to automatically create a processing work order according to the final processing instruction, and the work order execution result is fed back.

2. The method of claim 1, wherein, The method further comprises the following steps before obtaining operation and maintenance data from multiple data sources, and performing standardization processing on the operation and maintenance data to form a unified context information set: temporarily fluctuation corresponding invalid operation and maintenance events are identified and filtered by analyzing the change characteristics of performance indicators and the repetition mode of log data. The method comprises the following steps:

3. The method of claim 1, wherein, an obtaining unit is configured to obtain operation and maintenance data from multiple data sources, and perform standardization processing on the operation and maintenance data to form a unified context information set; a generating unit is configured to execute a pre-defined multi-step reasoning process based on the context information set to generate event grading and processing allocation suggestions; wherein each reasoning step of the multi-step reasoning process generates logical output with supporting evidence; 4. The method of claim 1, wherein, a verifying unit is configured to perform logical consistency verification on the event grading and the processing allocation suggestions, correct abnormal reasoning results according to pre-set business rules, and output a final processing instruction after verification; a feedback unit is configured to call a business management system interface to automatically create a processing work order according to the final processing instruction, and feed back the work order execution result. The generating unit is further configured to:

5. The method of claim 1, wherein, ​ ​ 6. An operation and maintenance event processing apparatus, characterized by comprising: ​ ​ ​ ​ ​ 7. The apparatus of claim 6, wherein, ​ Determine the influence range of the operation and maintenance event based on the business topology relationship and the preset core business identifier, and determine whether the operation and maintenance event involves a key business process; When it is determined that the operation and maintenance event involves a key business process, analyze the influence degree of the operation and maintenance event in combination with the performance index data and the preset severity determination standard, and output a judgment result related to user perception influence.

8. An electronic device, comprising: Comprise: At least one processor; And The memory is in communication connection with the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method of any one of claims 1-5.

9. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to execute the method according to any one of claims 1-5.

10. A computer program product, characterised in that, Comprise a computer program, which realizes the method according to any one of claims 1-5 when executed by a processor.

Images