Abnormal repair method, device and system, electronic equipment and storage medium

Abstract

The invention provides an exception repair method, device and system, electronic equipment and a computer readable storage medium, and relates to the technical field of computers. The exception repairing method comprises the following steps: acquiring system data; inputting the system data into an anomaly detection neural network to obtain system anomaly information; wherein the system exception information is used for representing system exception corresponding to the system data; and repairing the corresponding system exception based on the system exception information. According to the invention, the system abnormity and potential risks are automatically identified through the abnormity detection neural network, the dependence on manual threshold setting is reduced, and the accuracy and timeliness of abnormity detection are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an abnormality repair method, device, system, electronic device and computer-readable storage medium. Background Art

[0002] With the development of information technology and the popularization of the Internet, modern computing systems are becoming increasingly complex and distributed. The widespread application of cloud computing, microservice architecture, and containerization technology has led to a sharp increase in the number of system components, and the interactions between these components have become more frequent and complex. Although these technologies have brought significant flexibility and scalability to the system, they have also introduced new challenges, especially in service anomaly detection and analysis.

[0003] In the related technologies, the anomaly detection and analysis of system services are mainly carried out through log analysis, performance monitoring or distributed tracing methods. However, the above methods are based on simple rules and threshold settings, and lack intelligent anomaly detection and prediction capabilities. Summary of the invention

[0004] According to a first aspect of the present disclosure, there is provided an exception repair method, comprising: acquiring system data; inputting the system data into an exception detection neural network to obtain system exception information; wherein the system exception information is used to characterize the system exception corresponding to the system data; and repairing the corresponding system exception based on the system exception information.

[0005] According to a second aspect of the present disclosure, there is provided an abnormality repair device, comprising: an acquisition module for acquiring system data; a detection module for inputting the system data into an abnormality detection neural network to obtain system abnormality information; wherein the system abnormality information is used to characterize the system abnormality corresponding to the system data; and a repair module for repairing the corresponding system abnormality based on the system abnormality information.

[0006] According to a third aspect of the present disclosure, an abnormality repair system is provided, the abnormality repair system includes a data collection unit, a real-time analysis unit, an intelligent analysis unit and a user interface unit, the user interface unit includes a monitoring subunit and an interface subunit; wherein: the data collection unit is used to obtain system data and transmit the system data to the real-time analysis unit; the system data includes log data, performance indicator data and distributed tracking data; the real-time analysis unit is used to receive the system data transmitted by the data collection unit, locate system abnormalities based on the system information, generate system abnormality information, and transmit the system abnormality information to the intelligent analysis unit and the monitoring subunit; the interface subunit is used to obtain the system abnormality information from the monitoring subunit in real time; and repair the system abnormality corresponding to the system abnormality information; the monitoring subunit is used to receive the system abnormality information transmitted by the real-time analysis unit; and transmit the system abnormality information to the interface subunit and the intelligent analysis unit; the intelligent analysis unit is used to receive the system abnormality information transmitted by the real-time analysis unit and the monitoring subunit, and obtain an abnormality detection neural network based on the system abnormality information. The abnormality detection neural network is used to detect the system abnormality.

[0007] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to perform the above-mentioned abnormality repair method.

[0008] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned abnormality repair method.

[0009] The exemplary embodiments of the present disclosure may have some or all of the following beneficial effects:

[0010] In the anomaly repair method provided in the exemplary implementation of the present disclosure, system data is obtained; the system data is input into an anomaly detection neural network to obtain system anomaly information; wherein the system anomaly information is used to characterize the system anomaly corresponding to the system data; and the corresponding system anomaly is repaired based on the system anomaly information. By obtaining system data and inputting the system data into an anomaly detection neural network, the embodiment of the present disclosure can automatically identify system anomalies and potential risks through the anomaly detection neural network, and repair the corresponding system anomalies, thereby reducing the reliance on manually set thresholds and improving the accuracy and timeliness of anomaly detection.

[0011] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Further details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0013] Figure 1 A flowchart of an abnormality repair method according to an exemplary embodiment of the present disclosure is shown;

[0014] Figure 2 A schematic block diagram of an abnormality repairing device according to an exemplary embodiment of the present disclosure is shown;

[0015] Figure 3 A schematic block diagram of an abnormality repair system according to an exemplary embodiment of the present disclosure is shown;

[0016] Figure 4 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0019] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] System anomaly detection is an important means to ensure the stable operation and security of the system. It involves continuous monitoring and analysis of the system operation status in order to promptly discover and handle abnormal situations. Related technologies mainly achieve system anomaly detection and analysis through the following methods:

[0023] Log analysis: Detect and locate anomalies by collecting and analyzing system logs. This method relies on the comprehensiveness and accuracy of logs, but when faced with large-scale systems, the log volume is huge, manual analysis is inefficient and key information is easily missed.

[0024] Performance monitoring: Use performance monitoring tools to collect system indicator data and detect anomalies by setting thresholds. This method is simple and intuitive, but it is difficult to handle complex anomaly patterns and multi-dimensional data associations.

[0025] Distributed tracing: Use distributed tracing technology to monitor and analyze the flow path of requests to help locate performance bottlenecks and anomalies. This method has high implementation and maintenance costs in large-scale systems, and has limited real-time analysis capabilities for tracing data.

[0026] However, the above method is based on simple rules and threshold settings, and lacks intelligent anomaly detection and prediction capabilities. In order to solve the above problems, the embodiments of the present disclosure provide an anomaly repair method, device, system, electronic device and computer-readable storage medium. The following describes the scheme of the present disclosure with reference to the accompanying drawings for illustration.

[0027] The present disclosure first provides an abnormality repair method. Figure 1 As shown, the abnormality repair method specifically includes the following steps:

[0028] S110: Obtain system data;

[0029] S120: Inputting the system data into the anomaly detection neural network to obtain system anomaly information; wherein the system anomaly information is used to characterize the system anomaly corresponding to the system data;

[0030] S130: Repair the corresponding system abnormality based on the system abnormality information.

[0031] In the anomaly repair method provided in the embodiment of the present disclosure, by acquiring system data and inputting the system data into the anomaly detection neural network, the anomaly detection neural network can automatically identify system anomalies and potential risks, and repair the corresponding system anomalies, thereby reducing the reliance on manually set thresholds and improving the accuracy and timeliness of anomaly detection.

[0032] Next, in another embodiment, the above steps are described in more detail.

[0033] In step S110 , system data is acquired.

[0034] In the embodiment of the present application, the above-mentioned system data is data processed, stored and generated during the operation of the system, covering various information in the electronic device or computer system.

[0035] In the embodiment of the present application, the above-mentioned system data can be in various forms such as numbers, text, images, audio or video.

[0036] In an embodiment of the present application, the above-mentioned system data may include log data, performance indicator data and distributed tracking data.

[0037] In the embodiment of the present application, the above log data records the system's operating status, user operations, errors and exceptions, etc. By analyzing these data, problems in the system can be discovered and solved in a timely manner to ensure the stability and reliability of the system. Exemplarily, the above log data can be obtained from the system log.

[0038] In the embodiment of the present application, the above performance indicator data is used to characterize system performance. For example, the above performance indicator data may include data such as response time, throughput, resource utilization, reliability, and security.

[0039] In an embodiment of the present application, the above-mentioned distributed tracing data can be obtained based on distributed tracing technology. Among them, the above-mentioned distributed tracing technology records the propagation process of requests between various services by tracking the call relationship between various services in the system, thereby realizing full-link monitoring.

[0040] In an embodiment of the present application, the acquisition of system data can be implemented as follows: acquiring multi-source system data including log data, performance indicator data and distributed tracing data. Exemplarily, the log data can be acquired by reading system log files (such as application log files, etc.), and the log files can be collected in real time through the system log service; the performance indicator data can be acquired through a performance monitoring tool, and the performance monitoring tool will continuously monitor the system's central processing unit (CPU), memory, disk usage, etc., store the acquired real-time performance indicators of the system in a database, and provide a query interface; the acquisition of the distributed tracing data can be implemented as follows: acquiring the call link data between each microservice through a distributed tracing system. Specifically, the distributed tracing system embeds tracing information in the request link between each service through an interceptor, and provides a query interface.

[0041] In an embodiment of the present application, by fusing multi-source data including the above-mentioned log data, performance indicator data and distributed tracking data, a more comprehensive system status view can be provided, thereby improving the accuracy of anomaly detection and positioning.

[0042] In an embodiment of the present application, after the system data is acquired, the acquired system data may also be preprocessed. Exemplarily, the above-mentioned data preprocessing process may include operations such as data cleaning, format conversion, and data aggregation. Exemplarily, the above-mentioned data aggregation process may be implemented as follows: cleaning, formatting, and fusing log data, performance indicator data, and distributed tracing data. Specifically, the above-mentioned log data, performance indicator data, and distributed tracing data may be aggregated in real time through a data processing framework, and stored in a unified data platform for subsequent query and analysis.

[0043] In step S120, the system data is input into the anomaly detection neural network to obtain system anomaly information; wherein the system anomaly information is used to characterize the system anomaly corresponding to the system data.

[0044] In an embodiment of the present application, the above-mentioned anomaly detection neural network is used to detect and predict system anomalies based on the acquired system data.

[0045] In an embodiment of the present application, the anomaly detection neural network can be trained based on historical system data. Exemplarily, the training process of the anomaly detection neural network can be implemented as follows: acquiring historical system data; and training the anomaly detection neural network based on the historical system data.

[0046] Specifically, the system anomaly can be located through the log data, performance indicator data and distributed tracking data in the above historical system data, and the corresponding anomaly data can be obtained. Exemplarily, the above anomaly data can include the error code corresponding to the system anomaly; the anomaly data determined from the historical system data is used as a training data set to train the network parameters of the neural network to obtain the above anomaly detection neural network. Among them, the above training data can include historical system log data, performance indicator data, distributed tracking data. Specifically, the above historical system log data, performance indicator data, distributed tracking data, etc. can be used as training data, and the abnormal mark can be set manually, or the label corresponding to the training data can be generated based on the system crash or error event in the historical data; the network parameters of the neural network are trained based on the training data and the label to obtain the above anomaly detection neural network. Furthermore, during the training process, correction functions such as the cross entropy loss function or the mean square error (MSE) can be used to optimize the network parameters, and the model's perception of important abnormal patterns can also be enhanced by introducing mechanisms such as attention mechanisms; at the same time, the training effect can be improved by adaptive learning rates.

[0047] In the embodiment of the present application, the above-mentioned anomaly detection neural network is trained by machine learning and deep learning algorithms, and intelligent anomaly detection and prediction are realized based on the above-mentioned anomaly detection neural network. The above-mentioned anomaly detection neural network can automatically identify abnormal patterns and potential risks through the analysis of historical data and real-time data, reducing the dependence on manually set thresholds and improving the accuracy and timeliness of anomaly detection.

[0048] In the embodiment of the present application, the system abnormality information is used to characterize the system abnormality corresponding to the system data. Exemplarily, the system abnormality information may include an error code corresponding to the system and a system location where the abnormality occurs.

[0049] In an embodiment of the present application, the above process of inputting system data into an anomaly detection neural network to obtain system anomaly information can be implemented, illustratively, as follows: real-time monitoring of abnormal data in the system data; inputting the abnormal data into the anomaly detection neural network to generate system anomaly information.

[0050] In an embodiment of the present application, the abnormal data in the above-mentioned real-time monitoring system data can be implemented based on stream processing technology. Stream processing is a big data processing technology used to process continuous data streams. Stream processing technology can quickly detect abnormal conditions within a short time of receiving the data. Exemplarily, the process of real-time monitoring of abnormal data based on the above-mentioned stream processing technology can be implemented as follows: based on the stream processing framework, real-time processing of data streams from the log system, performance monitoring system, and distributed tracking system. When an abnormal pattern is detected (such as abnormal system load, increased delay), an alarm is immediately triggered or a corresponding repair operation is performed.

[0051] In an embodiment of the present application, when abnormal data is detected in the system data, system abnormality alarm information can also be generated. Exemplarily, the abnormality repair method provided in the embodiment of the present application can query the data stream from the temperature sensor in the system through the above-mentioned stream processing technology, and when the temperature reaches the freezing point, the above-mentioned system abnormality alarm information can be generated. Among them, the above-mentioned system abnormality alarm information can be a combination of one or more prompting methods such as voice prompts and pop-up window prompts, and the embodiment of the present application does not make special restrictions on this.

[0052] In the embodiments of the present application, by adopting technologies such as stream processing, the processing and analysis of real-time data in a large-scale distributed system is achieved. By monitoring and analyzing real-time stream data, abnormal situations in the system can be discovered in a timely manner and responded to quickly, reducing the impact of abnormalities on system stability.

[0053] In step S130, the corresponding system abnormality is repaired based on the system abnormality information.

[0054] In an embodiment of the present application, after obtaining system abnormality information through the above-mentioned abnormality detection neural network, the corresponding system abnormality can be repaired based on the system abnormality information.

[0055] In the embodiment of the present application, the user can interact with the system through the user interface to implement the above-mentioned repair of the corresponding system anomaly based on the system anomaly information. The above-mentioned user interface is an interactive interface between the user and the system, which supports user-defined monitoring panels and alarm strategy configurations. The user can flexibly configure monitoring indicators and alarm rules according to their own needs, thereby simplifying the operation process and improving operation efficiency.

[0056] In an embodiment of the present application, the above-mentioned repair of the corresponding system anomaly based on the system anomaly information can be implemented as follows, for example: displaying the system anomaly data and the system anomaly information to the user through the user interface; and repairing the system anomaly corresponding to the system anomaly information in response to the repair operation performed by the user on the user interface.

[0057] In an embodiment of the present application, the above-mentioned display of system abnormality data and system abnormality information to the user through the user interface can be implemented as follows: receiving a data request from the user to obtain abnormal data in real time on the user interface; in response to the data request, displaying the abnormal data and system abnormality information on the user interface. Exemplarily, when a trigger operation is received from the user on the abnormal query control, the error code obtained by real-time monitoring of the system data and the specific error information obtained by analyzing the error code through the abnormal detection neural network can be displayed on the user interface. The embodiment of the present application helps users quickly understand the causes and effects of system abnormalities by providing users with detailed abnormality analysis reports.

[0058] In an embodiment of the present application, the above-mentioned response to the repair operation performed by the user on the user interface repairs the system anomaly corresponding to the system anomaly information. Exemplarily, it can be implemented as follows: if the user can locate the system anomaly based on the above-mentioned abnormal data and the system anomaly information, the system anomaly can be repaired by triggering the corresponding repair control, and the system is updated and restarted; if the user cannot locate the system anomaly based on the above-mentioned abnormal data and the system anomaly information, it is necessary to locate the system anomaly by further checking the upper and lower related logs, and then repair the system anomaly by triggering the corresponding repair control, and update and restart the system.

[0059] In the embodiments of the present application, distributed storage technology can also be used to store large-scale system historical data and real-time data, and provide data query and retrieval functions to ensure data availability and consistency, so that good performance and processing capabilities can be maintained in scenarios with massive data and complex systems, ensuring stable operation of the system at various scales.

[0060] In the anomaly repair method provided in the embodiment of the present disclosure, by acquiring system data and inputting the system data into the anomaly detection neural network, the anomaly detection neural network can automatically identify system anomalies and potential risks, and repair the corresponding system anomalies, thereby reducing the reliance on manually set thresholds and improving the accuracy and timeliness of anomaly detection.

[0061] The above mainly introduces the solution provided by the embodiment of the present invention from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0062] The embodiment of the present invention can divide the functional modules of the abnormal repair device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0063] The present disclosure provides an abnormality repair device. Figure 2 As shown, the abnormality repair device 200 may include an acquisition module 210, a detection module 220 and a repair module 230, wherein:

[0064] Acquisition module, used to obtain system data;

[0065] A detection module is used to input the system data into the anomaly detection neural network to obtain system anomaly information; wherein the system anomaly information is used to characterize the system anomaly corresponding to the system data;

[0066] The repair module is used to repair the corresponding system anomaly based on the system anomaly information.

[0067] In an embodiment of the present application, the above-mentioned system data includes log data, performance indicator data and distributed tracking data.

[0068] In the embodiment of the present application, the above-mentioned detection module is specifically used for: real-time monitoring of abnormal data in system data; inputting the abnormal data into the abnormal detection neural network to generate system abnormality information.

[0069] In an embodiment of the present application, the above-mentioned abnormality repair device also includes an alarm module, which is specifically used to generate system abnormality alarm information when abnormal data is detected in the system data.

[0070] In an embodiment of the present application, the above-mentioned repair module is specifically used to: display system abnormality data and system abnormality information to the user through the user interface; and repair the system abnormality corresponding to the system abnormality information in response to the user's repair operation on the user interface.

[0071] In an embodiment of the present application, the above-mentioned anomaly repair device also includes a model training module, which is specifically used to: obtain historical system data; and train an anomaly detection neural network based on the historical system data.

[0072] In addition, the specific implementation details of the above-mentioned abnormality repair device have been described in detail in the corresponding position of the abnormality repair method, so they will not be repeated here.

[0073] Related technologies mainly detect and analyze anomalies of system services through log analysis, performance monitoring or distributed tracing methods. The above methods have the following problems: single data source: many tools can only process a single data source and cannot integrate multi-source data, resulting in insufficient accuracy and comprehensiveness of anomaly positioning; poor real-time performance: existing technologies have delays in data processing and analysis and cannot achieve real-time anomaly detection and response; insufficient scalability: as the scale of the system expands, the performance and processing capabilities of existing tools are difficult to meet the needs; low level of intelligence: most tools rely on simple rules and thresholds and lack intelligent anomaly detection and prediction capabilities.

[0074] In order to solve the above problems, the present disclosure also provides an abnormality repair system, such as Figure 3 As shown, the above-mentioned abnormality repair system includes a data collection unit, a real-time analysis unit, an intelligent analysis unit and a user interface unit, and the above-mentioned user interface unit includes a monitoring subunit and an interface subunit; wherein:

[0075] The data collection unit is used to obtain system data and transmit the system data to the real-time analysis unit; the system data includes log data, performance indicator data and distributed tracking data;

[0076] The real-time analysis unit is used to receive the system data transmitted by the data collection unit, locate the system abnormality based on the system information, generate the system abnormality information, and transmit the system abnormality information to the intelligent analysis unit and the monitoring subunit;

[0077] The above-mentioned interface subunit is used to obtain system abnormality information from the monitoring subunit in real time; and to repair the system abnormality corresponding to the system abnormality information;

[0078] The monitoring subunit is used to receive the system abnormality information transmitted by the real-time analysis unit; and transmit the system abnormality information to the interface subunit and the intelligent analysis unit;

[0079] The intelligent analysis unit is used to receive system anomaly information transmitted by the real-time analysis unit and the monitoring subunit, and to obtain an anomaly detection neural network based on the system anomaly information training. The anomaly detection neural network is used to detect system anomalies.

[0080] In an embodiment of the present application, the data collection unit is responsible for collecting data from different data sources (such as logs, indicators, and tracking data) and performing preprocessing. Preprocessing includes operations such as data cleaning, format conversion, and data aggregation. Exemplarily, log data can be obtained from system logs; the system performance indicator data can be collected based on performance monitoring tools; and distributed tracking data can be obtained based on distributed tracking technology.

[0081] In the embodiment of the present application, the data collection unit comprehensively collects and analyzes data from multiple data sources, including log data, performance indicators, distributed tracking data, etc. Through the fusion of multi-source data, the anomaly repair system can provide a more comprehensive system status view, thereby improving the accuracy of anomaly detection and location.

[0082] In the embodiment of the present application, the real-time analysis unit uses stream processing technology to process and analyze real-time data. The real-time analysis unit can detect anomalies in real-time data and generate real-time alarm information.

[0083] In the embodiment of the present application, the above-mentioned real-time analysis unit adopts advanced stream processing technology to realize real-time data processing and analysis of large-scale distributed systems. By monitoring and analyzing real-time stream data through the above process, abnormal situations in the system can be discovered in time and responded to quickly, reducing the impact of abnormalities on system stability.

[0084] In the embodiment of the present application, the intelligent analysis unit trains historical data based on machine learning and deep learning algorithms to generate an anomaly detection model. The intelligent analysis unit can use the trained model to perform intelligent anomaly detection and prediction on real-time data.

[0085] Exemplarily, the training process of the above anomaly detection model can be implemented as follows: obtain historical system data; train the anomaly detection model based on the historical system data. Specifically, the system anomaly can be located through the log data, performance indicator data and distributed tracking data in the above historical system data, and the corresponding anomaly data can be obtained. Exemplarily, the above anomaly data can include the error code corresponding to the system anomaly; the anomaly data determined from the historical system data is used as a training data set to train the network parameters of the neural network to obtain the above anomaly detection model.

[0086] In the embodiment of the present application, the intelligent analysis unit uses machine learning and deep learning algorithms to achieve intelligent anomaly detection and prediction. Through the analysis of historical data and real-time data, the anomaly repair system can automatically identify abnormal patterns and potential risks, reduce the reliance on manually set thresholds, and improve the accuracy and timeliness of anomaly detection.

[0087] In the embodiment of the present application, the user interface unit provides an intuitive and easy-to-use user interface, supports custom monitoring panels and alarm policy configuration, and users can view real-time monitoring data, historical data and abnormal analysis reports through the interface.

[0088] In an embodiment of the present application, the above-mentioned exception repair system can display the system exception data and system exception information to the user based on the above-mentioned user interface unit. Exemplarily, it can be implemented as follows: receiving a data request from a user to obtain exception data in real time on the user interface; in response to the data request, displaying the exception data and system exception information on the user interface. Exemplarily, when a trigger operation is received from a user on an exception query control, the error code obtained by real-time monitoring of the system data and the specific error information obtained by analyzing the error code through an anomaly detection neural network can be displayed on the user interface. Among them, the above-mentioned error code is usually a simple identifier used to represent a specific type of error. For example, error code 500 indicates an internal server error; the above-mentioned specific error information is a detailed explanation of the error code. For example, for error code 500, the specific error information may be "database connection failure" or "service timeout", etc.

[0089] In an embodiment of the present application, if the user can locate the system anomaly based on the above-mentioned abnormal data and system abnormal information, the system anomaly can be repaired by triggering the corresponding repair control, and the system is updated and restarted; if the user cannot locate the system anomaly based on the above-mentioned abnormal data and system abnormal information, it is necessary to locate the system anomaly by further checking the upper and lower associated logs, and then repair the system anomaly by triggering the corresponding repair control, and update and restart the system. In an embodiment of the present application, illustratively, the above-mentioned positioning of the system anomaly based on the abnormal data and system abnormal information can be implemented based on the error code. For example, error code 503 usually indicates that the service is unavailable, which may occur at the load balancer or the entry gateway of the service; when the error code cannot clearly locate the problem, the user can further investigate by analyzing the contextual system logs and tracking data to determine the specific source of the anomaly.

[0090] In the embodiment of the present application, the user interface unit provides an intuitive and easy-to-use user interface, and supports custom monitoring panels and alarm policy configuration. Users can flexibly configure monitoring indicators and alarm rules according to their own needs, thereby simplifying the operation process and improving operation efficiency. In addition, the abnormality repair system can also provide a detailed abnormality analysis report based on the user interface unit to help users quickly understand the causes and effects of the abnormality.

[0091] In an embodiment of the present application, the above-mentioned abnormality repair system may further include a storage management unit. The storage management unit uses distributed storage technology to store large-scale historical data and real-time data. The storage management unit supports efficient data query and retrieval to ensure data availability and consistency.

[0092] In the embodiment of the present application, the storage management unit adopts a highly scalable distributed system architecture design, which can support the processing and storage of large-scale data. Through distributed computing and storage technology, the abnormality repair system can still maintain good performance and processing capabilities when facing massive data and complex systems, ensuring the stable operation of the system at various scales.

[0093] The anomaly repair system provided in the embodiment of the present application realizes efficient, accurate and intelligent positioning and analysis of service anomalies in a distributed system through multi-source data fusion, real-time analysis, high-scalability architecture and intelligent anomaly detection.

[0094] It should be noted that the specific implementation details of the above-mentioned exception repair system have been described in detail in the corresponding position of the exception repair method, so they will not be repeated here.

[0095] Figure 4 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 4 , which shows a structural schematic diagram of an electronic device 400 suitable for implementing the embodiments of the present disclosure. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0096] like Figure 4 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 to a random access memory (RAM) 403 to implement the voice control method of the embodiment described in the present disclosure. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0097] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0098] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the voice control method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0099] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0100] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0101] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0102] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0103] Get system data;

[0104] Input the system data into the anomaly detection neural network to obtain system anomaly information; wherein the system anomaly information is used to characterize the system anomaly corresponding to the system data;

[0105] Repair the corresponding system exception based on the system exception information.

[0106] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0107] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0108] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0110] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0111] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0113] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0114] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An abnormality repair method, characterized in that: include: Get system data; Inputting the system data into an anomaly detection neural network to obtain system anomaly information; wherein the system anomaly information is used to characterize the system anomaly corresponding to the system data; The corresponding system abnormality is repaired based on the system abnormality information.

2. The abnormality repair method according to claim 1, characterized in that: The system data includes log data, performance indicator data and distributed tracking data.

3. The abnormality repair method according to claim 1, characterized in that: The inputting the system data into the anomaly detection neural network to obtain system anomaly information includes: Real-time monitoring of abnormal data in the system data; The abnormal data is input into the abnormality detection neural network to generate the system abnormality information.

4. The abnormality repair method according to claim 3, characterized in that: When the abnormal data is detected in the system data, the method further includes: Generate system abnormality alarm information.

5. The abnormality repair method according to claim 3, characterized in that: The repairing the corresponding system abnormality based on the system abnormality information includes: Displaying the abnormal data and the system abnormal information to the user through a user interface; In response to a repair operation performed by the user on the user interface, the system anomaly corresponding to the system anomaly information is repaired.

6. The abnormality repair method according to claim 1, characterized in that: The method further comprises: Get historical system data; The anomaly detection neural network is obtained by training based on the historical system data.

7. An abnormality repair device, characterized in that: include: Acquisition module, used to obtain system data; A detection module, used for inputting the system data into an anomaly detection neural network to obtain system anomaly information; wherein the system anomaly information is used to characterize the system anomaly corresponding to the system data; A repair module is used to repair the corresponding system abnormality based on the system abnormality information.

8. An abnormality repair system, characterized in that: The abnormality repair system includes a data collection unit, a real-time analysis unit, an intelligent analysis unit and a user interface unit, and the user interface unit includes a monitoring subunit and an interface subunit; wherein: The data collection unit is used to obtain system data and transmit the system data to the real-time analysis unit; the system data includes log data, performance indicator data and distributed tracking data; The real-time analysis unit is used to receive the system data transmitted by the data collection unit, locate system abnormalities based on the system information, generate system abnormality information, and transmit the system abnormality information to the intelligent analysis unit and the monitoring subunit; The interface subunit is used to obtain the system abnormality information from the monitoring subunit in real time; and to repair the system abnormality corresponding to the system abnormality information; The monitoring subunit is used to receive the system abnormality information transmitted by the real-time analysis unit; and transmit the system abnormality information to the interface subunit and the intelligent analysis unit; The intelligent analysis unit is used to receive the system abnormality information transmitted by the real-time analysis unit and the monitoring subunit, and to obtain an abnormality detection neural network based on the system abnormality information training. The abnormality detection neural network is used to detect the system abnormality.

9. An electronic device, comprising: processor; as well as Memory for storing programs, The program includes instructions, which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

Images