Fault analysis method and device, server, medium and vehicle

By using the fault analysis model in a cloud-native environment to analyze the historical and target operation data of the business system, the problem of determining the source of the fault in service failure is solved, and fast and accurate fault resolution is achieved, reducing the fault resolution time.

CN119065875APending Publication Date: 2024-12-03BEIJING CO WHEELS TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310639787.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-31
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the cloud native era, it is difficult for developers to accurately determine the source of the fault through a large number of fault logs, alarms, indicators, etc. when service failures, resulting in a significant increase in the fault resolution time.

Method used

By obtaining the historical operation data of the business system for model training, establishing a fault analysis model, and obtaining the target operation data within the preset time when the fault occurs, using the fault analysis model for fault analysis, and automatically, quickly and accurately analyze to obtain fault results.

Benefits of technology

It shortens the time for fault resolution, realizes automatic, fast and accurate fault analysis, and improves fault handling efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065875A_ABST
    Figure CN119065875A_ABST
Patent Text Reader

Abstract

The invention relates to a fault analysis method and device, a server, a medium and a vehicle. The fault analysis method comprises the steps of obtaining historical operation data of a service system, and performing model training according to the historical operation data to obtain a fault analysis model; in response to the fault event of the service system, obtaining target operation data of the service system within a preset time; and performing fault analysis processing on the target operation data through the fault analysis model to obtain a fault result corresponding to the fault event. According to the embodiment of the invention, the fault result can be obtained through automatic, rapid and accurate analysis, and the fault solving time is shortened.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a fault analysis method, device, server, medium and vehicle. Background Art

[0002] With the development of technology, Docker containerization and the popularization of Kubernetes container orchestration engines have enabled a large number of traditional servers to transition to the cloud-native era. The cloud-native era is service-centric. For users, it only describes the final status of the service and tries to shield the underlying hardware and server distribution details. The orchestration engine and container technology ensure that the service reaches the final expected state.

[0003] In related technologies, a large number of services are transformed from individually created virtual machines into lighter-weight containers. However, when a service fails, it will affect multiple containers or even clusters on the entire server, creating an avalanche effect. Developers cannot accurately determine the source of the failure through a large number of fault logs, alarms, indicators, etc., which greatly increases the time to resolve the fault. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a fault analysis method, device, server, medium and vehicle.

[0005] In a first aspect, the present disclosure provides a fault analysis method, comprising:

[0006] Obtain the historical operation data of the business system, and train the model based on the historical operation data to obtain the fault analysis model;

[0007] In response to a failure event in a business system, obtain target operation data of the business system within a preset time;

[0008] The fault analysis model is used to perform fault analysis on the target operation data to obtain the fault result corresponding to the fault event.

[0009] In a second aspect, the present disclosure provides a fault analysis device, comprising:

[0010] The first acquisition module is used to acquire the historical operation data of the business system and perform model training based on the historical operation data to obtain a fault analysis model;

[0011] A second acquisition module is used to obtain target operation data of the business system within a preset time in response to a failure event of the business system;

[0012] The first processing module is used to perform fault analysis processing on the target operation data through the fault analysis model to obtain the fault result corresponding to the fault event.

[0013] In a third aspect, the present disclosure provides a server, including:

[0014] processor;

[0015] A memory for storing executable instructions;

[0016] The processor is used to read executable instructions from the memory and execute the executable instructions to implement the fault analysis method of the first aspect.

[0017] In a fourth aspect, the present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the fault analysis method of the first aspect.

[0018] In a fifth aspect, the present disclosure provides a vehicle, comprising the above fault analysis device.

[0019] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0020] The fault analysis method, device, server, medium and vehicle of the embodiments of the present disclosure can obtain the historical operation data of the business system, and perform model training based on the historical operation data to obtain a fault analysis model, and then, in response to a fault event occurring in the business system, obtain the target operation data of the business system within a preset time, and finally, perform fault analysis processing on the target operation data through the fault analysis model to obtain a fault result corresponding to the fault event. As a result, after a fault event occurs in the business system, fault analysis processing can be performed on the target operation data within a preset time through the acquired historical operation data, so that the fault result can be automatically, quickly and accurately analyzed and obtained, thereby shortening the time for fault resolution. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A flowchart of a fault analysis method provided by an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of the structure of a fault analysis device provided in an embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram of the structure of a server provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] 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.

[0026] 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.

[0027] The term "including" and its variations used herein are open inclusions, i.e., "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 additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in the present 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.

[0029] 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".

[0030] 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.

[0031] In order to solve the above problems, the present disclosure provides a fault analysis method, device, server, medium and vehicle. Figure 1 The fault analysis method provided in the embodiment of the present disclosure is described in detail.

[0032] Figure 1 A flow chart of a fault analysis method provided by an embodiment of the present disclosure is shown.

[0033] In the embodiment of the present disclosure, the fault analysis method may be executed by a server. Specifically, the server may include but is not limited to a cloud server or a cloud server cluster.

[0034] like Figure 1 As shown, the fault analysis method may include the following steps.

[0035] S110 . Obtain historical operation data of the business system, and perform model training based on the historical operation data to obtain a fault analysis model.

[0036] In an embodiment of the present disclosure, the server may obtain historical operation data of the business system, and perform model training based on the historical operation data to obtain a fault analysis model.

[0037] Optionally, the business system may be various business processing systems that can be directly perceived by the user. For example, the business system may be a human resources system, an order system, etc., which are not limited here.

[0038] Optionally, the historical operation data may be various data generated during the operation of the business system. For example, the historical operation data may include at least one of log data, link data, and indicator data.

[0039] Optionally, the fault analysis model may be a model used to perform fault analysis processing on target operating data.

[0040] Specifically, when the business system is running, the server can collect data from the business system to obtain historical operation data, and then perform model training based on the historical operation data to obtain a fault analysis model.

[0041] S120 . In response to a failure event of the business system, obtain target operation data of the business system within a preset time.

[0042] In an embodiment of the present disclosure, the server may obtain target operating data within a preset time in response to a failure event occurring in the business system.

[0043] Optionally, the fault event may be a fault occurring during the operation of the business system.

[0044] Optionally, the preset time may be a predefined time. For example, the preset time may be a specified time before a failure event occurs in the business system, such as a time corresponding to 10 seconds, 20 seconds, etc.

[0045] Optionally, the target operation data may be data of the business system operation within a preset time.

[0046] Specifically, when a failure event occurs during the operation of a business system, the server can obtain the target operation data of the business system within a specified time window, such as 10 seconds, through the data platform.

[0047] S130 , performing fault analysis processing on the target operation data through the fault analysis model to obtain a fault result corresponding to the fault event.

[0048] In the disclosed embodiment, after acquiring the target operation data, the server may perform fault analysis processing on the target operation data through a fault analysis model to obtain a fault result corresponding to the fault event.

[0049] Optionally, the fault analysis process may be to perform data analysis on target operation data to obtain corresponding fault result processing.

[0050] Optionally, the fault result may include a fault cause, a fault service, a fault source, etc.

[0051] Specifically, after obtaining the target operation data, the server can use a data platform, such as a technical platform built through a big data technology stack, which can quickly analyze and process massive data. According to the fault analysis model, the server can perform fault analysis and processing on the target operation data to obtain the fault result corresponding to the fault event.

[0052] Therefore, in the embodiments of the present disclosure, it is possible to obtain historical operating data of the business system, and perform model training based on the historical operating data to obtain a fault analysis model. Then, in response to a fault event occurring in the business system, the target operating data of the business system within a preset time is obtained. Finally, the fault analysis model is used to perform fault analysis processing on the target operating data to obtain a fault result corresponding to the fault event. Therefore, after a fault event occurs in the business system, it is possible to perform fault analysis processing on the target operating data within a preset time through the acquired historical operating data, so that the fault result can be automatically, quickly and accurately analyzed and obtained, thereby shortening the time for fault resolution.

[0053] Optionally, S110 may specifically include: collecting all operating data of the business system through a data collection system, the data collection system including at least one of a log collection system, a link tracking system and an indicator monitoring system; performing data extraction processing on all operating data to obtain historical operating data.

[0054] In the embodiment of the present disclosure, the server can collect all operating data of the business system through the data collection system.

[0055] Optionally, the data collection system may include at least one of a log collection system, a link tracking system, and an indicator monitoring system.

[0056] Specifically, the server may collect all operating data of the business system through a data collection system, such as through a log collection system, a link tracking system, and an indicator monitoring system.

[0057] Furthermore, the server may perform data extraction processing on all operation data to obtain historical operation data.

[0058] Optionally, the data extraction process may be a process of extracting specific data.

[0059] Optionally, the historical operation data may include at least one of log data, link data, and indicator data.

[0060] Specifically, the server may perform data extraction processing on all operation data to obtain historical operation data.

[0061] In some embodiments of the present disclosure, the server may obtain log data of the business system through a log collection system.

[0062] Optionally, the log collection system may be a system that collects log data by integrating a software development kit (SDK) with a business system or deploying an agent collector.

[0063] Specifically, the server can collect log data of the business system through the log collection system, such as operation log data and version release deployment log data, etc., which is not limited here.

[0064] In other embodiments of the present disclosure, the server may obtain link data of the business system through a link tracking system.

[0065] Optionally, under the microservice architecture, the link tracking system can collect link data in the business system to display the sequence delay of events, etc.

[0066] Specifically, the server can collect various link data running in the business system to display the sequence delay of events through the link tracking system.

[0067] In some other embodiments of the present disclosure, the server may obtain indicator data of the business system through an indicator monitoring system.

[0068] Optionally, the indicator monitoring system can be used to deploy an indicator collector in the system and develop an indicator exporter in the business system to collect various operating indicators of each system, including the underlying infrastructure platform, in real time through the indicator monitoring system, that is, indicator data.

[0069] Specifically, the server can collect indicator data of each system through the indicator monitoring system.

[0070] Optionally, the server may also include a container orchestration engine, a DevOps (Development, Operations) platform system, a data platform, etc. The container orchestration engine can be the technical base for the deployment and operation of the business system backend services; the DevOps platform can be a platform for iterative development and online release of requirements; the data platform can be a technical platform established through the big data technology stack, which can quickly analyze and process massive data and serve as the data base of the entire system.

[0071] In this way, different historical operation data of the business system can be accurately collected and stored through different systems, thereby providing accurate data support for subsequent processing, which is conducive to improving the accuracy of fault results.

[0072] Optionally, the fault analysis method may further include: performing data processing on historical operation data through preset data processing tasks to obtain corresponding operation training data; generating a corresponding training data set based on the operation training data and the corresponding historical operation status; performing distributed model training on the training data set to obtain a trained fault analysis model.

[0073] In the embodiment of the present disclosure, after acquiring the historical operation data, the server can perform data processing on the historical operation data through a preset data processing task to obtain corresponding operation training data.

[0074] Optionally, the preset data processing task may be a predefined data processing task.

[0075] Optionally, data processing may be deduplication, sorting, preprocessing, etc. of historical operation data, which is not limited here.

[0076] Optionally, the running training data may be data used for model training.

[0077] Specifically, after obtaining the historical operation data, the server can perform data processing on the historical operation data based on the data platform through preset data processing tasks, so as to obtain corresponding operation training data.

[0078] Furthermore, after obtaining the operation training data, the server may generate a corresponding training data set according to the operation training data and the corresponding historical operation status.

[0079] Optionally, the training data set may be a data set used for model training.

[0080] Specifically, after obtaining the operation training data, the server can generate a training data set for model training according to the specific operation training data and the corresponding historical operation status.

[0081] Furthermore, after obtaining the training data set, the server can perform distributed model training on the training data set to obtain a trained fault analysis model.

[0082] Optionally, distributed model training can be performed by dividing historical operation data into multiple parts and performing distributed simultaneous training, thereby increasing the model training speed.

[0083] Optionally, the fault analysis model may be a model used to perform fault analysis processing on target operating data.

[0084] Specifically, after the server obtains the training data set, it can use the pipeline technology in the data platform to start the algorithm model training program and algorithm training framework, and perform model training according to historical operation data to obtain a trained fault analysis model.

[0085] Therefore, a fault analysis model can be obtained through model training based on historical operation data, and the fault analysis model can quickly and accurately output the corresponding fault results, thus shortening the time for fault resolution.

[0086] Optionally, S130 may specifically include: inputting the target operation data into the fault analysis model, so that the fault analysis model performs fault analysis processing on the target operation data according to the historical operation data to obtain a fault result.

[0087] In the disclosed embodiment, after obtaining the target operation data, the server may input the target operation data into the fault analysis model, so that the fault analysis model performs fault analysis processing on the target operation data according to the historical operation data to obtain a fault result.

[0088] Specifically, after obtaining the target operation data, the server can input the target operation data into the trained fault analysis model through the data platform. The fault analysis model can combine the historical operation data to perform fault analysis on the target operation data, such as analyzing the cause of the fault, the source of the fault, etc., and output the corresponding fault result.

[0089] Therefore, the fault analysis model in the data platform can be used to automatically, quickly and accurately analyze the fault results, shortening the time for fault resolution.

[0090] Optionally, the fault analysis method may also include: obtaining recent operating data and recent operating status of the business system; performing model enhancement training on the fault analysis model based on the recent operating data and recent operating status to obtain an enhanced fault analysis model; and updating the fault analysis model to the enhanced fault analysis model.

[0091] In the disclosed embodiment, the server may obtain recent operation data and recent operation status of the business system.

[0092] Optionally, the recent operation data may be operation data within a recent period of time, such as 1 day, 2 days, etc., which is not limited here.

[0093] Optionally, the recent operating status may be an operating status within a recent period of time.

[0094] Specifically, the server can obtain recent operation data and recent operation status of the business system through the data collection system.

[0095] Furthermore, the server may perform model enhancement training on the fault analysis model according to recent operation data and recent operation status to obtain an enhanced fault analysis model.

[0096] Optionally, the model enhancement training may be training for enhancing model accuracy.

[0097] Specifically, the server can perform model enhancement training on the fault analysis model through recent operation data and recent operation status, thereby enhancing the accuracy of the fault analysis model and obtaining an enhanced fault analysis model.

[0098] Furthermore, the server may update the fault analysis model to an enhanced fault analysis model.

[0099] Therefore, in the disclosed embodiments, the fault analysis model can be continuously enhanced through target operation data, and fault analysis can be performed through the enhanced fault analysis model, thereby effectively improving the accuracy of the fault results and shortening the fault resolution time.

[0100] Optionally, the fault analysis method may further include: acquiring real-time operation data of the business system; performing fault prediction processing on the real-time operation data according to the enhanced fault analysis model to obtain corresponding prediction results; and providing early warning prompts according to the prediction results.

[0101] In the disclosed embodiment, the server may obtain real-time operation data of the business system.

[0102] Optionally, the real-time operation data may be data of real-time operation of a business system.

[0103] Specifically, the server may collect real-time operation data of the business system through a data collection system, which is not limited here.

[0104] Furthermore, the server can perform fault prediction processing on the real-time operation data according to the enhanced fault analysis model to obtain corresponding prediction results.

[0105] Optionally, the fault prediction process may be a process of performing fault prediction.

[0106] Optionally, the prediction result may include a result of predicting the cause of the fault, the source of the fault, etc.

[0107] Specifically, the server can perform fault prediction processing on the real-time operation data based on the historical operation data through the data platform, that is, predict whether a fault event will occur in the real-time operation data, thereby obtaining a prediction result.

[0108] Furthermore, after obtaining the prediction results, the server can issue an early warning prompt based on the prediction results.

[0109] Optionally, the warning prompt may be a prompt for warning the user. For example, the warning prompt may be a sound prompt, a text prompt, etc., which is not limited here.

[0110] Specifically, after obtaining the prediction result, the server may give a warning prompt to the user according to the prediction result, for example, by giving a warning prompt of the prediction result in the form of a sound prompt or a text prompt.

[0111] Therefore, in the embodiments of the present disclosure, early warning reminders can be issued, which is conducive to users to handle in advance, reduce the occurrence of fault events, and improve the operating capacity of the business system.

[0112] Figure 2 A schematic structural diagram of a fault analysis device provided in an embodiment of the present disclosure is shown.

[0113] In some embodiments of the present disclosure, Figure 2 The fault analysis device shown can be arranged in a server. Specifically, the server can include but is not limited to a cloud server or a cloud server cluster.

[0114] like Figure 2 As shown, the fault analysis device 200 may include a first acquisition module 210 , a second acquisition module 220 and a first processing module 230 .

[0115] The first acquisition module 210 can be used to acquire historical operation data of the business system, and perform model training based on the historical operation data to obtain a fault analysis model.

[0116] The second acquisition module 220 can be used to obtain target operation data of the business system within a preset time in response to a failure event of the business system.

[0117] The first processing module 230 can be used to perform fault analysis processing on the target operation data through the fault analysis model to obtain a fault result corresponding to the fault event.

[0118] Therefore, in the embodiments of the present disclosure, it is possible to obtain historical operating data of the business system, and perform model training based on the historical operating data to obtain a fault analysis model. Then, in response to a fault event occurring in the business system, the target operating data of the business system within a preset time is obtained. Finally, the fault analysis model is used to perform fault analysis processing on the target operating data to obtain a fault result corresponding to the fault event. Therefore, after a fault event occurs in the business system, it is possible to perform fault analysis processing on the target operating data within a preset time through the acquired historical operating data, so that the fault result can be automatically, quickly and accurately analyzed and obtained, thereby shortening the time for fault resolution.

[0119] In some embodiments of the present disclosure, historical operation data may include at least one of log data, link data, and indicator data.

[0120] In some embodiments of the present disclosure, the first acquisition module 210 may specifically include a first acquisition unit and a first processing unit.

[0121] The first acquisition unit can be used to collect all operating data of the business system through a data collection system, and the data collection system includes at least one of a log collection system, a link tracking system and an indicator monitoring system.

[0122] The first processing unit can be used to perform data extraction processing on all operating data to obtain historical operating data.

[0123] In some embodiments of the present disclosure, the first acquisition module 210 may further specifically include a second processing unit, a third processing unit and a first training unit.

[0124] The second processing unit can be used to perform data processing on historical operation data through preset data processing tasks to obtain corresponding operation training data.

[0125] The third processing unit may be configured to generate a corresponding training data set according to the running training data and the corresponding historical running status.

[0126] The first training unit can be used to perform distributed model training on the training data set to obtain a trained fault analysis model

[0127] In some embodiments of the present disclosure, the fault analysis device 200 may further include a third acquisition module, a second processing module and a model updating module.

[0128] The third acquisition module can be used to acquire recent operation data and recent operation status of the business system.

[0129] The second processing module can be used to perform model enhancement training on the fault analysis model according to recent operation data and recent operation status to obtain an enhanced fault analysis model.

[0130] The model updating module can be used to update the fault analysis model to an enhanced fault analysis model.

[0131] In some embodiments of the present disclosure, the fault analysis device 200 may further include a fourth acquisition module, a third processing module and an early warning prompt module.

[0132] The fourth acquisition module can be used to acquire real-time operation data of the business system.

[0133] The third processing module can be used to perform fault prediction processing on the real-time operation data according to the enhanced fault analysis model to obtain corresponding prediction results.

[0134] The early warning prompt module can be used to provide early warning prompts based on the prediction results.

[0135] It should be noted that Figure 2 The fault analysis device 200 shown can perform Figure 1 The various steps in the method embodiment shown in the figure are implemented Figure 1 The various processes and effects in the method embodiment shown are not described in detail here.

[0136] Figure 3 A schematic diagram of the structure of a server provided by an embodiment of the present disclosure is shown.

[0137] In some embodiments of the present disclosure, Figure 3 The server shown may be a server with a fault analysis function. Specifically, the server may include but is not limited to a cloud server or a cloud server cluster.

[0138] like Figure 3 As shown, the server may include a processor 301 and a memory 302 storing computer program instructions.

[0139] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0140] The memory 302 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 302 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 302 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 302 is a non-volatile solid-state memory. In a particular embodiment, the memory 302 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0141] The processor 301 reads and executes the computer program instructions stored in the memory 302 to perform the steps of the fault analysis method provided in the embodiment of the present disclosure.

[0142] In one example, the server may further include a transceiver 303 and a bus 304. Figure 3 As shown, the processor 301, the memory 302 and the transceiver 303 are connected via a bus 304 and communicate with each other.

[0143] The bus 304 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a Memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 304 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0144] The embodiments of the present disclosure further provide a computer-readable storage medium, which may store a computer program. When the computer program is executed by a processor, the processor implements the fault analysis method provided by the embodiments of the present disclosure.

[0145] The above-mentioned storage medium may, for example, include a memory 302 of computer program instructions, and the above-mentioned instructions may be executed by the processor 301 of the server to complete the fault analysis method provided in the embodiment of the present disclosure. Optionally, the storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0146] The present disclosure also provides a vehicle, which includes the above-mentioned fault analysis device. It is understood that the vehicle may also include: a processor, a memory, and a computer program. The computer program is stored in the memory and is configured to be executed by the processor to implement the fault analysis method provided by the present disclosure. The processor and the memory are already in Figure 3 The parts described in the illustrated embodiment are not repeated here.

[0147] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0148] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fault analysis method, characterized in that: include: Acquire historical operation data of the business system, and perform model training based on the historical operation data to obtain a fault analysis model; In response to a failure event of the business system, obtaining target operation data of the business system within a preset time; The target operation data is subjected to fault analysis processing by using the fault analysis model to obtain a fault result corresponding to the fault event.

2. The method according to claim 1, characterized in that: The historical operation data includes at least one of log data, link data, and indicator data.

3. The method according to claim 2, characterized in that The obtaining of historical operation data of the business system includes: Collect all operation data of the business system through a data collection system, wherein the data collection system includes at least one of a log collection system, a link tracking system, and an indicator monitoring system; Data extraction is performed on all the operation data to obtain the historical operation data.

4. The method according to claim 1, characterized in that: The performing model training according to the historical operation data to obtain a fault analysis model includes: By presetting the data processing task, the historical operation data is processed to obtain corresponding operation training data; Generate a corresponding training data set according to the operation training data and the corresponding historical operation status; Distributed model training is performed on the training data set to obtain a trained fault analysis model.

5. The method according to claim 1, characterized in that The method further comprises: Obtaining recent operation data and recent operation status of the business system; Performing model enhancement training on the fault analysis model according to the recent operation data and the recent operation status to obtain an enhanced fault analysis model; The fault analysis model is updated to the enhanced fault analysis model.

6. The method according to claim 5, characterized in that The method further comprises: Acquiring real-time operation data of the business system; According to the enhanced fault analysis model, the real-time operation data is subjected to fault prediction processing to obtain corresponding prediction results; An early warning is issued according to the prediction result.

7. A fault analysis device, characterized in that: include: A first acquisition module is used to acquire historical operation data of the business system, and perform model training based on the historical operation data to obtain a fault analysis model; A second acquisition module, configured to acquire target operation data of the business system within a preset time in response to a failure event of the business system; The first processing module is used to perform fault analysis processing on the target operation data through the fault analysis model to obtain a fault result corresponding to the fault event.

8. A server, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the fault analysis method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the fault analysis method described in any one of claims 1 to 6.

10. A vehicle, characterized in that: It includes the fault analysis device according to claim 7, the server according to claim 8, or the computer-readable storage medium according to claim 9.