Data analysis method, apparatus, device, medium, and program product

Abstract

This application provides a data analysis method, apparatus, device, medium, and program product, which can be applied to the fields of artificial intelligence and data processing technology. The method includes: for any one of multiple service systems involved in providing a target service, dividing multiple system objects into multiple application objects based on the functions of different system objects within the service system; for any application object, training a preset language model using application instances obtained from the application object through a target interface to obtain a problem analysis model, and deploying the problem analysis model in a configuration system; generating analysis prompt words for the application object based on the alarm types of any application object in the service system during historical periods; and inputting the analysis prompt words and configuration data obtained from the application object corresponding to the analysis prompt words through calling the target interface into the problem analysis model in the configuration system to perform fault analysis on the configuration data.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and data processing technology, and more specifically to a data analysis method, apparatus, device, medium, and program product. Background Technology

[0002] Many online application service systems provide customer service systems to help businesses or service providers communicate effectively with users, including answering user questions and providing communication channels to maximize customer satisfaction.

[0003] However, various problems can easily arise during the transformation and operation of business systems that provide services. In severe cases, these problems can cause the system to be unable to provide services to the outside world, which can have a significant impact on users and thus form incident problems of varying severity.

[0004] When analyzing system faults, related technologies require access to a large amount of data, resulting in low efficiency and poor accuracy of the analysis results. Summary of the Invention

[0005] In view of the above problems, this application provides a data analysis method, apparatus, device, medium and program product.

[0006] According to a first aspect of this application, a data analysis method is provided, comprising: for any one of multiple service systems involved in providing a target service, dividing the multiple system objects based on the functions of different system objects in the service system to obtain multiple application objects, wherein the service system represents the equipment, network, or service involved in providing the target service, and the application object represents at least one of different types of software, hardware, and data involved in the service system; for any application object, training a preset language model using application instances obtained from the application object through a target interface to obtain a problem analysis model, and deploying the problem analysis model in a configuration system; generating analysis prompt words for the application object based on the alarm types of any application object in the service system during historical periods; and inputting the analysis prompt words and configuration data obtained from the application object corresponding to the analysis prompt words through calling the target interface into the problem analysis model in the configuration system to perform fault analysis on the configuration data.

[0007] According to the embodiments of this application, the above application examples include fault configuration data and fault analysis results, wherein the above fault analysis results include at least one of the following: alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information of the above fault configuration data.

[0008] According to an embodiment of this application, the above method further includes: constructing an object model for any of the above-mentioned application objects; generating multiple new application instances based on the object model using chaos engineering techniques; and training the above-mentioned problem analysis model using the multiple new application instances to obtain a new problem analysis model.

[0009] According to an embodiment of this application, multiple new application instances are generated using chaos engineering techniques, including: generating configuration parameters for multiple faults based on the above object model using chaos engineering techniques; generating fault analysis information for any of the above fault configuration parameters based on the above fault configuration parameters, wherein the above fault analysis information includes at least one of alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information; and constructing the above new application instances based on the above fault configuration parameters and the corresponding fault analysis information.

[0010] According to an embodiment of this application, the analysis results of the fault analysis are displayed, wherein the analysis results include whether the configuration data has a fault of the alarm type in the analysis prompt and the information on the suggested fault handling measures; the problem analysis model is optimized and adjusted using the processing feedback information obtained based on the analysis results.

[0011] According to an embodiment of this application, generating analysis prompts for any application object in the service system based on alarm types during historical periods includes: in response to an alarm type input for the application object, constructing the analysis prompts based on the application object and the alarm type.

[0012] According to the embodiments of this application, multiple fault configuration data of the above-mentioned application object that have failed during historical periods are obtained; for each fault configuration data, in the case of recovery of the fault event of the above-mentioned fault configuration data, the relevant information involved in the recovery fault event is analyzed to obtain the fault analysis result; based on the above-mentioned fault configuration data and the above-mentioned fault analysis result, the above-mentioned application instance is generated.

[0013] According to embodiments of this application, the above-mentioned service system includes at least one of the following: an application system, an operation system, a platform system, a computing system, a storage system, a network system, a security system, and an infrastructure system that characterize the business of the above-mentioned target service.

[0014] A second aspect of this application provides a data analysis apparatus, comprising: a partitioning module, configured to partition multiple system objects based on the functions of different system objects in multiple service systems involved in providing a target service, to obtain multiple application objects, wherein the service system represents the equipment, network, or service involved in providing the target service, and the application object represents at least one of different types of software, hardware, and data involved in the service system; a training module, configured to train a preset language model for any application object using application instances obtained from the application object through a target interface to obtain a problem analysis model, and deploy the problem analysis model in a configuration system; a generation module, configured to generate analysis prompt words for any application object in the service system based on the alarm types of the application object in historical time periods; and an analysis module, configured to input the analysis prompt words and configuration data obtained from the application object corresponding to the analysis prompt words by calling the target interface into the problem analysis model in the configuration system to perform fault analysis on the configuration data.

[0015] A third aspect of this application provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0016] A fourth aspect of this application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0017] The fifth aspect of this application also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0018] According to the embodiments of this application, multiple system objects in each service system of the target service are divided based on function, and the model is trained specifically using application instances of each application object. During problem analysis, corresponding analysis prompt words are generated based on the alarm type of the application object of interest, so as to complete the fault analysis using the trained problem analysis model. Since the training is based on the application object instances divided by function, the model does not need to process the data of other irrelevant objects during fault analysis, thereby improving the efficiency and accuracy of fault analysis. Attached Figure Description

[0019] The above-mentioned contents, other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1 This diagram illustrates an application scenario of the data analysis method according to an embodiment of this application.

[0021] Figure 2 A flowchart illustrating a data analysis method according to an embodiment of this application is shown schematically.

[0022] Figure 3 A flowchart illustrating a data analysis method according to an embodiment of this application is shown schematically.

[0023] Figure 4 A schematic diagram illustrating the structure of a data analysis apparatus according to an embodiment of this application is shown; and

[0024] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing the above-described method according to an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0026] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0027] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0028] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0029] In the technical solution of this application, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, and necessary processing measures have been taken. They do not violate public order and good morals, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0030] In scenarios involving automated decision-making using personal information, the methods, devices, and systems provided in this application all offer users corresponding entry points for choosing to agree to or reject the automated decision-making results. If the user chooses to reject, the process proceeds to the expert decision-making stage. Here, "automated decision-making" refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests, or economic, health, and credit status through computer programs, and then making a decision. Here, "expert decision-making" refers to the activity of making decisions by personnel who specialize in a particular field, possess specialized experience, knowledge, and skills, and have reached a certain level of professional expertise.

[0031] When faced with faults or incidents, project teams and system maintenance personnel often need to collect a large amount of relevant information about application errors, and combine the information to make judgments, quickly locate and solve problems. However, due to the dispersed system load and fragmented information, collecting and viewing this information often takes a long time, which can cause the problem or incident to spread, turning what may have been a small issue into a major impact or even loss.

[0032] In view of this, embodiments of this application provide a data analysis method, apparatus, device, medium, and program product method. The method includes, for any one of multiple service systems involved in providing a target service, dividing multiple system objects based on the functions of different system objects within the service system to obtain multiple application objects. The service system represents the equipment, network, or service involved in providing the target service, and the application object represents at least one of different types of software, hardware, and data involved in the service system. For any application object, a preset language model is trained using application instances obtained from the application object through a target interface to obtain a problem analysis model, and the problem analysis model is deployed in a configuration system. Analysis prompt words for the application object are generated based on the alarm types of any application object in the service system during historical periods. The analysis prompt words and configuration data obtained from the application object corresponding to the analysis prompt words through calling the target interface are input into the problem analysis model in the configuration system to perform fault analysis on the configuration data.

[0033] It should be noted that the data analysis method and apparatus provided in this application can be used in the financial field, such as financial institutions like banks, and can also be used in any field other than finance, such as e-commerce. Therefore, the application field of the data analysis method and apparatus provided in this application is not limited.

[0034] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0035] Figure 1 The diagram illustrates an application scenario of the data analysis method according to an embodiment of this application.

[0036] like Figure 1 As shown, application scenario 100 according to this embodiment may include various system objects involved in financial services. Network 104 is used as a medium to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0037] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0038] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0039] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0040] It should be noted that the data analysis method provided in this application embodiment can generally be executed by server 105. Correspondingly, the data analysis device provided in this application embodiment can generally be located in server 105. The data analysis method provided in this application embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the data analysis device provided in this application embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0041] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0042] The following will be based on Figure 1 The described scene, through Figures 2-4 The data analysis method of the disclosed embodiments will be described in detail.

[0043] Figure 2 A flowchart illustrating a data analysis method according to an embodiment of this application is shown schematically.

[0044] like Figure 2 As shown, the data analysis method of this embodiment includes operations S210 to S240, and the transaction processing method can be executed by an electronic device.

[0045] In operation S210, for any one of the multiple service systems involved in providing the target service, the multiple system objects are divided based on the functions of different system objects in the service system to obtain multiple application objects. Among them, the service system represents the equipment, network or service involved in providing the target service, and the application object represents at least one of the different types of software, hardware and data involved in the service system.

[0046] In operation S220, for any application object, the preset language model is trained using the application instance obtained from the application object through the target interface to obtain the problem analysis model, and the problem analysis model is deployed in the configuration system.

[0047] In operation S230, analysis prompts are generated for any application object in the service system based on the alarm type during a historical period.

[0048] In operation S240, the analysis prompt word and the configuration data obtained from the application object corresponding to the analysis prompt word by calling the target interface are input into the problem analysis model in the configuration system to perform fault analysis on the configuration data.

[0049] According to embodiments of this application, the target service can be any type of service, such as data storage service, email service, and financial service.

[0050] According to the embodiments of this application, when providing the target service, different service systems need to cooperate, such as application systems and storage systems. For each service system, it can be divided according to the functions of different system objects in the service system, thereby obtaining multiple application objects of the service system, such as databases, operating systems and cloud disks.

[0051] According to an embodiment of this application, for each application object obtained by segmentation, a target interface (such as an API (Application Programming Interface)) can be called to obtain an application instance in the application object. The application instance includes attribute information of different attributes. The preset language model is trained through different application instances. After all application instances of the service system have been trained, a problem analysis model can be obtained. The model is then deployed in the configuration system so that problem analysis can be performed on any application object in the service system. The preset language model can refer to a large language model (LLM).

[0052] According to an embodiment of this application, during the problem analysis process, the user can generate analysis prompt words for the application object based on the alarm types (such as queue anomalies) of alarms that have occurred in the historical period of the application object of interest. At the same time, based on the analysis prompt words, the user can obtain the corresponding configuration data from the corresponding application object and transmit the configuration data and analysis prompt words to the configuration system. This allows the configuration system to perform data analysis based on the deployed problem analysis model to determine whether the application object has the alarm type in the analysis prompt words. If the alarm exists, the system can also provide a corresponding handling solution.

[0053] According to the embodiments of this application, multiple system objects in each service system of the target service are divided based on function, and the model is trained specifically using application instances of each application object. During problem analysis, corresponding analysis prompt words are generated based on the alarm type of the application object of interest, so as to complete the fault analysis using the trained problem analysis model. Since the training is based on the application object instances divided by function, the model does not need to process the data of other irrelevant objects during fault analysis, thereby improving the efficiency and accuracy of fault analysis.

[0054] According to the embodiments of this application, the application example includes fault configuration data and fault analysis results, wherein the fault analysis results include at least one of the following: alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information of the fault configuration data.

[0055] According to embodiments of this application, the alarm types for fault configuration data may include, but are not limited to, abnormal process count, abnormal port status, abnormal JDBC (Java Database Connectivity) connection pool of the application server, abnormal server process count, abnormal garbage collection time, log keyword matching, high CPU utilization, high number of user-opened processes, abnormal file system mount status, ping timeout for connectivity address, database abnormality, high process memory usage, abnormal transaction volume, low available server memory, queue abnormality, abnormal port status, abnormal Uniform Resource Locator (URI) connection, excessively high thread pool queue count, abnormal number of zombie server processes, server host restart or network unreachable, and abnormal message queue sending channel status.

[0056] According to embodiments of this application, alarm phenomenon information represents the form of data manifestation when a certain alarm occurs. Fault troubleshooting information describes the types of data investigated when troubleshooting a fault corresponding to a certain alarm, and fault analysis process data represents the steps taken to perform fault analysis on the application object during fault troubleshooting. Fault handling measure information represents the operations performed when eliminating the fault. Fault recovery information indicates that the fault was eliminated under certain fault handling measure information.

[0057] According to embodiments of this application, the above method further includes: constructing an object model for any application object; generating multiple new application instances based on the object model using chaos engineering techniques; and training the problem analysis model using the multiple new application instances to obtain a new problem analysis model.

[0058] According to embodiments of this application, chaos engineering is a practical method for verifying and improving the stability of distributed systems by proactively injecting faults into them. Its goal is to expose system vulnerabilities before real failures occur and to enhance the system's resilience and fault tolerance in complex production environments by fixing these hidden dangers.

[0059] According to embodiments of this application, for each application object, an object model of that application object can be constructed, for example, through methods such as structured modeling, object-oriented modeling, component-based modeling, and deployment modeling.

[0060] According to embodiments of this application, for each object model, multiple new application instances can be generated using chaos engineering techniques. These new application instances also include the alarm types and fault handling measures information involved in the aforementioned application instances. The problem analysis model is then trained using these new application instances to obtain a new problem analysis model.

[0061] According to embodiments of this application, for each new application instance, it can be deployed on an application object in a pre-production environment to verify the application instance, thereby ensuring that the application instance matches the real environment.

[0062] According to embodiments of this application, each application object is expanded with application instances through chaos engineering techniques. As a result, the problem analysis model trained with a large number of application instances can achieve higher analysis accuracy in subsequent fault analysis.

[0063] According to an embodiment of this application, multiple new application instances are generated using chaos engineering techniques, including: generating configuration parameters for multiple faults based on an object model using chaos engineering techniques; generating fault analysis information for any fault based on the configuration parameters, wherein the fault analysis information includes at least one of alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information; and constructing new application instances based on the fault configuration parameters and the corresponding fault analysis information.

[0064] According to embodiments of this application, for each object model, configuration parameters for various faults are first generated using chaos engineering techniques. For each fault, these configuration parameters can be assigned to the application object. Fault analysis is then performed based on the actual faults generated by the application object during runtime, resulting in corresponding fault analysis information. Alternatively, maintenance personnel can directly provide the corresponding fault analysis information based on domain knowledge. After obtaining the fault analysis, it is combined with the corresponding configuration parameters to obtain a new application instance.

[0065] According to the embodiments of this application, since some faults have a variety of causes, different configuration parameters can be given for the fault type through chaos engineering techniques, ultimately forming a variety of new application instances for the fault type.

[0066] According to embodiments of this application, configuration parameters for different fault types are simulated using chaos engineering techniques. The problem analysis model trained based on these new application instances can provide different fault analysis results that may exist under alarm types during subsequent fault analysis, thereby improving the fault recovery efficiency of the application object.

[0067] According to an embodiment of this application, the analysis results of the fault analysis are displayed, wherein the analysis results include whether the configuration data has a fault of the type of alarm in the analysis prompt and the information of the suggested fault handling measures; the problem analysis model is optimized and adjusted using the processing feedback information obtained based on the analysis results.

[0068] According to an embodiment of this application, after the problem analysis model performs fault analysis and obtains the analysis results, the analysis results can be displayed, for example, through a webpage. Maintenance personnel can perform targeted fault recovery operations based on the fault handling measures information in the analysis results, and input the processing feedback information after execution into the problem analysis model so that the problem analysis model can optimize and adjust the model based on the processing feedback information.

[0069] According to the embodiments of this application, fault analysis is performed by a trained problem analysis model, enabling maintenance personnel to perform fault recovery based on the analysis results. This reduces the professional knowledge requirements for maintenance personnel, and the analysis accuracy of the problem analysis model is further improved through a feedback optimization mechanism.

[0070] According to an embodiment of this application, generating analysis prompts for an application object based on the alarm types of any application object in the service system during a historical period includes: in response to an alarm type input for the application object, constructing analysis prompts based on the application object and the alarm type.

[0071] According to the embodiments of this application, when constructing prompt words, the analysis prompt words for the application object can be constructed based on the application object that the user is interested in and the types of alarms that have occurred or may occur in the past. For example, it can be whether there are abnormal alarms in the database of the platform system. Furthermore, time information can be added to the analysis prompt words, such as whether there were abnormal alarms in the database of the platform system in the previous hour.

[0072] According to the embodiments of this application, by constructing targeted analysis prompts for application objects, staff can quickly understand the operation status of the application objects, thus avoiding the problem of slow analysis efficiency caused by performing overall analysis on all objects involved in the entire service.

[0073] According to an embodiment of this application, multiple fault configuration data of an application object that has failed during a historical period are obtained; for each fault configuration data, in the case of recovery of the fault event of the fault configuration data, the relevant information involved in the recovery fault event is analyzed to obtain the fault analysis result; and an application instance is generated based on the fault configuration data and the fault analysis result.

[0074] According to the embodiments of this application, when constructing each application instance, fault configuration data of the fault type can be obtained, and files related to the maintenance of the fault uploaded by staff can also be obtained, such as fault reports formed by staff after review and analysis of the fault. These reports contain the complete process of fault analysis and the specific steps of recovery. By analyzing these data, the fault analysis results of the fault recovery event can be obtained. Based on the fault configuration data and fault analysis results, and combined with the fault type of the fault configuration data, an application instance can be generated.

[0075] According to the embodiments of this application, during the process of constructing an application instance, the application instance is generated by using relevant information on the handling of the fault in the real environment. The problem analysis model trained based on the application instance can provide reasonable fault handling measures in subsequent fault analysis, which helps to improve the fault recovery efficiency of the application object.

[0076] Figure 3 A flowchart illustrating a data analysis method according to an embodiment of this application is shown schematically.

[0077] like Figure 3 As shown, various systems support the target service. These include, but are not limited to: application systems, operation systems, platform systems, computing systems, storage systems, network systems, security systems, and infrastructure systems that characterize the target service.

[0078] According to embodiments of this application, the application system mainly includes application objects such as system, service code, business function, and business scenario. The operation system mainly includes application objects such as availability zone, high availability model, resource model, deployment model, and tenant account; the platform system mainly includes application objects such as operating system, database, middleware, and container; the computing system mainly includes application objects such as virtual machine, bare metal, rack server, minicomputer, mainframe, and resource pool; the storage system mainly includes application objects such as cloud disk, storage area network (SAN), network attached storage (NAS), object storage, and file storage; the network system mainly includes application objects such as network zone, load balancer, switch, router, and load balancing; the security system mainly includes application objects such as firewall, encryption device, antivirus device, and bastion host; and the data center system (i.e., infrastructure system) mainly includes application objects such as campus, building, floor, data center module, and rack.

[0079] In some embodiments, high-frequency prompt words that meet the frequency threshold can also be configured in the configuration system. At a set time (such as the start of work each day), the configuration system automatically inputs the high-frequency prompt words into the model. Finally, the analysis results of different high-frequency prompt words are generated into a system report and sent to the designated administrators so that the administrators can know the overall system performance in a timely manner.

[0080] Based on the above data analysis method, this application also provides a data analysis device. The following will be combined with... Figure 4 The device is described in detail.

[0081] Figure 4 A schematic block diagram of a data analysis apparatus according to an embodiment of this application is shown.

[0082] like Figure 4 As shown, the data analysis device 400 of this embodiment includes a partitioning module 410, a training module 420, a generation module 430, and an analysis module 440.

[0083] The partitioning module 410 is used to partition multiple system objects based on the functions of different system objects in the service system for any one of the multiple service systems involved in providing the target service, thereby obtaining multiple application objects. The service system represents the equipment, network or service involved in providing the target service, and the application object represents at least one of the different types of software, hardware and data involved in the service system.

[0084] The training module 420 is used to train a preset language model for any application object using application instances obtained from the application object through the target interface, to obtain a problem analysis model, and then deploy the problem analysis model in the configuration system.

[0085] The generation module 430 is used to generate analysis prompt words for any application object in the service system based on the alarm type of any application object in the historical time period.

[0086] The analysis module 440 is used to input analysis prompts and configuration data obtained from the application object corresponding to the analysis prompts by calling the target interface into the problem analysis model in the configuration system to perform fault analysis on the configuration data.

[0087] According to the embodiments of this application, multiple system objects in each service system of the target service are divided based on function, and the model is trained specifically using application instances of each application object. During problem analysis, corresponding analysis prompt words are generated based on the alarm type of the application object of interest, so as to complete the fault analysis using the trained problem analysis model. Since the training is based on the application object instances divided by function, the model does not need to process the data of other irrelevant objects during fault analysis, thereby improving the efficiency and accuracy of fault analysis.

[0088] According to the embodiments of this application, the application example includes fault configuration data and fault analysis results, wherein the fault analysis results include at least one of the following: alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information of the fault configuration data.

[0089] According to an embodiment of this application, the data analysis device 400 further includes a construction module, a second generation module, and a second training module.

[0090] Builder modules are used to construct the object model of any application object.

[0091] The second generation module is used to generate multiple new application instances based on the object model and using chaos engineering techniques.

[0092] The second training module is used to train the problem analysis model using multiple new application examples to obtain a new problem analysis model.

[0093] According to an embodiment of this application, the second generation module includes a first generation unit, a second generation unit, and a first construction unit.

[0094] The first generation unit is used to generate configuration parameters for multiple faults based on an object model and using chaos engineering techniques.

[0095] The second generation unit is used to generate fault analysis information based on the configuration parameters of any fault. The fault analysis information includes at least one of the following: alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information.

[0096] The first building unit is used to build a new application instance based on the fault configuration parameters and corresponding fault analysis information.

[0097] According to an embodiment of this application, the data analysis device 400 further includes a display module and an adjustment module.

[0098] The display module is used to show the analysis results of the fault analysis. The analysis results include whether the configuration data contains faults of the alarm type in the analysis prompts, as well as information on suggested fault handling measures.

[0099] The adjustment module is used to optimize and adjust the problem analysis model using the processing feedback information obtained from the analysis results.

[0100] According to an embodiment of this application, the generation module 430 includes a second building unit.

[0101] The second building unit is used to respond to the alarm type input for the application object and to build analysis prompt words based on the application object and alarm type.

[0102] According to an embodiment of this application, the data analysis device 400 further includes an acquisition module, an analysis module, and a third generation module.

[0103] The acquisition module is used to obtain multiple fault configuration data of application objects that have failed during historical periods.

[0104] The analysis module is used to analyze the relevant information involved in the recovery of the fault event for each fault configuration data, and obtain the fault analysis results.

[0105] The third generation module is used to generate application instances based on fault configuration data and fault analysis results.

[0106] According to embodiments of this application, the service system includes at least one of the following: an application system, an operation system, a platform system, a computing system, a storage system, a network system, a security system, and an infrastructure system that characterize the business of the target service.

[0107] According to embodiments of this application, any multiple modules among the partitioning module 410, training module 420, generation module 430, and analysis module 440 can be merged into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of this application, at least one of the partitioning module 410, training module 420, generation module 430, and analysis module 440 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable method of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any appropriate combination of any of these three implementation methods. Alternatively, at least one of the partitioning module 410, training module 420, generation module 430, and analysis module 440 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0108] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing the above-described method according to an embodiment of this application.

[0109] like Figure 5 As shown, an electronic device 500 according to an embodiment of this application includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0110] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0111] According to embodiments of this application, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0112] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0113] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this application, the computer-readable storage medium may include ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503 described above.

[0114] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this application.

[0115] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0116] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0117] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this application embodiment. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0118] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0120] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

[0121] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Without departing from the scope of this application, those skilled in the art can make various substitutions and modifications, all of which should fall within the scope of this application.

Claims

1. A data analysis method, characterized in that, The method includes: For any one of the multiple service systems involved in providing the target service, the multiple system objects are divided based on the functions of different system objects in the service system to obtain multiple application objects. The service system represents the equipment, network or service involved in providing the target service, and the application object represents at least one of the different types of software, hardware and data involved in the service system. For any application object, a preset language model is trained using an application instance obtained from the application object through the target interface to obtain a problem analysis model, and the problem analysis model is deployed in the configuration system. Based on the alarm type of any application object in the service system during a historical period, generate analysis prompt words for the application object; The analysis prompt and the configuration data obtained from the application object corresponding to the analysis prompt by calling the target interface are input into the problem analysis model in the configuration system to perform fault analysis on the configuration data.

2. The method according to claim 1, characterized in that, The application example includes fault configuration data and fault analysis results, wherein the fault analysis results include at least one of the following: alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information of the fault configuration data.

3. The method according to claim 1 or 2, characterized in that, The method further includes: For any of the application objects, construct an object model for the application object; Based on the object model, multiple new application instances are generated using chaos engineering techniques. The problem analysis model is trained using multiple new application examples to obtain a new problem analysis model.

4. The method according to claim 3, characterized in that, Several new application instances were generated using chaos engineering techniques, including: Based on the object model, configuration parameters for multiple faults are generated using chaos engineering techniques; For any of the configuration parameters of the aforementioned fault, fault analysis information of the fault is generated based on the configuration parameters of the fault, wherein the fault analysis information includes at least one of alarm type, alarm phenomenon information, fault investigation information, fault analysis process data, fault handling measures information, and fault recovery information; Based on the configuration parameters of the fault and the corresponding fault analysis information, the new application instance is constructed.

5. The method according to claim 1, characterized in that, The analysis results of the fault analysis are displayed, including whether the configuration data has a fault of the type of alarm in the analysis prompt and information on suggested fault handling measures. The problem analysis model is optimized and adjusted using the processing feedback information obtained based on the analysis results.

6. The method according to claim 1, characterized in that, Based on the alarm type of any application object in the service system during a historical period, analysis prompt words for that application object are generated, including: In response to the alarm type input for the application object, the analysis prompt words are constructed based on the application object and the alarm type.

7. The method according to claim 1 or 2, characterized in that, Obtain multiple fault configuration data of the application object that occurred during historical periods; For each fault configuration data, in the case of recovery of the fault event of the fault configuration data, the relevant information involved in the recovery fault event is analyzed to obtain the fault analysis results; The application instance is generated based on the fault configuration data and the fault analysis results.

8. The method according to claim 1, characterized in that, The service system includes at least one of the following: an application system, an operation system, a platform system, a computing system, a storage system, a network system, a security system, and an infrastructure system that characterize the business of the target service.

9. A data analysis device, characterized in that, The device includes: The partitioning module is used to partition multiple system objects based on the functions of different system objects in multiple service systems involved in providing a target service, thereby obtaining multiple application objects. The service system represents the equipment, network or service involved in providing the target service, and the application object represents at least one of different types of software, hardware and data involved in the service system. The training module is used to train a preset language model for any application object using application instances obtained from the application object through the target interface, to obtain a problem analysis model, and to deploy the problem analysis model in the configuration system. The generation module is used to generate analysis prompt words for any application object in the service system based on the alarm type of the application object in the historical time period; The analysis module is used to input the analysis prompt words and the configuration data obtained from the application object corresponding to the analysis prompt words by calling the target interface into the problem analysis model in the configuration system, so as to perform fault analysis on the configuration data.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 8.

Images