Cloud network exception processing method, system and device, storage medium and program product

Abstract

The invention provides a cloud network exception handling method, system and device, a storage medium and a program product, and relates to the technical field of artificial intelligence, and the method comprises the steps: firstly, obtaining the problem information of the exception of a tenant instance in a cloud network from a user terminal; then, according to the problem information, determining a target diagnosis item and a target diagnosis parameter corresponding to the target diagnosis item; determining root cause information of the problem information based on the target diagnosis item and the target diagnosis parameter; and finally, according to the root cause information, determining a processing result corresponding to the problem information, and returning the processing result to the user terminal. In the embodiment of the invention, the target diagnosis item and the target diagnosis parameter can be determined according to the problem information, and then the root cause information of the problem is determined, so that deep analysis of the problem is realized, and a targeted solution is convenient to provide.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a cloud network exception handling method, system, device, storage medium and program product. Background Art

[0002] In cloud network operation and maintenance, network problem troubleshooting is a key area and has always been a difficult point. The network architecture in the cloud environment is complex, involving multiple virtual networks, subnets, security groups, and routing tables. The interconnections between these components make it very difficult to locate the problem. Network problems may span multiple regions and services, making it difficult to determine the source of the problem. At present, most network diagnosis systems are based on the "predefined rules and scenarios" model, that is, through "predefined rule matching" to obtain "predefined abnormal problem names", according to the "abnormal problem name" to obtain "predefined solutions". However, this processing method is a relatively general model, usually unable to conduct in-depth analysis of the problem, and therefore, unable to provide targeted solutions. Summary of the invention

[0003] The embodiments of the present application provide a cloud network exception handling method, system, device, storage medium and program product, which can determine the root cause information of the problem, thereby achieving in-depth analysis of the problem and providing targeted solutions.

[0004] In the first aspect, an embodiment of the present application provides a cloud network exception handling method, wherein the cloud network includes a server and user terminals corresponding to one or more tenant instances. The method is applied to the server and includes: obtaining problem information of an abnormality of a tenant instance in the cloud network from the user terminal; determining a target diagnostic item and a target diagnostic parameter corresponding to the target diagnostic item based on the problem information; determining root cause information of the problem information based on the target diagnostic item and the target diagnostic parameter; determining a processing result corresponding to the problem information based on the root cause information, and returning it to the user terminal.

[0005] In the second aspect, an embodiment of the present application provides a cloud network exception handling method, wherein the cloud network includes a server and user terminals corresponding to one or more tenant instances. The method is applied to the user terminal and includes: sending problem information about an abnormality in a tenant instance in the cloud network to the server, so that the server determines a corresponding processing result based on the problem information, wherein the processing result is determined based on root cause information of the problem information, and the root cause information is determined based on a target diagnostic item and a target diagnostic parameter corresponding to the target diagnostic item; and receiving the processing result sent by the server.

[0006] In a third aspect, an embodiment of the present application provides a cloud network exception handling system, wherein the cloud network includes a server, and user terminals corresponding to one or more tenant instances, and the system includes a server and a user terminal: the server is used to: obtain problem information of abnormal tenant instances in the cloud network from the user terminal; determine the target diagnostic item and the target diagnostic parameter corresponding to the target diagnostic item based on the problem information; determine the root cause information of the problem information based on the target diagnostic item and the target diagnostic parameter; determine the processing result corresponding to the problem information based on the root cause information, and return it to the user terminal. The user terminal is used to: send problem information of abnormal tenant instances in the cloud network to the server, so that the server determines the corresponding processing result based on the problem information, and the processing result is determined based on the root cause information of the problem information, and the root cause information is determined based on the target diagnostic item and the target diagnostic parameter corresponding to the target diagnostic item; receive the processing result sent by the server.

[0007] In a fourth aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the above methods when executing the computer program.

[0008] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any of the above methods is implemented.

[0009] In a sixth aspect, an embodiment of the present application provides a computer program product, the computer program product including a computer program, and the computer program implements any of the above methods when executed by a processor.

[0010] Compared with the prior art, this application has the following advantages: The present application provides a cloud network exception processing method, system, device, storage medium and program product. First, the problem information of the tenant instance in the cloud network is obtained from the user terminal; then, according to the problem information, the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item are determined; based on the target diagnosis item and the target diagnosis parameter, the root cause information of the problem information is determined; finally, according to the root cause information, the processing result corresponding to the problem information is determined and returned to the user terminal. In this embodiment, the target diagnosis item and the target diagnosis parameter can be determined according to the problem information, and then the root cause information of the problem can be determined, which realizes an in-depth analysis of the problem and facilitates the provision of targeted solutions.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments according to the present application and should not be regarded as limiting the scope of the present application.

[0013] Figure 1 A schematic diagram of an application scenario of a cloud network exception handling method according to an embodiment of the present application.

[0014] Figure 2 This is a flow chart of a cloud network exception handling method according to an embodiment of the present application.

[0015] Figure 3 This is a flow chart of a cloud network exception handling method according to an embodiment of the present application.

[0016] Figure 4 This is a structural block diagram of a cloud network exception handling device according to an embodiment of the present application.

[0017] Figure 5 This is a structural block diagram of a cloud network exception handling device according to an embodiment of the present application.

[0018] Figure 6 A block diagram of an electronic device used to implement an embodiment of the present application. DETAILED DESCRIPTION

[0019] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the concept or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary in nature and not restrictive.

[0020] To facilitate understanding of the technical solutions of the embodiments of the present application, the following describes the related technologies of the embodiments of the present application. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0021] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0022] The following is an explanation of the technical names involved in the technical solution of this application: Frequently Asked Questions (FAQ): A document or page that lists and answers common questions that users may have.

[0023] Operation guide: Operation guide is a series of detailed steps or instructions to guide users on how to complete a specific task or operation.

[0024] Large Language Model (LLM): A natural language processing model with a large number of parameters and data training. It can perform a variety of natural language processing tasks such as generating coherent text, understanding complex contexts, dialogue, translation, etc. It is usually based on deep learning architectures, such as the Transformer model, and is trained on large-scale text data through self-supervised learning to learn the statistical laws and patterns of language.

[0025] Retrieval-Augmented Generation (RAG): is a technique that enhances LLM by integrating external knowledge bases. It uses a collaborative approach to improve the performance of LLM by combining information retrieval mechanisms and in-context learning (ICL).

[0026] Artificial Intelligence Agent (AI Agent): An intelligent system that can perceive data / tools, make decisions based on context, and take actions to achieve specific goals.

[0027] When problems occur in cloud networks, related technologies can only provide "predefined solutions / FAQs" based on the "predefined rules and scenarios" model. However, in actual applications, the impact of network failures is wide and difficult to predict. A small problem may trigger a series of chain reactions in a complex cloud environment, and even cause large-scale service interruptions. If the problem is not analyzed in depth, it is impossible to accurately locate the problem and take effective repair measures.

[0028] In order to solve the above problems, an embodiment of the present application provides a cloud network exception handling method, which is based on the AIAgent architecture, combined with RAG technology and LLM, to conduct in-depth analysis of problems occurring in the cloud network, obtain the root cause of the problem, and obtain targeted solutions based on the root cause of the problem.

[0029] The large language model of one or more embodiments of the technical solution of the present application can be a large language model based on deep learning, which contains more than one billion parameters, and the underlying converter of the large model contains a series of neural networks. In one or more embodiments, an encoder and / or a decoder may be included, and have a self-attention function. These two types of modules extract meaning from the input text and clarify the structural relationship of the context words. The model is pre-trained on a public data set containing more than 1TB of text data to learn general language representation.

[0030] In order to adapt to the specific application scenario of this application - problem diagnosis of tenant instances in cloud networks, we fine-tuned the model on a dedicated dataset containing thousands of problem diagnoses. This model receives multiple diagnostic items and the corresponding retrieval results in a preset database using RAG technology as input, and can generate target diagnostic items and target diagnostic parameters as output. Then, based on the target diagnostic items and target diagnostic parameters, the root cause information of the problem is obtained. Compared with the traditional model based on "predefined rules and scenarios", the advantage of this application is that it can determine the root cause information of the problem, thereby achieving in-depth analysis of the problem and providing targeted solutions.

[0031] Figure 1 A schematic diagram of an application scenario of the cloud network exception handling method provided in this application. In this embodiment, LLM is used to understand the problem, diagnose the problem and recommend solutions. Figure 1 As shown, the specific implementation process is as follows: First, construct an exception handling knowledge base in advance. Obtain the operation guide of the relevant network instance in the FAG or cloud network from the data warehouse and perform word segmentation. Then, extract the diagnosis / operation strategy from the word-segmented data and perform vectorization to obtain multiple text vectors, which are stored in the vector database and used as the exception handling knowledge base.

[0032] When receiving abnormal problem information (such as Figure 1 After the “ask a question” is clicked, LLM is used to understand the question. Specifically, the large language model is used to segment the question, and entity extraction and question extraction are performed to obtain the abnormal object and question information.

[0033] Then, the problem is diagnosed. Specifically, according to the object with the exception, multiple diagnostic items associated with the object are queried in the pre-configured association relationship between the object and the diagnostic item. The RAG service is called to retrieve the diagnostic items in the exception handling knowledge base to obtain the query result documents corresponding to the multiple diagnostic items. LLM is used to perform root cause analysis. Specifically, first, the query result document, multiple diagnostic items and prompt instructions are input into the LLM, and the large language model determines the target diagnostic items and corresponding target diagnostic parameters from the multiple diagnostic items. Among them, the prompt instructions are used to guide the large language model to better understand and respond to specific tasks or queries, and never generate expected, high-quality output. Then, the Application Programming Interface (API) is called to check the target diagnostic items and target diagnostic parameters of the object with the exception, including log checks and configuration checks, and obtain the inspection results corresponding to the target diagnostic parameters.

[0034] Finally, a solution is recommended. Based on the inspection results, the root cause of the problem information is determined and a solution is generated. Specifically, based on the inspection results, the RAG service is called to query the root cause and solution of the problem in the exception handling knowledge base, and the root cause and solution of the problem are returned and displayed through the console.

[0035] The following uses multiple embodiments to introduce the specific implementation process of the technical solution of this application from the perspective of the server and the perspective of the user terminal: An embodiment of the present application provides a cloud network exception handling method. The method in this embodiment can be applied to servers, platforms, devices, etc. with computing and processing capabilities, wherein the server can be a server cluster or a single server, a server deployed in the cloud, or a local server.

[0036] like Figure 2 The flowchart of the cloud network exception handling method according to an embodiment of the present application is shown, including: Step S201: Obtaining abnormal problem information of a tenant instance in a cloud network from a user terminal.

[0037] Step S202: determining a target diagnosis item and a target diagnosis parameter corresponding to the target diagnosis item according to the problem information.

[0038] Step S203: determining the root cause information of the problem information based on the target diagnosis item and the target diagnosis parameter.

[0039] Step S204: Determine the processing result corresponding to the problem information according to the root cause information, and return it to the user terminal.

[0040] Cloud Networking refers to network services based on cloud computing technology, which allow users to access and manage computing resources through the Internet. The core function of cloud networking is to connect a large number of computing resources to achieve resource sharing, management and scheduling. These resources include servers, storage devices, databases, etc., which are centrally managed to improve resource utilization efficiency. Cloud networks involve multiple virtual networks, subnets, security groups, and routing tables, and problems may occur during daily operation. Cloud networks include, but are not limited to, servers and user terminals corresponding to one or more tenant instances. Problem information can be abnormal conditions or fault information that occurs during the operation of tenant instances of enterprise tenants or individual tenants of the cloud network.

[0041] Tenant instances in cloud networks usually refer to virtual network entities created in cloud computing environments, which allow users to build, configure, and manage network resources on the cloud platform. These virtual network entities include but are not limited to virtual routers, load balancers, virtual switches, security groups, etc., which together constitute the cloud network architecture.

[0042] Diagnostic items refer to items that need to be diagnosed for a cloud network instance, and can be items of multiple dimensions associated with a cloud network instance. For example, if the problem information is "Accessing the load balancer returns error code 502", that is, the load balancer is abnormal, then the diagnostic items include the response time of the load balancer, the server associated with the load balancer, and the application running on the server. Each diagnostic item is associated with at least one diagnostic parameter, such as the CPU utilization of the server. The parameter value of the diagnostic parameter can be used to determine whether the object is abnormal.

[0043] According to the problem information, the target diagnostic items and target diagnostic parameters that need to be diagnosed can be determined from multiple diagnostic items. According to the target diagnostic items and target diagnostic parameters, the problem information can be deeply analyzed to obtain the root cause information of the problem. The root cause information refers to the information that describes the root cause of the problem. According to the root cause information, targeted solutions can be obtained.

[0044] The cloud network exception handling method provided in the embodiment of the present application first obtains the problem information of the tenant instance in the cloud network from the user terminal; then, according to the problem information, determines the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item; based on the target diagnosis item and the target diagnosis parameter, determines the root cause information of the problem information; finally, according to the root cause information, determines the processing result corresponding to the problem information, and returns it to the user terminal. In this embodiment, the target diagnosis item and the target diagnosis parameter can be determined according to the problem information, and then the root cause information of the problem can be determined, which realizes the in-depth analysis of the problem and facilitates the provision of targeted solutions.

[0045] The following introduces the specific implementation process of the above steps through multiple implementation methods: In one implementation, step S202, determining a target diagnosis item and a target diagnosis parameter corresponding to the target diagnosis item according to the problem information, includes: Step S2021, searching the exception handling knowledge base according to the problem information to obtain a search result corresponding to the problem information; Step S2022: obtaining target diagnostic items and target diagnostic parameters corresponding to the target diagnostic items based on the search results and the large language model.

[0046] In actual applications, after the server obtains the problem information of the cloud tenant's network instance, it calls the RAG service to search in the exception handling knowledge base and obtain multiple search result documents. The exception handling knowledge base is constructed using the exception problem information and the processing solution information. The problem information, search result documents and the prompt instructions obtained based on the prompt engineering are input into the large language model, and the large language model is used to obtain the target diagnosis items and target diagnosis parameters.

[0047] Optionally, the exception handling knowledge base is constructed in the following manner: obtain the operation guide of the network instance in the FAG or cloud network, perform word segmentation processing, extract the exception problem information and the processing solution information, perform vectorization processing, obtain multiple text vectors and store them.

[0048] In this embodiment, the target diagnosis items and target diagnosis parameters are obtained by searching in the exception handling knowledge base and using the large language model for reasoning. The target diagnosis items and target diagnosis parameters obtained by this processing method are more relevant to the problem information, which is convenient for laying a good foundation for subsequent location of the root cause of the problem.

[0049] In one implementation, step S2021, based on the problem information, searches are performed in the exception handling knowledge base to obtain search results corresponding to the problem information, including: Acquire multiple diagnostic items associated with the object with the exception corresponding to the problem information; the multiple diagnostic items are pre-configured for the object. Use the multiple diagnostic items to search in the exception handling knowledge base to obtain the search results.

[0050] In actual applications, by extracting entities from problem information, we can obtain the object with the exception corresponding to the problem information. For example, by extracting the entity "load balancer" from the problem information "accessing the load balancer returns error code 502", "load balancer" is the object with the exception. We query multiple diagnostic items pre-configured for "load balancer", call the RAG service, search the exception handling knowledge base for each diagnostic item, and obtain multiple retrieval result documents.

[0051] Optionally, multiple levels of diagnostic items may be preconfigured for the object, and the lowest level diagnostic items correspond to multiple diagnostic parameters. When obtaining multiple diagnostic items associated with the abnormal object corresponding to the problem information, all or part of the levels of diagnostic items may be configured to be obtained according to specific needs.

[0052] In this embodiment, the retrieval is performed using multiple diagnostic items associated with the abnormal object, which can make the retrieval more targeted and improve the relevance of the retrieval results to the question.

[0053] In one implementation, step S2022, based on the retrieval results and the large language model, obtains the target diagnostic items and the target diagnostic parameters corresponding to the target diagnostic items, including: inputting multiple diagnostic items and retrieval results into the large language model, and obtaining the target diagnostic items and target diagnostic parameters output by the large language model.

[0054] In actual applications, the search results, multiple diagnostic items and prompt instructions retrieved using the RAG service are input into the large language model. The large language model performs inference based on the search results, and screens out one or more target diagnostic items with a high relevance to the problem information from the multiple diagnostic items, as well as one or more target diagnostic parameters corresponding to the target diagnostic items. The target diagnostic items and target diagnostic parameters are used to perform targeted diagnosis on abnormal objects.

[0055] In this embodiment, a large language model is used to determine target diagnostic items and target diagnostic parameters from multiple diagnostic items, which facilitates subsequent problem processing and improves the efficiency of problem solving.

[0056] In one implementation, step S203, determining the root cause information of the problem information based on the target diagnosis item and the target diagnosis parameter, includes: Step S2031, based on the target diagnosis item and the target diagnosis parameter, the abnormal object corresponding to the problem information is inspected to obtain the inspection result corresponding to the target diagnosis parameter.

[0057] Step S2032: Determine the root cause information of the problem information according to the inspection result.

[0058] In actual applications, after obtaining the target diagnostic items and target diagnostic parameters that are highly relevant to the problem information, the AI ​​Agent is used to call the Application Programming Interface (API) to obtain the parameter values ​​of the target diagnostic parameters under the target diagnostic items of the abnormal object as the inspection results. Based on the inspection results, the root cause of the problem is determined.

[0059] For example, if there is a problem with the "load balancer", check the operation log and configuration information of the "load balancer", for example, check whether the parameters of the server associated with the load balancer are abnormal. If there is an abnormality, it means that the root cause of the problem with the "load balancer" is a problem with the associated server. If the indicators of the associated server are normal, the root cause of the problem may be a problem with the application currently running on the server.

[0060] In this embodiment, based on the target diagnostic items and target diagnostic parameters, the abnormal objects corresponding to the problem information are checked to determine the root cause of the problem, thereby achieving an in-depth analysis of the problem so as to obtain targeted solutions.

[0061] In one implementation, step S2032, determining the root cause information of the problem information according to the inspection result, includes: The inspection result is compared with the standard result of the target diagnostic parameter to obtain a comparison result. According to the comparison result, the root cause information of the problem information is determined.

[0062] The inspection result may be a parameter value of a diagnostic parameter, such as the CPU utilization of a server, or a symbol indicating a diagnostic result, such as a symbol indicating whether a port of the server is open. The parameter value or the indicator symbol standard result is compared to determine whether the parameter value is within the numerical range of the standard result, or whether the symbol indicating the diagnostic result indicates an abnormality according to the standard result indicator, so as to determine the root cause information of the problem information.

[0063] In one implementation, step S204, determining a processing result corresponding to the problem information according to the root cause information, includes: According to the root cause information, search in the exception handling knowledge base to obtain the corresponding processing results of the problem information.

[0064] In actual applications, after determining the root cause of the problem, the RAG service is called to search the exception handling knowledge base to obtain the corresponding processing result of the problem information, and the processing result is sent to the user terminal as a solution. The processing result includes at least one of the diagnosis exception description, diagnosis strategy description and diagnosis processing suggestion.

[0065] In this embodiment, by searching based on the root cause information of the problem information, a more targeted solution can be obtained.

[0066] In one implementation, step S201, obtaining information about an abnormal problem of a tenant instance in a cloud network from a user terminal, includes: Receive question information sent by a user terminal; or receive a selection instruction for a preset question list sent by the user terminal, and determine the question information according to the selection instruction.

[0067] In actual applications, the question information entered by the user in the question input box of the interactive interface can be received by the user terminal, or a question list can be configured for each cloud network instance, which lists commonly occurring problems, and the question information selected by the user in the question list can be determined according to the user's selection instructions.

[0068] The embodiment of the present application provides a cloud network exception handling method, and the method in the embodiment can be applied to user terminals, devices, etc. with computing and processing capabilities. The cloud network includes a server and user terminals corresponding to one or more tenant instances.

[0069] like Figure 3 The flowchart of the cloud network exception handling method according to an embodiment of the present application is shown, including: Step S301, sending problem information of an abnormality in a tenant instance in a cloud network to a server, so that the server determines a corresponding processing result based on the problem information, and the processing result is determined based on the root cause information of the problem information, and the root cause information is determined based on the target diagnostic item and the target diagnostic parameters corresponding to the target diagnostic item.

[0070] Step S302: receiving the processing result sent by the server.

[0071] The specific implementation process of the server obtaining the corresponding processing result according to the problem information has been described in detail in the above embodiments and will not be repeated here.

[0072] The cloud network exception processing method provided in the embodiment of the present application first sends the problem information of the tenant instance in the cloud network to the server, so that the server determines the corresponding processing result according to the problem information, and the processing result is determined according to the root cause information of the problem information, and the root cause information is determined according to the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item; finally, the processing result sent by the server is received. In this embodiment, the target diagnosis item and the target diagnosis parameter can be determined according to the problem information, and then the root cause information of the problem can be determined, so as to realize the in-depth analysis of the problem and facilitate the provision of targeted solutions.

[0073] In addition, an embodiment of the present application provides a cloud network exception handling system, including the server and user terminal in the above embodiments. The cloud network includes a server and user terminals corresponding to one or more tenant instances.

[0074] The server is used to: obtain problem information of abnormal tenant instances in the cloud network from the user terminal; determine the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item based on the problem information; determine the root cause information of the problem information based on the target diagnosis item and the target diagnosis parameter; determine the processing result corresponding to the problem information based on the root cause information, and return it to the user terminal.

[0075] The user terminal is used to: send problem information about abnormalities in tenant instances in the cloud network to the server, so that the server determines the corresponding processing results based on the problem information, and the processing results are determined based on the root cause information of the problem information, and the root cause information is determined based on the target diagnostic items and the target diagnostic parameters corresponding to the target diagnostic items; receive the processing results sent by the server.

[0076] The specific working processes of the server and the user terminal have been described in detail in the above embodiments and will not be repeated here.

[0077] The present application provides a cloud network exception handling system. First, the server obtains the problem information of the tenant instance in the cloud network from the user terminal; then, according to the problem information, the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item are determined; based on the target diagnosis item and the target diagnosis parameter, the root cause information of the problem information is determined; finally, according to the root cause information, the processing result corresponding to the problem information is determined and returned to the user terminal. In this embodiment, the target diagnosis item and the target diagnosis parameter can be determined according to the problem information, and then the root cause information of the problem can be determined, so as to realize the in-depth analysis of the problem and facilitate the provision of targeted solutions.

[0078] Corresponding to the application scenario and method of the method provided in the embodiment of the present application, the embodiment of the present application also provides a cloud network exception processing device. Figure 4 The structure diagram of a cloud network exception handling device according to an embodiment of the present application is shown, and the device includes: The problem acquisition module 401 is used to acquire the problem information of abnormal tenant instances in the cloud network from the user terminal.

[0079] The parameter determination module 402 is used to determine the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item according to the problem information.

[0080] The root cause determination module 403 is used to determine the root cause information of the problem information based on the target diagnosis item and the target diagnosis parameter.

[0081] The result determination module 404 is used to determine the processing result corresponding to the problem information according to the root cause information, and return it to the user terminal.

[0082] The cloud network anomaly processing device provided in the embodiment of the present application first obtains the problem information of the abnormal tenant instance in the cloud network from the user terminal; then, according to the problem information, determines the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item; based on the target diagnosis item and the target diagnosis parameter, determines the root cause information of the problem information; finally, according to the root cause information, determines the processing result corresponding to the problem information, and returns it to the user terminal. In this embodiment, the target diagnosis item and the target diagnosis parameter can be determined according to the problem information, and then the root cause information of the problem can be determined, which realizes the in-depth analysis of the problem and facilitates the provision of targeted solutions.

[0083] In one implementation, the parameter determination module 402 is used to: search the exception handling knowledge base according to the problem information to obtain the search results corresponding to the problem information; the exception handling knowledge base is constructed using the exception problem information and the processing solution information. Based on the search results and the large language model, the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item are obtained.

[0084] In one implementation, when the parameter determination module 402 searches the exception handling knowledge base according to the problem information and obtains the search result corresponding to the problem information, it is used to: obtain multiple diagnostic items associated with the object with the exception corresponding to the problem information; the multiple diagnostic items are pre-configured for the object. Use the multiple diagnostic items to search in the exception handling knowledge base to obtain the search result.

[0085] In one implementation, when the parameter determination module 402 obtains the target diagnostic items and the target diagnostic parameters corresponding to the target diagnostic items based on the retrieval results and the large language model, it is used to: input multiple diagnostic items and retrieval results into the large language model to obtain the target diagnostic items and target diagnostic parameters output by the large language model.

[0086] In one implementation, the root cause determination module 403 is used to: based on the target diagnosis item and the target diagnosis parameter, check the abnormal object corresponding to the problem information to obtain the inspection result corresponding to the target diagnosis parameter, and determine the root cause information of the problem information according to the inspection result.

[0087] In one implementation, when determining the root cause information of the problem information based on the inspection result, the root cause determination module 403 is used to: compare the inspection result with the standard result of the target diagnostic parameter to obtain a comparison result, and determine the root cause information of the problem information based on the comparison result.

[0088] In one implementation, the result determination module 404 is used to: search in the exception handling knowledge base according to the root cause information to obtain the processing result corresponding to the problem information, and the processing result includes at least one of the diagnosis exception description, the diagnosis strategy description and the diagnosis processing suggestion.

[0089] In one implementation, the question acquisition module 401 is used to: receive question information sent by a user terminal; or receive a selection instruction for a preset question list sent by a user terminal, and determine the question information according to the selection instruction.

[0090] The functions of each module in the embodiment of the present application can be referred to the corresponding description in the above method, and have corresponding beneficial effects, which will not be repeated here.

[0091] Corresponding to the application scenario and method of the method provided in the embodiment of the present application, the embodiment of the present application also provides a cloud network exception processing device. Figure 5 The structure diagram of a cloud network exception handling device according to an embodiment of the present application is shown, and the device includes: The problem sending module 501 is used to send problem information of abnormalities occurring in tenant instances in the cloud network to the server, so that the server determines the corresponding processing result based on the problem information. The processing result is determined based on the root cause information of the problem information, and the root cause information is determined based on the target diagnostic item and the target diagnostic parameters corresponding to the target diagnostic item.

[0092] The result receiving module 502 is used to receive the processing result sent by the server.

[0093] The cloud network exception processing device provided in the embodiment of the present application first sends the problem information of the tenant instance in the cloud network to the server, so that the server determines the corresponding processing result according to the problem information, and the processing result is determined according to the root cause information of the problem information, and the root cause information is determined according to the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item; finally, the processing result sent by the server is received. In this embodiment, the target diagnosis item and the target diagnosis parameter can be determined according to the problem information, and then the root cause information of the problem can be determined, so as to realize the in-depth analysis of the problem and facilitate the provision of targeted solutions.

[0094] The functions of each module in the embodiment of the present application can be referred to the corresponding description in the above method, and have corresponding beneficial effects, which will not be repeated here.

[0095] Figure 6 FIG. 1 is a block diagram of an electronic device used to implement an embodiment of the present application. Figure 6 As shown, the electronic device includes: a memory 610 and a processor 620. The memory 610 stores a computer program that can be run on the processor 620. When the processor 620 executes the computer program, the method in the above embodiment is implemented. The number of the memory 610 and the processor 620 can be one or more.

[0096] The electronic device also includes: The communication interface 630 is used to communicate with external devices and perform data exchange transmission.

[0097] If the memory 610, the processor 620 and the communication interface 630 are implemented independently, the memory 610, the processor 620 and the communication interface 630 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0098] Optionally, in a specific implementation, if the memory 610, the processor 620 and the communication interface 630 are integrated on a chip, the memory 610, the processor 620 and the communication interface 630 can communicate with each other through an internal interface.

[0099] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by a processor.

[0100] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method provided in the embodiment of the present application is implemented.

[0101] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.

[0102] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.

[0103] It should be understood that the above processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0104] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0105] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0106] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0107] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0108] Any process or method described in the flow chart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0109] The logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0110] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0111] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0112] The above is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope recorded in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A cloud network exception handling method, characterized in that: The cloud network includes a server and user terminals corresponding to one or more tenant instances. The method is applied to the server and includes: Acquire information about abnormal problems of tenant instances in the cloud network from the user terminal; Determine, according to the problem information, a target diagnostic item and a target diagnostic parameter corresponding to the target diagnostic item; Determining root cause information of the problem information based on the target diagnosis item and the target diagnosis parameter; According to the root cause information, a processing result corresponding to the problem information is determined and returned to the user terminal.

2. The method according to claim 1, characterized in that The step of determining a target diagnosis item and a target diagnosis parameter corresponding to the target diagnosis item according to the problem information includes: According to the problem information, searching in the exception handling knowledge base to obtain the search results corresponding to the problem information; the exception handling knowledge base is constructed using the exception problem information and the handling solution information; Based on the retrieval result and the large language model, the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item are obtained.

3. The method according to claim 2, characterized in that The step of searching the exception handling knowledge base according to the problem information to obtain a search result corresponding to the problem information includes: Acquire multiple diagnostic items associated with the object with abnormality corresponding to the problem information; the multiple diagnostic items are pre-configured for the object; The plurality of diagnosis items are used to search in an exception handling knowledge base to obtain the search result.

4. The method according to claim 3, characterized in that The obtaining, based on the search result and the large language model, the target diagnosis item and the target diagnosis parameter corresponding to the target diagnosis item comprises: The multiple diagnosis items and the search results are input into a large language model to obtain the target diagnosis items and the target diagnosis parameters output by the large language model.

5. The method according to claim 1, characterized in that The determining the root cause information of the problem information based on the target diagnosis item and the target diagnosis parameter includes: Based on the target diagnosis item and the target diagnosis parameter, an abnormal object corresponding to the problem information is inspected to obtain an inspection result corresponding to the target diagnosis parameter; According to the inspection result, the root cause information of the problem information is determined.

6. The method according to claim 5, characterized in that Determining the root cause information of the problem information according to the inspection result includes: Comparing the inspection result with the standard result of the target diagnostic parameter to obtain a comparison result; According to the comparison result, the root cause information of the problem information is determined.

7. The method according to any one of claims 1 to 6, characterized in that: The determining, according to the root cause information, a processing result corresponding to the problem information includes: According to the root cause information, a search is performed in the exception handling knowledge base to obtain a processing result corresponding to the problem information, wherein the processing result includes at least one of a diagnostic exception description, a diagnostic strategy description, and a diagnostic processing suggestion.

8. The method according to any one of claims 1 to 6, characterized in that The obtaining, from the user terminal, information about an abnormal problem of a tenant instance in the cloud network includes: receiving the question information sent by the user terminal; or A selection instruction for a preset question list sent by a user terminal is received, and the question information is determined according to the selection instruction.

9. A cloud network exception handling method, characterized in that: The cloud network includes a server and a user terminal corresponding to one or more tenant instances. The method is applied to the user terminal and includes: Sending to the server problem information indicating an abnormality of a tenant instance in the cloud network, so that the server determines a corresponding processing result according to the problem information, wherein the processing result is determined according to root cause information of the problem information, wherein the root cause information is determined according to a target diagnosis item and a target diagnosis parameter corresponding to the target diagnosis item; Receive the processing result sent by the server.

10. A cloud network exception handling system, characterized in that: The cloud network includes a server and a user terminal corresponding to one or more tenant instances, and the system includes the server and the user terminal; The server is used to: obtain problem information of abnormal tenant instances in the cloud network from the user terminal; determine a target diagnosis item and a target diagnosis parameter corresponding to the target diagnosis item according to the problem information; Based on the target diagnosis item and the target diagnosis parameter, determining the root cause information of the problem information; according to the root cause information, determining the processing result corresponding to the problem information, and returning it to the user terminal; The user terminal is used to: send problem information about an abnormality in a tenant instance in a cloud network to the server, so that the server determines a corresponding processing result based on the problem information, wherein the processing result is determined based on root cause information of the problem information, and the root cause information is determined based on a target diagnostic item and a target diagnostic parameter corresponding to the target diagnostic item; and receive the processing result sent by the server.

11. An electronic device, characterized in that: The electronic device comprises a memory, a processor and a computer program stored in the memory, and the processor implements the method according to any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images