Performance tuning method, device, cloud server, storage medium and program product

Abstract

The present application provides a performance tuning method, device, cloud server, storage medium and program product. The method relates to the field of artificial intelligence. When it is necessary to perform performance tuning on any target application, when it is determined that the tuning tool has not integrated the tuning knowledge base corresponding to the target application, with the help of a tuning decision model, a tuning knowledge base corresponding to the target application is automatically generated according to performance tuning instructions, and the tuning knowledge base corresponding to the target application is integrated into the tuning tool; further, by calling the tuning tool, the target application is performance tuned according to the tuning knowledge base corresponding to the target application. With the help of the tuning decision model and the tuning tool, automatic performance tuning of any application can be achieved, the complexity of performance tuning is reduced, the efficiency of performance tuning is improved, and performance tuning of various different applications can be more widely supported.

Description

Technical Field

[0001] The present application relates to computer technology, and in particular to a performance tuning method, device, cloud server, storage medium and program product. Background Art

[0002] When users on the cloud perform performance tuning, they often ask questions directly about the tuning of a certain application, such as "How to perform MySQL performance tuning?" At present, most intelligent assistants based on large models can only give some tuning suggestions. The tuning methods are scattered in multiple suggestions, which is not convenient for users to use directly. Moreover, the tuning operations need to be performed manually by users, which requires high knowledge in various fields for the tuners. Performance tuning is complex and inefficient. Summary of the invention

[0003] The present application provides a performance tuning method, device, cloud server, storage medium and program product to solve the problem that tuning operations need to be performed manually by users, and performance tuning is highly complex and inefficient.

[0004] In a first aspect, the present application provides a performance tuning method, comprising:

[0005] In response to receiving a performance tuning instruction for a target application, if it is determined that the tuning tool does not integrate a tuning knowledge base corresponding to the target application, generating a tuning knowledge base corresponding to the target application according to the performance tuning instruction through a tuning decision model;

[0006] Integrating a tuning knowledge base corresponding to the target application into the tuning tool;

[0007] The tuning tool integrated with the tuning knowledge base corresponding to the target application is called to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application.

[0008] In a second aspect, the present application provides a performance tuning method applied to an intelligent assistant, comprising:

[0009] Receiving a natural language instruction input in a command line of an operating system, wherein the natural language instruction is used to request performance tuning of a target application;

[0010] If it is determined according to the natural language instruction that the tuning tool does not integrate the tuning knowledge base corresponding to the target application, generating the tuning knowledge base corresponding to the target application according to the performance tuning instruction through the tuning decision model;

[0011] Integrating a tuning knowledge base corresponding to the target application into the tuning tool;

[0012] Calling the tuning tool integrated with the tuning knowledge base corresponding to the target application to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application;

[0013] Output performance tuning results.

[0014] In a third aspect, the present application provides a computing device, including:

[0015] Memory and processor;

[0016] The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the method provided in any of the aforementioned aspects is implemented.

[0017] In a fourth aspect, the present application provides a cloud server, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the cloud server performs a method provided in any of the preceding aspects.

[0018] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the method provided in any of the foregoing aspects is implemented.

[0019] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method provided in any of the aforementioned aspects.

[0020] The performance tuning method, device, cloud server, storage medium and program product provided by the present application, when it is necessary to perform performance tuning on any target application, when it is determined that the tuning tool has not integrated the tuning knowledge base corresponding to the target application, the method automatically generates a tuning knowledge base corresponding to the target application according to the performance tuning instructions with the help of a tuning decision model, and integrates the tuning knowledge base corresponding to the target application into the tuning tool; further, by calling the tuning tool, the performance of the target application is tuned according to the tuning knowledge base corresponding to the target application. By using the tuning decision model and the tuning tool, automatic performance tuning of any application can be achieved, the complexity of performance tuning is reduced, the efficiency of performance tuning is improved, and performance tuning of various different applications can be more widely supported. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] Figure 1 An example diagram of a system architecture for performance tuning provided by an exemplary embodiment of the present application;

[0023] Figure 2 A flowchart of a performance tuning method provided for an exemplary embodiment of the present application;

[0024] Figure 3 A complete flow chart of a performance tuning method provided for another exemplary embodiment of the present application;

[0025] Figure 4 A performance optimization process diagram provided for this embodiment;

[0026] Figure 5 A flow chart of a performance tuning method provided for another exemplary embodiment of the present application;

[0027] Figure 6 is a structural block diagram of a computing device according to an embodiment of the present application;

[0028] Figure 7 A schematic diagram of the structure of a cloud server provided in an embodiment of the present application.

[0029] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0030] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0031] It should be noted that the user information (including but not limited to user device information, user attribute 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 relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] First, the terms involved in this application are explained:

[0033] AI Agent: An intelligent entity that can perceive the environment, make decisions or perform tasks based on the information collected, and improve its behavior to achieve specific goals through learning and adaptation.

[0034] Plugin: An extensible functional module in an AI Agent that is used to enhance or add specific capabilities.

[0035] Workflow: The workflow in AI Agent is used to define how plugins collaborate in sequence to complete complex tasks.

[0036] Profilling Agent: An AI agent for performance tuning.

[0037] Command Line (CLI): Linux Shell (i.e. the command line interface of the operating system) interaction method.

[0038] Multimodal pre-trained model: refers to a pre-trained model whose input and output data involve multiple modal data such as images and text. After fine-tuning and training, it can be applied to multimodal task processing.

[0039] Pre-trained language model: A pre-trained model obtained by pre-training a large language model (LLM).

[0040] A large model refers to a deep learning model with large-scale model parameters, usually containing hundreds of millions, tens of billions, or even hundreds of billions of model parameters. A large model can also be called a foundation model / foundation model (FM). It is pre-trained with large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks and has good generalization capabilities, such as the large language model LLM, multi-modal pre-training model, etc.

[0041] When the big model is used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. The big model can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, it can be applied to computer vision tasks such as visual question answering (VQA), image caption (IC), image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of the big model include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0042] In the field of performance tuning, most intelligent assistants based on large models can only give some tuning suggestions. However, the tuning methods are often scattered among multiple suggestions, which is not convenient for users to use directly. Performance tuning operations still need to be performed manually, which requires the tuner to master knowledge in various fields such as computer hardware, operating systems, and applications. Performance tuning is highly complex and inefficient.

[0043] Currently, there are some tuning tools, such as intelligent assistants for operating systems, which can provide a fixed tuning knowledge base for performance tuning for specific application types (such as databases, servers, etc.). However, they only support applications that have integrated the tuning knowledge base and cannot support performance tuning for other applications.

[0044] The present application provides a performance tuning method. When it is necessary to perform performance tuning on any target application, when it is determined that the tuning tool has not integrated the tuning knowledge base corresponding to the target application, the tuning knowledge base corresponding to the target application is automatically generated according to the performance tuning instructions by means of a tuning decision model, and the tuning knowledge base corresponding to the target application is integrated into the tuning tool; further, by calling the tuning tool, the performance of the target application is tuned according to the tuning knowledge base corresponding to the target application. The method of the present application, with the help of a tuning decision model and a tuning tool, can realize automatic performance tuning of any application, reduce the complexity of performance tuning, improve the efficiency of performance tuning, and can more widely support performance tuning of various different applications.

[0045] The tuning knowledge base integrated in the tuning tool can be a tuning knowledge base predefined based on expert knowledge, or a tuning knowledge base generated by a tuning decision model. An application can correspond to one or more tuning knowledge bases, and a tuning knowledge base records one or more tuning rules and tuning strategies of the application. When the tuning tool performs performance tuning on the application, it can execute the corresponding tuning strategy when matching the tuning rules.

[0046] For example, if a tuning rule indicates that an application frequently reads disk I / O, the corresponding tuning strategy may include merging multiple I / O read operations of the application into block operations, or using memory to cache data so that the application's CPU requests data directly from the memory, thereby reducing I / O pressure.

[0047] Figure 1 This is an example diagram of a system architecture for performance tuning provided by an exemplary embodiment of the present application. Figure 1 As shown, the system architecture includes a cloud server and terminal devices.

[0048] Among them, a variety of applications (such as application 1, application 2, etc. shown in the figure) and intelligent assistants are deployed and run on the cloud server. The intelligent assistant can be an intelligent auxiliary tool on the operating system built based on the tuning decision model, which aims to help users manage tasks more efficiently, optimize system performance, provide personalized suggestions, and simplify complex operation processes. In this embodiment, the intelligent assistant can be an intelligent agent (AI Agent) to help users perform performance tuning of applications more efficiently.

[0049] The terminal device refers to the electronic device used by the user that runs the client of the smart assistant. Specifically, it can be a hardware device with network communication function, computing function and information display function, which includes but is not limited to smart phones, tablet computers, desktop computers, Internet of Things devices, servers, etc.

[0050] When performance tuning of any application is required, the user can send a performance tuning instruction for the target application to the intelligent assistant through the end-side device. For example, the user can input the performance tuning instruction for the target application to the command line of the cloud server operating system through the end-side device, or the user can input the performance tuning instruction for the target application through the visual interactive interface. The performance tuning instruction for the target application can be a natural language instruction, such as "Please perform performance tuning on MySQL in this environment."

[0051] The intelligent assistant determines whether the tuning tool has integrated the tuning knowledge base corresponding to the target application based on the performance tuning instructions for the target application. If it is determined that the tuning tool has not integrated the tuning knowledge base corresponding to the target application, the tuning decision model generates the tuning knowledge base corresponding to the target application based on the performance tuning instructions, and integrates the tuning knowledge base corresponding to the target application into the tuning tool.

[0052] Furthermore, by calling the tuning tool, the tuning tool automatically performs performance tuning on the target application according to the tuning knowledge base corresponding to the target application.

[0053] If it is determined that the tuning tool has integrated the tuning knowledge base corresponding to the target application, the intelligent assistant can directly call the tuning tool so that the tuning tool automatically performs performance tuning on the target application based on the integrated tuning knowledge base corresponding to the target application.

[0054] Among them, the tuning decision model can use any large model with powerful reasoning capabilities, such as various large language models LLM, or multimodal large models, etc., without specific limitation here.

[0055] Furthermore, the intelligent assistant can also output the performance tuning results of the target application to the terminal device.

[0056] It should be noted that the intelligent assistant, as an intelligent agent, uses the tuning tool as a main functional module (plugin) of the intelligent agent, so that the intelligent assistant has the ability to perform application tuning based on the integrated tuning knowledge base. The intelligent agent also extends other functional modules, which are not specifically limited here.

[0057] It should be noted that the type of application to be tuned in this application can be at least one of the types of database, server, engine, etc. Each application type can be further divided into multiple specific applications. For example, database type applications can be different versions under the database category such as MySQL or Oceanbase. Server types can include servers such as Nginx or HaProxy.

[0058] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0059] Figure 2 This is a flow chart of a performance tuning method provided by an exemplary embodiment of the present application. The execution subject of this embodiment is a cloud server that implements application performance tuning, such as the cloud server running the smart assistant mentioned above, etc. This embodiment does not make specific limitations at this time. Figure 2 As shown, the specific steps of this method are as follows:

[0060] Step S201, in response to receiving a performance tuning instruction for a target application, if it is determined that the tuning tool does not integrate a tuning knowledge base corresponding to the target application, a tuning knowledge base corresponding to the target application is generated according to the performance tuning instruction through a tuning decision model.

[0061] In actual applications, when performance tuning of a target application is required, a user can send a performance tuning instruction for the target application to the smart assistant through a terminal device running a client of the smart assistant.

[0062] For example, the user can access the command line interface of the cloud server where the intelligent assistant is located through the end-side device used, and enter the performance tuning instructions for the target application in the command line of the cloud server operating system through the command line interface. Among them, the performance tuning instructions entered in the command line can be natural language instructions, such as "please perform performance tuning on MySQL in this environment", which can help users perform application performance tuning more efficiently and simplify complex tuning operation processes.

[0063] For example, the intelligent assistant may provide a visual interactive interface to the terminal device. The user may input a performance tuning instruction for the target application through the visual interactive interface, and the performance tuning instruction may be an instruction in a natural language.

[0064] In this step, in response to receiving a performance tuning instruction for a target application, the intelligent assistant may determine an application identifier of the target application to be tuned, such as an application name of the target application, based on the content of the performance tuning instruction.

[0065] Among them, the performance tuning instruction for the target application can be a natural language text input by the user, input voice, etc. According to the content of the performance tuning instruction of the target application, the application identifier (such as application name, application type, etc.) of the target application to be tuned can be determined. Specifically, when obtaining the content of the performance tuning instruction of the target application, for the performance tuning instruction of the input voice type, the performance tuning instruction can be converted into the corresponding content text by automatic speech recognition and other methods. Further, the application identifier of the target application to be tuned is extracted from the content text of the performance tuning instruction of the target application. Specifically, the content of the performance tuning instruction of the target application can be input into a natural language understanding model, such as an entity recognition model, LLM, etc., and the application identifier of the target application can be automatically extracted from the content of the performance tuning instruction of the target application through the natural language understanding model. Exemplarily, the application identifier entity (such as application name) contained in the content of the performance tuning instruction of the target application is identified by the entity recognition model; or the powerful natural language processing capability of the LLM is used to extract the application identifier of the target application from the content of the performance tuning instruction of the target application.

[0066] Optionally, when the application identifier of the target application cannot be determined based on the performance tuning instruction, the intelligent assistant can output prompt information to prompt the user to enter the identifier of the target application for the specified performance tuning, such as the application name. Alternatively, the intelligent assistant can output an application list and prompt the user to select the target application for performance tuning from the application list, and obtain the corresponding application identifier based on the target application selected by the user.

[0067] Further, after determining the application identifier of the target application to be tuned, the intelligent assistant determines, based on the application identifier of the target application, whether the application identifiers of the tuning knowledge base integrated by the tuning tool include the application identifier of the target application.

[0068] Exemplarily, the intelligent assistant / tuning tool can maintain an integrated application identification set, including identifications of applications that have been integrated with corresponding tuning knowledge bases. The intelligent assistant determines whether the integrated application identification set includes the application identification of the target application. If the integrated application identification set includes the application identification of the target application, then the application identification of the target application is included in the application identification of the tuning knowledge base that has been integrated by the tuning tool, and it is determined that the tuning tool has integrated the tuning knowledge base corresponding to the target application. If the integrated application identification set does not include the application identification of the target application, then the application identification of the target application is not included in the application identification of the tuning knowledge base that has been integrated by the tuning tool, and it is determined that the tuning tool has not integrated the tuning knowledge base corresponding to the target application.

[0069] In the case that the tuning tool does not integrate the tuning knowledge base corresponding to the target application, the tuning knowledge base corresponding to the target application is generated according to the performance tuning instructions with the help of the tuning decision model.

[0070] Among them, the tuning decision model can use any large model with powerful reasoning capabilities, such as various large language models LLM, or multimodal large models, etc., without specific limitation here.

[0071] In an optional embodiment, a tuning knowledge base corresponding to the target application is generated according to performance tuning instructions through a tuning decision model, which can be implemented in the following manner: performance tuning enhancement data is obtained, the performance tuning instructions and the performance tuning enhancement data are input into the tuning decision model, and a tuning knowledge base corresponding to the target application is generated.

[0072] The performance tuning enhancement data includes performance tuning knowledge of various applications, and may include performance tuning-related knowledge of various applications that can be collected, specifically including but not limited to: performance tuning documents / manuals of various applications, and instructions for use of various applications.

[0073] Exemplarily, a first generation prompt may be preconfigured, the first generation prompt including a first task description and a slot to be inserted with input data. The first task description gives the task that the first generation prompt requires the tuning decision model to perform. The performance tuning instructions and performance tuning enhancement data are inserted as input data into the corresponding slots of the first generation prompt, respectively, to generate the corresponding first generation prompt information. The first generation prompt information is used to prompt the tuning decision model to perform the task given in the first task description, that is, to generate a tuning knowledge base corresponding to the target application mentioned in the performance tuning instruction based on the input performance tuning enhancement data.

[0074] In addition, the first generated prompt word may also include system prompts, task requirements (such as output format), etc., which can be designed and adjusted according to the actual task requirements, and are not specifically limited here. In some example scenarios, it may be necessary to provide other input information to the performance tuning model, and the first generated prompt word may also include slots for inserting other input information. For example, the storage location of the performance tuning enhancement data can be provided to the tuning decision model, and the tuning decision model can obtain the performance tuning enhancement data based on the storage location. The first generated prompt word may also include a slot for inserting the storage location of the performance tuning enhancement data.

[0075] The performance tuning instruction and the performance tuning enhancement data are embedded into the first generated prompt word to generate the first generated prompt information. The first generated prompt information is input into the tuning decision model, and the tuning decision model is used to perform reasoning based on the first generated prompt information to generate a tuning knowledge base corresponding to the target application, thereby realizing automatic generation of the tuning knowledge base.

[0076] In an optional embodiment, a tuning suggestion text corresponding to the performance tuning instruction can be generated by the tuning decision model. When it is determined that the tuning tool does not integrate the tuning knowledge base corresponding to the target application and the tuning knowledge base corresponding to the target application fails to be generated by the tuning decision model, the intelligent assistant outputs the tuning suggestion text.

[0077] Optionally, in the case where the tuning knowledge base corresponding to the target application fails to be generated in the aforementioned manner, the performance tuning instructions and the performance tuning enhancement data are input into the tuning decision model, and a tuning suggestion text is generated through the tuning decision model.

[0078] Optionally, the tuning decision model can be used to generate a tuning suggestion text and a tuning knowledge base corresponding to the target application through one reasoning, so as to reduce the number of reasoning times of the tuning decision model, save computing resources, and improve the efficiency of performance tuning.

[0079] Specifically, a pre-configured second generation prompt word can be obtained, and the second generation prompt word includes a second task description and a slot to be inserted with input data. The second task description gives the task that the second generation prompt word requires the tuning decision model to do. The performance tuning instructions and performance tuning enhancement data are used as input data and inserted into the corresponding slots of the second generation prompt word respectively, and the corresponding second generation prompt information can be generated. The second generation prompt information is used to prompt the tuning decision model to perform the task given by the second task description, that is, based on the input performance tuning enhancement data, the tuning suggestion text corresponding to the performance tuning instruction and the tuning knowledge base corresponding to the target application mentioned in the performance tuning instruction are generated. In addition, the second generation prompt word can also include system prompts, task requirements (such as output format), etc., which can be designed and adjusted according to the actual task requirements, and are not specifically limited here.

[0080] The performance tuning instruction and the performance tuning enhancement data are embedded into the second generated prompt word to generate the second generated prompt information. The second generated prompt information is input into the tuning decision model, and the tuning decision model is used to perform reasoning based on the second generated prompt information to generate a tuning suggestion text corresponding to the performance tuning instruction and a tuning knowledge base corresponding to the target application.

[0081] When the tuning knowledge base corresponding to the target application is generated successfully, subsequent steps are performed to integrate the tuning knowledge base corresponding to the target application into the tuning tool, and the tuning tool is called to perform performance tuning on the target application using the generated tuning knowledge base.

[0082] In the event that the generation of the tuning knowledge base corresponding to the target application fails, the intelligent assistant outputs a tuning suggestion text corresponding to the performance tuning instruction to the end-side device.

[0083] Step S202: Integrate the tuning knowledge base corresponding to the target application into the tuning tool.

[0084] After generating a tuning knowledge base corresponding to the target application with the help of the tuning decision model, the tuning knowledge base corresponding to the target application is integrated into the tuning tool.

[0085] Exemplarily, when an integrated application identification set is maintained, the application identification of the target application is added to the integrated application identification set.

[0086] Step S203: calling a tuning tool that integrates a tuning knowledge base corresponding to the target application, so as to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application.

[0087] After the tuning knowledge base corresponding to the target application is integrated into the tuning tool, the tuning tool is called so that the tuning tool performs performance tuning on the target application according to the tuning knowledge base corresponding to the target application, thereby realizing automatic performance tuning of the target application.

[0088] Optionally, after the performance tuning of the target application is performed, the intelligent assistant can also output the performance tuning results. The performance tuning results include, but are not limited to: the tuning content and performance improvement information executed on the target application. The tuning content executed on the target application can include the executed tuning items, and the parameter values ​​of each tuning item. The performance improvement information can include the overall performance improvement of the target application and / or the performance improvement corresponding to a single tuning item.

[0089] Optionally, when outputting the performance tuning results, the intelligent assistant may also output guidance information for further refinement of the tuning, such as functional description information and links of other refinement tuning tools.

[0090] The solution of this embodiment, when it is necessary to perform performance tuning on any target application, when it is determined that the tuning tool has not integrated the tuning knowledge base corresponding to the target application, the tuning knowledge base corresponding to the target application is automatically generated according to the performance tuning instructions with the help of the tuning decision model, and the tuning knowledge base corresponding to the target application is integrated into the tuning tool, and the performance of the target application is tuned according to the tuning knowledge base corresponding to the target application by calling the tuning tool. The method of the present application, with the help of the tuning decision model and the tuning tool, can realize automatic performance tuning of any application, reduce the complexity of performance tuning, improve the efficiency of performance tuning, and can more widely support the performance tuning of various different applications.

[0091] Based on the foregoing embodiment, in response to receiving a performance tuning instruction for a target application, if it is determined that the tuning tool has integrated a tuning knowledge base corresponding to the target application, the intelligent assistant can directly call the tuning tool to perform performance tuning on the target application based on the tuning knowledge base corresponding to the target application.

[0092] Figure 3 A complete flow chart of a performance tuning method provided by another exemplary embodiment of the present application. Figure 3 As shown, the method specifically comprises the following steps:

[0093] Step S301: Receive a performance tuning instruction for a target application.

[0094] In actual applications, when performance tuning of a target application is required, a user can send a performance tuning instruction for the target application to the smart assistant through a terminal device running a client of the smart assistant.

[0095] For example, the user can access the command line interface of the cloud server where the intelligent assistant is located through the end-side device used, and enter the performance tuning instructions for the target application in the command line of the cloud server operating system through the command line interface. Among them, the performance tuning instructions entered in the command line can be natural language instructions, such as "please perform performance tuning on MySQL in this environment", which can help users perform application performance tuning more efficiently and simplify complex tuning operation processes.

[0096] For example, the intelligent assistant may provide a visual interactive interface to the terminal device. The user may input a performance tuning instruction for the target application through the visual interactive interface, and the performance tuning instruction may be an instruction in a natural language.

[0097] The intelligent assistant receives the performance tuning instructions for the target application sent by the terminal device.

[0098] Step S302: Determine whether the tuning tool has integrated a tuning knowledge base corresponding to the target application.

[0099] In this step, the intelligent assistant can determine the application identifier of the target application to be tuned, such as the application name of the target application, based on the content of the performance tuning instruction. Further, after determining the application identifier of the target application to be tuned, the intelligent assistant determines whether the application identifier of the target application is included in the application identifier of the tuning knowledge base that has been integrated into the tuning tool based on the application identifier of the target application. For the specific implementation principle, please refer to the relevant content of step S201 in the aforementioned embodiment, which will not be repeated here.

[0100] If it is determined that the tuning tool does not integrate the tuning knowledge base corresponding to the target application, step S303 is executed to automatically generate the tuning knowledge base corresponding to the target application with the help of the tuning decision model. If the tuning knowledge base corresponding to the target application is successfully generated, step S304 is executed to integrate the generated tuning knowledge base corresponding to the target application into the tuning tool. Then step S305 is executed to perform performance tuning on the target application through the tuning tool according to the tuning knowledge base corresponding to the target application.

[0101] When it is determined that the tuning tool has integrated the tuning knowledge base corresponding to the target application, step S305 is directly executed to perform performance tuning on the target application through the tuning tool according to the integrated tuning knowledge base corresponding to the target application.

[0102] Step S303: Generate a tuning suggestion text corresponding to the performance tuning instruction and a tuning knowledge base corresponding to the target application through the tuning decision model.

[0103] In this step, the tuning decision model can be used to generate a tuning suggestion text and a tuning knowledge base corresponding to the target application through one reasoning, so as to reduce the number of reasoning times of the tuning decision model, save computing resources, and improve the efficiency of performance tuning.

[0104] Specifically, a pre-configured second generation prompt word is obtained, and the second generation prompt word includes a second task description and a slot to be inserted with input data. The second task description gives the task that the second generation prompt word requires the tuning decision model to do. In addition, the second generation prompt word may also include a system prompt, task requirements (such as output format), etc., which can be specifically designed and adjusted according to actual task requirements, and are not specifically limited here.

[0105] The performance tuning instruction and the performance tuning enhancement data are used as input data and are respectively embedded into the corresponding slots of the second generated prompt word to generate the corresponding second generated prompt information. The second generated prompt information is used to prompt the tuning decision model to perform the task given by the second task description, that is, based on the input performance tuning enhancement data, generate the tuning suggestion text corresponding to the performance tuning instruction and the tuning knowledge base corresponding to the target application mentioned in the performance tuning instruction.

[0106] The second generated prompt information is input into the tuning decision model, and the tuning decision model performs reasoning based on the second generated prompt information to generate a tuning suggestion text corresponding to the performance tuning instruction and a tuning knowledge base corresponding to the target application.

[0107] When the tuning knowledge base corresponding to the target application is generated successfully, continue to execute steps S304-S306. The intelligent assistant integrates the tuning knowledge base corresponding to the target application into the tuning tool, calls the tuning tool to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application, and outputs the performance tuning results.

[0108] In the event that the generation of the tuning knowledge base corresponding to the target application fails, step S307 is continued, and the intelligent assistant outputs a tuning suggestion text for user reference.

[0109] Step S304: If the tuning knowledge base corresponding to the target application is generated successfully, the tuning knowledge base corresponding to the target application is integrated into the tuning tool.

[0110] Step S305: calling a tuning tool to perform performance tuning on the target application according to a tuning knowledge base corresponding to the target application.

[0111] Optionally, before calling the tuning tool to perform performance tuning on the target application, the intelligent assistant may output tuning interaction information. The tuning interaction information is used to instruct the client (i.e., the user) to confirm whether to use the tuning tool that integrates the tuning knowledge base corresponding to the target application to perform performance tuning on the target application. The tuning interaction information may include introduction information of the tuning tool that integrates the tuning knowledge base corresponding to the target application, and confirmation prompt information. The confirmation prompt information is used to prompt the user whether to use the tuning tool to perform performance tuning on the target application.

[0112] When the user confirms through the client that the tuning tool is used to perform performance tuning on the target application, the tuning tool is called to perform performance tuning on the target application according to a tuning knowledge base corresponding to the target application.

[0113] In an optional embodiment, before calling the tuning tool to perform performance tuning on the target application, the intelligent assistant can back up the target application's operating environment data. Specifically, the intelligent assistant can store the backup data of the target application's operating environment data to provide a data basis for restoring the target application's operating environment data, thereby supporting the rollback operation of performance tuning.

[0114] After the performance tuning of the target application, when the user needs to restore the target application operating environment data to the state before the performance tuning, the user can issue a rollback instruction for the performance tuning of the target application to the intelligent assistant. In response to the rollback instruction for the performance tuning of the target application, the intelligent assistant restores the target application operating environment data based on the backup of the target application operating environment data, thereby restoring the target application operating environment data to the state before the performance tuning, and realizing the rollback of the target application operating environment.

[0115] The solution of this embodiment not only provides customers with automatic application performance tuning capabilities, but also can perform backup and recovery of the application running environment, thereby ensuring the security of the tuning.

[0116] Step S306: output the performance tuning result.

[0117] After the target application is performance tuned, the intelligent assistant can also output the performance tuning results. The performance tuning results include, but are not limited to, the tuning content and / or performance improvement information executed on the target application. The tuning content executed on the target application may include the executed tuning items, and information such as the parameter values ​​of each tuning item. The performance improvement information may include information on the overall performance improvement of the target application and / or the performance improvement corresponding to a single tuning item.

[0118] Optionally, when outputting the performance tuning results, the intelligent assistant may also output guidance information for further refinement of the tuning, such as functional description information and links of other refinement tuning tools.

[0119] It should be noted that the intelligent assistant can output the performance tuning results through a visual interface, a command line interface, etc., or can output the performance tuning results in other preset defined ways, which is not specifically limited in this embodiment.

[0120] Step S307: If the generation of the tuning knowledge base corresponding to the target application fails, output tuning suggestions.

[0121] In the case of failure to generate a tuning knowledge base corresponding to the target application, the intelligent assistant outputs tuning suggestions to provide users with reference tuning suggestions. The tuning suggestions output by the intelligent assistant can be text or voice.

[0122] In this embodiment, the intelligent assistant can use the tuning decision model to perform a reasoning operation and generate a tuning suggestion text corresponding to the performance tuning instruction and a tuning knowledge base corresponding to the target application.

[0123] For example, Figure 4 This is a performance tuning process framework diagram provided in this embodiment. Figure 4 As shown in the figure, in an example scenario where the tuning tool has not integrated the tuning knowledge base corresponding to the target application, the performance tuning instructions input by the user are embedded in a predefined prompt and then input into a tuning decision model (such as LLM) for reasoning together with the performance tuning enhancement data (including performance tuning knowledge of various applications) to generate tuning suggestion text corresponding to the performance tuning instructions and a tuning knowledge base corresponding to the target application.

[0124] If the tuning knowledge base corresponding to the target application is generated successfully, the tuning knowledge base corresponding to the target application is integrated into the tuning tool, and the tuning tool is called to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application, and the performance tuning result is output. If the tuning knowledge base corresponding to the target application is generated unsuccessfully, a tuning suggestion text is output for user reference.

[0125] It should be noted that in addition to tuning tools, the intelligent agent can also expand other functional modules, such as file cleaning, real-time monitoring, task management, network management, data backup and recovery, etc.

[0126] In some optional embodiments, the intelligent assistant can use any large language model (such as the aforementioned tuning decision model) to independently generate tuning suggestion text.

[0127] Furthermore, when it is necessary to output tuning suggestions, the intelligent assistant can output tuning suggestion text, or generate voice corresponding to the tuning suggestion text and output the voice. The way in which the intelligent assistant outputs tuning suggestions can be set according to actual application requirements and is not specifically limited here.

[0128] The solution of this embodiment can dynamically select a better tuning method for different target applications: for applications in which the tuning tool does not have an integrated tuning knowledge base, the tuning knowledge base can be automatically generated with the help of a tuning decision model (such as LLM), and the tuning knowledge base can be integrated into the tuning tool to achieve automatic performance tuning of the application. The tuning decision model (such as LLM) can be used to perform performance tuning for any application, rather than being limited to fixed applications in which the tuning tool has integrated the tuning knowledge base, thereby ensuring the breadth of applications that support tuning; for applications in which the tuning tool has integrated the tuning knowledge base, the tuning tool can be directly called to use the integrated tuning knowledge base to perform performance tuning of the application, and more accurate expert knowledge can be used for performance tuning of the corresponding application, thereby improving the accuracy of performance tuning.

[0129] The following takes an intelligent assistant for a certain type of operating system (such as Linux) as an example. The intelligent assistant supports natural language input. Users can directly enter questions expressed in natural language in the command line of the operating system. The intelligent assistant can provide knowledge related to daily use and operating systems, help users answer information related to daily life and operating systems, and simplify the steps for users to switch to browser search.

[0130] Figure 5 This is a flow chart of a performance tuning method provided by another exemplary embodiment of the present application. The execution subject of this embodiment is an intelligent assistant of the operating system, and the intelligent assistant has the ability to tune application performance. Figure 5 As shown, the specific steps of this method are as follows:

[0131] Step S501: receiving a natural language instruction input in a command line of an operating system, where the natural language instruction is used to request performance tuning of a target application.

[0132] Users can access the command line interface of the cloud server where the smart assistant is located through the end-side device they are using, and enter natural language commands in the command line of the cloud server operating system through the command line interface. The natural language commands entered in the command line are used to request performance tuning of the target application. For example, "Please perform performance tuning on MySQL in this environment." Through natural language input, users can perform application performance tuning more efficiently and simplify complex tuning operation processes.

[0133] The intelligent assistant can receive natural language instructions entered into the command line of the operating system.

[0134] Step S502: If it is determined according to the natural language instruction that the tuning tool does not integrate the tuning knowledge base corresponding to the target application, a tuning knowledge base corresponding to the target application is generated according to the performance tuning instruction through the tuning decision model.

[0135] In this step, the intelligent assistant can determine whether the tuning tool has integrated the tuning knowledge base corresponding to the target application based on the content of the natural language instruction.

[0136] Specifically, the intelligent assistant can determine the application identifier of the target application to be tuned, such as the application name of the target application, based on the content of the natural language instruction. Further, the intelligent assistant determines whether the application identifier of the tuning knowledge base integrated by the tuning tool contains the application identifier of the target application based on the application identifier of the target application. The specific implementation principle of this step refers to the relevant content of step S201 in the aforementioned embodiment, and is not specifically limited here.

[0137] Step S503: Integrate the tuning knowledge base corresponding to the target application into the tuning tool.

[0138] The specific implementation principle of this step refers to the relevant content of step S202 in the above embodiment, and is not specifically limited here.

[0139] Step S504: calling a tuning tool that integrates a tuning knowledge base corresponding to the target application, so as to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application.

[0140] The specific implementation principle of this step refers to the relevant content of step S203 in the above embodiment, and is not specifically limited here.

[0141] Step S505: output the performance tuning result.

[0142] After the target application is performance tuned, the intelligent assistant can also output the performance tuning results. The performance tuning results include, but are not limited to, the tuning content and performance improvement information of the target application. The tuning content of the target application may include the executed tuning items and the parameter values ​​of each tuning item. The performance improvement information may include the overall performance improvement of the target application and / or the performance improvement corresponding to a single tuning item.

[0143] For example, an example of input performance tuning results is as follows:

[0144] "MySQL in your environment has been tuned in the following aspects:

[0145] CPU: ... [The CPU tuning operations, parameters, effects, etc. are omitted here];

[0146] Memory: ... [The tuning operations, parameters, effects, etc. performed on memory are omitted here];

[0147] Network: ... [the tuning operations, parameters, effects, etc. performed on the network are omitted here]".

[0148] Optionally, when outputting the performance tuning results, the intelligent assistant may also output guidance information for further refinement of the tuning, such as functional description information and links of other refinement tuning tools.

[0149] Optionally, the intelligent assistant can obtain the execution results returned by the tuning tool, and generate performance tuning results output to the user based on the execution results, so that the performance tuning results are more readable and easier for users to understand.

[0150] In the scheme of this embodiment, when it is necessary to perform performance tuning on any target application, the intelligent assistant of the operating system, when determining that the tuning tool does not integrate the tuning knowledge base corresponding to the target application, automatically generates the tuning knowledge base corresponding to the target application according to the performance tuning instructions with the help of the tuning decision model, and integrates the tuning knowledge base corresponding to the target application into the tuning tool, and performs performance tuning on the target application according to the tuning knowledge base corresponding to the target application by calling the tuning tool. The method of the present application, with the help of the tuning decision model and the tuning tool, can realize automatic performance tuning of any application, reduce the complexity of performance tuning, improve the efficiency of performance tuning, and can more widely support performance tuning of various different applications.

[0151] Figure 6 is a structural block diagram of a computing device according to an embodiment of the present application. Figure 6 As shown, the computing device may include: one or more (only one is shown in the figure) processors 601 and a memory 602. The memory 602 is used to store computer programs / instructions, and the processor 601 is used to execute computer programs / instructions. When the computer programs / instructions are executed by the processor 601, the technical solutions provided by any of the aforementioned method embodiments are implemented. The specific functions and technical effects that can be achieved are similar and will not be described in detail here.

[0152] The above-mentioned computing device can be understood as an integrated intelligent terminal, including but not limited to a server, a desktop computer, a PC (Personal Computer), an all-in-one model machine, a mobile phone, a tablet computer or other portable intelligent terminal, etc., and the computing device can be pre-installed with the model in the above-mentioned embodiments of the present application.

[0153] Specifically, the computing device can pre-set multiple types of models, including but not limited to models in the fields of natural language processing, visual processing, speech processing, code processing, multimodal task processing, etc., so as to provide a variety of model choices. In different product forms, the computing device can support one or more model usage methods, including but not limited to model training, model calling, model fine-tuning, model deployment, model reasoning and application, etc. In some product forms, the computing device also supports model management, including but not limited to multi-type model management (supporting the management of multiple types of models such as discriminants and generative models), model version control (supporting the control of different model versions), model evaluation (based on model evaluation tools, evaluating the performance and effect of the model), etc. In other product forms, the computing device can also create applications based on the model, provide API (Application Programming Interface, application programming interface) calling capabilities, and can call the model to the created application through the API interface, while providing application management tools to achieve management and monitoring of the application.

[0154] Furthermore, the computing device can also include data management (supporting the creation and management of model tuning data sets), training center (providing rich training resources to help users learn and master AI technology), and basic management and control capabilities (providing enterprise-level basic management and control capabilities to ensure the security and efficient operation of the system). Through the above functions, a comprehensive, integrated AI development, training, deployment and application device is provided.

[0155] Figure 7 A schematic diagram of the structure of a cloud server provided in an embodiment of the present application. Figure 7 As shown, the cloud server includes: a memory 701 and a processor 702. The memory 701 is used to store computer-executable instructions and can be configured to store various other data to support operations on the cloud server. The processor 702 is connected to the memory 701 in communication and is used to execute the computer-executable instructions stored in the memory 701 to implement the technical solution provided by any of the above method embodiments. The specific functions and technical effects that can be achieved are similar and will not be repeated here.

[0156] Optional, such as Figure 7 As shown, the cloud server also includes: a firewall 703, a load balancer 704, a communication component 705, a power supply component 706 and other components. Figure 7 The following only shows some components, which does not mean that the cloud server only includes Figure 7 Components shown.

[0157] An embodiment of the present application also provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the method of any of the aforementioned embodiments is implemented. The specific functions and technical effects that can be achieved are not repeated here.

[0158] The present application also provides a computer program product, including a computer program, which implements the method of any of the above embodiments when executed by a processor. The computer program is stored in a readable storage medium, and at least one processor of the cloud server can read the computer program from the readable storage medium. At least one processor executes the computer program so that the cloud server executes the technical solution provided by any of the above method embodiments. The specific functions and technical effects that can be achieved are not repeated here.

[0159] The embodiment of the present application provides a chip, including: a processing module and a communication interface, the processing module can execute the technical solution of the cloud server in the aforementioned method embodiment. Optionally, the chip also includes a storage module (such as a memory), the storage module is used to store instructions, the processing module is used to execute the instructions stored in the storage module, and the execution of the instructions stored in the storage module enables the processing module to execute the technical solution provided by any of the aforementioned method embodiments.

[0160] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

[0161] It should be understood that the above processor can be a processing unit (Central Processing Unit, referred to as CPU), a graphics processing unit (graphics processing unit, referred to as GPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, referred to as DSP), application-specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in at least one processor.

[0162] The memory may include high-speed random access memory (RAM), and may also include non-volatile storage, such as at least one disk storage, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk.

[0163] The above storage may be an object storage service (OSS).

[0164] The above-mentioned memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0165] The above-mentioned communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as a mobile hotspot (WiFi), a second-generation mobile communication system (2G), a third-generation mobile communication system (3G), a fourth-generation mobile communication system (4G) / Long Term Evolution (LTE), a fifth-generation mobile communication system (5G) and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared technology, ultra-wide band (UWB) technology, Bluetooth technology and other technologies.

[0166] The power supply assembly provides power to various components of the device where the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply assembly is located.

[0167] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0168] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in a dedicated integrated circuit. Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0169] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0170] The order of the above-mentioned embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. In addition, in some of the processes described in the above-mentioned embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed or executed in parallel in the order in which they appear in this article, and are only used to distinguish between different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or less operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit "first" and "second" to different types. The meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0171] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0172] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application.

[0173] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A performance tuning method, characterized in that: include: In response to receiving a performance tuning instruction for a target application, if it is determined that the tuning tool does not integrate a tuning knowledge base corresponding to the target application, generating a tuning knowledge base corresponding to the target application according to the performance tuning instruction through a tuning decision model; Integrating a tuning knowledge base corresponding to the target application into the tuning tool; The tuning tool integrated with the tuning knowledge base corresponding to the target application is called to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application.

2. The method according to claim 1, characterized in that Also includes: In response to receiving a performance tuning instruction for a target application, if it is determined that the tuning tool integrates a tuning knowledge base corresponding to the target application, the tuning tool is called to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application.

3. The method according to claim 1, characterized in that The step of generating a tuning knowledge base corresponding to the target application according to the performance tuning instruction through the tuning decision model includes: Acquire performance tuning enhancement data, wherein the performance tuning enhancement data includes performance tuning knowledge of various applications; The performance tuning instruction and the performance tuning enhancement data are input into the tuning decision model to generate a tuning knowledge base corresponding to the target application.

4. The method according to claim 3, characterized in that The step of inputting the performance tuning instruction and the performance tuning enhancement data into the tuning decision model to generate a tuning knowledge base corresponding to the target application includes: The performance tuning instruction and the performance tuning enhancement data are embedded in a first generation prompt word to generate first generation prompt information, wherein the first generation prompt information is used to prompt the tuning decision model, and a tuning knowledge base corresponding to the target application mentioned in the performance tuning instruction is generated according to the performance tuning enhancement data; The first generated prompt information is input into the tuning decision model to generate a tuning knowledge base corresponding to the target application.

5. The method according to claim 1, characterized in that Also includes: Generate a tuning suggestion corresponding to the performance tuning instruction through the tuning decision model; In the event that the generation of the tuning knowledge base corresponding to the target application fails, the tuning suggestion is output.

6. The method according to claim 5, characterized in that Generating a tuning suggestion corresponding to the performance tuning instruction by using the tuning decision model includes: The performance tuning instruction and the performance tuning enhancement data are embedded in a second generation prompt word to generate second generation prompt information, wherein the second generation prompt information is used to prompt the tuning decision model, and a tuning suggestion corresponding to the performance tuning instruction and a tuning knowledge base corresponding to the target application mentioned in the performance tuning instruction are generated according to the performance tuning enhancement data; The second generated prompt information is input into a tuning decision model to generate the tuning suggestion and a tuning knowledge base corresponding to the target application.

7. The method according to any one of claims 1 to 6, characterized in that Also includes: In response to receiving a performance tuning instruction for a target application, determining an application identifier of the target application according to the performance tuning instruction; According to the application identifier of the target application, determining whether the application identifier of the tuning knowledge base integrated by the tuning tool includes the application identifier of the target application; If it is determined that the application identifier of the tuning knowledge base that has been integrated by the tuning tool includes the application identifier of the target application, it is determined that the tuning tool has been integrated with the tuning knowledge base corresponding to the target application.

8. The method according to any one of claims 1 to 6, characterized in that The calling of the tuning tool integrated with the tuning knowledge base corresponding to the target application to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application includes: Outputting tuning interaction information, where the tuning interaction information is used to instruct the client to confirm whether to use a tuning tool that integrates a tuning knowledge base corresponding to the target application to perform performance tuning on the target application; When the client confirms to use the tuning tool to perform performance tuning on the target application, the tuning tool is called to perform performance tuning on the target application according to a tuning knowledge base corresponding to the target application.

9. The method according to any one of claims 1 to 4, characterized in that: Before calling the tuning tool that integrates the tuning knowledge base corresponding to the target application to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application, the method further includes: Back up the operating environment data of the target application.

10. The method according to claim 9, characterized in that After calling the tuning tool that integrates the tuning knowledge base corresponding to the target application to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application, the method further includes: In response to a rollback instruction for performance tuning of the target application, the operating environment data of the target application is restored according to a backup of the operating environment data of the target application.

11. The method according to any one of claims 1 to 4, characterized in that: Also includes: Outputting a performance tuning result obtained by performing performance tuning on the target application, wherein the performance tuning result includes tuning content and / or performance improvement information performed on the target application.

12. A performance tuning method, characterized in that: Applications in smart assistants, including: Receiving a natural language instruction input in a command line of an operating system, wherein the natural language instruction is used to request performance tuning of a target application; If it is determined according to the natural language instruction that the tuning tool does not integrate the tuning knowledge base corresponding to the target application, generating the tuning knowledge base corresponding to the target application according to the performance tuning instruction through the tuning decision model; Integrating a tuning knowledge base corresponding to the target application into the tuning tool; Calling the tuning tool integrated with the tuning knowledge base corresponding to the target application to perform performance tuning on the target application according to the tuning knowledge base corresponding to the target application; Output performance tuning results.

13. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the method according to any one of claims 1 to 12 is implemented.

14. A cloud server, characterized in that: include: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the cloud server executes the method described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the method according to any one of claims 1 to 12 is implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

Images