System optimization method, device, and storage medium

Abstract

This application provides a system optimization method that can be applied to the fields of computer technology and artificial intelligence technology. The system optimization method includes: analyzing the obtained system performance indicators and system error logs to determine the system optimization target; based on the optimization target, filtering the obtained system configuration information, system performance indicators, and system error logs to obtain multidimensional reference data; performing multimodal association on the multidimensional reference data based on the parameter knowledge graph used for the system to determine the target system parameters used to achieve the optimization target, and optimizing the system using the target system parameters. This application also provides a device and a storage medium.

Description

Technical Field

[0001] The present application relates to the fields of computer technology and artificial intelligence technology, and more specifically to a system optimization method, device, and storage medium. Background Art

[0002] With the emergence of storage systems for cloud computing, artificial intelligence training, and other application scenarios, optimizing system error reporting or performance indicators to improve service effectiveness has become a pressing issue for current systems. Related technologies implement semi-automated system tuning based on a pre-configured tuning rule library.

[0003] In the process of realizing the concept of this application, there are at least the following problems in the related technologies: the preset tuning rule library has a bottleneck of knowledge solidification, which makes the optimization methods in the related technologies unable to achieve more accurate system optimization for complex scenarios. Summary of the Invention

[0004] In view of the above problems, the present application provides a system optimization method, device, and storage medium.

[0005] According to the first aspect of the present application, a system optimization method is provided, which includes: analyzing the obtained system performance indicators and system error logs to determine the optimization goals of the system; based on the above optimization goals, performing data screening on the obtained system configuration information, the above system performance indicators and the above system error logs to obtain multidimensional reference data; based on the parameter knowledge graph used for the above system, performing multimodal association on the above multidimensional reference data to determine the target system parameters for achieving the above optimization goals, so as to optimize the above system using the above target system parameters.

[0006] According to an embodiment of the present application, the above-mentioned multi-dimensional reference data is multimodally associated based on the parameter knowledge graph used for the above-mentioned system to determine the target system parameters for achieving the above-mentioned optimization goals, including: based on the preset parameter effectiveness level, the above-mentioned parameter knowledge graph and the above-mentioned multi-dimensional reference data are processed for at least one round using a preset model to determine the above-mentioned target system parameters.

[0007] According to an embodiment of the present application, the above-mentioned parameter effectiveness levels include: the first level, the above-mentioned first level represents that the adjusted parameters take effect during the system operation; the above-mentioned parameter effectiveness conditions based on the preset parameters, using the preset model to perform at least one round of processing on the above-mentioned parameter knowledge graph and the above-mentioned multidimensional reference data to determine the above-mentioned target system parameters, including: using the above-mentioned preset model to process the above-mentioned parameter knowledge graph and the above-mentioned multidimensional reference data to determine the first parameter information that meets the first level; determining the first optimization result of the first optimization system corresponding to the above-mentioned first parameter information based on the above-mentioned first parameter information; when the above-mentioned first optimization result represents the realization of the above-mentioned optimization goal, the above-mentioned first parameter information is determined as the target parameter information.

[0008] According to an embodiment of the present application, the above-mentioned parameter effectiveness level also includes: the second level, the above-mentioned second level represents that the adjusted parameters take effect after restarting the system service; the above-mentioned method also includes: when the above-mentioned first optimization result represents that the above-mentioned optimization goal has not been achieved, the above-mentioned preset model is used to process the above-mentioned parameter knowledge graph and the above-mentioned multidimensional reference data to determine the second parameter information that meets the second level; based on the above-mentioned second parameter information, the second optimization result of the second optimization system corresponding to the above-mentioned second parameter information is determined; when the above-mentioned second optimization result represents that the above-mentioned optimization goal has been achieved, the above-mentioned first parameter information and the above-mentioned second parameter information are determined as target parameter information.

[0009] According to an embodiment of the present application, the above-mentioned parameter effectiveness level also includes: the third level, the above-mentioned third level represents that the adjusted parameters take effect after restarting the device of the running system; the above-mentioned method also includes: when the above-mentioned second optimization result represents that the above-mentioned optimization goal has not been achieved, the above-mentioned parameter knowledge graph and the above-mentioned multidimensional reference data are processed using a preset model to determine the third parameter information that meets the third level; based on the above-mentioned third parameter information, the third optimization result of the third optimization system corresponding to the above-mentioned third parameter information is determined; when the above-mentioned third optimization result represents that the above-mentioned optimization goal has been achieved, the above-mentioned first parameter information, the above-mentioned second parameter information and the above-mentioned third parameter information are determined as target parameter information.

[0010] According to an embodiment of the present application, the second optimization result of the second optimization system corresponding to the second parameter information is determined based on the second parameter information, including: generating an operation instruction for updating the data system parameters based on the second parameter information; issuing the operation instruction to the first optimization system based on the obtained system service time of the first optimization system to update the system parameters of the system to obtain the second optimization system; inputting the collected system configuration information, system performance indicators, system error log and first prompt information of the second optimization system into the preset model, and outputting the second optimization result, wherein the first prompt information is used to prompt the preset model to determine whether the optimization goal is achieved.

[0011] According to an embodiment of the present application, based on the above-mentioned optimization goal, the obtained system configuration information, the above-mentioned system performance indicators and the above-mentioned system error log are subjected to data screening to obtain multi-dimensional reference data, including: determining a plurality of knowledge fragments matching the above-mentioned optimization goal from a preset knowledge base; inputting the above-mentioned plurality of knowledge fragments, the above-mentioned system configuration information, the above-mentioned system performance indicators, the above-mentioned system error log and the second prompt information into the above-mentioned preset model, and outputting the above-mentioned multi-dimensional reference data, wherein the above-mentioned second prompt information is used to prompt the above-mentioned preset model to refer to the above-mentioned plurality of knowledge fragments to perform data screening on the system configuration information, the above-mentioned system performance indicators and the above-mentioned system error log according to the optimization goal.

[0012] According to an embodiment of the present application, the above method also includes: preprocessing the above optimization objectives, the above multidimensional reference data and the above target system parameters to obtain knowledge fragments that meet the preset format; and storing the above knowledge fragments in the above preset knowledge base.

[0013] The second aspect of the present application provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0014] The fourth aspect of the present application further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the computer program or instructions are executed by a processor.

[0015] According to the embodiments of the present application, based on the analysis of system performance indicators and system error logs, it is determined that the current system may have optimization targets; the optimization targets are used to screen information in three dimensions, namely, system configuration information, system performance indicators, and system error logs, to obtain multidimensional reference data, so as to improve the correlation between data and optimization targets while ensuring rich data dimensions, and reduce the influence of irrelevant data on determining target system parameters; the reference data dimensions are expanded through multidimensional reference data, the number of adjustable parameters used to achieve the optimization targets is expanded through the parameter knowledge graph, and the multidimensional reference data is multimodally associated based on the parameter knowledge graph used for the system to determine the target system parameters used to complete the optimization targets, so as to break the bottleneck of knowledge solidification in related technologies, improve the accuracy of target system parameters, and systematically optimize the target system parameters through various parameters in the target system parameters, so as to more accurately optimize the performance of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above contents and other objects, features and advantages of the present application will become more apparent through the following description of the embodiments of the present application with reference to the accompanying drawings, in which:

[0017] Figure 1 An application scenario diagram of the system optimization method according to an embodiment of the present application is shown.

[0018] Figure 2 A flow chart of a system optimization method according to an embodiment of the present application is shown.

[0019] Figure 3 A flow chart of a system optimization method according to another embodiment of the present application is shown.

[0020] Figure 4 A schematic diagram of a system optimization method according to an embodiment of the application is shown.

[0021] Figure 5 A structural block diagram of a system optimization device according to an embodiment of the present application is shown.

[0022] Figure 6 A block diagram of an electronic device suitable for implementing a system optimization method according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present application. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present application. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present application.

[0024] The terms used herein are only for describing specific embodiments and are not intended to limit this application. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0025] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0026] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0027] In the technical solution of this application, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0028] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided in the embodiments of the present application all provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0029] Related technologies use a preset optimization rule base to achieve semi-automatic tuning. For example, an optimization rule base is built into the distributed storage system Ceph. Specifically, when it is detected that the processor load of storage node A is greater than a preset threshold, the preset optimization rule base is matched with the corresponding processing method for the current problem of "processor load greater than the preset threshold".

[0030] However, in actual production applications, system loads are dynamic, and pre-configured optimization rule bases cannot automatically learn, adapt, or update themselves to cope with these new and unknown situations. Furthermore, updating the optimization rule base often requires manual work from developers, which is time-consuming and lags. Furthermore, the system's hardware configuration can also affect the optimization direction. An optimization rule base that relies solely on manual experience cannot solve the problems encountered in actual production.

[0031] Embodiments of the present application provide a system optimization method that analyzes acquired system performance indicators and system error logs to determine the system's optimization target. Based on the optimization target, the acquired system configuration information, system performance indicators, and system error logs are filtered to obtain multidimensional reference data. Based on a parameter knowledge graph for the system, multimodal association is performed on the multidimensional reference data to determine target system parameters for achieving the optimization target, and the system is optimized using the target system parameters.

[0032] Figure 1 An application scenario diagram of the system optimization method according to an embodiment of the present application is shown.

[0033] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a server 104, and a system 105. A medium provides a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 104, and between the server 104 and the system 105. The medium of the communication link may include various connection types, such as wired or wireless communication links or optical fiber cables, etc.

[0034] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0035] The first terminal device 101 , the second terminal device 102 , and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0036] The server 104 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal devices.

[0037] It should be noted that the system optimization method provided in the embodiment of the present application can generally be executed by the server 104. Accordingly, the system optimization device provided in the embodiment of the present application can generally be set in the server 104. The system optimization method provided in the embodiment of the present application can also be executed by a server or server cluster that is different from the server 104 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the system 105. Accordingly, the system optimization device provided in the embodiment of the present application can also be set in a server or server cluster that is different from the system 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 104.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only . According to the implementation requirements, there can be any number of terminal devices, networks and servers.

[0039] The following will be based on Figure 1 The scene described by Figures 2 to 4 The system optimization method of the embodiment of the present application is described in detail.

[0040] Figure 2 A flow chart of a system optimization method according to an embodiment of the present application is shown.

[0041] like Figure 2 As shown, the system optimization method of this embodiment includes operations S210 to S230.

[0042] In operation S210 , the acquired system performance indicators and system error logs are analyzed to determine a system optimization target.

[0043] In operation S220 , based on the optimization goal, data screening is performed on the acquired system configuration information, system performance indicators, and system error logs to obtain multi-dimensional reference data.

[0044] In operation S230 , multimodal association is performed on the multidimensional reference data based on the parameter knowledge graph for the system, and target system parameters for achieving the optimization goal are determined, so as to optimize the system using the target system parameters.

[0045] According to embodiments of the present application, system performance indicators may include collected disk input / output rates, processor load, memory load, storage space utilization, and the like. For example, for the distributed storage system Ceph, system performance indicators may also include the utilization of each storage node, the storage status of each storage node, and the like. System error logs may include error logs generated by the hardware running the system and error logs generated by applications in the system. System error logs may include information such as operation timeouts and network packet loss. System performance indicators and system error logs may be obtained by deploying a collection program in the system.

[0046] The obtained system performance indicators and system error logs are input into the trained model for determining the optimization target, so that the model can analyze the system performance indicators and system error logs to determine the optimization target of the system. The optimization target of the system may include improving the system throughput, reducing the processor load of the system, etc. Specifically, the optimization target may also include reducing the processor load of the system by 5%, increasing the throughput of the system by 10%, etc.

[0047] In the process of determining the optimization target, the model used to determine the optimization target can be obtained by training using a large amount of data. The input data of the training model can be historical system performance indicators and historical system error logs. The label can be the optimization target determined manually.

[0048] System configuration information may include system kernel parameters, system version, etc. For example, for a distributed storage system Ceph, system configuration information may also include the number of storage nodes in the distributed storage system, etc. System configuration information may be acquired based on a pre-deployed information collection program.

[0049] Based on the optimization goal, the obtained system configuration information, system performance indicators and system error logs are screened to select multi-dimensional reference data with high relevance to the optimization goal from the data of multiple dimensions, enriching the data dimensions used to determine them while reducing the amount of data to improve data accuracy.

[0050] The parameter knowledge graph includes the relationships between system parameters. For example, parameter A must be adjusted simultaneously with parameter B. The system parameters included in the parameter knowledge graph can be configurable parameters of the system. Based on the relationships between the various parameters in the parameter knowledge graph, as well as the multiple parameters included in the parameter knowledge graph, multimodal association is performed on the multidimensional reference data to simulate the influence relationship between each data item in the multidimensional reference data and the system parameters, thereby determining the target system parameters for achieving the optimization goal.

[0051] The target system parameters may include multiple system parameters and parameter values ​​corresponding to the multiple parameters. The multiple system parameters included in the target system parameters may be parameters included in the parameter knowledge graph. The target system parameters are used to update the system parameters, thereby optimizing the system and improving the service quality of the system.

[0052] According to the embodiments of the present application, based on the analysis of system performance indicators and system error logs, it is determined that the current system may have optimization targets; the optimization targets are used to screen information in three dimensions, namely, system configuration information, system performance indicators, and system error logs, to obtain multidimensional reference data, so as to improve the correlation between data and optimization targets while ensuring rich data dimensions, and reduce the influence of irrelevant data on determining target system parameters; the reference data dimensions are expanded through multidimensional reference data, the number of adjustable parameters used to achieve the optimization targets is expanded through the parameter knowledge graph, and the multidimensional reference data is multimodally associated based on the parameter knowledge graph used for the system to determine the target system parameters used to complete the optimization targets, so as to break the bottleneck of knowledge solidification in related technologies, improve the accuracy of target system parameters, and systematically optimize the target system parameters through various parameters in the target system parameters, so as to more accurately optimize the performance of the system.

[0053] According to an embodiment of the present application, based on the optimization goal, the obtained system configuration information, system performance indicators and system error logs are screened to obtain multi-dimensional reference data, including: determining multiple knowledge fragments that match the optimization goal from a preset knowledge base; inputting the multiple knowledge fragments, system configuration information, system performance indicators, system error logs and second prompt information into a preset model, and outputting multi-dimensional reference data, wherein the second prompt information is used to prompt the preset model to refer to multiple knowledge fragments to screen the system configuration information, system performance indicators and system error logs according to the optimization goal.

[0054] According to an embodiment of the present application, a preset knowledge base includes multiple knowledge fragments, each of which includes a system optimization goal from a historical data screening process and multidimensional reference data corresponding to the optimization goal. Multiple knowledge fragments matching the optimization goal are determined from the preset knowledge base, and fuzzy matching can be used to determine the multiple knowledge fragments matching the optimization goal.

[0055] The preset model is a neural network model based on the self-attention mechanism and deep learning model architecture. The preset model is pre-trained with corpus data including prompt information and input data, and completes reinforcement learning of "multi-dimensional reference data output based on multiple knowledge fragments, system configuration information, system performance indicators and system error logs" through supervised fine-tuning and manual feedback.

[0056] Multiple knowledge fragments, system configuration information, system performance indicators, system error logs, and second prompt information are input into a preset model, allowing the preset model to learn from the multiple knowledge fragments and increase the preset model's ability to output multidimensional reference data. The preset model filters data from the system configuration information, system performance indicators, and system error logs to output multidimensional reference data.

[0057] The second prompt information is used to prompt the preset model to refer to multiple knowledge fragments to perform data screening on system configuration information, system performance indicators and system error logs according to the optimization goal. For example, the second prompt information can be "Please use the data types screened from the input 'multiple knowledge fragments' as a reference to screen the data related to completing the optimization goal: increasing bandwidth from the input data including 'system configuration information, system performance indicators, and system error logs'."

[0058] According to an embodiment of the present application, multiple knowledge fragments in a preset knowledge base that match the optimization target are used to provide knowledge supplements for the preset model to increase the learning scope of the preset model, thereby improving the accuracy of the multidimensional reference data output by the preset model, and further improving the accuracy of the target system parameters.

[0059] According to an embodiment of the present application, the system optimization method further includes: preprocessing the optimization target, multidimensional reference data and target system parameters to obtain knowledge fragments that meet a preset format; and storing the knowledge fragments in a preset knowledge base.

[0060] According to an embodiment of the present application, the optimization objective, multidimensional reference data, and target system parameters are preprocessed to cleanse the optimization objective, multidimensional reference data, and target system parameters. The cleansed content is then combined with data descriptions to generate knowledge fragments that meet a preset format. For example, the preset format may be "optimization objective: ...; multidimensional reference data: ...; target system parameters: ...." The knowledge fragments can be stored in a preset knowledge base in ".json" format.

[0061] According to an embodiment of the present application, the optimization objectives, multidimensional reference data and target system parameters are stored in a preset knowledge base as learning data of a preset model, so as to improve the accuracy of the output multidimensional reference data by improving the learning ability of the preset model, thereby improving the accuracy of the target system parameters.

[0062] According to an embodiment of the present application, multimodal association is performed on multidimensional reference data based on a parameter knowledge graph for the system to determine target system parameters for achieving optimization goals, including: based on a preset parameter effectiveness level, using a preset model to perform at least one round of processing on the parameter knowledge graph and multidimensional reference data to determine the target system parameters.

[0063] According to an embodiment of the present application, the preset parameter effectiveness level may be a parameter effectiveness level set according to a parameter effectiveness condition. The parameter effectiveness level is used as a condition for processing the parameter knowledge graph and multidimensional reference data in each round, so that the preset model processes the parameter knowledge graph and multidimensional reference data based on the preset parameter effectiveness level until the optimization goal is achieved or all parameter effectiveness levels are traversed to determine the target system parameters.

[0064] The preset model is a neural network model based on the self-attention mechanism and deep learning model architecture. The preset model is pre-trained with corpus data including prompt information and input data, and completes reinforcement learning for the task of "determining target system parameters" through supervised fine-tuning and manual feedback.

[0065] According to an embodiment of the present application, based on a preset parameter effectiveness level, the parameter knowledge graph and multidimensional reference data are processed for at least one round using a preset model, and the target system parameters are gradually determined based on the parameter effectiveness level, thereby reducing the parameter quantity of the target system parameters obtained by a single decision, so as to reduce faults caused by parameter conflicts, thereby improving the quality of the target system parameters in a more refined manner, and further improving the accuracy of system optimization.

[0066] According to an embodiment of the present application, multi-dimensional reference data is multimodally associated based on the parameter knowledge graph used for the system to determine the target system parameters for achieving the optimization goal, and it also includes: modal unification processing is performed on the various heterogeneous data included in the multi-dimensional reference data to obtain a standardized multi-modal data set, wherein key-value pair extraction and feature conversion are performed on the information filtered from the system configuration information included in the multi-dimensional reference data to obtain system configuration features; vector embedding processing is performed on the error log text filtered from the system error log based on the semantic encoder to obtain semantic features; time alignment processing is performed on the time series performance data filtered from the system performance indicators, and the data after time alignment is subjected to feature conversion to obtain performance indicator features.

[0067] The system configuration features, semantic features, and performance indicator features are mapped to nodes of the parameter knowledge graph to obtain an updated parameter knowledge graph. Based on the graph neural network reasoner, a cross-modal association path search is performed on the updated parameter knowledge graph to determine the association weights between the nodes corresponding to the system configuration features and multiple parameters, the association weights between the nodes corresponding to the semantic features and multiple parameters, and the association weights between the nodes corresponding to the performance indicator features and multiple parameters. Based on the association weights, the multiple parameters included in the parameter knowledge graph are screened to obtain a candidate parameter set. Based on the parameter matrix composed of the candidate parameter set, the effect of system tuning is simulated, and the parameter values ​​of each parameter in the candidate parameter set used to achieve the optimization goal are determined to obtain the target system parameters.

[0068] According to the embodiments of the present application, by combining multimodal data processing with knowledge graphs, graph neural networks are used to accurately analyze the associations between features and parameters, screen key parameters, and simulate to determine the optimal parameter values, thereby effectively improving the accuracy of target system parameters.

[0069] According to an embodiment of the present application, the parameter effectiveness levels include: the first level, the first level characterizes that the adjusted parameters take effect during the system operation; based on the preset parameter effectiveness conditions, the parameter knowledge graph and multidimensional reference data are processed by the preset model for at least one round to determine the target system parameters, including: using the preset model to process the parameter knowledge graph and multidimensional reference data to determine the first parameter information that meets the first level; based on the first parameter information, determine the first optimization result of the first optimization system corresponding to the first parameter information; when the first optimization result characterizes the achievement of the optimization goal, the first parameter information is determined as the target parameter information.

[0070] According to an embodiment of the present application, the third prompt information, the parameter knowledge graph and the multidimensional reference data are input into the preset model, and the first parameter information is output, wherein the third prompt information is used to prompt the preset model to process the parameter knowledge graph and the multidimensional reference data, and determine the parameter information that meets the requirements of taking effect during the system operation and can achieve the optimization goal, wherein the parameter information may include multiple parameter names and parameter values ​​corresponding to the multiple parameter names.

[0071] Based on the first parameter information, the system parameters are updated to obtain a first optimization system, and based on the system performance indicators of the first optimization system, a first optimization result representing whether the optimization target is achieved is determined. When the first optimization result represents that the optimization target is achieved, the first parameter information is determined as the target parameter information.

[0072] According to an embodiment of the present application, the adjusted parameters are made effective during the operation of the system as a condition for the first round of determining parameter information for determining the target system parameters, so that when the first optimization result represents the achievement of the optimization target, the first parameter information is determined as the target parameter information to reduce the possibility of system errors caused by updating the system parameters using the target parameter information, thereby improving the quality of the target system parameters in a more refined manner, and further improving the accuracy of system optimization.

[0073] According to an embodiment of the present application, the parameter effectiveness level also includes: the second level, the second level indicates that the adjusted parameters take effect after restarting the system service; the system optimization method also includes: when the first optimization result indicates that the optimization target has not been achieved, using a preset model to process the parameter knowledge graph and multidimensional reference data to determine the second parameter information that meets the second level; based on the second parameter information, determining the second optimization result of the second optimization system corresponding to the second parameter information; when the second optimization result indicates that the optimization target has been achieved, determining the first parameter information and the second parameter information as target parameter information.

[0074] According to an embodiment of the present application, when the first optimization result indicates that the optimization target has not been achieved, the fourth prompt information, the parameter knowledge graph and the multidimensional reference data are input into the preset model, and the second parameter information is output, wherein the fourth prompt information is used to prompt the preset model to process the parameter knowledge graph and the multidimensional reference data, and determine the parameter information that meets the requirements of taking effect after restarting the system service and can achieve the optimization target, wherein the parameter information may include multiple parameter names and parameter values ​​corresponding to the multiple parameter names.

[0075] According to an embodiment of the present application, the parameters of the first optimization system are updated based on the second parameter information to obtain a second optimization system. A second optimization result is determined based on the system performance indicator of the second optimization system to indicate whether the second optimization system has achieved an optimization target. If the second optimization result indicates that the optimization target has been achieved, the first parameter information and the second parameter information are determined as target parameter information. If the second optimization result indicates that the optimization target has been achieved, the first parameter information and the second parameter information are determined as target parameter information.

[0076] According to an embodiment of the present application, the adjusted parameters are made effective after the system service is restarted as a condition for the second round of determining parameter information for determining the target system parameters, so that when the second optimization result represents the achievement of the optimization target, the first parameter information and the second parameter information are determined as the target parameter information to reduce the possibility of system errors caused by updating the system parameters using the target parameter information, thereby improving the quality of the target system parameters in a more refined manner, and further improving the accuracy of system optimization.

[0077] According to an embodiment of the present application, the parameter effectiveness level also includes: the third level, the third level indicates that the adjusted parameters take effect after restarting the device running the system; the system optimization method also includes: when the second optimization result indicates that the optimization target has not been achieved, using a preset model to process the parameter knowledge graph and multidimensional reference data to determine the third parameter information that meets the third level; based on the third parameter information, determining the third optimization result of the third optimization system corresponding to the third parameter information; when the third optimization result indicates that the optimization target has been achieved, determining the first parameter information, the second parameter information and the third parameter information as the target parameter information.

[0078] According to an embodiment of the present application, when the second optimization result indicates that the optimization target has not been achieved, the fifth prompt information, the parameter knowledge graph and the multidimensional reference data are input into the preset model, and the third parameter information is output, wherein the fifth prompt information is used to prompt the preset model to process the parameter knowledge graph and the multidimensional reference data, and determine the parameter information that meets the requirements of taking effect after restarting the system service and can achieve the optimization target, wherein the parameter information may include multiple parameter names and parameter values ​​corresponding to the multiple parameter names.

[0079] The parameters of the second optimization system are updated based on the third parameter information to obtain a third optimization system. A second optimization result is determined based on a system performance indicator of the third optimization system to indicate whether the third optimization system has achieved an optimization target. If the second optimization result indicates that the optimization target has been achieved, the first parameter information and the second parameter information are determined as target parameter information. If the second optimization result indicates that the optimization target has been achieved, the first parameter information and the second parameter information are determined as target parameter information.

[0080] When the second optimization result indicates that the optimization target has not been achieved, the fifth prompt information, the parameter knowledge graph and the multidimensional reference data are input into the preset model, and the first parameter information is output, wherein the fifth prompt information is used to prompt the preset model to process the parameter knowledge graph and the multidimensional reference data, and determine the parameter information that is effective after the device of the running system is restarted and can achieve the optimization target, wherein the parameter information may include multiple parameter names and parameter values ​​corresponding to the multiple parameter names.

[0081] According to an embodiment of the present application, the adjusted parameters are made effective after the device of the running system is restarted as a condition for determining the third parameter information for determining the target system parameters, so that when the third optimization result represents the achievement of the optimization target, the first parameter information, the second parameter information and the third parameter information are determined as the target parameter information to reduce the possibility of system errors caused by updating the system parameters using the target parameter information, thereby improving the quality of the target system parameters in a more refined manner, and further improving the accuracy of system optimization.

[0082] Figure 3 A flow chart of a system optimization method according to another embodiment of the present application is shown.

[0083] like Figure 3 As shown, the system optimization method of this embodiment includes operations S301 to S312.

[0084] In operation S301, first parameter information satisfying a first level is determined.

[0085] In operation S302 , a first optimization result is determined based on the first parameter information.

[0086] In operation S303 , it is determined whether the first optimization result represents that the optimization goal is achieved.

[0087] If the first optimization result indicates that the optimization goal is achieved, operation S304 is performed; otherwise, operation S305 is performed.

[0088] In operation S304, the first parameter information is determined as target parameter information.

[0089] In operation S305, second parameter information satisfying the second level is determined.

[0090] In operation S306 , a second optimization result is determined based on the second parameter information.

[0091] In operation S307 , it is determined whether the second optimization result indicates that the optimization goal is achieved.

[0092] If the second optimization result indicates that the optimization goal is achieved, operation S308 is performed; otherwise, operation S309 is performed.

[0093] In operation S308, the first parameter information and the second parameter information are determined as target parameter information.

[0094] In operation S309 , a second optimization result is determined based on the third parameter information.

[0095] In operation S310 , it is determined whether the third optimization result indicates that the optimization goal is achieved.

[0096] If the second optimization result indicates that the optimization target is achieved, operation S311 is performed; otherwise, operation S312 is performed.

[0097] In operation S311, target parameter information is determined based on the first parameter information, the second parameter information, and the third parameter information.

[0098] In operation S312 , the preset model is fine-tuned based on the system configuration information, the system performance index, the system error log, and the target parameter information.

[0099] According to an embodiment of the present application, when the third optimization result indicates that the optimization target has not been achieved, the preset model is fine-tuned based on system configuration information, system performance indicators, system error logs and target parameter information to improve the accuracy of the preset model.

[0100] According to an embodiment of the present application, a second optimization result of a second optimization system corresponding to the second parameter information is determined based on the second parameter information, including: generating an operation instruction for updating the data system parameters based on the second parameter information; issuing an operation instruction to the first optimization system based on the obtained system service time of the first optimization system to update the system parameters of the system to obtain a second optimization system; inputting the collected system configuration information, system performance indicators and system error log of the second optimization system and the first prompt information into a preset model, and outputting a second optimization result, wherein the first prompt information is used to prompt the preset model to determine whether the optimization goal is achieved.

[0101] According to an embodiment of the present application, each parameter in the second parameter information is identified to generate an operation instruction for updating the parameters of the first optimization system for each parameter. The system service time of the first optimization system is obtained to determine a non-service time period during which the first optimization system is not in service. During the non-service time period, an operation instruction is issued to the first optimization system, and the system service is restarted to update the system parameters of the system, thereby obtaining a second optimization system.

[0102] The system configuration information, system performance indicators and system error log of the second optimization system, as well as the first prompt information are collected and input into the preset model so that the preset model outputs the second optimization result based on the context information in each round of operation. Specifically, the context information includes the system configuration information, system performance indicators and system error log of the system.

[0103] According to an embodiment of the present application, operation instructions are dynamically issued based on the system service time of the first optimization system so that operations such as restarting the service can be performed during the time period when the system service is not being performed, so as to avoid system service interruption and reduce the possibility of system errors caused by updating the system parameters using target parameter information, thereby improving the quality of the target system parameters in a more refined manner and further improving the accuracy of system optimization.

[0104] Figure 4 A schematic diagram of a system optimization method according to an embodiment of the application is shown.

[0105] like Figure 4As shown, the parameter knowledge graph 401 and the multidimensional reference data 402 are input into the preset model M410, and the preset model M410 processes the parameter knowledge graph and the multidimensional reference data to output the second parameter information 403 that is effective after the service of the system is restarted and can achieve the optimization goal.

[0106] The second parameter information 403 is identified based on a pre-edited program to generate an operation instruction 404 for performing a parameter update operation. The operation instruction 404 is used to update the parameters of the first optimization system 405 to obtain a second optimization system. Specifically, the operation instruction 404 can be sent to the first optimization system in advance so that the first optimization system can restart the service in time during the non-service time period and make the parameters updated based on the second parameter information effective in time.

[0107] The system configuration information 406 , the system performance index 407 , the system error log 408 and the first prompt information 409 of the second optimization system are obtained and input into the preset model M410 , so that the preset model M410 outputs the second optimization result 410 .

[0108] According to an embodiment of the present application, the system configuration information 406, system performance indicators 407 and system error log 408 of the second optimization system, and the context understanding ability of the preset model M410 enhance the ability to discover hidden problems, improve the accuracy of the second optimization results, thereby improving the quality of the target system parameters, and further improving the accuracy of system optimization.

[0109] According to the above system optimization method, this application also provides a system optimization device. Figure 5 The device is described in detail.

[0110] Figure 5 A structural block diagram of a system optimization device according to an embodiment of the present application is shown.

[0111] like Figure 5 As shown, the system optimization device 500 of this embodiment includes a target determination module 510 , a data screening module 520 and a system optimization module 530 .

[0112] The target determination module 510 is used to analyze the obtained system performance indicators and system error logs to determine the optimization target of the system. In one embodiment, the target determination module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0113] The data screening module 520 is used to screen the acquired system configuration information, system performance indicators and system error logs based on the optimization target to obtain multi-dimensional reference data. In one embodiment, the data screening module 520 can be used to perform the operation S220 described above, which will not be repeated here.

[0114] System optimization module 530 is configured to perform multimodal association on the multidimensional reference data based on the parameter knowledge graph for the system, determine target system parameters for achieving the optimization goal, and optimize the system using the target system parameters. In one embodiment, system optimization module 530 can be configured to perform operation S230 described above, which will not be further described here.

[0115] According to an embodiment of the present application, the system optimization module 530 includes: a parameter determination submodule, which is used to determine the target system parameters by processing the parameter knowledge graph and multidimensional reference data for at least one round using a preset model based on a preset parameter effectiveness level.

[0116] According to an embodiment of the present application, the parameter effectiveness level includes: Level 1, which indicates that the adjusted parameter is effective during system operation. The parameter determination submodule includes: a first determination unit, a second determination unit, and a third determination unit.

[0117] The first determination unit is used to process the parameter knowledge graph and the multidimensional reference data using a preset model to determine first parameter information that meets the first level.

[0118] The second determining unit is configured to determine, based on the first parameter information, a first optimization result of the first optimization system corresponding to the first parameter information.

[0119] The third determining unit is configured to determine the first parameter information as target parameter information when the first optimization result indicates that the optimization target has been achieved.

[0120] According to an embodiment of the present application, the parameter effectiveness level further includes: a second level, wherein the second level indicates that the adjusted parameter takes effect after the system service is restarted. The parameter determination submodule further includes: a fourth determination unit, a fifth determination unit, and a sixth determination unit.

[0121] The fourth determination unit is used to process the parameter knowledge graph and the multidimensional reference data using a preset model to determine second parameter information that meets the second level when the first optimization result indicates that the optimization target has not been achieved.

[0122] The fifth determining unit is configured to determine, based on the second parameter information, a second optimization result of the second optimization system corresponding to the second parameter information.

[0123] The sixth determining unit is configured to determine the first parameter information and the second parameter information as target parameter information when the second optimization result indicates that the optimization target has been achieved.

[0124] According to an embodiment of the present application, the parameter effectiveness level further includes: a third level, wherein the third level indicates that the adjusted parameter takes effect after the device running the system is restarted. The parameter determination submodule further includes: a seventh determination unit, an eighth determination unit, and a ninth determination unit.

[0125] The seventh determination unit is used to process the parameter knowledge graph and the multidimensional reference data using a preset model to determine third parameter information that meets the third level when the second optimization result indicates that the optimization target has not been achieved.

[0126] An eighth determining unit is configured to determine, based on the third parameter information, a third optimization result of the third optimization system corresponding to the third parameter information.

[0127] The ninth determining unit is configured to determine the first parameter information, the second parameter information, and the third parameter information as target parameter information when the third optimization result indicates that the optimization target has been achieved.

[0128] According to an embodiment of the present application, the fifth determination unit includes: an instruction generation subunit and a parameter update subunit.

[0129] The instruction generation subunit is used to generate an operation instruction for updating the data system parameters based on the second parameter information.

[0130] The parameter updating subunit is used to send an operation instruction to the first optimization system based on the obtained system service time of the first optimization system, so as to update the system parameters of the system and obtain a second optimization system.

[0131] The collected system configuration information, system performance indicators, system error logs and first prompt information of the second optimization system are input into the preset model to output the second optimization result, wherein the first prompt information is used to prompt the preset model to determine whether the optimization goal is achieved.

[0132] According to an embodiment of the present application, the data screening module 520 includes: a knowledge determination submodule and a data determination module.

[0133] The knowledge determination submodule is used to determine multiple knowledge fragments that match the optimization target from a preset knowledge base.

[0134] The data determination module is used to input multiple knowledge fragments, system configuration information, system performance indicators, system error logs and second prompt information into a preset model and output multidimensional reference data, wherein the second prompt information is used to prompt the preset model to refer to multiple knowledge fragments to perform data screening on system configuration information, system performance indicators and system error logs according to optimization goals.

[0135] According to an embodiment of the present application, the data screening module 520 further includes: a pre-processing sub-module and a storage sub-module.

[0136] The preprocessing submodule is used to preprocess the optimization target, multi-dimensional reference data and target system parameters to obtain knowledge fragments that meet the preset format.

[0137] The storage submodule is used to store knowledge fragments in a preset knowledge base.

[0138] According to embodiments of the present application, any multiple modules among the target determination module 510, data screening module 520, and system optimization module 530 can be combined into a single module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present application, at least one of the target determination module 510, data screening module 520, and system optimization module 530 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or any appropriate combination of any of these. Alternatively, at least one of the target determination module 510, data screening module 520, and system optimization module 530 can be at least partially implemented as a computer program module that, when executed, performs the corresponding functionality.

[0139] Figure 6 A block diagram of an electronic device suitable for implementing a system optimization method according to an embodiment of the present application is shown.

[0140] like Figure 6 As shown, an electronic device 600 according to an embodiment of the present application includes a processor 601, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 602 or a program loaded from a storage unit 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present application.

[0141] Various programs and data required for the operation of the electronic device 600 are stored in the RAM 603. The processor 601, ROM 602, and RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of the method flow according to the embodiment of the present application by executing the programs in the ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than the ROM 602 and RAM 603. The processor 601 may also perform various operations of the method flow according to the embodiment of the present application by executing the programs stored in the one or more memories.

[0142] According to an embodiment of the present application, electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to bus 604. Electronic device 600 may also include one or more of the following components connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or modem. Communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. Removable media 611, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 610 as needed, so that computer programs read from the removable media can be installed into storage section 608 as needed.

[0143] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the method according to the embodiments of this application is implemented.

[0144] According to an embodiment of the present application, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present application, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0145] The embodiments of the present application also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the system optimization method provided in the embodiments of the present application.

[0146] The computer program executes the above functions defined in the system / device of the embodiment of the present application when the computer program is executed by the processor 601. According to the embodiment of the present application, the above-described devices, modules, units, etc. can be implemented by computer program modules.

[0147] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0148] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present application are performed. According to the embodiment of the present application, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0149] According to an embodiment of the present application, the program code for executing the computer program provided by the embodiment of the present application can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0151] Those skilled in the art will appreciate that the features described in the various embodiments of this application may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in this application. In particular, the features described in the various embodiments of this application may be combined and / or coupled in various ways without departing from the spirit and teachings of this application. All such combinations and / or couplings fall within the scope of this application.

[0152] The embodiments of the present application have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present application. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. Without departing from the scope of the present application, those skilled in the art may make various substitutions and modifications, and these substitutions and modifications should all fall within the scope of the present application.

Claims

1. A system optimization method, characterized in that: The method comprises: Analyze the obtained system performance indicators and system error logs to determine the system optimization goals; Determining, from a preset knowledge base, a plurality of knowledge fragments that match the optimization objective; Inputting the multiple knowledge fragments, the system configuration information, the system performance indicators, the system error log, and the second prompt information into a preset model to output multidimensional reference data, wherein the second prompt information is used to prompt the preset model to refer to the multiple knowledge fragments to perform data screening on the system configuration information, the system performance indicators, and the system error log according to the optimization goal; Based on a preset parameter effectiveness level, processing the parameter knowledge graph and the multidimensional reference data for at least one round using a preset model to determine target system parameters, and optimizing the system using the target system parameters; The parameter effectiveness levels include: a first level, which indicates that the adjusted parameters are effective during system operation; The method of processing the parameter knowledge graph and the multi-dimensional reference data using a preset model based on the preset parameter validation conditions for at least one round to determine the target system parameters includes: Processing the parameter knowledge graph and the multidimensional reference data using the preset model to determine first parameter information that meets a first level; determining a first optimization result of a first optimization system corresponding to the first parameter information based on the first parameter information; In a case where the first optimization result indicates that the optimization goal is achieved, the first parameter information is determined as target parameter information.

2. The method according to claim 1, characterized in that The parameter effectiveness levels also include: a second level, wherein the second level indicates that the adjusted parameters take effect after the service of the system is restarted; The method further comprises: When the first optimization result indicates that the optimization goal has not been achieved, the parameter knowledge graph and the multidimensional reference data are processed using the preset model to determine second parameter information that meets the second level; determining a second optimization result of a second optimization system corresponding to the second parameter information based on the second parameter information; In a case where the second optimization result indicates that the optimization goal is achieved, the first parameter information and the second parameter information are determined as target parameter information.

3. The method according to claim 2, characterized in that The parameter effectiveness levels also include: a third level, wherein the third level indicates that the adjusted parameters take effect after the device running the system is restarted; The method further comprises: If the second optimization result indicates that the optimization goal has not been achieved, processing the parameter knowledge graph and the multidimensional reference data using a preset model to determine third parameter information that meets the third level; determining, based on the third parameter information, a third optimization result of the third optimization system corresponding to the third parameter information; In a case where the third optimization result indicates that the optimization goal is achieved, the first parameter information, the second parameter information, and the third parameter information are determined as target parameter information.

4. The method according to claim 2, characterized in that The determining, based on the second parameter information, a second optimization result of the second optimization system corresponding to the second parameter information includes: generating an operation instruction for updating a data system parameter based on the second parameter information; Based on the obtained system service time of the first optimization system, issuing the operation instruction to the first optimization system to update the system parameters of the system to obtain the second optimization system; The collected system configuration information, system performance indicators, system error logs and first prompt information of the second optimization system are input into the preset model, and the second optimization result is output, wherein the first prompt information is used to prompt the preset model to determine whether the optimization goal is achieved.

5. The method according to claim 1, characterized in that The method further comprises: Preprocessing the optimization target, the multidimensional reference data, and the target system parameters to obtain knowledge fragments that meet a preset format; The knowledge fragment is stored in the preset knowledge base.

6. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images