System performance optimization method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of intelligent decision, and discloses a system performance optimization method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining operation data and user behavior data of an application program; according to the operation data of the application program and the user behavior data, performing statistics on a plurality of key performance indexes of current operation of the system; based on a target performance index in the plurality of key performance indexes, splitting and evaluating a resource file which needs to be loaded for running the application program to obtain a file splitting and evaluating result; and determining a target performance optimization strategy of the system according to the file splitting evaluation result and the plurality of key performance indexes. According to the method, the optimal performance optimization suggestion can be given by comprehensively considering the current operation condition of the system, so that the accurate optimization of the system performance can be realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent decision-making technology, and in particular to a system performance optimization method, device, computer equipment and storage medium. Background Art

[0002] Optimizing system performance can make applications run more smoothly and quickly, improving user experience and satisfaction. It can also reduce the occurrence of problems such as system crashes and program crashes, and improve the reliability and security of applications.

[0003] At present, static analysis tools are usually used to analyze problems in the system operation process and give optimization suggestions. However, this method only focuses on local problems and it is difficult to give the best performance optimization suggestions by comprehensively considering the current operation of the system. Summary of the invention

[0004] The present invention provides a system performance optimization method, device, computer equipment and storage medium, which are mainly capable of comprehensively considering the current operation status of the system to give the best performance optimization suggestions, thereby realizing accurate optimization of system performance.

[0005] In a first aspect, a system performance optimization method is provided, comprising:

[0006] Obtain application operation data and user behavior data;

[0007] According to the operation data of the application and the user behavior data, statistics are collected on a plurality of key performance indicators of the current operation of the system;

[0008] Based on the target performance indicator among the multiple key performance indicators, splitting and evaluating the resource files required to be loaded to run the application program to obtain a file splitting and evaluation result;

[0009] A target performance optimization strategy for the system is determined based on the file splitting evaluation results and the multiple key performance indicators.

[0010] In a second aspect, a system performance optimization device is provided, comprising:

[0011] An acquisition unit, used to acquire application operation data and user behavior data;

[0012] A statistical unit, used for collecting statistics of a plurality of key performance indicators of the current operation of the system based on the operation data of the application and the user behavior data;

[0013] An evaluation unit, configured to perform split evaluation on resource files required to be loaded for running the application based on a target performance indicator among the multiple key performance indicators, and obtain a file split evaluation result;

[0014] A determination unit is used to determine a target performance optimization strategy for the system according to the file splitting evaluation result and the multiple key performance indicators.

[0015] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned system performance optimization method when executing the computer program.

[0016] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned system performance optimization method are implemented.

[0017] The present application provides a system performance optimization method, device, computer equipment and storage medium. Compared with the existing static analysis tools, it can first count multiple key performance indicators of the current operation of the system based on the operation data of the application and the user behavior data, and then split and evaluate the resource files that need to be loaded to run the application based on the target performance indicators among the multiple key performance indicators, and obtain the file splitting evaluation results. Finally, according to the file splitting evaluation results and multiple key performance indicators, the target performance optimization strategy of the system is determined. It can be seen that the present application can comprehensively consider the current operation of the system by counting multiple performance indicators of the current operation of the system, and give the best performance optimization suggestions, so as to achieve accurate optimization of system performance. At the same time, the present application also combines the splitting of resource files when giving the best performance optimization strategy, so as to ensure that the best performance optimization strategy given can meet the resource loading requirements when the application is running, and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0019] Figure 1 A schematic diagram of an application environment provided by an embodiment of the present application is shown.

[0020] Figure 2 A schematic diagram of a process flow of a system performance optimization method provided by an embodiment of the present application is shown;

[0021] Figure 3 A schematic diagram of a cache hit rate prediction method provided in an embodiment of the present application is shown;

[0022] Figure 4A schematic diagram of the code structure optimization method provided in an embodiment of the present application is shown;

[0023] Figure 5 A schematic diagram of the structure of a system performance optimization device provided in an embodiment of the present application is shown;

[0024] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The system performance optimization method provided by the embodiment of the present invention can be applied in Figure 1 In an application environment, the client communicates with the server through a network. The server can receive the application running data and user behavior data collected by the client, and then count the multiple key performance indicators of the current operation of the system based on the application running data and the user behavior data, and then split and evaluate the resource files that need to be loaded to run the application based on the target performance indicators in the multiple key performance indicators, and obtain the file splitting evaluation results, and finally determine the target performance optimization strategy of the system based on the file splitting evaluation results and the multiple key performance indicators. This application can comprehensively consider the current operation of the system by counting the multiple performance indicators of the current operation of the system, and give the best performance optimization suggestions. At the same time, this application also combines the splitting of resource files when giving the best performance optimization strategy, so as to ensure that the best performance optimization strategy given can meet the resource loading requirements when the application is running and improve the user experience. Among them, the client can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0027] See also Figure 2 As shown, Figure 2 A schematic flow chart of a system performance optimization method provided by an embodiment of the present invention includes the following steps:

[0028] S10. Obtain application operation data and user behavior data.

[0029] Among them, the application's operating data mainly includes response time, CPU (Central Processing Unit) usage and memory usage, etc., and the user behavior data includes user access path, access frequency, access time, browsing history and click history, etc.

[0030] For the embodiment of the present invention, in order to optimize the system performance, it is necessary to collect the application's operating data and user behavior data in advance. With respect to the data collection process, the method includes: using a preset application performance monitoring tool to collect the application's operating data; using a preset front-end monitoring tool to collect the user behavior data. Among them, the preset application performance detection tool is any tool that can monitor the application's runtime performance, and the preset front-end monitoring tool is any tool that can monitor the front-end user's operating behavior.

[0031] Specifically, the preset application performance monitoring tool is used to collect the application's response time, CPU (Central Processing Unit) usage, and memory usage, etc., and the preset front-end monitoring tool is used to collect the user's access path, access frequency, access time, browsing history, and click history, etc.

[0032] S20. Counting a plurality of key performance indicators of the current operation of the system based on the operation data of the application and the user behavior data.

[0033] The multiple key performance indicators specifically include: system memory consumption, CPU usage, cache space size, network latency, cache hit rate, etc. It should be noted that the key performance indicators in the embodiments of the present invention are not limited to the above examples, and may also be other key performance indicators.

[0034] For the embodiment of the present invention, after obtaining the running data and user behavior data of the application, it is necessary to count the key performance indicators such as the system's memory consumption, CPU usage, cache space size, network latency and cache hit rate based on the running data and user behavior data of the application. Different statistical methods can be used for different key performance indicators.

[0035] Statistical procedures for multiple key performance indicators, such as Figure 3 As shown, the method includes:

[0036] S21. Based on the running data of the application and the user behavior data, the memory consumption and CPU usage of the system are counted.

[0037] For the embodiment of the present invention, the response time and memory usage in the operation data, as well as the access frequency and access time in the user behavior data, can be input into a preset memory consumption regression prediction model to predict memory consumption, and obtain the memory consumption of the device system running the application. Similarly, the response time and CPU usage in the operation data, as well as the access frequency and access time in the user behavior data, can be input into a preset CPU usage regression prediction model to predict CPU usage, and obtain the CPU usage of the device system running the application.

[0038] The embodiment of the present invention can pre-build a memory consumption regression prediction model and a CPU usage regression prediction model based on historical application operation data and historical user behavior data.

[0039] The embodiment of the present invention can accurately predict the memory consumption and CPU usage of the system by adopting a memory consumption regression prediction model and a CPU usage regression prediction model, thereby ensuring the accuracy of the key performance indicator analysis results.

[0040] S22. Using a preset system performance monitoring tool to monitor the cache space size and network delay of the system.

[0041] Among them, the preset system performance monitoring tools include network monitoring tools and cache monitoring tools. The network monitoring tools can be used to measure network delay, packet loss rate and other indicators, and the cache monitoring tools can be used to capture the cache space size.

[0042] For the embodiment of the present invention, a network monitoring tool and a cache monitoring tool may be used to capture the network delay and the size of the cache space.

[0043] The embodiment of the present invention can accurately measure the cache space size and network delay by adopting a preset system performance monitoring tool, thereby ensuring the accuracy of the key performance indicator analysis results.

[0044] S23: Analyze the user behavior data to determine the access pattern corresponding to the user behavior data.

[0045] Among them, the access patterns include strong temporal locality, strong spatial locality, and strong spatiotemporal locality.

[0046] For the embodiment of the present invention, when predicting the cache hit rate, it is necessary to classify the user behavior data to determine the user's access pattern, and different classifications correspond to different access patterns. Specifically, the access time, access frequency, and access resource type in the user behavior data can be input into a preset access pattern prediction model to predict the access pattern, wherein the preset access pattern prediction model is a classification model, which can be a multi-layer perceptron, a support vector machine, etc.

[0047] For example, based on the user's behavioral data such as access time, access frequency and access resource type, the feature vector corresponding to the user behavior data is determined, and then the feature vector corresponding to the user behavior data is input into a preset access pattern prediction model for access pattern classification to obtain the access pattern corresponding to the user behavior data.

[0048] Before using the preset access pattern prediction model, it is necessary to collect historical user behavior data in advance, and then annotate the historical user behavior data based on access patterns such as temporal locality, strong spatial locality, and strong spatiotemporal locality. Then, the annotated historical user behavior data is used as training data to construct the preset access pattern prediction model.

[0049] S24. Predicting the cache hit rate based on the access pattern and the access time and access frequency in the user behavior data.

[0050] For the embodiment of the present invention, after determining the user's access pattern, a corresponding cache hit rate regression prediction model can be selected for cache prediction. For this process, step S24 specifically includes: determining a preset cache hit rate regression prediction model corresponding to the access pattern; based on the access time, the access frequency and the cache space size, using the preset cache hit rate regression prediction model to predict the cache hit rate to obtain the cache hit rate. Among them, the preset cache hit rate regression prediction models corresponding to different access patterns are different.

[0051] For the embodiment of the present invention, historical user behavior data under different access modes can be collected in advance, and then based on the historical user behavior data under different access modes, preset cache hit rate regression prediction models under different access modes can be constructed. When the cache hit rate prediction is formally performed, the corresponding preset cache hit rate regression prediction model can be selected according to the user's access mode, and then the user's access time, access frequency and cache space size are input into the preset cache hit rate regression prediction model for regression prediction to obtain the cache hit rate.

[0052] The embodiment of the present invention analyzes user behavior data, determines the user's access pattern, and selects a preset cache hit rate regression prediction model that matches the access pattern to predict the cache hit rate. It can accurately predict the cache hit rate, thereby ensuring the accuracy of the key performance indicator analysis results.

[0053] S30. Based on the target performance indicator among the multiple key performance indicators, split and evaluate the resource files that need to be loaded to run the application program to obtain a file split evaluation result.

[0054] The target performance indicator includes network delay, and the resource files include executable files, configuration files, image files, video files, audio files, etc. The file splitting evaluation result includes whether the resource file needs to be split or not.

[0055] For the embodiment of the present invention, since the resource file loading method will also affect the system performance, it is necessary to pre-evaluate whether the resource file needs to be split, so as to adopt the corresponding resource file loading method to ensure the optimal system performance.

[0056] Regarding the split evaluation process of resource files, step S30 specifically includes: inputting the network delay, the file size corresponding to the resource file, and the dependency relationship between the file resources into a preset split evaluation decision tree model for split evaluation, and obtaining the file split evaluation result. Among them, the stronger the dependency relationship between file resources, the worse the splitability of the file. When performing split evaluation on resource files, by introducing the dependency relationship between file resources, the accuracy of the file split evaluation result can be guaranteed.

[0057] Specifically, the statistical network delay, resource file size, and dependency relationship between file resources (such as strong dependency or weak dependency) can be input into the preset split evaluation decision tree model for split evaluation to obtain the file split evaluation result. For example, if the current network delay is relatively serious, the resource file is large, and the dependency relationship between file resources is weak, it means that the file needs to be split to ensure systemicity; if there is basically no network delay, the resource file is small, and the dependency relationship between file resources is strong, it means that the file does not need to be split.

[0058] The embodiment of the present invention can accurately evaluate whether resource files need to be split based on resource file size, dependency between file resources, network delay and a preset split evaluation decision tree model, thereby ensuring the accuracy of the file split evaluation result.

[0059] S40: Determine a target performance optimization strategy for the system according to the file splitting evaluation result and the multiple key performance indicators.

[0060] Among them, the target performance optimization strategy includes various combinations of possible optimization results in cache space optimization strategy, cache duration optimization strategy and resource file optimization strategy. The cache space optimization strategy includes increasing cache space and reducing cache space. The cache duration optimization strategy includes extending cache duration and shortening cache duration. The resource file optimization strategy includes loading resource files in parallel and prioritizing loading important resource files.

[0061] For the embodiment of the present invention, in order to determine the final target performance optimization strategy, step S40 specifically includes: inputting the file splitting evaluation results and the multiple key performance indicators into a preset performance optimization analysis neural network model for optimization analysis to obtain a cache space optimization strategy, a cache duration optimization strategy and a resource file optimization strategy; determining the target performance optimization strategy based on the cache space optimization strategy, the cache duration optimization strategy and the resource file optimization strategy.

[0062] Among them, the preset performance optimization analysis neural network models include multi-layer perceptron, recurrent neural network, convolutional neural network and support vector machine.

[0063] Specifically, the corresponding characteristic component will be determined according to the file splitting evaluation result. For example, if the file splitting evaluation result is that the resource file needs to be split, the corresponding characteristic component is 01; on the contrary, if the file splitting evaluation result is that the resource file does not need to be split, the corresponding characteristic component is 10. At the same time, according to the system's memory consumption, CPU usage, cache space size, network latency and cache hit rate, the corresponding characteristic component of each key performance indicator is determined. For example, if the cache hit rate is below 40%, the corresponding characteristic component is 001; if the cache hit rate is between 40% and 70%, the corresponding characteristic component is 010; if the cache hit rate is above 70%, the corresponding characteristic component is 001.

[0064] After determining the feature components corresponding to the file splitting evaluation results and the feature components corresponding to each key performance indicator, the above feature components are horizontally spliced ​​in turn to obtain a spliced ​​feature vector, and then the spliced ​​feature vector is input into the preset performance optimization analysis neural network model for classification to obtain the target performance optimization strategy. For example, the final target performance optimization strategy is to increase cache space, extend cache duration, and prioritize loading important resource files, or to reduce cache space, shorten cache duration, and load resource files in parallel.

[0065] The embodiment of the present invention can comprehensively consider the current operation of the system and give the best performance optimization suggestion by counting multiple key performance indicators of the current system operation. At the same time, the embodiment of the present invention also combines the splitting of resource files when giving the best performance optimization strategy, thereby ensuring that the given best performance optimization strategy can meet the resource loading requirements during application runtime and improve user experience.

[0066] After determining the target performance optimization strategy, the target performance optimization strategy is configured and applied using a preset configuration management tool to optimize system performance.

[0067] Specifically, the generated target performance optimization strategy can be automatically applied to the application configuration using configuration management tools to achieve automated configuration updates. The application operation can then be continuously monitored and feedback collected to evaluate the optimization effect of the optimization strategy. The optimization algorithms and strategies can then be iterated in turn to improve the accuracy and effectiveness of the optimization system.

[0068] In some embodiments, the embodiments of the present invention can also optimize the code structure of the application program, such as Figure 4 As shown, including:

[0069] S50: Obtain the response time and throughput of the application program to the user request.

[0070] For the embodiment of the present invention, a monitoring tool may be used to obtain the response time of user requests and the throughput of user requests in real time.

[0071] S60: Determine whether the application needs to be optimized in code structure according to the response time, the throughput and a plurality of key performance indicators of the system.

[0072] For the embodiments of the present invention, the characteristic components corresponding to the response time, throughput and each key performance indicator can be determined respectively according to the range intervals to which the response time, throughput and each key performance indicator belong. Then, the above-mentioned characteristic vectors are horizontally spliced ​​to generate a structural characteristic vector. Then, the structural characteristic vector is input into a preset code structure optimization prediction model for optimization prediction. Finally, a conclusion can be obtained as to whether the code structure of the application needs to be optimized.

[0073] Among them, the preset code structure optimization prediction model can specifically be a binary classification model such as a support vector machine and a neural network model.

[0074] S70: If the application needs to be optimized in code structure, a preset code detection tool is used to detect the code file of the application to determine the code module with duplicate logic.

[0075] For the embodiment of the present invention, if it is determined based on the prediction results that the application does not need to perform code structure optimization, the following steps are not executed; if it is determined based on the prediction results that the application needs to perform code structure optimization, the code of the application is detected using a preset code detection tool. If it is detected that the loop logic in the two functions is almost exactly the same, but the calculation formulas are different, then it can be determined that there is a code module with repeated logic.

[0076] S80: Encapsulate the code module with repeated logic to generate a universal function.

[0077] According to the embodiment of the present invention, after locking the code module with repeated logic, it is encapsulated and determined as a universal function, thereby optimizing the code structure and simplifying the algorithm complexity.

[0078] A system performance optimization method provided by an embodiment of the present invention can comprehensively consider the current operation status of the system by counting multiple performance indicators of the current system operation, and give optimal performance optimization suggestions, thereby achieving accurate optimization of system performance. At the same time, when giving the best performance optimization strategy, this application also combines the splitting of resource files, thereby ensuring that the given best performance optimization strategy can meet the resource loading requirements during application runtime and improve user experience.

[0079] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0080] In one embodiment, a system performance optimization device is provided, which corresponds one-to-one to the system performance optimization method in the above embodiment. Figure 5 As shown, the system performance optimization device includes an acquisition unit 101, a statistical unit 102, an evaluation unit 103 and a determination unit 104. Each functional unit is described in detail as follows:

[0081] The acquisition unit 101 may be used to acquire application operation data and user behavior data.

[0082] The statistical unit 102 may be used to collect statistics of multiple key performance indicators of the current operation of the system based on the operation data of the application and the user behavior data.

[0083] The evaluation unit 103 may be configured to perform split evaluation on the resource files required to be loaded to run the application based on the target performance indicator among the multiple key performance indicators, and obtain a file split evaluation result.

[0084] The determining unit 104 may be configured to determine a target performance optimization strategy for the system according to the file splitting evaluation result and the multiple key performance indicators.

[0085] In some embodiments, the plurality of key performance indicators include the system's memory consumption, CPU usage, cache size, network latency, and cache hit rate. The statistical unit 102 includes: a statistical module, a monitoring module, a determination module, and a prediction module.

[0086] The statistical module can be used to count the memory consumption and CPU usage of the system based on the running data of the application and the user behavior data.

[0087] The monitoring module can be used to monitor the cache space size and network delay of the system using a preset system performance monitoring tool.

[0088] The determination module may be used to analyze the user behavior data and determine the access pattern corresponding to the user behavior data.

[0089] The prediction module may be used to predict the cache hit rate based on the access pattern and the access time and access frequency in the user behavior data.

[0090] In some embodiments, the prediction module may be specifically used to determine a preset cache hit rate regression prediction model corresponding to the access pattern;

[0091] Based on the access time, the access frequency and the cache space size, the cache hit rate is predicted using the preset cache hit rate regression prediction model to obtain the cache hit rate.

[0092] In some embodiments, when the target performance indicator is network delay, the evaluation unit 103 can be specifically used to input the network delay, the file size corresponding to the resource file, and the dependency relationship between the file resources into a preset split evaluation decision tree model for split evaluation to obtain the file split evaluation result, wherein the file split evaluation result includes that the resource file needs to be split and that the resource file does not need to be split.

[0093] In some embodiments, the determination unit 104 can be specifically used to input the file splitting evaluation results and the multiple key performance indicators into a preset performance optimization analysis neural network model for optimization analysis, to obtain a cache space optimization strategy, a cache duration optimization strategy and a resource file optimization strategy, wherein the cache space optimization strategy includes increasing the cache space and reducing the cache space, the cache duration optimization strategy includes extending the cache duration and shortening the cache duration, and the resource file optimization strategy includes loading resource files in parallel and prioritizing loading important resource files; according to the cache space optimization strategy, the cache duration optimization strategy and the resource file optimization strategy, the target performance optimization strategy is determined.

[0094] In some embodiments, the determination unit 104 can also be specifically used to obtain the response time and throughput of the application to user requests; determine whether the application needs to perform code structure optimization based on the response time, the throughput and multiple key performance indicators of the system; if the application needs to perform code structure optimization, use a preset code detection tool to detect the code file of the application to determine the code module with duplicate logic; encapsulate the code module with duplicate logic to generate a general function.

[0095] In some embodiments, the acquisition unit 101 may be specifically used to collect the operation data of the application using a preset application performance monitoring tool; and collect the user behavior data using a preset front-end monitoring tool.

[0096] In some embodiments, the apparatus further comprises: a configuration unit.

[0097] The configuration unit may be used to configure and apply the target performance optimization strategy using a preset configuration management tool to optimize system performance.

[0098] The present invention provides a system performance optimization device, which can comprehensively consider the current operation status of the system by counting multiple performance indicators of the current system operation, and give the best performance optimization suggestions, so as to achieve accurate optimization of system performance. At the same time, when giving the best performance optimization strategy, the application also combines the splitting of resource files, so as to ensure that the best performance optimization strategy given can meet the resource loading requirements when the application is running, thereby improving the user experience.

[0099] For the specific definition of the system performance optimization device, please refer to the definition of the system performance optimization method above, which will not be repeated here. Each module in the above-mentioned system performance optimization device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0100] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the functions or steps of a system performance optimization method are implemented.

[0101] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0102] Obtain application operation data and user behavior data;

[0103] According to the operation data of the application and the user behavior data, statistics are collected on a plurality of key performance indicators of the current operation of the system;

[0104] Based on the target performance indicator among the multiple key performance indicators, splitting and evaluating the resource files required to be loaded to run the application program to obtain a file splitting and evaluation result;

[0105] A target performance optimization strategy for the system is determined based on the file splitting evaluation results and the multiple key performance indicators.

[0106] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0107] Obtain application operation data and user behavior data;

[0108] According to the operation data of the application and the user behavior data, statistics are collected on a plurality of key performance indicators of the current operation of the system;

[0109] Based on the target performance indicator among the multiple key performance indicators, splitting and evaluating the resource files required to be loaded to run the application program to obtain a file splitting and evaluation result;

[0110] A target performance optimization strategy for the system is determined based on the file splitting evaluation results and the multiple key performance indicators.

[0111] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0112] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0113] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0114] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A system performance optimization method, characterized in that: include: Obtain application operation data and user behavior data; According to the operation data of the application and the user behavior data, statistics are collected on a plurality of key performance indicators of the current operation of the system; Based on the target performance indicator among the multiple key performance indicators, splitting and evaluating the resource files required to be loaded to run the application program to obtain a file splitting and evaluation result; A target performance optimization strategy for the system is determined based on the file splitting evaluation results and the multiple key performance indicators.

2. The method according to claim 1, characterized in that The multiple key performance indicators include the system's memory consumption, CPU usage, cache space size, network latency, and cache hit rate. The multiple key performance indicators currently running the system are counted based on the application's running data and the user's behavior data, including: Based on the running data of the application and the user behavior data, the memory consumption and CPU usage rate of the system are counted; Using a preset system performance monitoring tool to monitor the cache space size and network latency of the system; Analyze the user behavior data to determine the access pattern corresponding to the user behavior data; The cache hit rate is predicted based on the access pattern and the access time and the access frequency in the user behavior data.

3. The method according to claim 2, characterized in that The predicting the cache hit rate based on the access pattern and the access time and the access frequency in the user behavior data includes: Determine a preset cache hit rate regression prediction model corresponding to the access pattern; Based on the access time, the access frequency and the cache space size, the cache hit rate is predicted using the preset cache hit rate regression prediction model to obtain the cache hit rate.

4. The method according to claim 1, characterized in that: When the target performance indicator is network delay, the resource files required to be loaded for running the application are split and evaluated based on the target performance indicator among the multiple key performance indicators to obtain a file split evaluation result, including: The network delay, the file size corresponding to the resource file, and the dependency relationship between the file resources are input into a preset split evaluation decision tree model for split evaluation to obtain the file split evaluation result, wherein the file split evaluation result includes whether the resource file needs to be split and whether the resource file does not need to be split.

5. The method according to any one of claims 1 to 4, characterized in that: Determining the target performance optimization strategy of the system according to the file splitting evaluation result and the multiple key performance indicators includes: Input the file splitting evaluation result and the multiple key performance indicators into a preset performance optimization analysis neural network model for optimization analysis, and obtain a cache space optimization strategy, a cache duration optimization strategy, and a resource file optimization strategy, wherein the cache space optimization strategy includes increasing the cache space and reducing the cache space, the cache duration optimization strategy includes extending the cache duration and shortening the cache duration, and the resource file optimization strategy includes loading resource files in parallel and loading important resource files in priority; The target performance optimization strategy is determined according to the cache space optimization strategy, the cache duration optimization strategy and the resource file optimization strategy.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining the response time and throughput of the application to user requests; Determining whether the application needs code structure optimization according to the response time, the throughput, and a plurality of key performance indicators of the system; If the application needs to be optimized in code structure, the code file of the application is detected by using a preset code detection tool to determine the code modules with duplicate logic; Encapsulating the code module with repeated logic to generate a universal function; and / or obtaining the running data of the application and the user behavior data, including: Using a preset application performance monitoring tool to collect operation data of the application; The user behavior data is collected using a preset front-end monitoring tool.

7. The method according to claim 1, characterized in that The method further comprises: The target performance optimization strategy is configured and applied using a preset configuration management tool to optimize system performance.

8. A system performance optimization device, characterized in that: include: An acquisition unit, used to acquire application operation data and user behavior data; A statistical unit, used for collecting statistics of a plurality of key performance indicators of the current operation of the system according to the operation data of the application and the user behavior data; An evaluation unit, configured to perform split evaluation on resource files required to be loaded for running the application based on a target performance indicator among the multiple key performance indicators, and obtain a file split evaluation result; A determination unit is used to determine a target performance optimization strategy for the system according to the file splitting evaluation result and the multiple key performance indicators.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the system performance optimization method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the system performance optimization method according to any one of claims 1 to 7 are implemented.

Images