Resource allocation method for data processing and related equipment
By calculating and classifying the load of cloud desktop applications, and combining various load models and execution strategies, the problem of insufficient intelligence in cloud desktop resource allocation is solved, achieving efficient resource utilization and improved system stability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAN ZHENGLIANG ENERGY TECHNOLOGY CO LTD
- Filing Date
- 2026-02-06
- Publication Date
- 2026-05-26
AI Technical Summary
Existing technologies for cloud desktop load management and resource allocation suffer from several problems, including insufficiently intelligent resource scheduling, inaccurate load prediction, lack of adaptability to multiple scenarios, inconsistent load assessment standards, slow response speed, resource waste and performance bottlenecks, lack of support for multiple load types, and lack of precise application priority settings.
By calculating the standardized values and weights of various metrics for each target application, application levels are classified, and corresponding load models and execution strategies are selected, including basic load models, load variation models, extreme load models, and comprehensive load models. Combined with customized mode, random mode, and manual mode, resource allocation is dynamically adjusted.
It achieves improved resource utilization, performance optimization, flexible configuration, and reduced system pressure, ensuring efficient operation and stability of cloud desktops under different load conditions.
Smart Images
Figure CN122093401A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of cloud desktop technology, specifically to a resource allocation method and related equipment for data processing. Background Technology
[0002] Existing technologies have the following main drawbacks in cloud desktop load management and application distribution: Resource scheduling is not intelligent enough: Many existing technologies lack intelligence in resource scheduling and cannot automatically adjust the allocation of resources for data processing based on real-time application load. The system may face uneven resource utilization, with some applications having excess resources while others experience resource shortages, leading to performance degradation.
[0003] Inaccurate load forecasting: Current technologies have weak predictive capabilities for load changes, making it difficult to anticipate fluctuations in application load. Systems typically rely on simple load balancing strategies and lack effective dynamic load adjustment mechanisms, leading to congestion or slow response times under high load conditions.
[0004] Lack of adaptability to multiple scenarios: Existing technologies are usually optimized only for specific application scenarios and cannot achieve flexible resource scheduling and load management under different usage scenarios (such as low load, medium load, and high load). There is no unified load model that can be effectively applied in all situations.
[0005] Inconsistent load assessment standards: Different systems, platforms, and applications may have different load assessment standards and calculation methods. Existing technologies often lack a unified standardized method, making it difficult to compare and be compatible with load calculations across different systems, and lacking cross-platform compatibility.
[0006] Lack of granular control: In existing technologies, load and application matching mechanisms are mostly based on static rules or simple calculation formulas, lacking granular control for specific applications and tasks. This prevents personalized optimization for specific business needs and application scenarios.
[0007] Insufficient response speed: Current load management technologies are typically based on preset rules or periodic scheduling, which cannot respond instantly to rapid changes in system load. This slow response to sudden traffic spikes or load fluctuations can easily lead to system performance degradation or instability.
[0008] Resource waste and performance bottlenecks: The lack of robust resource optimization algorithms leads to some applications consuming excessive system resources while others receive insufficient support. This not only wastes valuable computing resources but can also cause system bottlenecks, impacting overall operational efficiency.
[0009] The technology does not support multiple load types: Most existing technologies can only handle fixed types of loads and lack flexible support for load changes, such as transitions between different load phases and handling extreme loads. In addition, existing technologies often lack comprehensive consideration for dynamic load change scenarios.
[0010] Lack of precise application prioritization: Existing technologies typically use fixed or singular application priority scheduling, lacking the ability to dynamically adjust application priorities based on actual business needs. In multitasking scenarios, this may lead to insufficient priority for critical tasks, thereby impacting the overall stability and performance of the business. Summary of the Invention
[0011] The purpose of this disclosure is to overcome the shortcomings of the prior art and provide a resource allocation method and related equipment for data processing. This resource allocation method for data processing can avoid resource waste and ensure the efficient operation of cloud desktops under different load conditions.
[0012] According to a first aspect of the present disclosure, a resource allocation method for data processing is provided, the method comprising: Calculate the standardized values of each indicator for each target application, and calculate the weight of each indicator for each target application based on the standardized values of each indicator; wherein, the indicators include CPU, memory, network, and disk. The overall load value of each target application under different systems is calculated based on the standardized values of each indicator of each target application and the weights of each indicator of each target application. Each target application is classified into application levels based on its overall load value under different systems; wherein, the application levels include low load application, medium load application, high load application, and high load application. Select the load model corresponding to each target application based on the application level of each target application. The load model includes a basic load model, a load variation model, an extreme load model, and a comprehensive load model. The load execution strategy is determined based on the load model corresponding to each target application; wherein the load execution strategy includes: custom mode, random mode and manual mode.
[0013] In one embodiment, calculating the standardized values of each indicator for each target application includes: Calculate the difference between the actual value and the minimum value of each indicator for each target application; Calculate the difference between the maximum and minimum values of each indicator for each target application; Calculate the ratio of the difference between the actual value and the minimum value of each indicator for each target application to the ratio of the difference between the maximum value and the minimum value of each indicator for each target application; The standardized value of each indicator for each target application is obtained by comparing the difference between the actual value and the minimum value of each indicator for each target application with the ratio of the difference between the maximum value and the minimum value of each indicator for each target application.
[0014] In one embodiment, calculating the weight of each indicator for each target application based on the standardized values of each indicator for each target application includes: Calculate the sum of the average values of all indicators for each target application; The weight of each indicator for each target application is calculated by summing the values of each indicator for each target application and the average values of each indicator for each target application.
[0015] In one embodiment, calculating the overall load value of each target application under different systems based on the standardized values of each indicator of each target application and the weights of each indicator of each target application includes: The load value of a single-path operating system is calculated based on the standardized values of each indicator of each target application and the weights of each indicator of each target application. Calculate the average load value of the same system type based on the load value of the single-path system; Calculate the overall load value of each target application under different systems based on the average load value of the same system type.
[0016] In one embodiment, selecting the load model corresponding to each target application based on the application level of each target application includes: The basic load model includes a persistent load model, which is used to execute application scenarios of low load, medium load, high load and high load applications. The load change model includes a gradually increasing load model and a gradually decreasing load model. The gradually increasing load model is used for application scenarios of low load application - medium load application - high load application - high load application, and the gradually decreasing load model is used for application scenarios of high load application - high load application - medium load application - low load application. The extreme load model includes a peak load model and a burst load model. The peak load model is used for scenarios where high-load applications run continuously, and the burst load model is used for scenarios where high-load applications are repeatedly opened and closed. The comprehensive load model includes a hybrid load model, which is used to execute scenario applications with different load levels and different application scenarios.
[0017] In one embodiment, determining the load execution strategy based on the load model corresponding to each target application includes: The customization mode includes model scenario customization and application scenario customization. Model scenario customization is based on the load model scenario application, where the execution scenario and number of executions are freely selected, and a customized process for load changes is formed according to the selection order. Application scenario customization is based on the selection of the execution scenario and the number of executions, and a customized process for load changes is formed according to the selection order. The random mode includes model scenario randomness and application scenario randomness. The model scenario is to freely select the execution scenario and execution number based on the load model scenario application, and then randomly execute the selected scenario and execution number. The application scenario randomness is to select the execution application and execution number, and then randomly execute the selected application and execution number.
[0018] In one embodiment, the target application includes at least one of: Notepad, image player, file manager, office software, browser, file copy operation, and file paste operation.
[0019] According to a second aspect of the present disclosure, a resource allocation apparatus for data processing is provided, the apparatus comprising: a first calculation module, a second calculation module, a partitioning module, a selection module, and a determination module; wherein; The first calculation module is used to calculate the standardized values of each indicator of each target application, and to calculate the weight of each indicator of each target application based on the standardized values of each indicator of each target application; wherein, the indicators include CPU, memory, network and disk; The second calculation module is used to calculate the overall load value of each target application under different systems based on the standardized values of each indicator of each target application and the weights of each indicator of each target application. The segmentation module is used to classify each target application into application levels based on the overall load value of each target application under different systems; wherein, the application levels include low-load applications, medium-load applications, relatively high-load applications, and high-load applications; The selection module is used to select the load model corresponding to each target application according to the application level of each target application. The load model includes a basic load model, a load variation model, an extreme load model, and a comprehensive load model. The determining module is used to determine the load execution strategy based on the load model corresponding to each target application; wherein the load execution strategy includes: custom mode, random mode and manual mode.
[0020] According to a third aspect of the present disclosure, a computer device is provided, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above methods.
[0021] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the method as described in any of the above.
[0022] The resource allocation method for data processing provided in this disclosure has the following technical effects: Improve resource utilization: By accurately calculating and classifying application load values, resource waste can be avoided, ensuring efficient operation of cloud desktops under different load conditions.
[0023] Optimize performance: By dynamically adjusting load levels and execution strategies, the allocation of system resources can be optimized, improving the response speed and operational stability of cloud desktop products.
[0024] Flexible configuration: Supports multiple load execution modes to adapt to the needs of different application scenarios. It is highly flexible and can adjust the load execution mode according to actual needs.
[0025] Reduce system pressure: By accurately calculating and classifying the load, it helps the system identify high-load applications and make adjustments, effectively reducing system pressure and avoiding performance degradation or system crashes caused by resource overload. Attached Figure Description
[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0027] Figure 1 This is a flowchart illustrating a resource allocation method for data processing provided in an embodiment of this disclosure.
[0028] Figure 2 This is a flowchart illustrating a resource allocation method for data processing provided in an embodiment of this disclosure.
[0029] Figure 3 This is a flowchart illustrating a resource allocation method for data processing provided in an embodiment of this disclosure.
[0030] Figure 4 This is an architectural diagram of a resource allocation device for data processing provided in an embodiment of the present disclosure.
[0031] Figure 5 This is an architectural diagram of a computer device provided in an embodiment of the present disclosure. Detailed Implementation
[0032] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0033] The main technical solution of a resource allocation method for data processing provided in this disclosure is as follows: Load and application tier matching: By standardizing the operation process of common applications in cloud desktop products (such as office software, image players, video players, etc.), the weights of various indicators (CPU, memory, network, disk) are obtained, and the load value of each application is calculated, thereby classifying the applications by load.
[0034] Load value calculation: Using the load calculation formula, based on the standardized values and weights of CPU, memory, network, and disk, the load value of different systems (such as Win7, Win10, Kylin) is calculated and further divided into four load levels (low, medium, high, and high) to achieve precise control over the use of cloud desktop resources.
[0035] Load Models: Four main load models are proposed, including the basic load model, the load variation model, the extreme load model, and the comprehensive load model, which are suitable for application execution in different scenarios and can adjust system resources according to different load variation situations.
[0036] Load Execution Strategy: Offers three execution strategies: custom mode, random mode, and manual mode. This allows you to select and adjust the execution load and application scenarios according to your needs, thus enabling more flexible management of cloud desktop load.
[0037] Figure 1 This is a flowchart illustrating a resource allocation method for data processing provided in an embodiment of this disclosure. Figure 1 As shown, the method includes: Calculate the standardized values of each indicator for each target application, and calculate the weight of each indicator for each target application based on the standardized values of each indicator; wherein, the indicators include CPU, memory, network, and disk. Among them, the target applications and their functions and operations commonly used by cloud desktop product users include, but are not limited to: Notepad (entering text, deleting text, changing text size and searching text), image player (zooming in, zooming out and toggling), file manager (opening, closing and dragging), office software (Word: entering text, deleting text, changing text size, color and font, searching text; Excel: data entry, formula calculation, sorting and filtering, chart creation and formatting adjustment; PowerPoint: creating new slides, inserting text / images, adjusting layout, setting animations and controlling presentation), browser (entering URLs, refreshing pages, managing multiple tabs, bookmarking and viewing history), video player (opening files, playing / pausing control, dragging progress bars, adjusting volume and switching to full screen), copying and pasting files, etc.
[0038] In this step, the normalized values of CPU, memory, network, and disk for the above applications during normal operation are calculated respectively.
[0039] In one embodiment, such as Figure 2 As shown, the calculation of the standardized values of each indicator for each target application includes: Step 201: Calculate the difference between the actual value and the minimum value of each indicator for each target application; Step 202: Calculate the difference between the maximum and minimum values of each indicator for each target application; Step 203: Calculate the ratio of the difference between the actual value and the minimum value of each indicator of each target application to the ratio of the difference between the maximum value and the minimum value of each indicator of each target application; Step 204: Based on the ratio of the difference between the actual value and the minimum value of each indicator of each target application to the difference between the maximum value and the minimum value of each indicator of each target application, obtain the standardized value of each indicator of each target application.
[0040] In this step, we first calculate the difference between the actual and minimum values of each indicator for each target application. Next, we calculate the difference between the maximum and minimum values of each indicator for each target application. Then, we calculate the ratio of the difference between the actual and minimum values of each indicator for each target application to the difference between the maximum and minimum values of each indicator for each target application. Finally, we obtain the standardized value of each indicator for each target application based on this ratio. That is, standardized value = (actual value - minimum value) / (maximum value - minimum value).
[0041] In one embodiment, calculating the weight of each indicator for each target application based on the standardized values of each indicator for each target application includes: Calculate the sum of the average values of all indicators for each target application; The weight of each indicator for each target application is calculated by summing the values of each indicator for each target application and the average values of each indicator for each target application.
[0042] In this step, the sum of the average values of all metrics for each target application is first calculated. Then, the weight of each metric for each target application is calculated based on the sum of the average values of all metrics for each target application. That is, the weight calculation formula is: metric / (CPU) 标准化值 +Memory 标准化值 +Network 标准化值 +Disk 标准化值 Calculate the weights respectively CPU Weight 内存 Weight 网络 and 权重磁盘 .
[0043] Step 102: Calculate the overall load value of each target application under different systems based on the standardized values of each indicator of each target application and the weights of each indicator of each target application; In one embodiment, such as Figure 3 As shown, the step of calculating the overall load value of each target application under different systems based on the standardized values of each indicator of each target application and the weights of each indicator of each target application includes: Step 301: Calculate the load value of a single-path operating system based on the standardized values of each indicator of each target application and the weights of each indicator of each target application; In this step, the load of a single circuit is calculated using the load value calculation formula, as follows: Single-channel load value = (CPU) 标准化值 / CPU 阈值 ) 100 Weight CPU +(memory) 标准化值 / Memory 阈值 ) 100 Weight 内存 +(Network) 标准化值 / network 阈值 ) 100 Weight 网络 +(disk) 标准化值 / disk 阈值 ) 100 Weight 磁盘 It should be noted that, in this embodiment, the CPU 阈值 ,Memory 阈值 ,network 阈值 and disk 阈值All are set to 80% by default. Calculate the load value for each single-processor operating system.
[0044] Step 302: Calculate the average load value of the same system type based on the load value of the single-path system; In this step, we first calculate the average load value for the same system type. For example: Win7 average load value = (Win7 load value 1 + Win7 load value 2 + ... + Win7 load value x) / x, Win10 average load value = (Win10 load value 1 + Win10 load value 2 + ... + Win10 load value y) / y, Kylin average load value = (Kylin load value 1 + Kylin load value 2 + ... + Kylin load value z) / z; where x is the number of Win7 virtual machines, y is the number of Win10 virtual machines, and z is the number of Kylin virtual machines.
[0045] Step 303: Calculate the overall load value of each target application under different systems based on the average load value of the same system type.
[0046] In this step, the overall load is calculated based on the average load of the same system type. For example: Overall load = Win7 average load. x / (x+y+z)+Win10 average load value.
[0047] Step 103: Divide each target application into application levels based on the overall load value of each target application under different systems; wherein, the application levels include low-load applications, medium-load applications, relatively high-load applications, and high-load applications; In this step, the load value is divided into four levels: low load (<=37.5), where the system load is very low, system resources are underutilized, and there are almost no waiting tasks; medium load (37.6~62.5), where the system load is normal, and resource utilization matches the number of system cores; high load (62.6~81.25), where the system load is high, and task queuing may occur; and high load (>81.26), where the system load is very high, which may lead to severe task queuing and slow system response. It should be noted that in this embodiment, the load value thresholds are defined as follows: a load value of 37.5 at 30% of all indicators represents the maximum value for low load; a load value of 62.5 at 50% of all indicators represents the maximum value for medium load; and a load value of 81.25 at 65% of all indicators represents the maximum value for high load.
[0048] Step 104: Select the load model corresponding to each target application according to the application level of each target application. The load model includes a basic load model, a load variation model, an extreme load model, and a comprehensive load model. In this step, the load value of each application is calculated using the model formula, and then the applications corresponding to the load values are divided into four levels according to the load grading standard: low load applications (a1, a2, a3), medium load applications (b1, b2, b3), relatively high load applications (c1, c2, c3) and high load applications (d1, d2, d3).
[0049] In one embodiment, selecting the load model corresponding to each target application based on the application level of each target application includes: The basic load model includes a persistent load model, which is used to execute application scenarios of low load, medium load, high load and high load applications. The load change model includes a gradually increasing load model and a gradually decreasing load model. The gradually increasing load model is used for application scenarios of low load application - medium load application - high load application - high load application, and the gradually decreasing load model is used for application scenarios of high load application - high load application - medium load application - low load application. The extreme load model includes a peak load model and a burst load model. The peak load model is used for scenarios where high-load applications run continuously, and the burst load model is used for scenarios where high-load applications are repeatedly opened and closed. The comprehensive load model includes a hybrid load model, which is used to execute scenario applications with different load levels and different application scenarios.
[0050] In this embodiment, the basic load model mainly includes a continuous load model, which is applicable to applications that execute at four load levels: low, medium, high, and high. That is, low load application (scenario 1), medium load application (scenario 2), high load application (scenario 3), and high load application (scenario 4).
[0051] The load change models mainly include the gradually increasing load model and the gradually decreasing load model. The gradually increasing load model is applicable to applications where the execution load value gradually increases from low to medium to high to high, i.e., the scenario of low-load application - medium-load application - high-load application - high-load application (Scenario 5). The gradually decreasing load model is applicable to applications where the execution load value gradually decreases from high to high to medium to low, i.e., the scenario of high-load application - high-load application - medium-load application - low-load application (Scenario 6).
[0052] Extreme load models mainly include peak load model and burst load model. Peak load model is applicable to the scenario of applications that continuously run high load values under the maximum virtual machine density, i.e., applications that continuously run high load applications (Scenario 7); burst load model is applicable to the scenario of applications that repeatedly open and close high load applications (Scenario 8).
[0053] The comprehensive load model mainly includes the hybrid load model, which is applicable to scenarios where different load levels are executed randomly, that is, scenarios with different load levels and different applications are executed randomly (Scenario 9).
[0054] Step 105: Determine the load execution strategy based on the load model corresponding to each target application; wherein the load execution strategy includes: customized mode, random mode and manual mode.
[0055] In one embodiment, determining the load execution strategy based on the load model corresponding to each target application includes: The customization mode includes model scenario customization and application scenario customization. Model scenario customization is based on the load model scenario application, where the execution scenario and number of executions are freely selected, and a customized process for load changes is formed according to the selection order. Application scenario customization is based on the selection of the execution scenario and the number of executions, and a customized process for load changes is formed according to the selection order. The random mode includes model scenario randomness and application scenario randomness. The model scenario is to freely select the execution scenario and execution number based on the load model scenario application, and then randomly execute the selected scenario and execution number. The application scenario randomness is to select the execution application and execution number, and then randomly execute the selected application and execution number.
[0056] In this embodiment, the customization mode mainly includes model scenario customization and application scenario customization. Model scenario customization involves freely selecting the execution scenario and the number of executions from the nine scenarios in the above-mentioned load model, and forming a customized process for load changes based on the selection order. Application scenario customization involves selecting the execution application and the number of executions, and forming the execution order of the load application scenarios based on the order of application selection.
[0057] The random mode mainly includes model scenario randomization and application scenario randomization. Model scenario randomization allows you to freely select the execution scenario and the number of executions from the nine scenarios in the load model, and then randomly execute the selected scenario and the number of executions. Application scenario randomization involves selecting the execution application and the number of executions, and then randomly executing the selected application and the number of executions.
[0058] Manual mode allows you to switch between customized model and application scenarios in customized mode and random model and application scenarios in random mode, regardless of whether you are currently in customized mode or random mode.
[0059] This disclosure provides a resource allocation method for data processing. By accurately calculating and classifying the load value of applications, resource waste is avoided, thereby ensuring the efficient operation of cloud desktops under different load conditions. By dynamically adjusting the load level and execution strategy, the allocation of system resources is optimized, thereby improving the response speed and operational stability of cloud desktop products. By supporting multiple load execution modes to adapt to the needs of different application scenarios, the method offers high flexibility, allowing for adjustments to the load execution method according to actual needs, thus achieving flexible configuration. Through accurate calculation and classification of loads, the system can identify high-load applications and make adjustments, thereby effectively reducing system pressure and avoiding performance degradation or system crashes caused by resource overload.
[0060] Figure 4 This is an architectural diagram of a resource allocation device for data processing provided in an embodiment of this disclosure. Figure 4 As shown, the device includes: a first calculation module 401, a second calculation module 402, a partitioning module 403, a selection module 403, and a determination module 404; wherein, the first calculation module 401 is used to calculate the standardized values of various indicators of each target application, and calculate the weight of each indicator of each target application based on the standardized values of the various indicators of each target application; wherein, the various indicators include CPU, memory, network, and disk; the second calculation module 402 is used to calculate the overall load value of each target application under different systems based on the standardized values of the various indicators of each target application and the weight of each indicator of each target application; the partitioning... Module 403 is used to classify each target application into application levels based on the overall load value of each target application under different systems; wherein, the application levels include low-load applications, medium-load applications, relatively high-load applications, and high-load applications; the selection module 404 is used to select the load model corresponding to each target application based on the application level of each target application; wherein, the load model includes a basic load model, a load variation model, an extreme load model, and a comprehensive load model; the determination module 405 is used to determine the load execution strategy based on the load model corresponding to each target application; wherein, the load execution strategy includes: a customized mode, a random mode, and a manual mode.
[0061] In one embodiment, a computer device is provided, the internal structure of which can be as follows: Figure 5As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the resource allocation method for data processing described above. It includes: memory and a processor; the memory stores the computer program; and the processor, when executing the computer program, implements any step of the resource allocation method for data processing described above.
[0062] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, can perform any of the steps in the resource allocation implementation method for data processing described above.
[0063] Although preferred embodiments of this disclosure have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this disclosure.
[0064] Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.
Claims
1. A resource allocation method for data processing, characterized in that, The method includes: Calculate the standardized values of each indicator for each target application, and calculate the weight of each indicator for each target application based on the standardized values of each indicator; wherein, the indicators include CPU, memory, network, and disk. The overall load value of each target application under different systems is calculated based on the standardized values of each indicator of each target application and the weights of each indicator of each target application. Each target application is classified into application levels based on its overall load value under different systems; wherein, the application levels include low load application, medium load application, high load application, and high load application. Select the load model corresponding to each target application based on the application level of each target application. The load model includes a basic load model, a load variation model, an extreme load model, and a comprehensive load model. The load execution strategy is determined based on the load model corresponding to each target application; wherein the load execution strategy includes: custom mode, random mode and manual mode.
2. The method according to claim 1, characterized in that, The calculation of standardized values for each target application indicator includes: Calculate the difference between the actual value and the minimum value of each indicator for each target application; Calculate the difference between the maximum and minimum values of each indicator for each target application; Calculate the ratio of the difference between the actual value and the minimum value of each indicator for each target application to the ratio of the difference between the maximum value and the minimum value of each indicator for each target application; The standardized value of each indicator for each target application is obtained by comparing the difference between the actual value and the minimum value of each indicator for each target application with the ratio of the difference between the maximum value and the minimum value of each indicator for each target application.
3. The method according to claim 2, characterized in that, The calculation of the weights of each indicator for each target application based on the standardized values of each indicator for each target application includes: Calculate the sum of the average values of all indicators for each target application; The weight of each indicator for each target application is calculated by summing the values of each indicator for each target application and the average values of each indicator for each target application.
4. The method according to claim 1, characterized in that, The calculation of the overall load value of each target application under different systems based on the standardized values of each indicator of each target application and the weights of each indicator of each target application includes: The load value of a single-path operating system is calculated based on the standardized values of each indicator of each target application and the weights of each indicator of each target application. Calculate the average load value of the same system type based on the load value of the single-path system; Calculate the overall load value of each target application under different systems based on the average load value of the same system type.
5. The method according to claim 1, characterized in that, The step of selecting the load model corresponding to each target application based on the application level of each target application includes: The basic load model includes a persistent load model, which is used to execute application scenarios of low load, medium load, high load and high load applications. The load change model includes a gradually increasing load model and a gradually decreasing load model. The gradually increasing load model is used for application scenarios of low load application - medium load application - high load application - high load application, and the gradually decreasing load model is used for application scenarios of high load application - high load application - medium load application - low load application. The extreme load model includes a peak load model and a burst load model. The peak load model is used for scenarios where high-load applications run continuously, and the burst load model is used for scenarios where high-load applications are repeatedly opened and closed. The comprehensive load model includes a hybrid load model, which is used to execute scenario applications with different load levels and different application scenarios.
6. The method according to claim 5, characterized in that, The process of determining the load execution strategy based on the load model corresponding to each target application includes: The customization mode includes model scenario customization and application scenario customization. Model scenario customization is based on the load model scenario application, where the execution scenario and number of executions are freely selected, and a customized process for load changes is formed according to the selection order. Application scenario customization is based on the selection of the execution scenario and the number of executions, and a customized process for load changes is formed according to the selection order. The random mode includes model scenario randomness and application scenario randomness. The model scenario is to freely select the execution scenario and execution number based on the load model scenario application, and then randomly execute the selected scenario and execution number. The application scenario randomness is to select the execution application and execution number, and then randomly execute the selected application and execution number.
7. The method according to any one of claims 1 to 6, characterized in that, The target applications include at least one of the following: Notepad, image player, file manager, office software, browser, file copy operation, and file paste operation.
8. A resource allocation device for data processing, characterized in that, The device includes: a first calculation module, a second calculation module, a partitioning module, a selection module, and a determination module; wherein, The first calculation module is used to calculate the standardized values of each indicator of each target application, and to calculate the weight of each indicator of each target application based on the standardized values of each indicator of each target application; wherein, the indicators include CPU, memory, network and disk; The second calculation module is used to calculate the overall load value of each target application under different systems based on the standardized values of each indicator of each target application and the weights of each indicator of each target application. The segmentation module is used to classify each target application into application levels based on the overall load value of each target application under different systems; wherein, the application levels include low-load applications, medium-load applications, relatively high-load applications, and high-load applications; The selection module is used to select the load model corresponding to each target application according to the application level of each target application. The load model includes a basic load model, a load variation model, an extreme load model, and a comprehensive load model. The determining module is used to determine the load execution strategy based on the load model corresponding to each target application; wherein the load execution strategy includes: custom mode, random mode and manual mode.
9. A computer device, comprising: A memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.