Cloud resource balancing method during end-cloud fusion, computer device and medium

Abstract

The application provides a cloud resource balancing method in end-cloud fusion, a computer device and a medium. The method comprises the following steps: obtaining target computing tasks of a plurality of user terminals of a cloud resource pool; determining an application scene type of each target computing task, and determining a data computing amount of each target computing task; determining a cloud resource demand degree of each user terminal based on the application scene type, the data computing amount and local resource configuration information of each user terminal; determining a target allocation ratio of the cloud resources of the plurality of user terminals according to the cloud resource demand degree; and allocating the cloud resources in the cloud resource pool to the plurality of user terminals according to the target allocation ratio. The application can make the performance of the plurality of user terminals relatively balanced in end-cloud fusion, avoid the situation that some user terminals have low performance, make the configuration of the cloud resources more reasonable, and thus improve the overall processing efficiency of the computing tasks.

Description

Technical Field

[0001] This application relates to the field of edge-cloud convergence processing technology, specifically to a cloud resource balancing method, computer equipment, and media for edge-cloud convergence. Background Technology

[0002] In related technologies, when using edge-cloud convergence technology to process computing tasks on user terminals, data processing is often performed according to a pre-specified cloud resource configuration. However, the pre-specified cloud resource configuration is often not applicable to all user terminals, which can easily lead to low performance on some user terminals, thereby reducing the processing efficiency of computing tasks.

[0003] Therefore, how to rationally allocate cloud resources to improve the processing efficiency of computing tasks is an urgent problem to be solved. Summary of the Invention

[0004] The embodiments of this application provide a cloud resource balancing method, computer equipment, and medium for edge-cloud convergence, aiming to make cloud resource allocation more reasonable, thereby improving the processing efficiency of computing tasks.

[0005] In a first aspect, embodiments of this application provide a cloud resource balancing method for edge-cloud convergence, the cloud resource balancing method for edge-cloud convergence comprising:

[0006] Obtain the target computing tasks from multiple user terminals in the cloud resource pool;

[0007] Determine the application scenario type for each of the target computing tasks, and determine the data computation volume for each of the target computing tasks;

[0008] Based on the application scenario type, the data computation volume, and the local resource configuration information of each user terminal, the cloud resource requirement of each user terminal is determined.

[0009] Based on the cloud resource demand, determine the target allocation ratio of cloud resources for multiple user terminals;

[0010] According to the target allocation ratio, cloud resources in the cloud resource pool are allocated to multiple user terminals.

[0011] In some embodiments, determining the cloud resource requirement of each user terminal based on the application scenario type, the data computation volume, and the local resource configuration information of each user terminal includes:

[0012] Based on the data computation volume and the local resource configuration information of each user terminal, cluster analysis is performed on multiple user terminals to obtain multiple categories of user terminals.

[0013] Based on the application scenario type, determine the cloud resource demand tier for each category of user terminal;

[0014] Based on the cloud resource demand tiers, determine the cloud resource demand level of the corresponding user terminal.

[0015] In some embodiments, determining the cloud resource demand tier for each category of user terminals based on the application scenario type includes:

[0016] For each category, the target application scenario type is determined from the application scenario types of the target computing tasks of multiple user terminals in that category;

[0017] Based on the cloud resource demand priority pre-associated with the target application scenario type, the cloud resource demand tier to which the user terminal of the category belongs is determined.

[0018] In some embodiments, determining the target application scenario type from the application scenario types of the target computing tasks of the multiple user terminals in the category includes:

[0019] In the application scenario types of the target computing tasks of multiple user terminals in the aforementioned category, determine the number of each application scenario type.

[0020] The application scenario type with the largest number of occurrences is taken as the target application scenario type.

[0021] In some embodiments, determining the cloud resource demand level of the corresponding user terminal based on the cloud resource demand tier includes:

[0022] Determine the preset demand level for each user terminal;

[0023] The cloud resource demand level of the user terminal is determined based on the sum of the preset demand level and the cloud resource demand level of the same user terminal.

[0024] In some embodiments, determining the application scenario type for each of the target computing tasks includes:

[0025] For each of the target computing tasks, a target page in the corresponding user terminal is determined for triggering the target computing task;

[0026] Based on the scene tags associated with the target page, the application scene type of the target computing task is determined.

[0027] In some embodiments, determining the data computation amount for each of the target computing tasks includes:

[0028] For each target computation task, obtain the computational volume prediction model associated with the corresponding scene label;

[0029] The task information of the target computing task is input into the corresponding computing volume prediction model, and the computing volume output by the corresponding computing volume prediction model is received and used as the data computing volume of the target computing task.

[0030] In some embodiments, the computational cost prediction model is generated through the following steps:

[0031] Retrieve multiple historical computation tasks triggered on the target page;

[0032] Determine the historical time consumed when processing data for each of the aforementioned historical computing tasks using preset computing resources;

[0033] Based on the historical time consumption, the historical data calculation volume of the corresponding historical calculation task is determined;

[0034] The computational volume prediction model is obtained by training a model based on multiple historical computation tasks and the historical data computation volume of each historical computation task.

[0035] Secondly, embodiments of this application provide a cloud resource balancing device for edge-cloud convergence, the cloud resource balancing device for edge-cloud convergence comprising:

[0036] The acquisition module is used to acquire the target computing tasks of multiple user terminals in the cloud resource pool;

[0037] The determination module is used to determine the application scenario type of each target computing task and the data computing volume of each target computing task; based on the application scenario type, the data computing volume and the local resource configuration information of each user terminal, determine the cloud resource demand of each user terminal; and determine the target allocation ratio of cloud resources for multiple user terminals according to the cloud resource demand.

[0038] The allocation module is used to allocate cloud resources in the cloud resource pool to multiple user terminals according to the target allocation ratio.

[0039] Thirdly, embodiments of this application provide a computer device including a processor and a memory, wherein the memory stores a computer program configured to be executed by the processor to implement the cloud resource balancing method for edge-cloud convergence as described in any of the preceding claims.

[0040] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program configured to be executed by a processor to implement the cloud resource balancing method for edge-cloud convergence as described in any of the preceding claims.

[0041] Fifthly, embodiments of this application provide a computer program product, including a computer program or instructions, which are executed by a processor to implement the cloud resource balancing method for edge-cloud convergence as described in any of the preceding claims.

[0042] The beneficial effects of the embodiments of this application are as follows:

[0043] In the embodiments of this application, by comprehensively considering the application scenario type, data computation volume, and local resource configuration information of the target computing tasks of multiple user terminals, the cloud resource requirement of each user terminal is determined, and then cloud resources are allocated to multiple user terminals in proportion. This can make the performance of multiple user terminals relatively balanced when the end-to-cloud is integrated, avoid the situation where some user terminals have low performance, make the configuration of cloud resources more reasonable, and thus improve the overall processing efficiency of computing tasks. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic flowchart of an embodiment of the cloud resource balancing method for edge-cloud convergence provided in the embodiments of this application;

[0046] Figure 2 This is a flowchart illustrating another embodiment of the cloud resource balancing method for edge-cloud convergence provided in the embodiments of this application;

[0047] Figure 3 This is a flowchart illustrating another embodiment of the cloud resource balancing method for edge-cloud convergence provided in the embodiments of this application;

[0048] Figure 4 This is a schematic diagram of an embodiment of the cloud resource balancing device for edge-cloud convergence provided in the embodiments of this application;

[0049] Figure 5 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, in the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features.

[0052] Firstly, embodiments of this application provide a method for cloud resource balancing in edge-cloud convergence. (Refer to...) Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of a cloud resource balancing method for edge-cloud convergence. Figure 1 In this context, the cloud resource balancing method during edge-cloud convergence may include:

[0053] 101. Obtain the target computing tasks of multiple user terminals in the cloud resource pool.

[0054] In the embodiments of this application, edge-cloud convergence is implemented based on a cloud resource pool, which refers to a resource pool that aggregates the computing resources of cloud servers. These computing resources may include, for example, CPU (Central Processing Unit) resources and GPU (Graphics Processing Unit) resources. The user terminal refers to the terminal device on which the user is located. The user can trigger computing tasks through the terminal device. Taking the interior design industry as an example, the target computing task may include the generation of virtual reality 3D images related to interior design. The cloud server differs from the user terminal; it is a device located in the cloud.

[0055] In the embodiments of this application, the multiple user terminals of the cloud resource pool refer to multiple user terminals connected to the cloud resource pool to facilitate the data processing of the target computing task using edge-cloud convergence technology. The target computing task can be a computing task that the corresponding user terminal is currently processing data for, or a computing task that the corresponding user terminal is about to process data for, and is not limited here.

[0056] 102. Determine the application scenario type for each target computing task, and determine the data computation volume for each target computing task.

[0057] In the embodiments of this application, the application scenario type of the target computing task refers to the type of application scenario in which the target computing task is located. Taking a user terminal in a school or college as an example, students of each major can log in to the user terminal to perform computing tasks related to their major's professional knowledge. Therefore, the application scenario type of the target computing task may include, for example, teaching scenarios, practice scenarios, and examination scenarios. The data computing volume of the target computing task refers to the computing volume when processing data for the target computing task, which can be evaluated in a specified way and is not limited here.

[0058] 103. Based on the application scenario type, data computation volume, and local resource configuration information of each user terminal, determine the cloud resource requirement of each user terminal.

[0059] In the embodiments of this application, the local resource configuration information of the user terminal records the specific details of the user terminal's local resources, such as the amount of local CPU resources and GPU resources. By combining the application scenario type, data computation volume, and the local resource configuration information of each user terminal, a more accurate cloud resource requirement for each user terminal can be determined.

[0060] In some embodiments of this application, determining the cloud resource requirement of each user terminal based on the application scenario type, data computation volume, and local resource configuration information of each user terminal may include: converting the application scenario type into a corresponding value, and then performing a weighted sum with the data computation volume and the local resource configuration information of each user terminal to obtain the cloud resource requirement of each user terminal. Of course, alternative methods may also be used. Figure 2 The method used in the illustrated embodiment to determine the cloud resource requirements of each user terminal is not limited here.

[0061] 104. Determine the target allocation ratio of cloud resources for multiple user terminals based on cloud resource demand.

[0062] In the embodiments of this application, the target allocation ratio of cloud resources for multiple user terminals may be the ratio between the cloud resource demand of multiple user terminals, or may be further calculated based on the ratio between the cloud resource demand of multiple user terminals, and is not limited here.

[0063] 105. Allocate cloud resources from the cloud resource pool to multiple user terminals according to the target allocation ratio.

[0064] In the embodiments of this application, cloud resources in the cloud resource pool can be allocated to multiple user terminals according to a target allocation ratio, so that the ratio of cloud resources allocated to multiple user terminals is equal to the target allocation ratio. In this way, the performance of multiple user terminals when performing data processing on corresponding target computing tasks using edge-cloud fusion technology will also be relatively balanced, achieving balanced allocation of cloud resources during edge-cloud fusion.

[0065] As can be seen, in the above embodiments of this application, by comprehensively considering the application scenario type, data computation volume, and local resource configuration information of the target computing tasks of multiple user terminals, the cloud resource requirement of each user terminal is determined, and then cloud resources are allocated to multiple user terminals in proportion. This can make the performance of multiple user terminals relatively balanced when the end-to-cloud is integrated, avoid the situation where some user terminals have low performance, make the configuration of cloud resources more reasonable, and thus improve the overall processing efficiency of computing tasks.

[0066] In some embodiments of this application, such as Figure 2 As shown, in Figure 1 Based on the illustrated embodiment, the cloud resource requirement of each user terminal is determined according to the application scenario type, data computation volume, and local resource configuration information of each user terminal. This may include:

[0067] 201. Based on the amount of data computation and the local resource configuration information of each user terminal, perform cluster analysis on multiple user terminals to obtain multiple categories of user terminals.

[0068] In the embodiments of this application, clustering analysis is an unsupervised learning method aimed at dividing multiple user terminals into several categories, such that user terminals within the same category are highly similar, while user terminals in different categories are as different as possible. Therefore, the computational cost and local resource configuration information of each user terminal can be used as the basis for clustering analysis, grouping user terminals with highly similar computational costs and local resource configuration information into the same category, thus obtaining multiple categories of user terminals. Specific clustering algorithms may include, for example, K-means clustering, hierarchical clustering, etc., and are not limited here.

[0069] 202. Based on the application scenario type, determine the cloud resource demand level to which each category of user terminal belongs.

[0070] In the embodiments of this application, the cloud resource requirements of each user terminal can be tiered and evaluated to obtain multiple different cloud resource requirement tiers, such as tier 1, tier 2, tier 3, etc. Since the application scenarios of the target computing tasks of different user terminals may be different, the cloud resource requirement tier to which each category of user terminal belongs can be determined based on the differences in application scenario types.

[0071] In some embodiments of this application, determining the cloud resource demand tier for each category of user terminals based on application scenario type may include: for each category, identifying the target application scenario type among the application scenario types of the target computing tasks of multiple user terminals in that category; and determining the cloud resource demand tier for the user terminals in that category based on the cloud resource demand priority pre-associated with the target application scenario type. For example, when the target application scenario type is a teaching scenario, the pre-associated cloud resource demand priority is level 1, and the cloud resource demand tier for the user terminals in that category is level 1. As another example, when the target application scenario type is a practice scenario, the pre-associated cloud resource demand priority is level 2, and the cloud resource demand tier for the user terminals in that category is level 2. As yet another example, when the target application scenario type is an examination scenario, the pre-associated cloud resource demand priority is level 3, and the cloud resource demand tier for the user terminals in that category is level 3.

[0072] It can be seen that by identifying the target application scenario type among the target computing tasks of multiple user terminals in this category, and then determining the cloud resource demand level to which the user terminals in this category belong, the determined cloud resource demand level can be more accurate and reasonable.

[0073] In some embodiments of this application, determining the target application scenario type among the application scenario types of the target computing tasks of multiple user terminals in this category may include: determining the number of existences of each application scenario type among the application scenario types of the target computing tasks of multiple user terminals in this category. Since each user terminal in this category has a corresponding application scenario type for its target computing task, the number of each application scenario type in this category can be counted to obtain the number of existences of the application scenario type. The application scenario type with the largest number of existences is taken as the target application scenario type, so that the target application scenario type can match the cloud resource requirements of most user terminals in this category.

[0074] 203. Determine the cloud resource demand level of the corresponding user terminal based on the cloud resource demand level.

[0075] In the embodiments of this application, the cloud resource demand of a user terminal varies depending on its cloud resource demand tier. For example, the cloud resource demand of a user terminal at tier 1 is less than that at tier 2. Similarly, the cloud resource demand of a user terminal at tier 2 is less than that at tier 3.

[0076] In some embodiments of this application, determining the cloud resource demand level of a corresponding user terminal based on cloud resource demand tiers may include: determining a preset demand tier for each user terminal, wherein the preset demand tier can be pre-set by relevant personnel (such as the user of the corresponding user terminal or the administrator of the cloud resource pool) based on actual needs; and determining the cloud resource demand level of a user terminal based on the sum of the preset demand tiers and the cloud resource demand tiers for the same user terminal. For example, the sum of the preset demand tiers and the cloud resource demand tiers for the same user terminal can be used as the comprehensive demand tier for that user terminal, and then the cloud resource demand level for that user terminal can be determined based on the comprehensive demand tier. The corresponding cloud resource demand level will differ depending on the comprehensive demand tier. It can be seen that this embodiment comprehensively considers both the preset demand tiers and the cloud resource demand tiers for user terminals, so that the determined cloud resource demand level for user terminals can take into account both the personalized needs of relevant personnel for cloud resources and the expected needs represented by the cloud resource demand tiers, making the allocation of cloud resources more reasonable and thereby improving the overall processing efficiency of computing tasks.

[0077] As can be seen, in the above embodiments of this application, multiple user terminals are clustered according to the amount of data computation and the local resource configuration information of each user terminal to obtain multiple categories of user terminals. Then, based on the application scenario type, the cloud resource demand level of each category of user terminal is determined, thereby determining the cloud resource demand degree of the corresponding user terminal. This makes the determined cloud resource demand degree more accurate and more in line with the overall demand of multiple user terminals for cloud resources.

[0078] In some embodiments of this application, such as Figure 3 As shown, in Figures 1 to 2 Based on any of the embodiments shown, determining the application scenario type for each target computing task may include:

[0079] 301. For each target computing task, determine the target page in the corresponding user terminal used to trigger the target computing task.

[0080] In the embodiments of this application, each target computing task can be triggered through a corresponding target page. For example, a user can trigger a target computing task by clicking on the target page of the corresponding user terminal. Taking the application scenario types of the target computing task as including teaching scenarios, practice scenarios, and examination scenarios as examples, the target page can be a teaching page, practice page, examination page, etc. on the corresponding user terminal.

[0081] 302. Based on the scene tags associated with the target page, determine the application scenario type of the target computing task.

[0082] In the embodiments of this application, each target page is pre-associated with a corresponding scene tag to distinguish different target pages. Therefore, the application scenario type of the target computing task can be determined based on the scene tags associated with the target page. Scene tags may include, for example, tags such as teaching scenario, practice scenario, and examination scenario.

[0083] In some embodiments of this application, determining the data computation volume of each target computing task may include: for each target computing task, obtaining a computation volume prediction model associated with a corresponding scene label, wherein the computation volume prediction model may be, for example, a neural network model. Since the data computation volume of target computing tasks may differ in different application scenarios, a separate computation volume prediction model may be associated with each scene label; that is, different computation volume prediction models are associated with different scene labels. This distinguishes the calculation rules for the data computation volume of target computing tasks in different application scenarios, making the calculated data computation volume more accurate. The task information of the target computing task is input into the corresponding computation volume prediction model, and the computation volume output by the corresponding computation volume prediction model is received and used as the data computation volume of the target computing task. It can be seen that this embodiment, based on the computation volume prediction model, realizes the calculation of the data computation volume of the target computing task, making the data computation volume more accurate.

[0084] In some embodiments of this application, the generation method of the computational prediction model associated with scene tags is described. Specifically, the computational load prediction model associated with scene tags can be generated through the following steps: First, obtain multiple historical computation tasks triggered on the target page associated with the scene tag, where each historical computation task is a computation task triggered at a historical moment. Second, determine the historical processing time for each historical computation task using preset computational resources. The preset computational resources can be, for example, pre-set computational resources with redundancy (e.g., CPU resources, GPU resources, etc.). Redundancy means that the preset computational resources can fully meet the resource requirements for data processing of each historical computation task without affecting the data processing speed due to insufficient computational resources. For example, the computational resources of the preset computational resources can be greater than a preset resource threshold, i.e., the computational resources of the preset computational resources are too large. Third, based on the historical processing time, determine the historical data computation volume of the corresponding historical computation task. The historical data computation volume can be positively correlated with the historical processing time; for example, the historical processing time can be directly used as the historical data computation volume. Fourth, train the model based on multiple historical computation tasks and the historical data computation volume of each historical computation task to obtain the computational load prediction model associated with scene tags.

[0085] In the process of model training, each historical computation task can be used as a sample for model training, and the historical data computation amount of each historical computation task can be used as the label of the corresponding sample. In this way, the computation amount prediction model associated with scene labels can be obtained by using model training.

[0086] As can be seen, this embodiment realizes the generation of a model for calculating the data computation volume of the target computing task.

[0087] In some embodiments of this application, determining the historical data computation volume of a corresponding historical computing task based on historical time consumption may include: for each historical computing task, obtaining the total amount of data generated during the data processing of the historical computing task using preset computing resources (including the total amount of intermediate data, result data, etc.); and performing a weighted summation of the historical time consumption and total data volume of the same historical computing task to obtain the historical data computation volume of the historical computing task, thereby making the determined historical data computation volume more accurate.

[0088] Secondly, based on the cloud resource balancing method for edge-cloud convergence in the above embodiments, embodiments of this application provide a cloud resource balancing apparatus for edge-cloud convergence. The cloud resource balancing apparatus for edge-cloud convergence is used to execute the steps in any embodiment of the cloud resource balancing method for edge-cloud convergence described above. Specifically, refer to... Figure 4 The cloud resource balancing device 400 for edge-cloud convergence may include:

[0089] The acquisition module 401 is used to acquire the target computing tasks of multiple user terminals in the cloud resource pool;

[0090] The determination module 402 is used to determine the application scenario type of each target computing task and the data computing volume of each target computing task; based on the application scenario type, data computing volume and local resource configuration information of each user terminal, it determines the cloud resource requirement of each user terminal; and based on the cloud resource requirement, it determines the target allocation ratio of cloud resources for multiple user terminals.

[0091] The allocation module 403 is used to allocate cloud resources in the cloud resource pool to multiple user terminals according to the target allocation ratio.

[0092] Thirdly, embodiments of this application provide a computer device that integrates any of the cloud resource balancing devices for edge-cloud convergence provided in the embodiments of this application. The computer device includes a processor and a memory, the memory storing a computer program configured to be executed by the processor to implement the cloud resource balancing method for edge-cloud convergence as described in any of the above embodiments, for example:

[0093] Obtain the target computing tasks of multiple user terminals in the cloud resource pool; determine the application scenario type and data computing volume of each target computing task; determine the cloud resource demand of each user terminal based on the application scenario type, data computing volume, and local resource configuration information of each user terminal; determine the target allocation ratio of cloud resources for multiple user terminals according to the cloud resource demand; and allocate cloud resources from the cloud resource pool to multiple user terminals according to the target allocation ratio.

[0094] Fourthly, embodiments of this application provide a computer device that integrates any of the cloud resource balancing devices for edge-cloud convergence provided in embodiments of this application. For example... Figure 5 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0095] The computer device may include components such as a processor 501 with one or more processing cores, a storage unit 502 with one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will understand that... Figure 5 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0096] The processor 501 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the storage unit 502, and by calling data stored in the storage unit 502, thereby providing overall monitoring of the computer device. Optionally, the processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 501.

[0097] Storage unit 502 can be used to store software programs and modules. Processor 501 executes various functional applications and data processing by running the software programs and modules stored in storage unit 502. Storage unit 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, storage unit 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, storage unit 502 may also include a memory controller to provide processor 501 with access to storage unit 502.

[0098] The computer equipment also includes a power supply 503 that supplies power to the various components. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 503 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0099] The computer device may also include an input unit 504, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0100] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processor 501 in the computer device loads the executable files corresponding to the processes of one or more application programs into the storage unit 502 according to the following instructions, and the processor 501 runs the application programs stored in the storage unit 502 to realize various functions, such as:

[0101] Obtain the target computing tasks of multiple user terminals in the cloud resource pool; determine the application scenario type and data computing volume of each target computing task; determine the cloud resource demand of each user terminal based on the application scenario type, data computing volume, and local resource configuration information of each user terminal; determine the target allocation ratio of cloud resources for multiple user terminals according to the cloud resource demand; and allocate cloud resources from the cloud resource pool to multiple user terminals according to the target allocation ratio.

[0102] Fifthly, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. The computer-readable storage medium stores a computer program configured to be executed by a processor to implement the cloud resource balancing method for edge-cloud convergence as described in any of the preceding claims, for example:

[0103] Obtain the target computing tasks of multiple user terminals in the cloud resource pool; determine the application scenario type and data computing volume of each target computing task; determine the cloud resource demand of each user terminal based on the application scenario type, data computing volume, and local resource configuration information of each user terminal; determine the target allocation ratio of cloud resources for multiple user terminals according to the cloud resource demand; and allocate cloud resources from the cloud resource pool to multiple user terminals according to the target allocation ratio.

[0104] Sixthly, embodiments of this application provide a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a cloud resource balancing method for edge-cloud convergence as described in any of the preceding claims, for example:

[0105] Obtain the target computing tasks of multiple user terminals in the cloud resource pool; determine the application scenario type and data computing volume of each target computing task; determine the cloud resource demand of each user terminal based on the application scenario type, data computing volume, and local resource configuration information of each user terminal; determine the target allocation ratio of cloud resources for multiple user terminals according to the cloud resource demand; and allocate cloud resources from the cloud resource pool to multiple user terminals according to the target allocation ratio.

[0106] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for balancing cloud resources in edge-cloud convergence, characterized in that, The cloud resource balancing method during edge-cloud convergence includes: Obtain the target computing tasks from multiple user terminals in the cloud resource pool; Determine the application scenario type for each of the target computing tasks, and determine the data computation volume for each of the target computing tasks; Based on the application scenario type, the data computation volume, and the local resource configuration information of each user terminal, the cloud resource requirement of each user terminal is determined. Based on the cloud resource demand, determine the target allocation ratio of cloud resources for multiple user terminals; According to the target allocation ratio, cloud resources in the cloud resource pool are allocated to multiple user terminals; The step of determining the cloud resource requirement of each user terminal based on the application scenario type, the data computation volume, and the local resource configuration information of each user terminal includes: Based on the data computation volume and the local resource configuration information of each user terminal, cluster analysis is performed on multiple user terminals to obtain multiple categories of user terminals. Based on the application scenario type, determine the cloud resource demand tier for each category of user terminal; Based on the cloud resource demand tiers, determine the cloud resource demand level of the corresponding user terminal; The step of determining the cloud resource demand tier for each category of user terminal based on the application scenario type includes: For each category, the target application scenario type is determined from the application scenario types of the target computing tasks of multiple user terminals in that category; Based on the cloud resource demand priority pre-associated with the target application scenario type, determine the cloud resource demand tier to which the user terminal of the category belongs; The determination of the target application scenario type among the application scenario types of the target computing tasks of multiple user terminals in the category includes: In the application scenario types of the target computing tasks of multiple user terminals in the aforementioned category, determine the number of each application scenario type. The application scenario type with the largest number of occurrences is taken as the target application scenario type.

2. The cloud resource balancing method for edge-cloud convergence as described in claim 1, characterized in that, The step of determining the cloud resource demand level of the corresponding user terminal based on the cloud resource demand tier includes: Determine the preset demand level for each user terminal; The cloud resource demand level of the user terminal is determined based on the sum of the preset demand level and the cloud resource demand level of the same user terminal.

3. The cloud resource balancing method for edge-cloud convergence as described in claim 1, characterized in that, The determination of the application scenario type for each of the target computing tasks includes: For each of the target computing tasks, a target page in the corresponding user terminal is determined for triggering the target computing task; Based on the scene tags associated with the target page, the application scene type of the target computing task is determined.

4. The cloud resource balancing method for edge-cloud convergence as described in claim 3, characterized in that, Determining the data computation amount for each of the target computation tasks includes: For each target computation task, obtain the corresponding computational volume prediction model associated with the scene label; The task information of the target computing task is input into the corresponding computing volume prediction model, and the computing volume output by the corresponding computing volume prediction model is received and used as the data computing volume of the target computing task.

5. The cloud resource balancing method for edge-cloud convergence as described in claim 4, characterized in that, The computational cost prediction model is generated through the following steps: Retrieve multiple historical computation tasks triggered on the target page; Determine the historical time consumed when processing data for each of the aforementioned historical computing tasks using preset computing resources; Based on the historical time consumption, the historical data calculation volume of the corresponding historical calculation task is determined; The computational volume prediction model is obtained by training a model based on multiple historical computation tasks and the historical data computation volume of each historical computation task.

6. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program configured to be executed by the processor to implement the cloud resource balancing method for edge-cloud convergence as described in any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program configured to be executed by a processor to implement the cloud resource balancing method for end-to-cloud convergence as described in any one of claims 1 to 5.

Images