Cloud resource allocation prediction method in edge-cloud fusion, computer device and medium

Abstract

The application provides a cloud resource allocation prediction method in an end-cloud fusion, a computer device and a medium. The method comprises the following steps: obtaining a user type of a current user terminal; determining historical use data of a plurality of historical user terminals in the user type, wherein the historical use data comprises a data volume of a computing task of each historical user terminal at a historical time and a use quantity of the historical user terminal at the historical time; predicting a data volume of a computing task of the current user terminal at a preset future time based on the historical use data to obtain an expected data volume; and determining a target cloud resource volume of the current user terminal based on the expected data volume to allocate cloud resources to the current user terminal according to the target cloud resource volume. The application can accurately predict the target cloud resource volume required by the current user terminal to allocate cloud resources, so that the cloud resource configuration is more reasonable and the cloud resource cost is effectively reduced.

Description

Technical Field

[0001] This application relates to the field of edge-cloud convergence processing technology, specifically to a cloud resource allocation prediction 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 reasonable enough. For example, if the cloud resource configuration is too high, it is easy to over-consume cloud resources and waste them, increasing cloud resource costs.

[0003] Therefore, how to rationally allocate cloud resources to reduce cloud resource costs is an urgent problem that needs to be solved. Summary of the Invention

[0004] Embodiments of this application provide a cloud resource allocation prediction method, computer equipment, and medium for edge-cloud convergence, aiming to make cloud resource allocation more reasonable, thereby reducing cloud resource costs.

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

[0006] Get the user type of the current user terminal;

[0007] Determine the historical usage data of multiple historical user terminals under the user type, wherein the historical usage data includes the amount of data of the computing task of each historical user terminal at a historical moment, and the number of times the historical user terminal was used at the historical moment;

[0008] Based on the historical usage data, the data volume of the current user terminal's computing task at a preset future time is predicted to obtain the expected data volume;

[0009] Based on the expected data volume, the target cloud resource volume for the current user terminal is determined, and cloud resources are allocated to the current user terminal according to the target cloud resource volume.

[0010] In some embodiments, predicting the data volume of the current user terminal's computing task at a preset future time based on the historical usage data to obtain the expected data volume includes:

[0011] Based on the amount of data in the computing task of each historical user terminal at the historical moment, a first trend of change in the amount of data in the computing task of the historical user terminal is determined.

[0012] Based on the number of historical user terminals used at the historical time, a second trend in the number of historical user terminals used is determined.

[0013] Based on the first trend and the second trend, the data volume of the current user terminal's computing task at a preset future time is predicted to obtain the expected data volume.

[0014] In some embodiments, predicting the data volume of the computing task of the current user terminal at a preset future time based on the first trend and the second trend to obtain the expected data volume includes:

[0015] Using the first trend of change, determine the first data volume of the computing task of each historical user terminal at the preset future time.

[0016] The sum of the first data volume of the computing tasks of all the historical user terminals at the preset future time is determined and used as the second data volume;

[0017] Using the second trend of change, determine the second number of times the historical user terminal is used at the preset future time.

[0018] The expected data volume is determined based on the ratio of the second data volume to the second usage quantity.

[0019] In some embodiments, determining the expected data volume based on the ratio of the second data volume to the second usage quantity includes:

[0020] Based on the data volume of the computing task of each historical user terminal at the historical time and the number of times the historical user terminal was used at the historical time, the average data volume of the computing task of the historical user terminal at the historical time is determined.

[0021] A third trend in the average data volume is determined based on the average data volume of the computational task at the historical moment.

[0022] Using the third trend of change, the average amount of data for the computational task at the preset future time is determined;

[0023] The expected data volume is determined based on the average data volume of the computational task at the preset future time and the ratio of the second data volume to the second usage quantity.

[0024] In some embodiments, determining the target cloud resource quantity for the current user terminal based on the expected data volume includes:

[0025] Based on the expected data volume of different current user terminals, determine the cloud resource allocation ratio for different current user terminals;

[0026] Based on the cloud resource allocation ratio, the target cloud resource amount for each current user terminal is determined.

[0027] In some embodiments, determining the target cloud resource amount for each current user terminal based on the cloud resource allocation ratio includes:

[0028] Determine resource allocation correction coefficients associated with different user types of the current user terminals, wherein the resource allocation correction coefficients include CPU resource correction coefficients and GPU resource correction coefficients;

[0029] Based on the cloud resource allocation ratio and the CPU resource correction coefficient, the target cloud resource amount for each current user terminal with respect to CPU resources is determined, and based on the cloud resource allocation ratio and the GPU resource correction coefficient, the target cloud resource amount for each current user terminal with respect to GPU resources is determined.

[0030] In some embodiments, obtaining the user type of the current user terminal includes:

[0031] Obtain the user tags of the currently logged-in users on the user terminal;

[0032] Based on the user tag, the user type of the current user terminal is determined.

[0033] In some embodiments, the user tag is determined in the following ways:

[0034] Obtain the number of times and / or frequency of use of multiple preset software programs on the current user's terminal by the logged-in user;

[0035] Based on the number of uses and / or frequency of use, the target software is determined from a plurality of preset software.

[0036] The preset tags associated with the target software are used as the user tags of the logged-in users.

[0037] Secondly, embodiments of this application provide a cloud resource allocation prediction device for edge-cloud convergence, the cloud resource allocation prediction device for edge-cloud convergence comprising:

[0038] The acquisition module is used to obtain the user type of the current user terminal;

[0039] The determination module is used to determine the historical usage data of multiple historical user terminals under the user type, wherein the historical usage data includes the amount of data of the computing task of each historical user terminal at a historical moment, and the number of times the historical user terminal is used at the historical moment.

[0040] The prediction module is used to predict the amount of data for the computing task of the current user terminal at a preset future time based on the historical usage data, so as to obtain the expected amount of data.

[0041] The allocation module is used to determine the target cloud resource amount of the current user terminal based on the expected data amount, so as to allocate cloud resources to the current user terminal according to the target cloud resource amount.

[0042] 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 allocation prediction method for edge-cloud convergence as described in any of the preceding claims.

[0043] 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 allocation prediction method for edge-cloud convergence as described in any of the preceding claims.

[0044] 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 allocation prediction method for edge-cloud convergence as described in any of the preceding claims.

[0045] The beneficial effects of the embodiments of this application are as follows:

[0046] In the embodiments of this application, by obtaining the user type of the current user terminal, and based on the data volume of the computing task of each historical user terminal under the user type at a historical moment, as well as the number of historical user terminals used at a historical moment, the data volume of the computing task of the current user terminal at a preset future moment can be accurately predicted, thereby accurately predicting the target amount of cloud resources required by the current user terminal, so as to allocate cloud resources, making the cloud resource configuration more reasonable and effectively reducing cloud resource costs. Attached Figure Description

[0047] 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.

[0048] Figure 1 This is a schematic flowchart of an embodiment of the cloud resource allocation prediction method for edge-cloud convergence provided in the embodiments of this application;

[0049] Figure 2 This is a schematic flowchart of another embodiment of the cloud resource allocation prediction method for edge-cloud convergence provided in the embodiments of this application;

[0050] Figure 3 This is a flowchart illustrating another embodiment of the cloud resource allocation prediction method for edge-cloud convergence provided in the embodiments of this application;

[0051] Figure 4 This is a schematic diagram of an embodiment of the cloud resource allocation prediction device for edge-cloud convergence provided in the embodiments of this application;

[0052] Figure 5 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0053] 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.

[0054] 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.

[0055] Firstly, embodiments of this application provide a method for predicting cloud resource allocation during edge-cloud convergence. Edge-cloud convergence is based on a target resource pool, which refers to a resource pool that aggregates computing resources from terminal devices and cloud servers. Computing resources may include, for example, CPU (Central Processing Unit) resources and GPU (Graphics Processing Unit) resources. Terminal devices refer to user terminal devices, through which users can trigger computing tasks. Taking the interior design industry as an example, computing tasks may include tasks related to generating virtual reality 3D images for interior design. Cloud servers, unlike terminal devices, are devices located in the cloud.

[0056] Reference Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of a cloud resource allocation prediction method for edge-cloud convergence. Figure 1 In this context, the cloud resource allocation prediction method during edge-cloud convergence may include:

[0057] 101. Obtain the user type of the current user terminal.

[0058] In the embodiments of this application, the current user terminal refers to the terminal device currently communicating with the cloud resource allocation prediction device during edge-cloud convergence. It should be noted that the cloud resource allocation prediction device during edge-cloud convergence can communicate with multiple terminal devices simultaneously, therefore, multiple current user terminals can exist at the same time.

[0059] In the embodiments of this application, user type refers to the type of user currently logged into the user terminal. Taking a user terminal in a school or college as an example, students of each major can log into the user terminal to perform computational tasks related to their major's professional knowledge. Therefore, logged-in users can be divided into multiple different user types according to different majors, different types of computational tasks, etc. User types may include, for example, art and design, computer science, architectural engineering, science and engineering, etc.

[0060] In some embodiments of this application, obtaining the user type of the current user terminal may include: obtaining the user tags of the logged-in users of the current user terminal, wherein the user tags may be preset based on actual needs, for example, students of different majors may be set with different user tags respectively, such as art design, computer science, architectural engineering, science and engineering, etc.; and determining the user type of the current user terminal based on the user tags, for example, different user tags may be directly used as different user types, thereby determining the user type of the current user terminal.

[0061] In some embodiments of this application, user tags may also be automatically generated based on different computing task types to avoid the manual costs and human error caused by manually setting user tags. Specifically, user tags can be determined in the following ways: First, obtain the number of times and / or frequency of use of multiple preset software programs on the current user's terminal by the logged-in user. These preset software programs may include software for various majors within a school or college, such as software for art and design, computer science, or architectural engineering (including but not limited to CAD software, Pro / E software, etc.). Second, based on the number of times and / or frequency of use, determine the target software from the multiple preset software programs. For example, the preset software with the number of times and / or frequency of use greater than or equal to a corresponding threshold can be used as the target software; or, among the multiple preset software programs, the preset software with the highest number of times and / or frequency of use can be used as the target software; or, among the multiple preset software programs, the preset software with the largest weighted sum of the number of times of use and the frequency of use can be used as the target software. This indicates that the logged-in user's software usage behavior matches the major associated with the target software. Third, use the preset tags associated with the target software as the user tags for the logged-in user. This achieves automatic generation of user tags for logged-in users on the current user's terminal, avoiding the need to set user tags for each user individually, thereby improving the efficiency of resource allocation prediction during edge-cloud convergence.

[0062] 102. Determine the historical usage data of multiple historical user terminals under the user type. The historical usage data includes the amount of data of the computing task of each historical user terminal at a historical moment, as well as the number of historical user terminals used at a historical moment.

[0063] In the embodiments of this application, usage data of multiple user terminals in historical time periods are recorded in advance, and these user terminals are designated as historical user terminals. Then, historical usage data of multiple historical user terminals under that user type are extracted from them. The historical time period includes multiple different historical moments, such as one month.

[0064] In the embodiments of this application, the historical usage data includes the data volume of the computing task of each historical user terminal at each historical moment, and the number of historical user terminals used at each historical moment. The computing task refers to a task that requires data processing using edge-cloud convergence, which can be triggered and generated by the corresponding user terminal. The number of historical user terminals used at each historical moment refers to the historical user terminals currently processing data using edge-cloud convergence for computing tasks at that historical moment. The calculation method for the data volume of the computing task can be set based on actual needs and is not limited here.

[0065] 103. Based on historical usage data, predict the amount of data for the current user terminal's computing tasks at a preset future time to obtain the expected data amount.

[0066] In the embodiments of this application, based on the changing patterns of historical usage data of multiple historical user terminals under a user type, the expected data volume of the computing task of the current user terminal under that user type at a preset future time can be predicted to obtain the expected data volume. The prediction method for the expected data volume may include modeling analysis based on time series methods (such as linear regression), neural network models, etc., and is not limited thereto.

[0067] 104. Based on the expected data volume, determine the target cloud resource volume for the current user terminal, and allocate cloud resources to the current user terminal according to the target cloud resource volume.

[0068] In the embodiments of this application, the target cloud resource quantity of the current user terminal may also be different based on the expected data volume. This ensures that after allocating cloud resources to the current user terminal according to the target cloud resource quantity, the end-to-cloud fusion resources for the current user terminal can meet the data processing requirements of the expected data volume. The target cloud resource quantity may be positively correlated with the expected data volume, and the correspondence between the target cloud resource quantity and the expected data volume can be set based on actual needs, and is not limited here.

[0069] As can be seen from the above embodiments of this application, by obtaining the user type of the current user terminal, and based on the data volume of the computing task of each historical user terminal under the user type at a historical moment, as well as the number of historical user terminals used at a historical moment, the data volume of the computing task of the current user terminal at a preset future moment can be accurately predicted, thereby accurately predicting the target amount of cloud resources required by the current user terminal, so as to allocate cloud resources, making the cloud resource configuration more reasonable and effectively reducing cloud resource costs.

[0070] In some embodiments of this application, such as Figure 2 As shown, in Figure 1 Based on the illustrated embodiment, and using historical usage data, the expected data volume is predicted for the current user terminal's computational tasks at a preset future time. This prediction may include:

[0071] 201. Based on the data volume of the computing tasks of each historical user terminal at a historical moment, determine the first trend of change in the data volume of the computing tasks of the historical user terminal.

[0072] In the embodiments of this application, for each historical user terminal, the data volume of the computing tasks of that historical user terminal at multiple different historical moments can be used to summarize the pattern of changes in the data volume with different historical moments, thereby obtaining a first trend of change in the data volume of the computing tasks of that historical user terminal. The first trend of change can be generated using methods such as linear regression, curve fitting, and neural network models; the specific generation process is not limited here.

[0073] 202. Based on the number of historical user terminals used at historical moments, determine the second trend of change in the number of historical user terminals used.

[0074] In the embodiments of this application, similar to the generation method of the first trend, the usage count of historical user terminals at multiple different historical moments can be used to summarize the pattern of changes in the usage count with different historical moments, thereby obtaining a second trend of historical user terminal usage. The second trend can be generated using methods such as linear regression, curve fitting, and neural network models; the specific generation process is not limited here.

[0075] 203. Based on the first and second trends of change, predict the amount of data for the current user terminal's computational tasks at a preset future time to obtain the expected amount of data.

[0076] In the embodiments of this application, the changing trend of the data volume of the current user terminal's computing task can be predicted by combining the first changing trend and the second changing trend, thereby obtaining the expected data volume. The prediction method may include, for example, a neural network model.

[0077] In some embodiments of this application, predicting the data volume of the current user terminal's computing task at a preset future time based on a first trend and a second trend to obtain the expected data volume may include: using the first trend to determine the first data volume of the computing task of each historical user terminal at the preset future time, for example, by performing time-series analysis on the data volume based on the first trend to predict the first data volume of the computing task of the corresponding historical user terminal at the preset future time; determining the sum of the first data volumes of the computing tasks of all historical user terminals at the preset future time, and using this sum as the second data volume; using the second trend to determine the second usage quantity of historical user terminals at the preset future time, for example, by performing time-series analysis on the usage quantity based on the second trend to predict the second usage quantity of historical user terminals at the preset future time; and determining the expected data volume based on the ratio of the second data volume to the second usage quantity, for example, by directly using the ratio of the second data volume to the second usage quantity as the expected data volume of the current user terminal's computing task at the preset future time.

[0078] In some embodiments of this application, determining the expected data volume based on the ratio of the second data volume to the second usage quantity may include: determining the average data volume of the computing tasks of each historical user terminal at a historical time based on the data volume of the computing tasks of each historical user terminal at a historical time and the usage quantity of the historical user terminals at that historical time. For example, for each historical time, the sum of the data volumes of the computing tasks of multiple historical user terminals at that historical time can be divided by the usage quantity of the historical user terminals at that historical time to obtain the average data volume of the computing tasks of the historical user terminals at that historical time; and determining a third trend of change in the average data volume based on the average data volume of the computing tasks at historical times. For example, the average data volume at multiple different historical times can be used to analyze the average data volume of the computing tasks at each historical time. The patterns of changes in average data volume over historical periods are summarized to obtain a third trend in average data volume. This third trend can be generated using methods such as linear regression, curve fitting, and neural network models; the specific generation process is not limited here. Using this third trend, the average data volume of computing tasks at a predetermined future time is determined. For example, based on the third trend, time-series analysis of the average data volume can be performed to predict the average data volume of computing tasks at the predetermined future time. Based on the average data volume of computing tasks at the predetermined future time, the ratio of the second data volume to the second usage quantity, the expected data volume is determined, making the predicted expected data volume more accurate. This leads to a more reasonable allocation of cloud resources.

[0079] In some embodiments of this application, determining the expected data volume based on the ratio of the average data volume of the computing task at a preset future time, the second data volume, and the second usage quantity may include: taking a weighted average of the ratio of the average data volume of the computing task at a preset future time, the second data volume, and the second usage quantity, and using the result of the weighted average as the expected data volume, thereby making the predicted expected data volume more accurate.

[0080] As can be seen, in the above embodiments of this application, by comprehensively considering the first trend of the data volume of the computing tasks of historical user terminals and the second trend of the number of historical user terminals used, the data volume of the computing tasks of the current user terminal at a preset future time can be predicted, and a more accurate expected data volume can be obtained.

[0081] 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 target cloud resource volume for the current user terminal based on the expected data volume may include:

[0082] 301. Based on the expected data volume of different current user terminals, determine the cloud resource allocation ratio for different current user terminals.

[0083] In the embodiments of this application, since multiple current user terminals can exist simultaneously, the cloud resource allocation ratio among the multiple different current user terminals can be determined based on the expected data volume of the multiple different current user terminals. For example, the ratio among the expected data volumes of the multiple different current user terminals can be directly used as the cloud resource allocation ratio among the multiple different current user terminals.

[0084] 302. Determine the target cloud resource amount for each current user terminal based on the cloud resource allocation ratio.

[0085] In the embodiments of this application, the target cloud resource quantity for each current user terminal can be determined directly according to the cloud resource quantity allocation ratio, such that the ratio among the target cloud resource quantities of multiple current user terminals is equal to the cloud resource quantity allocation ratio. Of course, the cloud resource quantity allocation ratio can also be further processed to obtain the target cloud resource quantity for each current user terminal, which is not limited here.

[0086] In some embodiments of this application, determining the target cloud resource amount for each current user terminal based on the cloud resource allocation ratio may include: determining resource allocation correction coefficients associated with different user types of current user terminals, wherein a corresponding resource allocation correction coefficient is pre-set for each current user type, including a CPU resource correction coefficient and a GPU resource correction coefficient. Taking art design and computer science as examples, art design requires more GPU resources, while computer science requires more CPU resources. Therefore, corresponding CPU resource correction coefficients and GPU resource correction coefficients are associated with different user types; determining the target cloud resource amount for each current user terminal for CPU resources based on the cloud resource allocation ratio and the CPU resource correction coefficient, and determining the target cloud resource amount for each current user terminal for GPU resources based on the cloud resource allocation ratio and the GPU resource correction coefficient. For example, the value of each current user terminal in the cloud resource allocation ratio can be multiplied by the CPU resource correction factor of that current user terminal to obtain a corrected first cloud resource allocation ratio. Then, based on the corrected first cloud resource allocation ratio, the target cloud resource amount for CPU resources of each current user terminal can be determined. CPU resources in the cloud resources can then be allocated to multiple different current user terminals according to this target cloud resource amount, ensuring that the CPU resource needs of different user types can be accurately met. As another example, the value of each current user terminal in the cloud resource allocation ratio can be multiplied by the GPU resource correction factor of that current user terminal to obtain a corrected second cloud resource allocation ratio. Then, based on the corrected second cloud resource allocation ratio, the target cloud resource amount for GPU resources of each current user terminal can be determined. GPU resources in the cloud resources can then be allocated to multiple different current user terminals according to this target cloud resource amount, ensuring that the GPU resource needs of different user types can be accurately met.

[0087] As can be seen, in the above embodiments of this application, the cloud resource allocation ratio of different current user terminals is determined based on the expected data volume of different current user terminals, and then the target cloud resource volume of each current user terminal is determined according to the cloud resource allocation ratio. This can ensure that the cloud resource needs of each current user terminal can be accurately met, making the cloud resource configuration more reasonable and effectively reducing the cloud resource cost.

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

[0089] Module 401 is used to obtain the user type of the current user terminal;

[0090] The determination module 402 is used to determine the historical usage data of multiple historical user terminals under the user type. The historical usage data includes the amount of data of the calculation task of each historical user terminal at a historical moment, and the number of historical user terminals used at a historical moment.

[0091] The prediction module 403 is used to predict the amount of data for the current user terminal's computing task at a preset future time based on historical usage data, so as to obtain the expected amount of data.

[0092] The allocation module 404 is used to determine the target cloud resource amount of the current user terminal based on the expected data amount, so as to allocate cloud resources to the current user terminal according to the target cloud resource amount.

[0093] Thirdly, embodiments of this application provide a computer device that integrates any of the cloud resource allocation prediction 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 allocation prediction method for edge-cloud convergence as described in any of the above embodiments, for example:

[0094] Obtain the user type of the current user terminal; determine the historical usage data of multiple historical user terminals under the user type, wherein the historical usage data includes the data volume of the computing task of each historical user terminal at a historical time, and the number of historical user terminals used at a historical time; based on the historical usage data, predict the data volume of the computing task of the current user terminal at a preset future time to obtain the expected data volume; based on the expected data volume, determine the target cloud resource volume of the current user terminal, so as to allocate cloud resources to the current user terminal according to the target cloud resource volume.

[0095] Fourthly, embodiments of this application provide a computer device that integrates any of the cloud resource allocation prediction 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:

[0096] 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:

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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:

[0102] Obtain the user type of the current user terminal; determine the historical usage data of multiple historical user terminals under the user type, wherein the historical usage data includes the data volume of the computing task of each historical user terminal at a historical time, and the number of historical user terminals used at a historical time; based on the historical usage data, predict the data volume of the computing task of the current user terminal at a preset future time to obtain the expected data volume; based on the expected data volume, determine the target cloud resource volume of the current user terminal, so as to allocate cloud resources to the current user terminal according to the target cloud resource volume.

[0103] 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 allocation prediction method for edge-cloud convergence as described in any of the preceding claims, for example:

[0104] Obtain the user type of the current user terminal; determine the historical usage data of multiple historical user terminals under the user type, wherein the historical usage data includes the data volume of the computing task of each historical user terminal at a historical time, and the number of historical user terminals used at a historical time; based on the historical usage data, predict the data volume of the computing task of the current user terminal at a preset future time to obtain the expected data volume; based on the expected data volume, determine the target cloud resource volume of the current user terminal, so as to allocate cloud resources to the current user terminal according to the target cloud resource volume.

[0105] 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 allocation prediction method for edge-cloud convergence as described in any of the preceding claims, for example:

[0106] Obtain the user type of the current user terminal; determine the historical usage data of multiple historical user terminals under the user type, wherein the historical usage data includes the data volume of the computing task of each historical user terminal at a historical time, and the number of historical user terminals used at a historical time; based on the historical usage data, predict the data volume of the computing task of the current user terminal at a preset future time to obtain the expected data volume; based on the expected data volume, determine the target cloud resource volume of the current user terminal, so as to allocate cloud resources to the current user terminal according to the target cloud resource volume.

[0107] 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 predicting cloud resource allocation in edge-cloud convergence, characterized in that, The cloud resource allocation prediction method for edge-cloud convergence includes: Get the user type of the current user terminal; Determine the historical usage data of multiple historical user terminals under the user type, wherein the historical usage data includes the amount of data of the computing task of each historical user terminal at a historical moment, and the number of times the historical user terminal was used at the historical moment; Based on the historical usage data, the data volume of the current user terminal's computing task at a preset future time is predicted to obtain the expected data volume; Based on the expected data volume, the target cloud resource volume of the current user terminal is determined, and cloud resources are allocated to the current user terminal according to the target cloud resource volume; The step of predicting the data volume of the current user terminal's computing task at a preset future time based on the historical usage data to obtain the expected data volume includes: Based on the amount of data in the computing task of each historical user terminal at the historical moment, a first trend of change in the amount of data in the computing task of the historical user terminal is determined. Based on the number of historical user terminals used at the historical time, a second trend in the number of historical user terminals used is determined. Based on the first trend and the second trend, the data volume of the computing task of the current user terminal at a preset future time is predicted to obtain the expected data volume; The step of predicting the data volume of the current user terminal's computing task at a preset future time based on the first and second trends to obtain the expected data volume includes: Using the first trend of change, determine the first data volume of the computing task of each historical user terminal at the preset future time. The sum of the first data volume of the computing tasks of all the historical user terminals at the preset future time is determined and used as the second data volume; Using the second trend of change, determine the second number of times the historical user terminal is used at the preset future time. The expected data volume is determined based on the ratio of the second data volume to the second usage quantity; Determining the expected data volume based on the ratio of the second data volume to the second usage quantity includes: Based on the data volume of the computing task of each historical user terminal at the historical time and the number of times the historical user terminal was used at the historical time, the average data volume of the computing task of the historical user terminal at the historical time is determined. A third trend in the average data volume is determined based on the average data volume of the computational task at the historical moment. Using the third trend of change, the average amount of data for the computational task at the preset future time is determined; The expected data volume is determined based on the average data volume of the computational task at the preset future time and the ratio of the second data volume to the second usage quantity.

2. The cloud resource allocation prediction method for edge-cloud convergence as described in claim 1, characterized in that, Determining the target cloud resource quantity for the current user terminal based on the expected data volume includes: Based on the expected data volume of different current user terminals, determine the cloud resource allocation ratio for different current user terminals; Based on the cloud resource allocation ratio, the target cloud resource amount for each current user terminal is determined.

3. The cloud resource allocation prediction method for edge-cloud convergence as described in claim 2, characterized in that, The step of determining the target cloud resource amount for each current user terminal based on the cloud resource allocation ratio includes: Determine resource allocation correction coefficients associated with different user types of the current user terminals, wherein the resource allocation correction coefficients include CPU resource correction coefficients and GPU resource correction coefficients; Based on the cloud resource allocation ratio and the CPU resource correction coefficient, the target cloud resource amount for each current user terminal with respect to CPU resources is determined, and based on the cloud resource allocation ratio and the GPU resource correction coefficient, the target cloud resource amount for each current user terminal with respect to GPU resources is determined.

4. The cloud resource allocation prediction method for edge-cloud convergence as described in claim 1, characterized in that, The process of obtaining the user type of the current user terminal includes: Obtain the user tags of the currently logged-in users on the user terminal; Based on the user tag, the user type of the current user terminal is determined.

5. The cloud resource allocation prediction method for edge-cloud convergence as described in claim 4, characterized in that, The user tags are determined in the following ways: Obtain the number of times and / or frequency of use of multiple preset software applications on the current user's terminal by the logged-in user; Based on the number of uses and / or frequency of use, the target software is determined from a plurality of preset software. The preset tags associated with the target software are used as the user tags of the logged-in users.

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 allocation prediction 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 allocation prediction method for edge-cloud convergence as described in any one of claims 1 to 5.

Images