Method, apparatus and device for configuring load information, and storage medium

Abstract

The application provides a load information configuration method and device, equipment and a storage medium. The method comprises the following steps: obtaining historical access data in a first preset time period, wherein the historical access data comprises historical access amounts corresponding to a plurality of historical time periods in the first preset time period; inputting the historical access data into an access amount prediction model to output predicted access amounts corresponding to a plurality of future time periods in a second preset time period; inputting the historical access data into a trend prediction model to output predicted trend information corresponding to the plurality of future time periods in the second preset time period; determining the trend information of the predicted access amounts; if the trend information is consistent with the predicted trend information, determining predicted load information corresponding to the predicted access amounts from an association between stored access amounts and load information according to the predicted access amounts, and configuring load information of a server according to the predicted load information. The application can improve the accuracy of the configuration method.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to a method, apparatus, device and storage medium for configuring load information. Background Technology

[0002] With the development of Internet technology, the number of visits to servers is increasing, and the number of visits often varies at different times. In order to make better use of server resources and ensure that the server can handle access requests normally, it is necessary to configure the server load information at different times.

[0003] In existing technologies, server load information for different time periods is configured based on historical access volume. For example, when configuring load information for different time periods on Monday, the server's access volume for each time period on the previous Monday is first obtained, and then the server's load information is configured based on the access volume for each time period on the previous Monday.

[0004] However, the inventors have found that the existing technology has at least the following technical problems: due to factors such as holidays and seasons, the number of visits in historical time periods may fluctuate greatly with the number of visits at the current moment, which may lead to waste of server resources or the server being unable to process access requests in a timely manner. Therefore, the accuracy of the above-mentioned load information configuration method is poor. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for configuring load information, which can improve the accuracy of the load information configuration method.

[0006] Firstly, this application provides a method for configuring load information, including:

[0007] Obtain historical access data within a first preset time period, wherein the historical access data includes the historical access volume corresponding to each of multiple historical time periods within the first preset time period;

[0008] The historical access data is input into the access volume prediction model, and the predicted access volume for each of the multiple future time periods within the second preset time period is output.

[0009] The historical access data is input into the trend prediction model, and the predicted trend information corresponding to each of the multiple future time periods within the second preset time period is output.

[0010] Determine the trend information of the predicted access volume. If the trend information is consistent with the predicted trend information, then determine the predicted load information corresponding to the predicted access volume from the stored correlation between access volume and load information, and configure the server load information according to the predicted load information.

[0011] In one possible design, the process of determining the correlation between access volume and load information includes: determining the bias parameters of an artificial neural network model; inputting the historical access volume and the bias parameters into the artificial neural network model and outputting load information; and associating the historical access volume with the load information to obtain the correlation between access volume and load information.

[0012] In one possible design, determining the bias parameters of the artificial neural network model includes: acquiring data information of multiple monitoring indicators related to the historical access volume, and determining the correlation coefficient between the data information of each monitoring indicator and the historical access volume; based on the correlation coefficient between the data information of each monitoring indicator and the historical access volume, acquiring a target monitoring indicator whose correlation coefficient is less than a preset coefficient from the data information of the multiple monitoring indicators; and preprocessing the data information of the target monitoring indicator to obtain the bias parameters of the artificial neural network model.

[0013] In one possible design, the preprocessing includes one or more of centralization, standardization, and normalization; wherein, the centralization includes: determining the average value of the data information of the target monitoring indicator, subtracting the average value from the data information to complete the centralization; the standardization includes: determining the standard deviation of the data information of the target monitoring indicator, dividing the data information by the standard deviation to complete the standardization; the normalization includes: multiplying the data information of the target monitoring indicator by a preset factor so that the resulting product is within a preset interval, wherein the preset interval is [0, 1] or [-1, 1].

[0014] In one possible design, the monitoring metrics include one or more of the following: heap memory, non-heap memory, system CPU utilization, thread CPU utilization, total number of threads, average memory usage per thread, maximum memory usage per thread, total number of open files, and number of class loads.

[0015] In one possible design, the visit volume prediction model is a trained Long Short-Term Memory (LSTM) network model, and the trend prediction model is a trained Prophet model.

[0016] In one possible design, the load information includes one or more of CPU utilization, memory utilization, and disk utilization.

[0017] Secondly, this application provides a load information configuration device, comprising:

[0018] The acquisition module is used to acquire historical access data within a first preset time period, wherein the historical access data includes the historical access volume corresponding to each of the multiple historical time periods within the first preset time period.

[0019] The access volume prediction module is used to input the historical access data into the access volume prediction model and output the predicted access volume for each of the multiple future time periods within the second preset time period.

[0020] The trend prediction module is used to input the historical access data into the trend prediction model and output the predicted trend information corresponding to each of the multiple future time periods within the second preset time period.

[0021] The configuration module is used to determine the trend information of the predicted access volume. If the trend information is consistent with the predicted trend information, then based on the predicted access volume, the predicted load information corresponding to the predicted access volume is determined from the stored correlation between access volume and load information, and the load information of the server is configured based on the predicted load information.

[0022] Thirdly, this application provides an electronic device, including: a processor and a memory;

[0023] The memory stores computer-executed instructions;

[0024] The processor executes computer execution instructions stored in the memory, causing the processor to perform the configuration method of load information as described in the first aspect and various possible designs of the first aspect.

[0025] Fourthly, this application provides a computer storage medium storing computer execution instructions, which, when executed by a processor, implement the load information configuration method described in the first aspect and various possible designs of the first aspect.

[0026] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the configuration method for load information described in the first aspect and various possible designs of the first aspect.

[0027] The load information configuration method, apparatus, device, and storage medium provided in this application acquire historical access data within a first preset time period, wherein the historical access data includes historical access volumes corresponding to multiple historical time periods within the first preset time period; input the historical access data into an access volume prediction model, and output the predicted access volumes corresponding to multiple future time periods within a second preset time period; input the historical access data into a trend prediction model, and output the predicted trend information corresponding to multiple future time periods within the second preset time period; determine the trend information of the predicted access volume; if the trend information is consistent with the predicted trend information, then, based on the predicted access volume, determine the predicted load information corresponding to the predicted access volume from the stored correlation between access volume and load information, and configure the server load information according to the predicted load information. In the embodiments of this application, since the predicted load information corresponding to the predicted access volume is determined by combining the predicted access volume and the trend prediction model, the accuracy of the obtained predicted load information is improved, thereby providing an accurate load information configuration method. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram illustrating an application scenario of the load information configuration method provided in the embodiments of this application;

[0030] Figure 2 The flow of the load information configuration method provided in the embodiments of this application Figure 1 ;

[0031] Figure 3 A schematic diagram of the load information configuration method provided in the embodiments of this application. Figure 1 ;

[0032] Figure 4 This is a schematic diagram of the structure of the load information configuration device provided in the embodiments of this application;

[0033] Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, 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.

[0035] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0036] With the development of Internet technology, the number of visits to servers is increasing, and the number of visits often varies at different times. In order to make better use of server resources and ensure that the server can handle access requests normally, it is necessary to configure the server load information at different times.

[0037] In existing technologies, server load information for different time periods is configured based on historical access volume. For example, when configuring load information for different time periods on Monday, the server's access volume for each time period of the previous Monday is first obtained, and then the server load information is configured based on that volume. However, due to factors such as holidays and seasons, historical access volume may fluctuate significantly from the current access volume. This can lead to wasted server resources or the server being unable to process access requests in a timely manner, thus the accuracy of the above load information configuration method is poor.

[0038] Therefore, improving the accuracy of load information configuration methods is a pressing technical problem that needs to be solved.

[0039] To address the aforementioned technical problems, this application proposes the following technical concept: First, historical access data within a first preset time period is acquired; the historical access data is input into an access volume prediction model, which outputs the predicted access volume for each of multiple future time periods within a second preset time period; the historical access data is input into a trend prediction model, which outputs the predicted trend information for each of multiple future time periods within the second preset time period; then, the trend information of the predicted access volume is determined; if the trend information matches the predicted trend information, the predicted load information corresponding to the predicted access volume is determined from the stored correlation between access volume and load information, based on the predicted access volume; finally, the server load information is configured based on the predicted load information. In this application, by combining the predicted access volume and the trend prediction model to determine the predicted load information corresponding to the predicted access volume, the accuracy of the obtained predicted load information is improved, thereby providing an accurate method for configuring load information.

[0040] Figure 1 This is a schematic diagram illustrating an application scenario of the load information configuration method provided in the embodiments of this application. For example... Figure 1 As shown, terminal 101 and server 102 are connected via wired or wireless connection. Terminal 101 can send a load information configuration request to server 102; server 102 receives the load information configuration request, determines the predicted load information using the load information configuration method of this application, and configures the load information of server 102 according to the predicted load information. The load information configuration method proposed in this application will be described in detail below through detailed embodiments.

[0041] Figure 2 The flow of the load information configuration method provided in the embodiments of this application Figure 1 In this embodiment, the executing entity can be a terminal or a server; this embodiment will be described using a server as the executing entity. Figure 2 As shown, the method includes:

[0042] S201. Obtain historical access data within a first preset time period, wherein the historical access data includes the historical access volume corresponding to each of the multiple historical time periods within the first preset time period.

[0043] In this embodiment of the disclosure, the value of the first preset duration is not specifically limited and can be set and modified as needed. For example, the first preset duration can be 12 hours, 1 day, 1 week, etc. Multiple historical time periods can be periodically distributed. For example, historical access data is obtained every 5 minutes, and the resulting historical access data is shown in Table 1 below.

[0044] Table 1 Historical Access Data

[0045] Multiple historical periods Historical visit count 2023 / 3 / 6 9:48 5821 2023 / 3 / 6 9:53 3709 2023 / 3 / 6 9:58 5863 2023 / 3 / 6 10:03 3433 2023 / 3 / 6 10:08 6191 2023 / 3 / 6 10:13 3311 2023 / 3 / 6 10:18 6153 2023 / 3 / 6 10:23 3154 2023 / 3 / 6 10:28 6076 2023 / 3 / 6 10:33 3234 2023 / 3 / 6 10:38 5630 2023 / 3 / 6 10:43 3333

[0046] S202. Input historical access data into the access volume prediction model and output the predicted access volume for each of the multiple future time periods within the second preset time period.

[0047] Optionally, the visit volume prediction model is a trained LSTM (Long Short Term Memory) model. In this embodiment, the value of the second preset duration is not specifically limited and can be set and modified as needed. Optionally, the second preset duration is less than the first preset duration. For example, as shown... Figure 3 As shown, the first preset duration is one week, with multiple historical time periods including: March 1, March 2, March 3, March 4, March 5, March 6 and March 7; the second preset duration is 2 days, with multiple future time periods including: March 8 and March 9.

[0048] It should be noted that before determining the predicted visit volume using historical visit data and the visit volume prediction model, the initial LSTM model needs to be trained using historical visit data. During training, the historical visit data can be divided into a training set and a validation set according to a first preset ratio. In this embodiment, the value of the first preset ratio is not specifically limited and can be set and modified as needed. For example, the first preset ratio can be 4:1, 6:1, 8:1, etc.

[0049] S203. Input historical access data into the trend prediction model and output the predicted trend information corresponding to each of the multiple future time periods within the second preset time period.

[0050] Optionally, the trend prediction model is a pre-trained Prophet model. For example, such as... Figure 3 As shown, the predicted trend information can be a predicted trend curve obtained based on historical access data. This predicted trend information includes multiple first peaks and multiple first troughs.

[0051] It should be noted that before determining the predicted trend information using the trend prediction model, the initial Prophet model needs to be trained using historical access data. During training, the historical access data can be divided into a training set and a validation set according to a second preset ratio. The second preset ratio can be 4:1, 6:1, 8:1, etc.

[0052] S204. Determine the trend information of the predicted access volume. If the trend information is consistent with the predicted trend information, then based on the predicted access volume, determine the predicted load information corresponding to the predicted access volume from the stored correlation between access volume and load information, and configure the server load information based on the predicted load information.

[0053] Optionally, the step of determining whether the trend information is consistent with the predicted trend information is as follows: determine the trend information of the predicted visit volume, which includes multiple second peaks and multiple second troughs; if the time period corresponding to the first peak is the same as the time period corresponding to the second peak and the time period corresponding to the first trough is the same as the time period corresponding to the second trough, then the trend information is determined to be consistent with the predicted trend information; if the time period corresponding to the first peak is different from the time period corresponding to the second peak and / or the time period corresponding to the first trough is different from the time period corresponding to the second trough, then the trend information is determined to be inconsistent with the predicted trend information.

[0054] For example, such as Figure 3 As shown, the time period corresponding to the first peak is the same as the time period corresponding to the second peak, and the time period corresponding to the first trough is the same as the time period corresponding to the second trough. At this point, the confirmed trend information is consistent with the predicted trend information.

[0055] It should be noted that if the trend information is inconsistent with the predicted trend information, the predicted visit volume obtained in step S201 should be discarded. In this case, the historical visit data can be re-divided into training and validation sets according to a preset ratio, and the LSTM model can be trained to obtain a new trained LSTM model. Then, the predicted visit volume can be redetermined using the newly trained LSTM model.

[0056] In this embodiment of the disclosure, the load information includes one or more of CPU utilization, memory utilization, and disk utilization. Accordingly, configuring the server's load information based on the predicted load information includes: configuring the server's CPU utilization based on the CPU utilization in the predicted load information, and / or configuring the server's memory utilization based on the memory utilization in the predicted load information, and / or configuring the server's disk utilization based on the disk utilization in the predicted load information.

[0057] Optionally, the correlation between traffic volume and load information can be determined using an artificial neural network model. Accordingly, the process of determining the correlation between traffic volume and load information includes: determining the bias parameters of the artificial neural network model; inputting historical traffic volume and the bias parameters into the artificial neural network model; outputting load information; and associating the historical traffic volume with the load information to obtain the correlation between traffic volume and load information.

[0058] Among them, the artificial neural network model can be an MLP (Multilayer Perceptron) model.

[0059] In some embodiments, bias parameters can be determined based on correlation coefficients. Accordingly, determining the bias parameters of the artificial neural network model includes: acquiring data information of multiple monitoring indicators related to historical access volume, and determining the correlation coefficient between the data information of each monitoring indicator and historical access volume; based on the correlation coefficient between the data information of each monitoring indicator and historical access volume, acquiring a target monitoring indicator whose correlation coefficient is less than a preset coefficient from the data information of multiple monitoring indicators; and preprocessing the data information of the target monitoring indicator to obtain the bias parameters of the artificial neural network model.

[0060] Optionally, the correlation coefficient can be the absolute value of the Pearson correlation coefficient. The monitoring metrics include one or more of the following: heap memory, non-heap memory, system CPU utilization, thread CPU utilization, total number of threads, average memory usage per thread, maximum memory usage per thread, total number of open files, and number of class loads.

[0061] For example, with a preset coefficient of 0.1, the correlation coefficient between the total number of threads and historical access volume is 0.026 (Pearson coefficient of 0.026), the correlation coefficient between the total number of open files and historical access volume is 0.014 (Pearson coefficient of 0.014), and the correlation coefficient between the number of class loads and historical access volume is 0.012 (Pearson coefficient of -0.012). Since the correlation coefficients between the total number of threads and historical access volume, the total number of open files and historical access volume, and the number of class loads and historical access volume are all less than the preset system value of 0.1, the target monitoring indicators include the total number of threads, the total number of open files, and the number of class loads. In this case, any target monitoring indicator can be preprocessed to obtain the bias parameters of the artificial neural network model. For example, the bias parameters of the artificial neural network model can be obtained by preprocessing the total number of threads.

[0062] Optionally, the preprocessing includes one or more of centralization processing, standardization processing, and normalization processing; wherein, the centralization processing includes: determining the average value of the data information of the target monitoring indicator, subtracting the average value from the data information to complete the centralization processing (i.e., the mean is 0); wherein, the standardization processing includes: determining the standard deviation of the data information of the target monitoring indicator, dividing the data information by the standard deviation to complete the standardization processing (i.e., the variance is 1); wherein, the normalization processing includes: multiplying the data information of the target monitoring indicator by a preset factor so that the resulting product is within a preset interval, wherein the preset interval is [0, 1] or [-1, 1].

[0063] It should be noted that the preprocessing method for the model can be determined based on the data distribution and model requirements. For example, if the distribution of error values ​​is skewed, centering and standardization can be chosen to make it more consistent with a normal distribution, thereby improving the model's performance. If the deviation values ​​are relatively large, normalization can be used to reduce the deviation values ​​to an acceptable range, thereby improving the model's identifiability.

[0064] This application provides a method for configuring load information: acquiring historical access data within a first preset time period, wherein the historical access data includes historical access volumes corresponding to multiple historical time periods within the first preset time period; inputting the historical access data into an access volume prediction model, outputting predicted access volumes corresponding to multiple future time periods within a second preset time period; inputting the historical access data into a trend prediction model, outputting predicted trend information corresponding to multiple future time periods within the second preset time period; determining the trend information of the predicted access volume; if the trend information is consistent with the predicted trend information, then determining the predicted load information corresponding to the predicted access volume from the stored correlation between access volume and load information, and configuring the server load information according to the predicted load information. In this embodiment, by combining the predicted access volume and the trend prediction model to determine the predicted load information corresponding to the predicted access volume, the accuracy of the obtained predicted load information is improved, thereby providing an accurate load information configuration method.

[0065] Figure 4 This is a schematic diagram of the structure of the load information configuration device provided in an embodiment of this application. Figure 4 As shown, the device includes: an acquisition module 401, a traffic prediction module 402, a trend prediction module 403, and a configuration module 404;

[0066] The acquisition module 401 is used to acquire historical access data within a first preset time period, wherein the historical access data includes the historical access volume corresponding to each of the multiple historical time periods within the first preset time period.

[0067] The access volume prediction module 402 is used to input historical access data into the access volume prediction model and output the predicted access volume for each of the multiple future time periods within the second preset time period.

[0068] The trend prediction module 403 is used to input historical access data into the trend prediction model and output the predicted trend information corresponding to each of the multiple future time periods within the second preset time period.

[0069] Configuration module 404 is used to determine the trend information of the predicted access volume. If the trend information is consistent with the predicted trend information, the predicted load information corresponding to the predicted access volume is determined from the stored correlation between access volume and load information based on the predicted access volume, and the load information of the server is configured based on the predicted load information.

[0070] In one possible design, the trend prediction module 403 determines the correlation between access volume and load information by: determining the bias parameters of the artificial neural network model; inputting the historical access volume and the bias parameters into the artificial neural network model and outputting load information; and associating the historical access volume with the load information to obtain the correlation between access volume and load information.

[0071] In one possible design, the trend prediction module 403 determines the bias parameters of the artificial neural network model, specifically including: acquiring data information of multiple monitoring indicators related to the historical access volume, and determining the correlation coefficient between the data information of each monitoring indicator and the historical access volume; based on the correlation coefficient between the data information of each monitoring indicator and the historical access volume, acquiring a target monitoring indicator whose correlation coefficient is less than a preset coefficient from the data information of the multiple monitoring indicators; and preprocessing the data information of the target monitoring indicator to obtain the bias parameters of the artificial neural network model.

[0072] In one possible design, the preprocessing includes one or more of centralization, standardization, and normalization; wherein, the centralization includes: determining the average value of the data information of the target monitoring indicator, subtracting the average value from the data information to complete the centralization; the standardization includes: determining the standard deviation of the data information of the target monitoring indicator, dividing the data information by the standard deviation to complete the standardization; the normalization includes: multiplying the data information of the target monitoring indicator by a preset factor so that the resulting product is within a preset interval, wherein the preset interval is [0, 1] or [-1, 1].

[0073] In one possible design, the monitoring metrics include one or more of the following: heap memory, non-heap memory, system CPU utilization, thread CPU utilization, total number of threads, average memory usage per thread, maximum memory usage per thread, total number of open files, and number of class loads.

[0074] In one possible design, the visit volume prediction model is a trained Long Short-Term Memory (LSTM) network model, and the trend prediction model is a trained Prophet model.

[0075] In one possible design, the load information includes one or more of CPU utilization, memory utilization, and disk utilization.

[0076] The apparatus provided in this embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effects are similar, and will not be described again here.

[0077] Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device of this embodiment includes: a processor 501 and a memory 502; wherein

[0078] Memory 502 is used to store instructions executed by the computer;

[0079] The processor 501 is used to execute computer execution instructions stored in the memory to implement the various steps performed by the electronic device in the above embodiments. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0080] Alternatively, the memory 502 can be either standalone or integrated with the processor 501.

[0081] When the memory 502 is set up independently, the electronic device also includes a bus 503 for connecting the memory 502 and the processor 501.

[0082] This application also provides a computer storage medium storing computer execution instructions, which, when executed by a processor, implements the load information configuration method of the above-described method embodiments.

[0083] This application also provides a computer program product, including a computer program, which, when executed by a processor, implements the load information configuration method of the above-described method embodiments.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0085] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0086] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0087] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute partial steps of the methods in the various embodiments of this application.

[0088] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0089] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0090] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0091] The aforementioned storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0092] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0093] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for configuring load information, characterized in that, include: Obtain historical access data within a first preset time period, wherein the historical access data includes the historical access volume corresponding to each of multiple historical time periods within the first preset time period; The historical access data is input into the access volume prediction model, and the predicted access volume for each of the multiple future time periods within the second preset time period is output. The historical access data is input into the trend prediction model, and the predicted trend information corresponding to each of the multiple future time periods within the second preset time period is output. The trend information of the predicted access volume is determined. If the trend information is consistent with the predicted trend information, the predicted load information corresponding to the predicted access volume is determined from the stored correlation between access volume and load information, and the server load information is configured according to the predicted load information. If the trend information is inconsistent with the predicted trend information, the predicted access volume is discarded, and the LSTM model is retrained by dividing the historical access data into training and validation sets according to a preset ratio to obtain a new trained LSTM model. The predicted access volume is then redetermined using the newly trained LSTM model.

2. The method according to claim 1, characterized in that, The process of determining the correlation between traffic and load information includes: Determine the bias parameters of the artificial neural network model; The historical access volume and the bias parameter are input into the artificial neural network model, and the load information is output. By associating the historical access volume with the load information, the correlation between access volume and load information is obtained.

3. The method according to claim 2, characterized in that, The determination of the bias parameters of the artificial neural network model includes: Obtain data information of multiple monitoring indicators related to the historical access volume, and determine the correlation coefficient between the data information of each monitoring indicator and the historical access volume; Based on the correlation coefficient between the data information of each monitoring indicator and the historical access volume, a target monitoring indicator with a correlation coefficient less than a preset coefficient is obtained from the data information of the multiple monitoring indicators. The data information of the target monitoring indicators is preprocessed to obtain the bias parameters of the artificial neural network model.

4. The method according to claim 3, characterized in that, The preprocessing includes one or more of the following: centralized processing, standardized processing, and normalized processing; The centralized processing includes: determining the average value of the data information of the target monitoring indicator, subtracting the average value from the data information, and completing the centralized processing; The standardization process includes: determining the standard deviation of the data information of the target monitoring indicator, dividing the data information by the standard deviation, and completing the standardization process. The normalization process includes multiplying the data information of the target monitoring indicator by a preset factor so that the resulting product is within a preset interval, wherein the preset interval is [0, 1] or [-1, 1].

5. The method according to claim 3, characterized in that, The monitoring metrics include one or more of the following: heap memory, non-heap memory, system CPU utilization, thread CPU utilization, total number of threads, average memory usage per thread, maximum memory usage per thread, total number of open files, and number of class loads.

6. The method according to claim 1, characterized in that, The visit volume prediction model is a trained Long Short-Term Memory (LSTM) network model, and the trend prediction model is a trained Prophet model.

7. The method according to any one of claims 1-6, characterized in that, The load information includes one or more of CPU utilization, memory utilization, and disk utilization.

8. A load information configuration device, characterized in that, include: The acquisition module is used to acquire historical access data within a first preset time period, wherein the historical access data includes the historical access volume corresponding to each of the multiple historical time periods within the first preset time period. The access volume prediction module is used to input the historical access data into the access volume prediction model and output the predicted access volume for each of the multiple future time periods within the second preset time period. The trend prediction module is used to input the historical access data into the trend prediction model and output the predicted trend information corresponding to each of the multiple future time periods within the second preset time period. The configuration module is used to determine the trend information of the predicted access volume. If the trend information is consistent with the predicted trend information, then based on the predicted access volume, the predicted load information corresponding to the predicted access volume is determined from the stored correlation between access volume and load information, and the server load information is configured according to the predicted load information. If the trend information is inconsistent with the predicted trend information, the predicted access volume is discarded, and the LSTM model is retrained by dividing the historical access data into training and validation sets according to a preset ratio to obtain a new trained LSTM model. The predicted access volume is then redetermined using the newly trained LSTM model.

9. An electronic device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the load information configuration method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, it implements the load information configuration method as described in any one of claims 1 to 7.

Images