An information processing method, apparatus, device, and readable storage medium

Abstract

The application discloses an information processing method and device, equipment and a readable storage medium, relates to the technical field of cloud computing, and aims to control service cost. The method comprises the following steps: dividing a plurality of candidate services into a plurality of service groups; determining the expected net income corresponding to a target service set in a target service group according to the ROI of each service in the target service group; wherein the target service group is any service group in the plurality of service groups, the target service group comprises one or more service sets, and the target service set is a service set in the target service group; and processing the target service set according to the expected net income. The embodiment of the application can control service cost.

Description

Technical Field

[0001] This application relates to the field of cloud computing technology, and in particular to an information processing method, apparatus, device and readable storage medium. Background Technology

[0002] Cloud-native is an application development model that prioritizes cloud architecture and has gained widespread adoption. Microservices (or microservice architecture) is a cloud-native architectural approach. The characteristic of microservice architecture is that a single application consists of many loosely coupled and independently deployable smaller components or services. These services are fine-grained, and the protocols are lightweight. This brings many advantages, such as good decoupling between services, simple deployment, and easy scalability.

[0003] However, due to the nature of microservices, a large number of services may be generated. This leads to significant overhead on public and private cloud server resources, increasing the challenge of cost control for enterprises. Therefore, how to manage service costs has become a technical problem that needs to be solved. Summary of the Invention

[0004] This application provides an information processing method, apparatus, device, and readable storage medium to control service costs.

[0005] In a first aspect, embodiments of this application provide an information processing method, including:

[0006] Divide multiple candidate services into multiple service groups;

[0007] Based on the ROI (Return On Investment) of each service in the target service group, determine the expected net income corresponding to the target service set in the target service group; wherein, the target service group is any one of the plurality of service groups, the target service group includes one or more service sets, and the target service set is the service set in the target service group;

[0008] The target service set is processed based on the expected net revenue.

[0009] Secondly, embodiments of this application also provide an information processing apparatus, including:

[0010] The first partitioning module is used to divide multiple candidate services into multiple service groups;

[0011] The first determining module is used to determine the expected net revenue corresponding to the target service set in the target service group based on the ROI of each service in the target service group; wherein, the target service group is any one of the plurality of service groups, the target service group includes one or more service sets, and the target service set is the service set in the target service group;

[0012] The first processing module is used to process the target service set according to the expected net revenue.

[0013] Thirdly, embodiments of this application also provide an electronic device, including: a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the information processing method described above.

[0014] Fourthly, embodiments of this application also provide a readable storage medium storing a program, which, when executed by a processor, implements the steps in the information processing method described above.

[0015] In this embodiment, candidate services are divided into multiple service groups, and the expected net revenue corresponding to the set of target services in the target service group is determined based on the ROI of each service in the target service group. The target service set is then processed based on the expected net revenue. Therefore, it can be seen that the solution using this embodiment allows for the estimation of expected net revenue, which is then used as a basis for processing the target service set, thereby achieving control over service costs. Attached Figure Description

[0016] Figure 1 This is a flowchart of the information processing method provided in the embodiments of this application;

[0017] Figure 2 This is a structural diagram of the information processing apparatus provided in the embodiments of this application;

[0018] Figure 3 This is a structural diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0019] In the embodiments of this application, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0020] In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0021] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0022] In the process of service cost control, the estimated service cost is obtained by calculation or estimation, and then the number of service replicas to be increased or reduced is determined according to the estimated service cost, so that the service node can provide the optimal service capacity, while ensuring the high availability of the service and also ensuring the benefits of the microservice. Hereinafter, the technical solutions of the embodiments of the present application will be described in detail.

[0023] See Figure 1 , Figure 1 is a flowchart of the information processing method provided by the embodiments of the present application. As Figure 1 [[ID=-12]]shown, it includes the following steps:

[0024] Step 101: Divide multiple candidate services into multiple service groups.

[0025] Herein, the service that can execute tasks in the system is called a candidate service. Herein, according to the number of service replicas of each candidate service, the candidate services are divided into multiple service groups.

[0026] Specifically, various index data of the service can be collected, such as the number of service replicas, computing power index, ROI, etc. Then, according to the number of service replicas of each service, each candidate service is divided into multiple service groups. For example, the number of service replicas can be used as the X-axis, and segmented by intervals of N*s + 0 < X ≤ (N + 1)*s + 0, where N is the number of segments (N ≥ 0 and is a positive integer), and s (s ≥ 1 and is a positive integer) is the segmentation step length, which can be set according to expert judgment or historical statistical data. That is, it is divided into multiple segments of the number of service replicas according to the segmentation step length. If the number of replicas of one or more services is within a certain segment of the same number of service replicas, then the service can be divided into the same service group. In this way, it can be ensured that the distribution of service replicas within each segment is uniform, so as to obtain a more accurate grouping of service groups.

[0027] To ensure the high availability of the service, in the actual online environment, the number of service replicas usually remains at 2 or more.

[0028] Step 102: Determine the expected net income corresponding to the target service set in the target service group according to the ROI of each service in the target service group.

[0029] The target service group is any one of the multiple service groups, and the target service group includes one or more service sets, the target service set being the service set in the target service group.

[0030] Specifically, this step may include the following:

[0031] (1021) Determine a first service set and / or a second service set from the target service group.

[0032] After obtaining the service groups, for each service group, a first service set and / or a second service set can be determined from it. The ROI of each service in the first service set is less than a first preset value, the ROI of each service in the second service set is greater than a second preset value, and the first preset value is less than the second preset value. Other services in the service group can be left unprocessed.

[0033] In practical applications, a range can be formed by the first preset value and the second preset value. The minimum value of this range is the first preset value, and the maximum value is the second preset value. If the ROI of a service is less than the first preset value, then the service's ROI is considered unsatisfactory, and it is thus assigned to the first service set. If the ROI of a service is greater than the second preset value, then the service's ROI is considered excessive, and it is thus assigned to the second service set. Other services, in this embodiment, may not be processed by the method of this embodiment.

[0034] Typically, peak CPU utilization of a service can be used as an indicator of service load or ROI. Generally, peak CPU utilization should fall within the aforementioned range. Therefore, in this embodiment, services can be divided into different service sets based on their peak CPU utilization. The peak CPU utilization of a service is the average of the peak CPU utilization of all service replicas of a particular service over a certain time period (e.g., one day).

[0035] Specifically, the peak CPU utilization of each service in the target service group is obtained, and the peak CPU utilization of each service is compared with the first preset value and the second preset value, respectively. If the peak CPU utilization of the first service is less than the first preset value, the first service is assigned to the first service set; or, if the peak CPU utilization of the first service is greater than the second preset value, the first service is assigned to the second service set; wherein, the first service is any service in the service group.

[0036] The first preset value and the second preset value can be set as needed. For example, in this embodiment, the first preset value can be set to 25% and the second preset value can be set to 40%.

[0037] (1022) Based on the number of service replicas currently in the target service set, determine the difference in the number of service replicas, and determine the first service cost corresponding to the difference in the number of service replicas, wherein the target service set is the first service set or the second service set.

[0038] For each service set, the principle of calculating the difference in the number of service replicas and determining the first service cost corresponding to the difference in the number of service replicas is the same. Here, the first service cost can be understood as a predicted value of the service cost when the number of service replicas in the target service set reaches a preset service replica number threshold.

[0039] Specifically, the difference between the current number of service replicas in the target service set and a preset service replica number threshold is used as the service replica number difference. This preset service replica number threshold can be set as needed. The first service cost corresponding to the service replica number difference is, that is, the first service cost corresponding to the service replica number difference for each service replica. When calculating the first service cost, the resource consumption when all a first number (the first number equals the service replica number difference) of service replicas executes the task can be determined first. Based on the resource consumption and resource energy consumption variation parameters, the first service cost is obtained.

[0040] Specifically, the product of the resource consumption and the resource energy consumption variation parameter is taken as the first service cost, expressed as the following formula (1):

[0041] G i (τ i )=δ(τ i E i ' (1)

[0042] Among them, G i (τ i ) represents the first service cost, δ(τ) i E represents the parameter indicating changes in resource energy consumption. i 'Indicates resource consumption.

[0043] The resource consumption when all of the first number of service replicas execute tasks is determined as follows:

[0044] The resource consumption required for each CPU cycle to process in the first number of service replicas is obtained. The resource consumption required for each CPU cycle to process in the first number of service replicas, the difference between the service replicas, and the number of users accessing the service network are multiplied as the resource consumption when all the first number of service replicas execute tasks. This can be expressed as the following formula (2):

[0045] E i '=L i η i θ i (2)

[0046] Among them, E i 'Indicates resource consumption, θ i L represents the resource consumption required for a single service replica to process each CPU cycle. i Represents the service replica difference, η i This indicates the number of users accessing the service network.

[0047] In this embodiment, considering that in some cases only some service replicas execute tasks, and the resource energy consumption cost corresponding to the service replicas also changes accordingly, the resource energy consumption variation parameter or resource energy consumption variation factor δ(τ) is considered when calculating the first service cost. i ), where δ(τ) i )=kτ i τ represents the ratio of the number of service replicas currently executing a task to the total number of service replicas. i This indicates the task computing power that the replica corresponding to the service replica difference can provide.

[0048] Based on the above, the cost of the first service can be expressed as formula (3):

[0049] G i (τ i )=δ(τ i E i '=kτ i L i η i θ i (3)

[0050] (1023) Determine the expected net revenue of the target service set based on the revenue corresponding to the difference between the first service cost and the number of service copies.

[0051] The expected net income can also be referred to as the optimal net income. In this step, the revenue corresponding to the difference in the number of service replicas is determined, and the difference between the first service cost and the revenue corresponding to the difference in the number of service replicas is taken as the expected net income.

[0052] The revenue corresponding to the difference in the number of service replicas is the revenue corresponding to the difference in the number of service replicas. Here, the product of the task computing power provided by the first number of service replicas and a preset weight is used as the revenue corresponding to the difference in the number of service replicas, where the first number is equal to the difference in the number of service replicas. This weight can be set as needed. The revenue can be expressed as formula (4):

[0053] F i (τ i ) = w i τ i (4)

[0054] Among them, F i (τ i ) represents the revenue mentioned, w i τ represents the weight. i This indicates the task computing power that the first number of service replicas can provide.

[0055] Therefore, the expected net income can be expressed as formula (5) or (6):

[0056] U i (τ i ) = F i (τ i )-G i (τ i (5)

[0057] U i (τ i ) = F i (τ i )-G i (τ i )=kτ i L i η i θ i -w i τ i (6)

[0058] Among them, U i (τ i F represents expected net income. i (τ i ) represents the revenue mentioned, G i (τ i () indicates the first service cost.

[0059] Step 103: Process the target service set according to the expected net revenue.

[0060] In this application embodiment, the processing may include adding or reducing service copies, etc.

[0061] This step may include the following procedures:

[0062] (1) Obtain the return on investment.

[0063] To ensure service reliability, in this embodiment, a return on investment (ROI) evaluation index can be established as a basis for evaluating enterprise investment and determining the return on service investment. Specifically, service cost can be used as the service input index, and peak service QPS (Queries-per-second) can be used as the service output index. The formula for calculating ROI is:

[0064] Return on investment = Peak QPS / First service cost.

[0065] The higher the return on investment (ROI), the higher the service's return on investment (ROI). Since 80% of the service's daily requests are concentrated in 20% of the time, the peak QPS (Queries Per Second) is calculated using the following formula:

[0066] Peak QPS = (Total daily requests * 80%) / (Total daily seconds * 20%)

[0067] (2) Compare the first parameter with the return on investment, wherein the first parameter is the quotient of the expected net income and the cost of the first service.

[0068] (3) If the first parameter is greater than or equal to the return on investment, reduce the number of service replicas corresponding to the difference in the number of service replicas for the first service set, or increase the number of service replicas corresponding to the difference in the number of service replicas for the second service set.

[0069] In other words, if (expected net revenue / first service cost) ≥ return on investment, then the service replica difference is used as the number of service replicas to be added or reduced, and the number of service replicas is increased or decreased according to this value. Specifically, the number of service replicas corresponding to the service replica difference is reduced for the first service set, or the number of service replicas corresponding to the service replica difference is increased for the second service set.

[0070] (4) If the first parameter is less than the return on investment and the number of service replicas currently in the target service set is greater than or equal to the preset service replica number threshold, determine the number of service replicas that the target service set needs to add or the number of service replicas that needs to be reduced based on the reference parameter.

[0071] The meaning of the preset service replica number threshold can be found in the description of the foregoing embodiments. The reference parameters may include: the second service cost of the target service set, the cost of a single service replica, etc.

[0072] In this process, a second service cost for the target service set can be determined, and a service cost difference is obtained based on the first service cost and the second service cost. Then, the quotient of the service cost difference and the cost of a single service replica is used as the number of service replicas to be added or removed. The cost of a single service replica can be a known value.

[0073] In this step, the second service cost can be calculated based on the return on investment formula, assuming the peak service QPS remains constant in the short term. Specifically, if the target service set is a first service set, the product of the first preset value and the peak service QPS is calculated to obtain a second parameter. The quotient of the second parameter and the return on investment is used as the second service cost. If the target service set is a second service set, the product of the second preset value and the peak service QPS is calculated to obtain a third parameter. The quotient of the third parameter and the return on investment is used as the second service cost. Both the first and second preset values ​​can be set as needed. For example, in this embodiment, the first preset value can be set to 25%, and the second preset value can be set to 40%.

[0074] For the first service set, reduce the number of service replicas required to be reduced; for the second service set, increase the number of service replicas required to be increased. It should be noted that if the peak CPU load of the current service in the first service set is greater than or equal to a second preset value, then replica reduction for this service can be ignored.

[0075] As can be seen from the above description, by quantitatively analyzing the return on investment and net income of services, the efficiency of service resource investment can be analyzed and evaluated. On the other hand, by analyzing ROI and expected net income, the number of replicas that need to be increased or decreased can be determined, thereby enabling cost control while ensuring service stability and high availability.

[0076] In this embodiment, candidate services are divided into multiple service groups. Based on the ROI of each service in the target service group, the expected net revenue corresponding to the target service set in the target service group is determined. Further, in this embodiment, the difference in the number of service replicas for the first service set and the second service set in the service group, and the first service cost corresponding to the difference in the number of service replicas, are determined respectively. Based on the first service cost and the revenue corresponding to the difference in the number of service replicas, the expected net revenue of the target service set is determined, and the target service set is processed based on the expected net revenue. It can be seen that, using the solution of this embodiment, the estimated expected net revenue can be obtained through the first service cost corresponding to the difference in the number of service replicas and the revenue corresponding to the difference in the number of service replicas, and the target service set can be processed based on this, thereby achieving control over service costs.

[0077] This application also provides an information processing apparatus. See also... Figure 2 , Figure 2 This is a structural diagram of the information processing apparatus provided in the embodiments of this application. Figure 2 As shown, the information processing device includes:

[0078] The first partitioning module 201 is used to partition multiple candidate services into multiple service groups; the first determining module 202 is used to determine the expected net revenue corresponding to the target service set in the target service group based on the ROI of each service in the target service group; wherein, the target service group is any one of the multiple service groups, the target service group includes one or more service sets, and the target service set is the service set in the target service group; the first processing module 203 is used to process the target service set according to the expected net revenue.

[0079] Optionally, the first partitioning module 201 is used to partition the candidate service into multiple service groups based on the number of service replicas of each candidate service.

[0080] Optionally, the first determining module includes:

[0081] The first determining submodule is used to determine a first service set and / or a second service set from the target service group, wherein the ROI of each service in the first service set is less than a first preset value, the ROI of each service in the second service set is greater than a second preset value, and the first preset value is less than the second preset value.

[0082] The second determining submodule is used to determine the service replica quantity difference based on the current number of service replicas in the target service set, and to determine the first service cost corresponding to the service replica quantity difference, wherein the target service set is the first service set or the second service set;

[0083] The third determining submodule is used to determine the expected net revenue of the target service set based on the revenue corresponding to the difference between the first service cost and the number of service replicas.

[0084] Optionally, the first determining submodule includes:

[0085] The first acquisition unit is used to acquire the peak CPU utilization of each service in the target service group.

[0086] The first comparison unit is used to compare the peak CPU utilization of each service with the first preset value and the second preset value respectively.

[0087] The first partitioning unit is configured to partition the first service into the first service set if the peak CPU utilization of the first service is less than the first preset value; or, if the peak CPU utilization of the first service is greater than the second preset value, partition the first service into the second service set; wherein the first service is any service in the service group.

[0088] Optionally, the second determining submodule includes:

[0089] The first acquisition unit is used to take the difference between the number of service replicas currently in the target service set and the preset service replica number threshold as the service replica number difference.

[0090] The second acquisition unit is used to determine the resource consumption when all the first number of service replicas execute the task, wherein the first number is equal to the difference in the number of service replicas.

[0091] The third acquisition unit is used to obtain the first service cost based on the resource consumption and resource energy consumption variation parameters.

[0092] Optionally, the third acquisition unit is used to multiply the resource consumption and the resource energy consumption variation parameter as the first service cost.

[0093] Optionally, the resource consumption when all service replicas of the first number of resources execute tasks is determined as follows:

[0094] In the first number of service replicas, each service replica handles the resource consumption required for each CPU cycle.

[0095] The resource consumption required for each CPU cycle of the single service replica, the product of the service replica difference and the number of users accessing the service network, is taken as the resource consumption when all the first number of service replicas execute tasks.

[0096] Optionally, the third determining submodule includes:

[0097] The first determining unit is used to determine the revenue corresponding to the difference in the number of service replicas;

[0098] The second determining unit is used to take the difference between the revenue corresponding to the difference between the first service cost and the number of service copies as the expected net income.

[0099] Optionally, the first determining unit is used to take the product of the task computing power that the first number of service replicas can provide and the preset weight as the revenue corresponding to the difference in the number of service replicas, wherein the first number is equal to the difference in the number of service replicas.

[0100] Optionally, the first processing module includes:

[0101] The first acquisition submodule is used to obtain the rate of return on investment;

[0102] The first comparison submodule is used to compare the first parameter with the return on investment, wherein the first parameter is the quotient of the expected net income and the first service cost;

[0103] The first processing submodule is configured to, if the first parameter is greater than or equal to the return on investment, reduce the number of service replicas corresponding to the difference in the number of service replicas for the first service set, or increase the number of service replicas corresponding to the difference in the number of service replicas for the second service set.

[0104] The second processing submodule is used to determine, based on reference parameters, the number of service replicas that need to be added or the number of service replicas that need to be reduced in the target service set if the first parameter is less than the return on investment and the number of service replicas currently in the target service set is greater than or equal to a preset service replica number threshold.

[0105] Optionally, the second processing submodule includes:

[0106] A determining unit is configured to determine the second service cost of the target service set;

[0107] The acquisition unit is used to obtain the service cost difference based on the first service cost and the second service cost;

[0108] The processing unit is configured to use the quotient of the service cost difference and the cost of a single service replica as the number of service replicas to be added or reduced.

[0109] Optionally, the determining unit is used for:

[0110] If the target service set is the first service set, calculate the product of the first preset value and the peak query rate per second (QPS) to obtain the second parameter, and use the quotient of the second parameter and the return on investment as the second service cost;

[0111] If the target service set is the second service set, the product of the second preset value and the service peak QPS is calculated to obtain the third parameter. The quotient of the third parameter and the return on investment is used as the second service cost.

[0112] The apparatus provided in this application embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0113] It should be noted that the division of units in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0114] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] See Figure 3This application provides an electronic device, including: a memory 310, a processor 300, and a program stored in the memory and executable on the processor; the processor 300 is used to read the program in the memory 310 to implement the steps in the information processing method described above.

[0116] This application also provides a readable storage medium storing a program. When executed by a processor, this program implements the various processes of the above-described information processing method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0117] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0118] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0119] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. An information processing method, characterized in that, include: Divide multiple candidate services into multiple service groups; Based on the return on investment (ROI) of each service in the target service group, the expected net income corresponding to the target service set in the target service group is determined; wherein, the target service group is any one of the plurality of service groups, the target service group includes one or more service sets, and the target service set is the service set in the target service group; The target service set is processed based on the expected net revenue; The ROI includes the peak CPU utilization of the service. Determining the expected net revenue corresponding to the target service set in the target service group based on the ROI of each service in the target service group includes: A first service set and / or a second service set are determined from the target service group, wherein the ROI of each service in the first service set is less than a first preset value, the ROI of each service in the second service set is greater than a second preset value, and the first preset value is less than the second preset value; Based on the number of service replicas currently present in the target service set, a service replica quantity difference is determined, and a first service cost corresponding to the service replica quantity difference is determined, wherein the target service set is either the first service set or the second service set; The expected net revenue of the target service set is determined based on the revenue corresponding to the difference between the first service cost and the number of service replicas.

2. The method according to claim 1, characterized in that, The multiple methods for dividing candidate services into multiple service groups include: The candidate services are divided into multiple service groups based on the number of service replicas of each candidate service.

3. The method according to claim 1, characterized in that, Determining the first service set and the second service set from the target service group includes: Obtain the peak CPU utilization of each service in the target service group; The peak CPU utilization of each service is compared with the first preset value and the second preset value, respectively. If the peak CPU utilization of the first service is less than the first preset value, the first service is assigned to the first service set; or, if the peak CPU utilization of the first service is greater than the second preset value, the first service is assigned to the second service set; wherein, the first service is any service in the service group.

4. The method according to claim 1, characterized in that, Determining the service replica quantity difference based on the current number of service replicas in the target service set includes: The difference between the current number of service replicas in the target service set and the preset service replica number threshold is used as the service replica number difference.

5. The method according to claim 1, characterized in that, Determining the first service cost corresponding to the difference in the number of service replicas includes: Determine the resource consumption when all a first number of service replicas execute the task, where the first number is equal to the difference between the number of service replicas. The first service cost is obtained based on the resource consumption and resource energy consumption variation parameters.

6. The method according to claim 5, characterized in that, The step of obtaining the first service cost based on the resource consumption and resource energy consumption variation parameters includes: The product of the resource consumption and the resource energy consumption variation parameters is taken as the first service cost.

7. The method according to claim 5 or 6, characterized in that, The resource consumption when all of the first number of service replicas execute tasks is determined as follows: In the first number of service replicas, each service replica handles the resource consumption required for each CPU cycle. The resource consumption required for each CPU cycle of the single service replica, the product of the service replica difference and the number of users accessing the service network, is taken as the resource consumption when all the first number of service replicas execute tasks.

8. The method according to claim 1, characterized in that, The step of determining the expected net revenue of the target service set based on the revenue corresponding to the difference between the first service cost and the number of service replicas includes: Determine the revenue corresponding to the difference in the number of service replicas; The difference between the revenue corresponding to the difference between the first service cost and the number of service copies is taken as the expected net income.

9. The method according to claim 8, characterized in that, Determining the revenue corresponding to the difference in the number of service replicas includes: The product of the task computing power provided by the first number of service replicas and the preset weight is used as the revenue corresponding to the difference in the number of service replicas, where the first number is equal to the difference in the number of service replicas.

10. The method according to claim 1, characterized in that, The process of processing the target service set based on the expected net revenue includes: To obtain a return on investment; The first parameter is compared with the return on investment, wherein the first parameter is the quotient of the expected net income and the cost of the first service. If the first parameter is greater than or equal to the return on investment, reduce the number of service replicas in the first service set by the number of service replicas corresponding to the difference in the number of service replicas, or increase the number of service replicas in the second service set by the number of service replicas corresponding to the difference in the number of service replicas. If the first parameter is less than the return on investment and the number of service replicas currently in the target service set is greater than or equal to a preset service replica number threshold, the number of service replicas that need to be added or reduced in the target service set is determined according to the reference parameters.

11. The method according to claim 10, characterized in that, The step of determining the number of service replicas to be added or reduced for the target service set based on reference parameters includes: Determine the second service cost of the target service set; The service cost difference is obtained based on the first service cost and the second service cost; The quotient of the service cost difference and the cost of a single service replica is used as the number of service replicas that need to be added or reduced.

12. The method according to claim 11, characterized in that, The second service cost for determining the target service set includes: If the target service set is the first service set, calculate the product of the first preset value and the peak query rate per second (QPS) to obtain the second parameter, and use the quotient of the second parameter and the return on investment as the second service cost; If the target service set is the second service set, the product of the second preset value and the service peak QPS is calculated to obtain the third parameter. The quotient of the third parameter and the return on investment is used as the second service cost.

13. An information processing device, characterized in that, include: The first partitioning module is used to divide multiple candidate services into multiple service groups; The first determining module is used to determine the expected net revenue corresponding to the target service set in the target service group based on the ROI of each service in the target service group; wherein, the target service group is any one of the plurality of service groups, the target service group includes one or more service sets, and the target service set is the service set in the target service group; The first processing module is used to process the target service set according to the expected net revenue; The ROI includes the peak CPU utilization of the service, and the first determining module includes: The first determining submodule is used to determine a first service set and / or a second service set from the target service group, wherein the ROI of each service in the first service set is less than a first preset value, the ROI of each service in the second service set is greater than a second preset value, and the first preset value is less than the second preset value. The second determining submodule is used to determine the service replica quantity difference based on the current number of service replicas in the target service set, and to determine the first service cost corresponding to the service replica quantity difference, wherein the target service set is the first service set or the second service set; The third determining submodule is used to determine the expected net revenue of the target service set based on the revenue corresponding to the difference between the first service cost and the number of service replicas.

14. An electronic device, comprising: A memory, a processor, and a program stored in the memory and executable on the processor; characterized in that the processor is configured to read the program from the memory to implement the steps of the information processing method as described in any one of claims 1 to 12.

15. A readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it implements the steps of the information processing method as described in any one of claims 1 to 12.

Images