Resource use charging management method of cloud product and related equipment

Abstract

The invention discloses a resource use charging management method and device of a cloud product, a server, a computer readable storage medium and a computer program product. The method comprises the following steps: after monitoring that the operation of a cloud product is completed, collecting resource use information of the cloud product, calling a pre-trained machine learning model to predict the demand resource quantity of a user according to the resource use information and historical data, predicting the resource use trend of the user by using the machine learning model, and dynamically adjusting resource allocation according to a prediction result. Accurate prediction of resource use trend and automatic adjustment of resource allocation are realized, and a more flexible and transparent cost control means is provided for users on the basis of improving charging accuracy. Besides, according to the method, a real-time monitoring and prediction algorithm is adopted, after each operation is completed, a preset charging rule is utilized to carry out cost calculation according to the resource use information, a real-time bill is generated, and the user can check the resource use condition and the cost expenditure at any time.

Description

Technical Field

[0001] The present disclosure generally relates to the field of cloud computing technology, and in particular to a resource usage billing management method, device, server, computer-readable storage medium, and computer program product for cloud products. Background Art

[0002] With the development of cloud computing technology, more and more enterprises and individuals use cloud products for business deployment and application development. However, in a multi-tenant environment, how to effectively manage and bill has become an important issue.

[0003] Traditional billing methods are usually fixed billing, charging a fixed fee for a fixed time period (such as one month) and a fixed amount of resources, or purchasing a prepaid card for a certain period of time, etc. Customers can use resources and submit jobs at a certain fee. However, this billing method lacks flexibility and can only charge a fixed fee in a fixed manner. No matter how many jobs a customer submits during this period, they need to pay the same fee, which may cause unnecessary waste of resources and excessive costs; and this method cannot reflect the actual needs and resource usage of customers, which may lead to insufficient or excessive resource allocation for cloud product providers, thus affecting service quality. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a resource usage billing management method, device, server, computer-readable storage medium and computer program product for a cloud product, which can significantly improve resource usage efficiency and job execution performance.

[0005] In a first aspect, an embodiment of the present application provides a resource usage billing management method for a cloud product, including:

[0006] After monitoring that the operation of the cloud product is completed, obtaining the resource usage information of the cloud product;

[0007] Calculate the cost based on the resource usage information using a preset billing rule, generate a real-time bill, and output the real-time bill;

[0008] Calling a pre-trained machine learning model to predict the user's required resource quantity based on the resource usage information and historical data to obtain a prediction result;

[0009] Dynamically adjust cloud product resource allocation based on the prediction results.

[0010] In one embodiment, the using a preset charging rule to calculate the fee according to the resource usage information includes:

[0011] Match the billing rule corresponding to the type of the job as the target billing rule;

[0012] Determining the charging parameters and unit prices in the target charging rules;

[0013] Extracting the actual usage corresponding to the billing parameter from the resource usage information;

[0014] The operation is charged according to the actual usage and the unit price, and a real-time bill is generated.

[0015] In one embodiment, the charging rules include: dynamic busy charging rules;

[0016] Accordingly, the charging parameters and unit prices in the target charging rule are determined, including:

[0017] Calculate the busyness of the system according to the resource usage information to obtain the busy state of the system;

[0018] Match the unit price corresponding to the busy state.

[0019] In one embodiment, the charging rules include: storage charging rules based on data changes;

[0020] Accordingly, the actual usage corresponding to the charging parameter is extracted from the resource usage information, including:

[0021] After responding to the data change request, record the amount of data changed;

[0022] The maximum usage of the path within a specified unit time is determined from the data volume of the data change as the actual usage.

[0023] In one embodiment, it also includes:

[0024] Collecting actual resource consumption corresponding to the prediction result;

[0025] Performing a forecast evaluation based on the deviation between the actual resource consumption and the forecast result to generate an evaluation result;

[0026] The machine learning model is optimized and adjusted according to the evaluation results.

[0027] In one embodiment, it also includes:

[0028] Collect users’ historical usage habits and consumption records;

[0029] Generating a personalized billing plan based on the historical usage habits and the consumption records;

[0030] Output a billing rule suggestion according to the billing scheme.

[0031] In a second aspect, an embodiment of the present application provides a resource usage billing management device for a cloud product, including:

[0032] An information processor, configured to obtain resource usage information of the cloud product after monitoring the completion of the operation of the cloud product;

[0033] A billing analyzer, used to calculate fees based on the resource usage information using preset billing rules and generate real-time bills;

[0034] A bill display platform, used to output the real-time bill;

[0035] The resource manager is used to call a pre-trained machine learning model to predict the user's required resource volume based on the resource usage information and historical data to obtain a prediction result; and dynamically adjust the cloud product resource allocation based on the prediction result.

[0036] In a third aspect, an embodiment of the present application provides a server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the embodiment of the present application when executing the program.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the embodiment of the present application.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method described in the embodiment of the present application.

[0039] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0041] Figure 1 A schematic diagram of a process for managing resource usage and billing of cloud products provided in an embodiment of the present application is shown;

[0042] Figure 2 A schematic diagram of a process for determining a target charging rule provided in an embodiment of the present application is shown;

[0043] Figure 3 A schematic diagram of a billing process of a dynamic busy billing model provided in an embodiment of the present application is shown;

[0044] Figure 4 A schematic diagram of a storage billing process based on data changes provided in an embodiment of the present application is shown;

[0045] Figure 5 An exemplary structural block diagram of a resource usage billing management device for a cloud product provided in an embodiment of the present application is shown;

[0046] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing a server of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0047] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0048] It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments. Although the embodiments of the present application provide the method operation instruction steps shown in the following embodiments or drawings, more or fewer operation instruction steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present application. The method may be executed in the order of the methods shown in the embodiments or drawings or in parallel during the actual processing process or when the device is executed.

[0049] Please refer to Figure 1 , Figure 1 The flowchart of the resource usage billing management method of the cloud product provided by an embodiment of the present application is shown. Figure 1 As shown, the method includes:

[0050] S101, after monitoring the completion of the operation of the cloud product, obtain the resource usage information of the cloud product;

[0051] This application monitors the completion of cloud products. If the completion of a cloud product's job is detected, the resource usage information of the cloud product is obtained immediately. The completion of the job can be detected by setting a callback notification to be triggered after the job is completed. For example, when a job executed by Spark, Hive, Presto or Hadoop is completed, a callback notification is triggered. The callback notification means that the job has ended and relevant information can be collected.

[0052] The method of obtaining the resource usage information of cloud products is not limited in this embodiment. It can be obtained through log information, or from a cloud monitoring platform or a third-party monitoring tool. Taking the acquisition through log information as an example, the corresponding execution log file can be obtained according to the type of job; the information used for billing and performance analysis can be extracted from the execution log file as usage information. The obtained execution log can be stored in a specified space, such as HDFS (Hadoop Distributed File System) storage space, for subsequent information analysis and processing.

[0053] The resource usage information obtained generally includes key information such as tenants, projects, job running time, resource usage, etc. This information is very important for subsequent billing and performance analysis. The specific type of information obtained can be set by referring to the billing items and bill types of cloud products, and this is not limited in this embodiment.

[0054] After obtaining resource usage information for subsequent billing and performance analysis, you can further break down and integrate the costs according to the project, tenant and other dimensions according to the different needs of the project, and generate real-time bill details. These bill details can help users understand their resource consumption and corresponding costs in a timely manner, and provide basic data for generating the final bill. This detailed billing model not only enables users to clearly understand their resource usage, but also provides managers with an opportunity to gain in-depth understanding of user behavior.

[0055] S102, using preset billing rules to calculate fees based on resource usage information, generating a real-time bill, and outputting the real-time bill;

[0056] The collected resource usage information is deeply analyzed to determine the actual amount of resources used by the user and the fees to be paid. After each job is completed, the latest real-time bill is generated for the user to view. The output mechanism of the real-time bill can be set according to the actual usage scenario. For example, it can be set to pop up automatically after each job, or it can be output after receiving the user's real-time bill viewing request. There is no limitation here.

[0057] Among them, the setting of billing rules can be flexibly set according to the actual configuration and usage of resources, market supply and demand, etc., to meet different supply needs.

[0058] The real-time bills generated by users during the use of cloud computing services can be output through the bill display platform to help users understand their own expenses. Real-time bills can also be pushed and output through the mobile terminal (such as a mobile phone) of the associated user. Taking the output through the bill display platform as an example, the bill display platform can receive bill data from the cloud service provider, analyze the cost details, display the cost details, issue cost warnings, calculate the total cost, generate cost reports, query specific costs, export cost data, set cost parameters, provide customer service support, recommend resource plans, optimize resource use, audit cost accuracy, protect cost information security, control cost permissions, synchronize cost information, record cost operations, monitor cost changes, generate cost reports, analyze cost patterns, predict cost trends and optimize cost structures. Through these functions, users can easily understand their own cost situation, control cost costs, plan cost budgets, and improve cost management efficiency.

[0059] S103, calling a pre-trained machine learning model to predict the user's required resource amount according to resource usage information and historical data, and obtaining a prediction result;

[0060] The acquired data mainly includes the current resource usage information and the user's historical usage data, including the user's behavior data, detailed job execution data, and cluster resource monitoring data. The specific data types include but are not limited to user operation records (such as login frequency, functional modules used, etc.), job scheduling information (such as job type, running time, resource consumption, etc.), and real-time monitoring data of infrastructure (such as CPU load, memory utilization, disk I / O, etc.).

[0061] In order to improve the model analysis effect, the acquired real-time resource usage information and historical data can be processed by data preprocessing and feature extraction. Data preprocessing includes but is not limited to data cleaning (removing erroneous or inconsistent data), data conversion (converting non-numerical data into a form that can be used for modeling), and data integration (merging data from different sources into a consistent format). Feature extraction includes but is not limited to feature selection (identifying which features are most valuable for prediction), feature construction (creating new features to enhance the performance of the model), and feature scaling (standardizing or normalizing feature values ​​to eliminate dimensional effects).

[0062] Use machine learning algorithms, such as automatic feature selection, parameter tuning, and ensemble learning, to pre-train an efficient prediction model. Use the pre-trained machine learning model to predict the user's required resource volume based on resource usage information and historical data, and predict resource demand in the future.

[0063] Wherein, for the model type and the training process of the model specifically selected, it is not limited in the present embodiment, and the training process can first perform automatic feature selection, and use the algorithm to automatically detect which features are most important for prediction, so as to reduce unnecessary noise and improve the generalization ability of the model. Then perform hyperparameter tuning, and find the optimal model parameter combination through grid search, random search or Bayesian optimization and other technologies, so as to achieve the best prediction effect. At the same time, multiple models are integrated, such as Bagging (bagging method), Boosting (boosting method) or Stacking (stacking method) and other strategies, to improve the stability and accuracy of prediction. In the present embodiment, only the above-mentioned model training process is used as an example for introduction, and other implementation methods can refer to the introduction of the present embodiment, which will not be repeated here.

[0064] S104. Dynamically adjust cloud product resource allocation according to the prediction results.

[0065] According to the prediction results, resource allocation is dynamically adjusted to reduce waste and improve service quality. For example, if it is predicted that a certain customer will submit a large number of jobs next week, sufficient computing resources can be reserved for it in advance to ensure that all jobs can run smoothly. At the same time, for those customers who are not expected to submit too many jobs, their resource allocation can be appropriately reduced to avoid resource waste. Priorities can also be set for different types of users or applications to ensure that critical tasks always have sufficient resource support. Specifically, the dynamic adjustment strategy of resource allocation can be set accordingly according to the needs of the actual application scenario. In this embodiment, only the above-mentioned adjustment method is introduced. The implementation of other methods can refer to the introduction of this embodiment, which will not be repeated here.

[0066] It should be noted that although the operations of the method of the present invention are described in a particular order in the drawings, this does not require or imply that the operations must be performed in this particular order or that all illustrated operations must be performed to achieve desired results.

[0067] Based on the above introduction, the method provided in this embodiment, after monitoring the completion of the cloud product operation, collects the resource usage information of the cloud product, calls the pre-trained machine learning model to predict the user's required resource amount based on the resource usage information and historical data, uses the machine learning model to predict the user's resource usage trend, and dynamically adjusts the resource allocation according to the prediction results, so as to achieve accurate prediction of resource usage trends and automatic adjustment of resource allocation. On the basis of improving the accuracy of billing, it provides users with a more flexible and transparent cost control method to ensure that users can get the right resource support at any time without causing excessive resource waste. In addition, the method adopts a real-time monitoring and prediction algorithm, and uses the preset billing rules to calculate the cost according to the resource usage information after each operation is completed, and generates a real-time bill. Users can check their resource usage and cost expenditure at any time, which not only improves the accuracy of billing, but also increases the transparency of billing, and also allows users to pay the corresponding fees according to actual needs without worrying about the additional costs caused by excess or insufficient resources.

[0068] The above embodiment does not limit the setting of the billing rules. This embodiment proposes a dynamic billing method based on the traditional fixed billing model to ensure the rationality of billing while encouraging users to use cloud product resources more effectively.

[0069] Specifically, different charging rules can be configured according to different job types. When using the preset charging rules to calculate the cost according to the resource usage information, the following steps can be performed:

[0070] S21. Match the billing rule corresponding to the job type as the target billing rule;

[0071] A configuration of a job type, such as single-core selling machines, SLA high-priority guarantee machines, emergency resource guarantee scheduling machines and other machines. Correspondingly, a billing rule configured for the above job types, such as single-core selling machines are charged cumulatively according to single-core billing, SLA high-priority guarantee machines are charged cumulatively according to SLA billing, emergency resource guarantee scheduling machines are charged cumulatively according to resource emergency scheduling machines, and other machines are charged according to core hours. Then a process of determining a target billing rule is as follows: Figure 2As shown, first determine whether it is a single-core machine based on the IP of the machine where the job is running; if it is not a single-core machine, then continue to determine whether it is an SLA high-priority guarantee machine; if it is an SLA high-priority guarantee machine, it is marked as "SLA" and charged cumulatively according to SLA billing (seconds); if it is not an SLA high-priority guarantee machine, then determine whether it is an emergency resource guarantee scheduling machine; if it is an emergency resource guarantee scheduling machine, it is marked as "Urgent" and charged cumulatively according to SLA billing (seconds); if it is neither an SLA high-priority guarantee machine nor an emergency resource guarantee scheduling machine, it is charged according to core time. If it is determined to be a single-core machine at the beginning, it is directly charged cumulatively according to single-core billing (seconds).

[0072] This allows different billing methods to be differentiated to suit various job types and customer needs, and the system can calculate the cost of each job more accurately, thus achieving a fair and transparent billing system.

[0073] S22, determining the charging parameters and unit price in the target charging rule;

[0074] Billing parameters refer to the parameters used to determine the specific indicators and standards for the fees that users should pay, such as time, usage, number of users, etc. Billing parameters and unit prices can be set according to the needs of actual usage scenarios and are not limited here.

[0075] S23, extracting the actual usage corresponding to the billing parameter from the resource usage information;

[0076] Statistics on actual user usage corresponding to the billing parameter. If the billing parameter is time, the total usage time is determined. If billing is based on memory usage, the memory size allocated to the instance is counted.

[0077] S24. Calculate the cost of the operation based on the actual usage and unit price, and generate a real-time bill.

[0078] This method can configure different billing rules for different job types, which can not only achieve more refined cloud product management and resource optimization, but also provide more flexible and efficient cloud services, ultimately improving user experience and satisfaction.

[0079] The billing rules configured for different job types can be freely configured according to actual needs, which is not limited in this embodiment. Two billing rules are proposed here to achieve fair billing in general scenarios.

[0080] In one embodiment, the charging rule is specifically: dynamic busy charging rule. Accordingly, step S22, determining the charging parameters and unit price in the target charging rule, is specifically:

[0081] S221, calculating the busyness of the system according to the resource usage information to obtain the busy state of the system;

[0082] First, obtain real-time collected information from resource usage information, calculate the system's busyness, and determine the overall load of the cluster.

[0083] In this embodiment, there is no limitation on the calculation method of the busyness, and the state recognition can be realized by building a model. One implementation method is to build a dynamic busy billing model, such as Figure 3 The figure shows the billing process of the dynamic busy billing model. First, the memory / CPU utilization rate and job queuing status in the cluster are obtained from the resource usage information. These data reflect the overall load of the cluster. Then the data is input into the dynamic busy billing model, and the model algorithm is used to calculate the busyness of the cluster (BusylIdleFactor) based on the collected data. This factor is a value between 0 and 1. The higher the value, the higher the busyness. According to the different ranges of BusylIdleFactor, the busyness of the cluster is divided into three states: idle, medium busy and busy.

[0084] A specific classification standard for cluster busy status is as follows:

[0085] When BusylIdleFactor is in the range of (0,0.3], it is considered to be in idle state;

[0086] BusylIdleFactor is in the range of (0.3,0.6], which is considered to be a medium busy state;

[0087] When BusylIdleFactor is in the range of (0.6,1), it is considered to be in a busy state.

[0088] It should be noted that, in this embodiment, only the implementation method of determining the busy state by the above-mentioned model is introduced, but it is not limited to this. The implementation of other methods can refer to the introduction of this embodiment and will not be repeated here.

[0089] S222. Match the unit price corresponding to the busy state.

[0090] Different unit prices are configured for different busy states. In idle state, the unit price may be lower; in busy state, the unit price is relatively higher. This pricing strategy can encourage users to use resources during non-peak hours to avoid congestion during peak hours, and also encourage users to make full use of resources during idle hours. It reflects the principle of user orientation and can meet the needs of different users.

[0091] The dynamic busy billing rules provided in this embodiment output different unit prices according to the busyness of the cluster, aiming to achieve a fairer billing method that is more in line with market demand. It is universally applicable and can be applied when, for example, the machine of the operation is neither an SLA high-priority guarantee machine nor an emergency resource guarantee scheduling machine.

[0092] In another embodiment, the charging rule is specifically: a storage charging rule based on data change. Accordingly, step S23 extracts the actual usage corresponding to the charging parameter from the resource usage information, specifically:

[0093] S231, after the data change request is responded, the amount of data changed is recorded;

[0094] S232. Determine the maximum usage of the path within a specified unit time from the amount of data changed as the actual usage.

[0095] like Figure 4 The figure shows a schematic diagram of the storage billing process based on data changes. When the computing engine initiates data change requests, the underlying storage system will process these requests and perform add, delete, and modify operations on the data. Subsequently, the HDFS (Hadoop Distributed File System) / BOS (an object storage service) system will record the amount of data for each data change and take the maximum usage of the path within 1 minute. Next, the recorded amount of data is multiplied by the preset unit price to obtain the cost of this operation, which is then accumulated in the total cost. Under this billing method, users only need to pay for the data changes that actually occur to them, which can more accurately reflect the actual usage of users, avoid unnecessary waste, and ensure the fairness of billing.

[0096] In one embodiment, in order to meet the needs of different users, the user's historical usage habits and consumption records can be collected; a personalized billing plan can be generated based on the historical usage habits and consumption records; and a billing rule suggestion can be output based on the billing plan.

[0097] Based on the user's historical usage habits and consumption records, we provide personalized billing plan recommendations, supporting multiple billing modes such as pay-as-you-go, reserved instances, and annual and monthly packages, allowing users to choose the best payment method based on their own business characteristics and needs.

[0098] All prediction results, optimization suggestions and personalized billing plans can be displayed to users through a friendly user interface, allowing users to clearly understand their resource consumption, cost expenditure and choose the best payment method.

[0099] Through this personalized billing plan and rule recommendations based on historical data, not only can more refined cost control and resource optimization be achieved, but also more flexible and efficient cloud services can be provided. Users can freely choose appropriate resource packages according to their usage habits and enjoy more personalized services, ultimately improving user experience and satisfaction.

[0100] In one embodiment, in order to ensure the prediction accuracy of the machine learning model, in addition to the above steps, the following steps may be further performed:

[0101] S105, collecting actual resource consumption corresponding to the prediction result;

[0102] S106, performing a forecast evaluation based on the deviation between the actual resource consumption and the forecast result, and generating an evaluation result;

[0103] S107. Optimize and adjust the machine learning model based on the evaluation results.

[0104] After each prediction, the prediction results of the model are evaluated, including but not limited to prediction accuracy, recall rate and other indicators. According to the evaluation results, the model is continuously adjusted and optimized to ensure that it is always in the best state.

[0105] Further references Figure 5 , which shows an exemplary structural block diagram of a resource usage billing management device for a cloud product according to an embodiment of the present application, which mainly includes:

[0106] The information processor 101 is used to obtain the resource usage information of the cloud product after monitoring the completion of the cloud product operation;

[0107] The billing analyzer 102 is used to calculate the cost according to the resource usage information using the preset billing rules and generate a real-time bill;

[0108] The bill display platform 103 is used to output real-time bills;

[0109] The resource manager 104 is used to call the pre-trained machine learning model to predict the user's required resource volume based on resource usage information and historical data to obtain a prediction result; and dynamically adjust the cloud product resource allocation based on the prediction result.

[0110] In one embodiment, the information processor 101 is specifically a log information processor, which is responsible for collecting and organizing the usage logs of various cloud products, including but not limited to key indicators such as CPU usage, memory usage, network traffic, etc. By cleaning and formatting these logs, structured data that can be used in subsequent steps is formed.

[0111] In one embodiment, the billing analyzer 102 is specifically used to predict the user's future resource needs based on the collected log information, using statistical and machine learning methods, and to provide reasonable billing suggestions in combination with the current billing policy. This module can also be used to regularly evaluate the effectiveness of the billing strategy so as to make timely adjustments.

[0112] In one embodiment, the resource manager 104 integrates a dynamic billing module based on real-time monitoring and prediction algorithms and an intelligent billing recommendation engine.

[0113] Among them, the dynamic billing module based on real-time monitoring and prediction algorithms is used to monitor the status of cloud resources currently being used by users in real time, and combines prediction algorithms to decide when and how to adjust the allocation of these resources. Specifically, information about applications and services currently being run by users is continuously collected, such as CPU utilization, memory usage, storage space consumption, and network traffic. These data are used to evaluate whether current resources are being used effectively. Then, based on historical data and current trends, advanced prediction models are used to estimate the amount of resources that users may need in the future. This can help prepare or release resources in advance to meet changes in user needs. Based on the prediction results, the system can automatically adjust the number of resources allocated to users, such as increasing or decreasing virtual machine instances, expanding or reducing storage capacity, etc., to ensure that resources are neither oversupplied nor insufficient;

[0114] The intelligent billing recommendation engine is used to provide personalized billing plan suggestions based on the user's historical usage habits and consumption records. It supports multiple billing modes such as pay-as-you-go, reserved instances, and annual and monthly packages, allowing users to choose the best payment method based on their business characteristics and needs.

[0115] In one embodiment, the bill display platform 103 is specifically used to display the billing results to the user in a clear and understandable manner, including but not limited to monthly bills, real-time consumption status, historical consumption trends, etc. Users can intuitively understand their consumption status through the bill display platform to facilitate decision making.

[0116] It should be understood that the units described in the above device are similar to those in the reference Figure 1 The steps in the method described above correspond to each other. Therefore, the operations and features described above for the method are also applicable to the device and the units contained therein, and will not be repeated here. The device can be pre-implemented in the browser or other security application of the server, or loaded into the browser or its security application of the server by downloading or the like. The corresponding units in the device can cooperate with the units in the server to implement the solution of the embodiment of the present application.

[0117] For the several units mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units described above can be embodied in one unit. On the contrary, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0118] It should be noted that for details not disclosed in the resource usage billing management device of the cloud product in the embodiment of the present application, please refer to the details disclosed in the above embodiments of the present application, which will not be repeated here.

[0119] Reference below Figure 6 , Figure 6 A schematic diagram of the structure of a computer system suitable for implementing a server of an embodiment of the present application is shown.

[0120] like Figure 6 As shown, the computer system includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation instructions of the system are also stored. The CPU 601, the ROM 602 and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0121] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0122] In particular, according to an embodiment of the present application, the above reference flow chart Figure 1The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present application are executed.

[0123] It should be noted that the computer-readable medium shown in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium such as a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0124] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operating instructions of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the aforementioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operating instruction, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0126] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the server described in the above embodiment, or may exist independently without being assembled into the server. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the resource usage billing management method for cloud products described in the present application.

[0127] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A resource usage billing management method for a cloud product, characterized in that: include: After monitoring that the operation of the cloud product is completed, obtaining the resource usage information of the cloud product; Calculate the cost based on the resource usage information using a preset billing rule, generate a real-time bill, and output the real-time bill; Calling a pre-trained machine learning model to predict the user's required resource quantity based on the resource usage information and historical data to obtain a prediction result; Dynamically adjust cloud product resource allocation based on the prediction results.

2. The method according to claim 1, characterized in that The using a preset charging rule to calculate the fee according to the resource usage information includes: Match the billing rule corresponding to the type of the job as the target billing rule; Determining the charging parameters and unit prices in the target charging rules; Extracting the actual usage corresponding to the billing parameter from the resource usage information; The operation is charged according to the actual usage and the unit price, and a real-time bill is generated.

3. The method according to claim 2, characterized in that The charging rules include: dynamic busy charging rules; Accordingly, the charging parameters and unit prices in the target charging rule are determined, including: Calculate the busyness of the system according to the resource usage information to obtain the busy state of the system; Match the unit price corresponding to the busy state.

4. The method according to claim 2, characterized in that The charging rules include: storage charging rules based on data changes; Accordingly, the actual usage corresponding to the charging parameter is extracted from the resource usage information, including: After responding to the data change request, record the amount of data changed; The maximum usage of the path within a specified unit time is determined from the data volume of the data change as the actual usage.

5. The method according to claim 1, characterized in that Also includes: Collecting actual resource consumption corresponding to the prediction result; Performing a forecast evaluation based on the deviation between the actual resource consumption and the forecast result to generate an evaluation result; The machine learning model is optimized and adjusted according to the evaluation results.

6. The method according to claim 1, characterized in that Also includes: Collect users’ historical usage habits and consumption records; Generating a personalized billing plan based on the historical usage habits and the consumption records; Output a billing rule suggestion according to the billing scheme.

7. A resource usage billing management device for a cloud product, characterized in that: include: An information processor, configured to obtain resource usage information of the cloud product after monitoring the completion of the operation of the cloud product; A billing analyzer, used to calculate fees based on the resource usage information using preset billing rules and generate real-time bills; A bill display platform, used to output the real-time bill; The resource manager is used to call a pre-trained machine learning model to predict the user's required resource volume based on the resource usage information and historical data to obtain a prediction result; and dynamically adjust the cloud product resource allocation based on the prediction result.

8. A server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images