Cloud resource cost estimation method and device, electronic equipment and storage medium

Abstract

The invention provides a cloud resource cost estimation method and device, electronic equipment and a storage medium, and relates to the technical field of electric digital data processing, and the method comprises the steps: determining a target cost type corresponding to a target user based on an application scene of cloud resources needed by the target user, the target cost type comprises at least one of price cost, bandwidth cost, time cost, technical cost and computing power gain cost; based on the resource information of each to-be-estimated cloud resource and / or the user information of the target user, obtaining a value of each to-be-estimated cloud resource relative to a target cost type of the target user; and calculating the comprehensive cost of each to-be-estimated cloud resource relative to the target user based on the value of the target cost type of each to-be-estimated cloud resource relative to the target user. According to the cloud resource cost estimation method and device, the electronic equipment and the storage medium provided by the invention, multiple influence factors can be comprehensively considered in a complex cloud environment, and more accurate estimation of the cloud resource cost is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a cloud resource cost estimation method, device, electronic equipment and storage medium. Background Art

[0002] With the rapid development of cloud computing technology, Infrastructure as a Service (IaaS) has become the preferred solution for many users to perform tasks and deploy applications. Users do not need to build and maintain physical servers by themselves, but can meet their computing and storage needs by purchasing cloud resources provided by IaaS providers.

[0003] Cloud resource costs are the fees incurred by users when using cloud resources. Cloud resource cost estimation is not only an important basis for users to make reasonable decisions, achieve cost control and resource optimization, but also an important guarantee for promoting business development and innovation.

[0004] However, in today's highly complex and dynamically changing cloud environment, it is difficult for users to accurately estimate the cost of cloud resources, which seriously restricts their selection decisions, cost control, and resource optimization. Therefore, how to achieve more accurate cloud resource cost estimation in a complex cloud environment is a technical problem that needs to be solved in this field. Summary of the invention

[0005] The present invention provides a cloud resource cost estimation method, device, electronic device and storage medium to solve the defect that it is difficult to accurately estimate the cloud resource cost in the prior art, and to achieve more accurate estimation of the cloud resource cost in a complex cloud environment.

[0006] The present invention provides a cloud resource cost estimation method, comprising the following steps.

[0007] Obtain resource information of each cloud resource to be estimated, user information of a target user, and application scenarios of the cloud resources required by the target user, wherein the resource information of the cloud resource to be estimated includes configuration information, price information, purchase records, usage information, and historical operation data of the cloud resource to be estimated, and the user information of the target user includes user information and historical operation data of the target user; Based on the application scenario of the cloud resources required by the target user, determine the target cost type corresponding to the target user, where the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost; Based on the resource information of each of the cloud resources to be estimated and / or the user information of the target user, obtaining a value of the target cost type of each of the cloud resources to be estimated relative to the target user; Based on the value of the target cost type of each of the cloud resources to be estimated relative to the target user, a comprehensive cost of each of the cloud resources to be estimated relative to the target user is calculated.

[0008] According to a cloud resource cost estimation method provided by the present invention, the determining of the target cost type corresponding to the target user based on the application scenario of the cloud resources required by the target user includes: Based on the predefined target correspondence relationship, determining the cost type corresponding to the application scenario of the cloud resources required by the target user as the target cost type; The target correspondence is used to describe the correspondence between different application scenarios and different cost types; the application scenarios include heterogeneous cloud application scenarios, distributed cloud application scenarios, joint cloud application scenarios, hybrid cloud application scenarios and edge cloud application scenarios; The cost types corresponding to the heterogeneous cloud application scenarios include price costs; The cost types corresponding to the distributed cloud application scenario include price cost, bandwidth cost and time cost; The cost types corresponding to the joint cloud application scenario include price cost, bandwidth cost, time cost and technical cost; The cost types corresponding to the hybrid cloud application scenario include price cost, bandwidth cost, time cost and technical cost; The cost types corresponding to the edge cloud application scenario include price cost, bandwidth cost, time cost, technology cost and computing power gain cost.

[0009] According to a cloud resource cost estimation method provided by the present invention, when the target cost type includes time cost, obtaining a value of the target cost type of each cloud resource to be estimated relative to the target user based on resource information of each cloud resource to be estimated and / or user information of the target user includes: Based on the resource information of each of the cloud resources to be estimated and the user information of the target user, acquiring a data transmission rate between each of the cloud resources to be estimated and the target user; Inputting the data transmission rate between each of the cloud resources to be estimated and the target user into a task delay duration estimation model, obtaining the task delay duration of each of the cloud resources to be estimated relative to the target user output by the task delay duration estimation model, wherein the task delay duration estimation model is trained based on the data transmission rate between the target user and the cloud resources within a preset historical period and the task delay duration of delayed tasks that the target user failed to complete on time within the preset historical period, and the data transmission rate between the target user and the cloud resources within the preset historical period and the delay duration of delayed tasks that the target user failed to complete on time within the preset historical period are obtained based on user information of the target user; Inputting the task delay duration of each of the to-be-estimated cloud resources relative to the target user into a time cost estimation model, obtaining a direct loss value of task delay and an indirect benefit reduction value of task delay for each of the to-be-estimated cloud resources relative to the target user output by the time cost estimation model, wherein the time cost estimation model is obtained after training based on the task delay duration of delayed tasks that the target user fails to complete on time within the preset historical period, and the direct loss value of task delay and the indirect benefit reduction value of task delay caused by the target user failing to complete the delayed tasks on time within the preset historical period, and the direct loss value of task delay and the indirect benefit reduction value of task delay caused by the target user failing to complete the delayed tasks on time within the preset historical period are obtained based on user information of the target user; Based on the direct loss value of task delay and the indirect benefit reduction value of task delay of each of the to-be-estimated cloud resources relative to the target user, the value of the time cost of each of the to-be-estimated cloud resources relative to the target user is calculated.

[0010] According to a cloud resource cost estimation method provided by the present invention, when the target cost type includes computing power gain cost, the value of the target cost type of each cloud resource to be estimated relative to the target user is calculated based on the resource information of each cloud resource to be estimated and / or the user information of the target user, including: Extracting the computing power value of each of the cloud resources to be estimated and the purchase price of each of the cloud resources to be estimated from the resource information of each of the cloud resources to be estimated, and extracting the computing power value of the target user from the user information of the target user; Calculate the quotient of the purchase price and the computing power value of each of the cloud resources to be estimated as the first intermediate result corresponding to each of the cloud resources to be estimated, and calculate the difference between the computing power value of each of the cloud resources to be estimated and the computing power value already possessed by the target user as the second intermediate result corresponding to each of the cloud resources to be estimated; The product of the first intermediate result and the second intermediate result corresponding to each of the cloud resources to be estimated is calculated as the value of the computing power gain cost of each of the cloud resources to be estimated relative to the target user.

[0011] According to a cloud resource cost estimation method provided by the present invention, the comprehensive cost of each cloud resource to be estimated relative to the target user is calculated based on the value of the target cost type of each cloud resource to be estimated relative to the target user, including: When the number of the target cost type is 1, the value of the target cost type of each cloud resource to be estimated relative to the target user is determined as the comprehensive cost of each cloud resource to be estimated relative to the target user. When the number of the target cost types is multiple, for each cloud resource to be estimated, the weighted sum of the values ​​of the target cost type of each cloud resource to be estimated relative to the target user is calculated as the comprehensive cost of each cloud resource to be estimated relative to the target user. The weight value corresponding to each target cost type is predefined.

[0012] According to a cloud resource cost estimation method provided by the present invention, after calculating the comprehensive cost of each of the cloud resources to be estimated relative to the target user based on the value of the target cost type of each of the cloud resources to be estimated relative to the target user, the method further includes: Based on the comprehensive cost of each of the cloud resources to be estimated relative to the target user, the cloud resources required by the target user are determined from among the cloud resources to be estimated.

[0013] The present invention also provides a cloud resource cost estimation device, comprising the following modules: an information acquisition module, used to acquire resource information of each cloud resource to be estimated, user information of a target user, and application scenarios of the cloud resources required by the target user, wherein the resource information of the cloud resource to be estimated includes configuration information, price information, purchase records, usage information, and historical operation data of the cloud resource to be estimated, and the user information of the target user includes user information and historical operation data of the target user; A scenario classification module, configured to determine a target cost type corresponding to the target user based on an application scenario of the cloud resources required by the target user, wherein the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost; A cost calculation module, configured to obtain a value of the target cost type of each of the cloud resources to be estimated relative to the target user based on the resource information of each of the cloud resources to be estimated and / or the user information of the target user; The cost estimation module is used to calculate the comprehensive cost of each of the cloud resources to be estimated relative to the target user based on the value of the target cost type of each of the cloud resources to be estimated relative to the target user.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the cloud resource cost estimation method as described above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the cloud resource cost estimation method as described in any one of the above is implemented.

[0016] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the cloud resource cost estimation method as described above is implemented.

[0017] The cloud resource cost estimation method, device, electronic device and storage medium provided by the present invention determine the target cost type corresponding to the target user based on the application scenario of the cloud resources required by the target user, and then obtain the value of the target cost type of each cloud resource to be estimated relative to the target user based on the resource information of each cloud resource to be estimated and / or the user information of the target user, and then calculate the comprehensive cost of each cloud resource to be estimated relative to the target user based on the value of the target cost type of each cloud resource to be estimated relative to the target user. In a complex cloud environment, multiple influencing factors such as price cost, transmission cost, bandwidth cost, time cost, technical cost and computing power gain of cloud resources can be comprehensively considered to achieve a more accurate estimation of cloud resource costs. By accurately matching user needs with cloud resources, the computing and storage costs of enterprises and individuals can be greatly reduced. By providing users with clearer cost information and comprehensive cost evaluation, users can better understand the cost structure of cloud resources, so as to make choices that better meet their own needs, which can improve user satisfaction, help cloud service providers improve service quality and user satisfaction, and promote the sustainable development of cloud services. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flowchart of the cloud resource cost estimation method provided by the present invention.

[0020] Figure 2 It is a structural schematic diagram of the cloud resource cost estimation device provided by the present invention.

[0021] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In the description of the invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] In the description of the present application, the terms "first", "second", etc. are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are usually a class, and the number of objects is not limited. For example, the first object can be one or more. In addition, in the description of the present application, "and / or" represents at least one of the connected objects, and the character " / " generally represents that the front and back associated objects are in an "or" relationship.

[0025] It should be noted that IaaS providers are key players in the field of cloud computing. IaaS providers meet users' business needs by providing cloud resources. The above cloud resources may include virtualized computing infrastructure. IaaS providers virtualize physical hardware resources (such as servers and storage devices) into multiple independently operable virtual machines (VMs) or containers. Users can allocate, configure, and manage these virtual machines or containers as needed.

[0026] Cloud resource users include individual users and application service providers. Individual users deploy their own applications or systems on cloud resources for their own use, while application service providers purchase cloud resources to provide services to their own users.

[0027] However, in today's highly complex and dynamically changing cloud environment, cloud resource costs are affected by a combination of factors, making it difficult for users to accurately estimate cloud resource costs, which seriously restricts users' selection decisions, cost control, and resource optimization.

[0028] In this regard, the present invention provides a cloud resource cost estimation method in a complex cloud environment. Based on the cloud resource cost estimation method provided by the present invention, multiple influencing factors such as price cost, transmission cost, bandwidth cost, time cost, technical cost and computing power gain of cloud resources can be comprehensively considered in a complex cloud environment to achieve a more accurate estimation of cloud resource costs, which can assist users to better select cloud resources according to their own needs, thereby lowering the threshold for using cloud resources and promoting the promotion and application of cloud computing.

[0029] Combine the following Figure 1 The cloud resource cost estimation method provided by the present invention is described.

[0030] Figure 1 is a flow chart of the cloud resource cost estimation method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101, obtaining resource information of each cloud resource to be estimated, user information of the target user, and application scenarios of the cloud resources required by the target user, the resource information of the cloud resources to be estimated includes configuration information, price information, purchase records, usage information, and historical operation data of the cloud resources to be estimated, and the user information of the target user includes user information and historical operation data of the target user.

[0031] It should be noted that the execution subject of the embodiment of the present invention is a cloud resource cost estimation device. The cloud resource cost estimation device can be configured in electronic devices such as computers and servers.

[0032] Specifically, in the embodiment of the present invention, the target user is a user who needs to purchase cloud resources, and the cloud resources to be estimated are cloud resources that the target user can purchase. The cloud resources to be estimated are the estimation objects of the cloud resource cost estimation method provided by the present invention. Based on the cloud resource cost estimation method provided by the present invention, the comprehensive cost of each cloud resource to be estimated relative to the target user can be estimated, so that the target user can select a cloud resource from the cloud resources to be estimated for purchase based on the comprehensive cost of each cloud resource to be estimated relative to the target user.

[0033] It is understandable that the target user and each cloud resource to be estimated in the embodiment of the present invention may be determined according to actual needs and actual conditions. The target user and each cloud resource to be estimated in the embodiment of the present invention are not specifically limited.

[0034] It should be noted that the resource information of the cloud resources to be estimated in the embodiment of the present invention may include but is not limited to price information of the cloud resources to be estimated, configuration information of the cloud resources to be estimated, bandwidth information of the cloud resources to be estimated, bandwidth price of the cloud resources to be estimated, purchase records of the cloud resources to be estimated, usage information of the cloud resources to be estimated, and historical operation data.

[0035] The configuration information of the cloud resources to be estimated may include, but is not limited to, computing resource configuration information, storage configuration information, database configuration information, and network configuration information of the cloud resources to be estimated.

[0036] The price information of the cloud resources to be estimated may include but is not limited to the basic fee and / or usage fee of the cloud resources to be estimated. The basic fee is a fixed fee calculated based on the configured service type and specifications, and the usage fee is a fee calculated based on actual usage (such as computing resource usage time, data transmission volume, storage volume, etc.).

[0037] The purchase records of the cloud resources to be estimated may include, but are not limited to, the purchase time of the cloud resources to be estimated, the purchased service type and specifications, quantity, payment method, and payment amount.

[0038] The usage information of the cloud resources to be estimated may include, but is not limited to, resource usage, service usage, and user behavior data of the cloud resources to be estimated.

[0039] The historical operation data of the cloud resources to be estimated may include, but are not limited to, historical status data of the hardware resources of the cloud resources to be estimated, historical status data of the service performance, and historical fault records.

[0040] The user information of the target user in the embodiment of the present invention may include but is not limited to the configuration information and historical operation data of the target user. The configuration information of the target user may include but is not limited to information such as the number of resources and resource configuration information. The historical operation data of the target user may include but is not limited to the delayed completion of the target user's tasks in historical projects and the corresponding cost increase data and revenue reduction data, including additional labor costs, resource costs, etc.

[0041] In the embodiment of the present invention, the resource information of the cloud resources to be estimated can be collected regularly through the API interface or tools provided by the IaaS provider. In addition to the general management interface, the IaaS provider can also configure a variety of interfaces and tools for users, and users can use the above interfaces and / or tools to obtain the purchase records and historical operation data of the cloud resources to be estimated.

[0042] After obtaining the resource information of each cloud resource to be estimated and the user information of the target user, the resource information of each cloud resource to be estimated and the user information of the target user can be stored in the Redis (Remote Dictionary Server) database. The Redis database is an open source, memory-based, high-performance, data-persistent key-value storage system. Redis complies with the BSD protocol, provides APIs in multiple languages, and is a widely used NoSQL database.

[0043] In the embodiment of the present invention, the application scenario of the cloud resources required by the target user can be determined based on the actual business needs and operating environment of the target user.

[0044] It should be noted that the application scenarios of cloud resources in the embodiments of the present invention may include but are not limited to heterogeneous cloud application scenarios, distributed cloud application scenarios, federated cloud application scenarios, hybrid cloud application scenarios, and edge cloud application scenarios.

[0045] Step 102: Based on the application scenario of the cloud resources required by the target user, determine the target cost type corresponding to the target user, where the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost.

[0046] It should be noted that in a highly complex and dynamically changing cloud environment, when estimating the cost of cloud resources, one should not only consider the price of cloud resources, but also multiple factors such as the location of cloud resources, data transmission delay, and software transformation.

[0047] Therefore, the embodiments of the present invention estimate the cloud resource cost in terms of cost types, including price cost, bandwidth cost, time cost, technology cost, and computing power gain cost.

[0048] Among them, the price cost is the purchase price of cloud resources; the bandwidth cost is the cost of using cloud resources and transmitting data with cloud resources; the time cost is the time consumed by data transmission, which leads to delayed task completion, and the delayed task completion may miss the nearest opportunity to solve the problem, thereby incurring additional costs; the technical cost is the cost incurred for adapting cloud resources; the computing power gain cost is the cost incurred by the instance gain brought by the use of cloud resources.

[0049] In an embodiment of the present invention, based on the application scenarios of cloud resources required by target users, one or more of price cost, bandwidth cost, time cost, technology cost and computing power gain cost can be determined as the target cost type through various methods such as condition judgment, target matching and deep learning technology.

[0050] As an optional embodiment, determining the target cost type corresponding to the target user based on the application scenario of the cloud resources required by the target user includes: determining the cost type corresponding to the application scenario of the cloud resources required by the target user as the target cost type based on a predefined target corresponding relationship; Among them, the target correspondence is used to describe the correspondence between different application scenarios and different cost types; the application scenarios include heterogeneous cloud application scenarios, distributed cloud application scenarios, joint cloud application scenarios, hybrid cloud application scenarios and edge cloud application scenarios; The cost types corresponding to heterogeneous cloud application scenarios include price costs; The cost types corresponding to distributed cloud application scenarios include price cost, bandwidth cost, and time cost; The cost types corresponding to the joint cloud application scenarios include price cost, bandwidth cost, time cost, and technical cost; The cost types corresponding to hybrid cloud application scenarios include price cost, bandwidth cost, time cost, and technical cost; The cost types corresponding to edge cloud application scenarios include price cost, bandwidth cost, time cost, technology cost, and computing power gain cost.

[0051] Specifically, using a single IaaS provider's data center, that is, using cloud resources that belong to the same region of the same IaaS provider, the cloud resources are heterogeneous, which can be called a heterogeneous cloud application scenario. The main consideration for using cloud resources in a heterogeneous cloud application scenario is price cost.

[0052] Using geographically distributed data centers of a single IaaS provider, that is, using cloud resources that belong to the same IaaS provider but are located in different regions, can be called a distributed cloud application scenario. Since cross-region data transmission consumes bandwidth and time, using cloud resources in a distributed cloud application scenario requires additional consideration of bandwidth and time costs in addition to price costs.

[0053] Using data centers of multiple IaaS providers is called a federated cloud application scenario. The cloud resources of multiple IaaS providers are usually located in different regions, and different IaaS providers usually use different architectures and technical routes. Therefore, in addition to considering price costs, bandwidth costs, and time costs, the use of cloud resources in a federated cloud application scenario also requires considering technical costs.

[0054] Using both your own servers and the data center of an IaaS provider is called a hybrid cloud application scenario. Using cloud resources in a hybrid cloud application scenario is similar to using joint cloud applications, and you need to consider price costs, bandwidth costs, time costs, and technical costs.

[0055] If the user has very limited computing power and hopes to use the cloud resources of the IaaS provider to offload tasks, it will constitute a cloud-edge application scenario. In addition to considering the price cost, bandwidth cost, time cost, and technical cost when using cloud resources in cloud-edge application scenarios, the computing power gain cost must also be considered due to the help that cloud resources bring to their own computing power.

[0056] The embodiments of the present invention fully consider the different demands and concerns for cloud resources in different application scenarios. Through predefined target correspondences, the application scenarios of cloud resources required by target users can be directly matched with specific cost types, thus avoiding subjectivity and arbitrariness in the cost evaluation process. It can more accurately reflect the cost requirements of users in actual use, and can improve users' satisfaction and trust in cost estimation through personalized matching.

[0057] Step 103: Based on the resource information of each cloud resource to be estimated and / or the user information of the target user, obtain a value of a target cost type of each cloud resource to be estimated relative to the target user.

[0058] Specifically, after determining the target cost type corresponding to the target user, the value of the target cost type of each cloud resource to be estimated that is equivalent to the target user can be obtained through numerical calculation, mathematical statistics, and deep learning technology based on the resource information of each cloud resource to be estimated and the user information of the target user.

[0059] Step 104: Calculate the comprehensive cost of each to-be-estimated cloud resource relative to the target user based on the value of the target cost type of each to-be-estimated cloud resource relative to the target user.

[0060] Specifically, after obtaining the value of the target cost type of each cloud resource to be estimated that is equivalent to the target user, the comprehensive cost of each cloud resource to be estimated relative to the target user can be calculated by numerical calculation, mathematical statistics, etc.

[0061] The embodiment of the present invention determines the target cost type corresponding to the target user based on the application scenario of the cloud resources required by the target user, and then obtains the value of the target cost type of each cloud resource to be estimated relative to the target user based on the resource information of each cloud resource to be estimated and / or the user information of the target user, and then calculates the comprehensive cost of each cloud resource to be estimated relative to the target user based on the value of the target cost type of each cloud resource to be estimated relative to the target user. In a complex cloud environment, multiple influencing factors such as price cost, transmission cost, bandwidth cost, time cost, technical cost and computing power gain of cloud resources can be comprehensively considered to achieve a more accurate estimation of cloud resource costs. By accurately matching user needs with cloud resources, the computing and storage costs of enterprises and individuals can be greatly reduced. By providing users with clearer cost information and comprehensive cost evaluation, users can better understand the cost structure of cloud resources, so as to make choices that better meet their own needs, which can improve user satisfaction, help cloud service providers improve service quality and user satisfaction, and promote the sustainable development of cloud services.

[0062] As an optional embodiment, when the target cost type includes price cost, based on the resource information of each cloud resource to be estimated and / or the user information of the target user, the value of the target cost type of each cloud resource to be estimated relative to the target user is obtained, including: extracting the purchase price of each cloud resource to be estimated from the resource information of each cloud resource to be estimated as the value of the price cost of each cloud resource to be estimated relative to the target user.

[0063] It should be noted that, in the embodiments of the present invention, Identify the cloud resources to be estimated, , Indicates the total number of cloud resources to be estimated.

[0064] Based on The resource information of the cloud resources to be estimated can be obtained The purchase price of the cloud resource to be estimated is used as the first The value of the price cost of the cloud resources to be estimated relative to the target user .

[0065] It should be noted that the purchase price of cloud resources depends on many factors, including the specifications of cloud resources (such as CPU, memory, storage and bandwidth configurations), billing mode (such as on-demand instances, reserved instances, spot instances, etc.), and purchase duration. The purchase price of cloud resources is determined by the IaaS provider.

[0066] As an optional embodiment, when the target cost type includes bandwidth cost, based on the resource information of each cloud resource to be estimated and / or the user information of the target user, the value of the target cost type of each cloud resource to be estimated relative to the target user is obtained, including: based on the bandwidth resource information and service quality information of each cloud resource to be estimated in the resource information of each cloud resource to be estimated, calculating the value of the bandwidth cost of each cloud resource to be estimated relative to the target user.

[0067] Specifically, no. The value of the bandwidth cost of the cloud resource to be estimated relative to the target user is the bandwidth cost of the target user. The cost of estimating cloud resources and transferring data can be used express.

[0068] No. The value of the bandwidth cost of the cloud resource to be estimated relative to the target user , can be based on the first The bandwidth resource information and service quality information of the cloud resources to be estimated are calculated.

[0069] As an optional embodiment, when the target cost type includes time cost, based on the resource information of each cloud resource to be estimated and / or the user information of the target user, the value of the target cost type of each cloud resource to be estimated relative to the target user is obtained, including: based on the resource information of each cloud resource to be estimated and the user information of the target user, obtaining the data transmission rate between each cloud resource to be estimated and the target user.

[0070] Based on The resource information of the cloud resources to be estimated and the user information of the target user can be obtained. The data transmission rate between the cloud resources to be estimated and the target user.

[0071] The data transmission rate between each cloud resource to be estimated and the target user is input into the task delay duration estimation model, and the task delay duration of each cloud resource to be estimated relative to the target user is obtained from the output of the task delay duration estimation model. The task delay duration estimation model is trained based on the data transmission rate between the target user and the cloud resources within a preset historical period and the task delay duration of delayed tasks that the target user failed to complete on time within the preset historical period. The data transmission rate between the target user and the cloud resources within the preset historical period and the delay duration of delayed tasks that the target user failed to complete on time within the preset historical period are obtained based on the user information of the target user.

[0072] The task delay duration of each to-be-estimated cloud resource relative to the target user is input into the time cost estimation model, and the direct loss value of the task delay and the indirect benefit reduction value of the task delay of each to-be-estimated cloud resource relative to the target user are obtained from the output of the time cost estimation model. The time cost estimation model is obtained after training based on the task delay duration of delayed tasks that the target user fails to complete on time within a preset historical period, as well as the direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the delayed task on time within the preset historical period. The direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the delayed task on time within the preset historical period are obtained based on the user information of the target user.

[0073] It should be noted that the time consumed for data transmission between users and cloud resources may cause delays in task completion for users. In special circumstances, delayed task completion may miss the best time to solve the problem, thereby causing users to incur additional costs. In addition, for application service providers, increased task delays may lead to reduced user satisfaction, causing the application service provider's users to choose other application service providers, resulting in reduced future revenue.

[0074] In an embodiment of the present invention, the data transmission rate between the target user and the cloud resources within a preset historical period and the delay duration of the delayed tasks that the target user failed to complete within the preset historical period can be extracted from the historical operation data of the target user, as well as the direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the delayed tasks within the preset historical period.

[0075] It should be noted that, in the embodiment of the present invention, the direct loss value of task delay and the indirect benefit reduction value of task delay caused by the target user's failure to complete the delayed task within the preset historical period can be 0.

[0076] It should be noted that, since historical data that is too far away from the current time has no reference value, in the embodiment of the present invention, a historical period of a preset time before the current time is determined as a preset historical period, and the preset time can be determined based on prior knowledge and / or actual conditions, for example, the preset time can be 1 year or 2 years. The specific value of the preset time is not limited in the embodiment of the present invention.

[0077] It can be understood that the delay duration of the delayed task that the target user fails to complete refers to the duration between the planned completion time and the actual completion time of the delayed task that the target user fails to complete.

[0078] After extracting the data transmission rate between the target user and the cloud resources within the preset historical period, the delay duration of the delayed tasks that the target user failed to complete within the preset historical period, and the direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the delayed tasks within the preset historical period from the historical operation data of the target user, the data transmission rate between the target user and the cloud resources within the preset historical period, the delay duration of the delayed tasks that the target user failed to complete within the preset historical period, and the direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the delayed tasks within the preset historical period can be preprocessed to meet the requirements of model training and eliminate the influence of different dimensions on the model calculation results. The data preprocessing can include but is not limited to one or more of data formatting, normalization and standardization.

[0079] After data preprocessing of the data transmission rate between the target user and the cloud resources within the preset historical period, the delay duration of the delayed tasks that the target user fails to complete within the above-preset historical period, and the direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the above-preset historical period, the first initial model can be trained with the data transmission rate between the target user and the cloud resources within the preset historical period as a sample and the delay duration of the delayed tasks that the target user fails to complete within the above-preset historical period as a sample label to obtain a trained task delay duration estimation model; the second initial model can also be trained with the delay duration of the delayed tasks that the target user fails to complete within the above-preset historical period as a sample and the direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the above-preset historical period as a sample label to obtain a trained time cost estimation model.

[0080] It should be noted that the first initial model and the second initial model in the embodiment of the present invention can be constructed based on a neural network model.

[0081] After obtaining the trained task delay duration estimation model and the trained time cost estimation model, the trained task delay duration estimation model and the trained time cost estimation model can be verified to evaluate the generalization ability and accuracy of the trained task delay duration estimation model and the trained time cost estimation model.

[0082] It should be noted that in the embodiments of the present invention, a data set that did not participate in the training can be used to verify the model, compare the difference between the model's prediction results and the actual values, and calculate error indicators (such as mean square error, mean absolute error, etc.) to evaluate the accuracy of the model.

[0083] When the above-trained task delay estimation model and the trained time cost estimation model are verified, The data transmission rate between the cloud resource to be estimated and the target user is input into the task delay duration estimation model. The task delay duration estimation module can be based on the The data transmission rate between the cloud resources to be estimated and the target user is estimated at When the estimated cloud resource provides services to the target user, the delay duration of the delayed task that the target user fails to complete on time is taken as the first The task delay time of the cloud resource to be estimated relative to the target user can then be obtained. The task delay duration of the cloud resource to be estimated relative to the target user.

[0084] The first The estimated cloud resource relative to the target user’s task delay is input into the time cost estimation model. The time cost estimation model can be based on the The estimated cloud resource is relative to the target user's task delay time, and the estimated direct loss value of the task delay and the indirect benefit reduction value of the task delay caused by the target user's failure to complete the delayed task on time are used as the first The direct loss value of task delay and the indirect benefit reduction value of task delay of the cloud resource to be estimated relative to the target user can be obtained, and then the output of the time cost estimation model can be obtained. The direct loss value of task delay and the indirect benefit reduction value of task delay of the cloud resources to be estimated relative to the target user.

[0085] Based on the direct loss value of task delay and the indirect benefit reduction value of task delay of each to-be-estimated cloud resource relative to the target user, the time cost value of each to-be-estimated cloud resource relative to the target user is calculated.

[0086] Specifically, obtain the After estimating the direct loss value of task delay and the indirect benefit reduction value of task delay of the cloud resource relative to the target user, the following formula can be used to calculate the first The value of the time cost of the cloud resource to be estimated relative to the target user.

[0087]

[0088] in, Indicates The value of the time cost of the cloud resources to be estimated relative to the target user; Indicates The direct loss value of the task delay of the target user relative to the cloud resource to be estimated; Indicates The indirect benefit reduction value of the task delay of the target user relative to the estimated cloud resource.

[0089] As an optional embodiment, when the target cost type includes computing power gain cost, based on the resource information of each cloud resource to be estimated and / or the user information of the target user, the value of the target cost type of each cloud resource to be estimated relative to the target user is obtained, including: extracting the computing power value of each cloud resource to be estimated and the purchase price of each cloud resource to be estimated from the resource information of each cloud resource to be estimated, and extracting the computing power value of the target user from the user information of the target user.

[0090] Calculate the quotient of the purchase price and the computing power value of each cloud resource to be estimated as the first intermediate result corresponding to each cloud resource to be estimated, and calculate the difference between the computing power value of each cloud resource to be estimated and the computing power value already owned by the target user as the second intermediate result corresponding to each cloud resource to be estimated; The product of the first intermediate result and the second intermediate result corresponding to each cloud resource to be estimated is calculated as the value of the computing power gain cost of each cloud resource to be estimated relative to the target user.

[0091] It should be noted that in the embodiments of the present invention, MIPS or FLOPS can be used to represent the computing power value of the cloud resources to be estimated and the computing power value of the target user. Among them, MIPS (Million Instructions Per Second) represents the number of million machine language instructions that can be executed per second, which is used to measure the second-level processing capability of electronic devices. FLOPS (Floating-point Operations Per Second) represents the number of floating-point operations performed per second, which is mainly used to measure the computing power of electronic devices.

[0092] No. The value of the computing power gain cost of the estimated cloud resource relative to the target user can be calculated by the following formula:

[0093] in, Indicates The value of the computing power gain cost of the cloud resource to be estimated relative to the target user; Indicates The computing power of the cloud resources to be estimated; Indicates the target user’s computing power value; Indicates The purchase price of the cloud resources to be estimated.

[0094] As an optional embodiment, when the target cost type includes technical cost, based on the resource information of each cloud resource to be estimated and / or the user information of the target user, the value of the target cost type of each cloud resource to be estimated relative to the target user is obtained, including: extracting the technical cost invested by the target user for adapting the cloud resources within a preset historical period from the user information of the target user.

[0095] Based on the technical cost invested by the target user for adapting the cloud resources in a preset historical period, the value of the technical cost of each cloud resource to be estimated relative to the target user is obtained.

[0096] It should be noted that in order to adapt to the architecture and technical routes of cloud resources provided by different IaaS providers, target users need to adapt their applications, which incurs technical costs.

[0097] In the embodiment of the present invention, Indicates The value of the technical cost of the cloud resources to be estimated relative to the target user. The value of the estimated cloud resource relative to the technical cost of the target user It can be obtained through numerical calculation, mathematical statistics or machine learning methods based on the technical cost invested by the target users in adapting cloud resources during a preset historical period.

[0098] As an optional embodiment, based on the value of the target cost type of each cloud resource to be estimated relative to the target user, the comprehensive cost of each cloud resource to be estimated relative to the target user is calculated, including: when the number of target cost types is 1, the value of the target cost type of each cloud resource to be estimated relative to the target user is determined as the comprehensive cost of each cloud resource to be estimated relative to the target user; when the number of target cost types is multiple, for each cloud resource to be estimated, the weighted sum of the values ​​of the target cost type of each cloud resource to be estimated relative to the target user is calculated as the comprehensive cost of each cloud resource to be estimated relative to the target user, and the weight value corresponding to each target cost type is predefined.

[0099] Specifically, no. The comprehensive cost of the estimated cloud resources relative to the target user can be calculated based on the following formula:

[0100] in, Indicates The comprehensive cost of the cloud resources to be estimated relative to the target users; The weights of price cost, bandwidth cost, time cost, technology cost and example gain cost respectively indicate the importance of each cost and satisfy , , , and is 0 or a positive value, 0 or negative value.

[0101] It should be noted that when a certain cost type is not included in the target cost type, the weight of the above cost type is 0. For example, when the target cost type does not include the example gain cost, The value of is 0.

[0102] As an optional embodiment, after calculating the comprehensive cost of each cloud resource to be estimated relative to the target user based on the value of the target cost type of each cloud resource to be estimated relative to the target user, the method also includes: determining the cloud resources required by the target user among each cloud resource to be estimated based on the comprehensive cost of each cloud resource to be estimated relative to the target user.

[0103] Specifically, after calculating the comprehensive cost of each cloud resource to be estimated relative to the target user, the cloud resource to be estimated with the lowest comprehensive cost relative to the target user can be determined as the cloud resource required by the target user based on the comprehensive cost of each cloud resource to be estimated relative to the target user.

[0104] The cloud resource cost estimation method provided by the present invention fully considers various application scenarios such as heterogeneous cloud, distributed cloud, federated cloud, hybrid cloud, edge cloud, etc., and flexibly responds to and adapts to complex and changeable cloud environments. No matter what cloud architecture or service model the user adopts, accurate and effective cost estimates can be obtained to meet diverse business needs.

[0105] The cloud resource cost estimation method provided by the present invention also fully considers multiple costs such as price cost, bandwidth cost, time cost, technology cost and computing power gain cost, and realizes comprehensive and accurate estimation of cloud resource costs, which helps users to more accurately grasp the real cost of cloud resource use and provide a scientific basis for decision-making, thereby lowering the threshold for cloud resource use and promoting the development of cloud computing business.

[0106] Figure 2 This is a schematic diagram of the structure of the cloud resource cost estimation device provided by the present invention. Figure 2 The cloud resource cost estimation device provided by the present invention is described. The cloud resource cost estimation device described below and the cloud resource cost estimation method provided by the present invention described above can be referred to each other. Figure 2 As shown, the device includes: an information acquisition module 201, a scene classification module 202, a cost calculation module 203 and a cost estimation module 204.

[0107] The information acquisition module 201 is used to acquire resource information of each cloud resource to be estimated, user information of a target user, and application scenarios of the cloud resources required by the target user. The resource information of the cloud resource to be estimated includes configuration information, price information, purchase records, usage information, and historical operation data of the cloud resource to be estimated. The user information of the target user includes user information and historical operation data of the target user. A scenario classification module 202 is used to determine a target cost type corresponding to a target user based on an application scenario of cloud resources required by the target user, where the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost; The cost calculation module 203 is used to obtain a value of a target cost type of each cloud resource to be estimated relative to a target user based on resource information of each cloud resource to be estimated and / or user information of the target user; The cost estimation module 204 is used to calculate the comprehensive cost of each to-be-estimated cloud resource relative to the target user based on the value of the target cost type of each to-be-estimated cloud resource relative to the target user.

[0108] Specifically, the information acquisition module 201, the scene classification module 202, the cost calculation module 203 and the cost estimation module 204 are electrically connected.

[0109] It should be noted that the cloud resource cost estimation device in the embodiment of the present invention may also include a log recording module, which can record user operations, administrator operations and system operation logs, including user requests, information acquisition records, scenario classification operations, resource cost estimation operation records, etc., to facilitate error backtracing and behavior auditing, and ensure the security and stability of the system.

[0110] The above-mentioned logging module can use log collection tools (such as Fluentd, Logstash, etc.) or custom log frameworks to capture all key events in user operations, administrator operations, and system operation. The log content includes detailed information such as timestamp, operation type, operation object, and operation result. The collected log data is stored in a high-performance database (such as Elasticsearch, MongoDB) or distributed file system for fast retrieval and query. Supports compression and encryption of log data to ensure data security and privacy. Provides log query and analysis interfaces, allowing users and administrators to filter and view log records based on time range, operation type, and other conditions. Use log analysis tools (such as Kibana, Grafana, etc.) to visualize log data to help quickly locate problems and discover potential security risks. When the system fails or is abnormal, the error is traced back through log records to quickly locate the cause of the problem and take corresponding solutions. Audit the operation behavior of users and administrators to ensure the compliance and security of the system.

[0111] The cloud resource cost estimation device in the embodiment of the present invention determines the target cost type corresponding to the target user based on the application scenario of the cloud resources required by the target user, and then obtains the value of the target cost type of each cloud resource to be estimated relative to the target user based on the resource information of each cloud resource to be estimated and / or the user information of the target user, and then calculates the comprehensive cost of each cloud resource to be estimated relative to the target user based on the value of the target cost type of each cloud resource to be estimated relative to the target user. It can comprehensively consider various influencing factors such as price cost, transmission cost, bandwidth cost, time cost, technical cost and computing power gain of cloud resources in a complex cloud environment, and realize more accurate estimation of cloud resource costs. By accurately matching user needs with cloud resources, it can greatly reduce the computing and storage costs of enterprises and individuals. By providing users with clearer cost information and comprehensive cost evaluation, users can better understand the cost structure of cloud resources, so as to make choices that better meet their own needs, which can improve user satisfaction, help cloud service providers improve service quality and user satisfaction, and promote the sustainable development of cloud services.

[0112] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 310 , a communications interface 320 , a memory 330 and a communication bus 340 , wherein the processor 310 , the communications interface 320 , and the memory 330 communicate with each other via the communication bus 340 . The processor 310 can call the logic instructions in the memory 330 to execute the cloud resource cost estimation method, which includes: obtaining resource information of each cloud resource to be estimated, user information of the target user, and application scenarios of the cloud resources required by the target user, the resource information of the cloud resources to be estimated includes configuration information, price information, purchase records, usage information and historical operation data of the cloud resources to be estimated, and the user information of the target user includes user information and historical operation data of the target user; based on the application scenarios of the cloud resources required by the target user, determining the target cost type corresponding to the target user, the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost and computing power gain cost; based on the resource information of each cloud resource to be estimated and / or the user information of the target user, obtaining the value of the target cost type of each cloud resource to be estimated relative to the target user; based on the value of the target cost type of each cloud resource to be estimated relative to the target user, calculating the comprehensive cost of each cloud resource to be estimated relative to the target user.

[0113] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0114] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the cloud resource cost estimation method provided by the above methods, which includes: obtaining resource information of each cloud resource to be estimated, user information of a target user, and an application scenario of the cloud resource required by the target user, the resource information of the cloud resource to be estimated includes configuration information, price information, purchase records, usage information, and historical operation data of the cloud resource to be estimated, and the user information of the target user includes user information and historical operation data of the target user; based on the application scenario of the cloud resource required by the target user, determining a target cost type corresponding to the target user, the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost; based on the resource information of each cloud resource to be estimated and / or the user information of the target user, obtaining a value of a target cost type of each cloud resource to be estimated relative to the target user; based on the value of the target cost type of each cloud resource to be estimated relative to the target user, calculating a comprehensive cost of each cloud resource to be estimated relative to the target user.

[0115] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the cloud resource cost estimation method provided by the above-mentioned methods, the method comprising: obtaining resource information of each cloud resource to be estimated, user information of a target user, and an application scenario of the cloud resource required by the target user, the resource information of the cloud resource to be estimated comprising configuration information, price information, purchase records, usage information, and historical operation data of the cloud resource to be estimated, and the user information of the target user comprising user information and historical operation data of the target user; based on the application scenario of the cloud resource required by the target user, determining a target cost type corresponding to the target user, the target cost type comprising at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost; based on the resource information of each cloud resource to be estimated and / or the user information of the target user, obtaining a value of a target cost type of each cloud resource to be estimated relative to the target user; based on the value of the target cost type of each cloud resource to be estimated relative to the target user, calculating a comprehensive cost of each cloud resource to be estimated relative to the target user.

[0116] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0117] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A cloud resource cost estimation method, characterized in that: include: Obtain resource information of each cloud resource to be estimated, user information of a target user, and application scenarios of the cloud resources required by the target user, wherein the resource information of the cloud resource to be estimated includes configuration information, price information, purchase records, usage information, and historical operation data of the cloud resource to be estimated, and the user information of the target user includes user information and historical operation data of the target user; Based on the application scenario of the cloud resources required by the target user, determine the target cost type corresponding to the target user, where the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost; Based on the resource information of each of the cloud resources to be estimated and / or the user information of the target user, obtaining a value of the target cost type of each of the cloud resources to be estimated relative to the target user; Based on the value of the target cost type of each of the cloud resources to be estimated relative to the target user, a comprehensive cost of each of the cloud resources to be estimated relative to the target user is calculated.

2. The cloud resource cost estimation method according to claim 1, characterized in that: The determining the target cost type corresponding to the target user based on the application scenario of the cloud resources required by the target user includes: Based on the predefined target correspondence relationship, determining the cost type corresponding to the application scenario of the cloud resources required by the target user as the target cost type; The target correspondence is used to describe the correspondence between different application scenarios and different cost types; the application scenarios include heterogeneous cloud application scenarios, distributed cloud application scenarios, joint cloud application scenarios, hybrid cloud application scenarios and edge cloud application scenarios; The cost types corresponding to the heterogeneous cloud application scenarios include price costs; The cost types corresponding to the distributed cloud application scenario include price cost, bandwidth cost and time cost; The cost types corresponding to the joint cloud application scenario include price cost, bandwidth cost, time cost and technical cost; The cost types corresponding to the hybrid cloud application scenario include price cost, bandwidth cost, time cost and technical cost; The cost types corresponding to the edge cloud application scenario include price cost, bandwidth cost, time cost, technology cost and computing power gain cost.

3. The cloud resource cost estimation method according to claim 2, characterized in that: In a case where the target cost type includes time cost, acquiring a value of the target cost type of each cloud resource to be estimated relative to the target user based on resource information of each cloud resource to be estimated and / or user information of the target user includes: Based on the resource information of each of the cloud resources to be estimated and the user information of the target user, acquiring a data transmission rate between each of the cloud resources to be estimated and the target user; Inputting the data transmission rate between each of the cloud resources to be estimated and the target user into a task delay duration estimation model, obtaining the task delay duration of each of the cloud resources to be estimated relative to the target user output by the task delay duration estimation model, wherein the task delay duration estimation model is trained based on the data transmission rate between the target user and the cloud resources within a preset historical period and the task delay duration of delayed tasks that the target user failed to complete on time within the preset historical period, and the data transmission rate between the target user and the cloud resources within the preset historical period and the delay duration of delayed tasks that the target user failed to complete on time within the preset historical period are obtained based on user information of the target user; Inputting the task delay duration of each of the to-be-estimated cloud resources relative to the target user into a time cost estimation model, obtaining a direct loss value of task delay and an indirect benefit reduction value of task delay for each of the to-be-estimated cloud resources relative to the target user output by the time cost estimation model, wherein the time cost estimation model is obtained after training based on the task delay duration of delayed tasks that the target user fails to complete on time within the preset historical period, and the direct loss value of task delay and the indirect benefit reduction value of task delay caused by the target user failing to complete the delayed tasks on time within the preset historical period, and the direct loss value of task delay and the indirect benefit reduction value of task delay caused by the target user failing to complete the delayed tasks on time within the preset historical period are obtained based on user information of the target user; Based on the direct loss value of task delay and the indirect benefit reduction value of task delay of each of the to-be-estimated cloud resources relative to the target user, the value of the time cost of each of the to-be-estimated cloud resources relative to the target user is calculated.

4. The cloud resource cost estimation method according to claim 2, characterized in that: In a case where the target cost type includes computing power gain cost, acquiring a value of the target cost type of each cloud resource to be estimated relative to the target user based on resource information of each cloud resource to be estimated and / or user information of the target user includes: Extracting the computing power value of each of the cloud resources to be estimated and the purchase price of each of the cloud resources to be estimated from the resource information of each of the cloud resources to be estimated, and extracting the computing power value of the target user from the user information of the target user; Calculate the quotient of the purchase price and the computing power value of each of the cloud resources to be estimated as the first intermediate result corresponding to each of the cloud resources to be estimated, and calculate the difference between the computing power value of each of the cloud resources to be estimated and the computing power value already possessed by the target user as the second intermediate result corresponding to each of the cloud resources to be estimated; The product of the first intermediate result and the second intermediate result corresponding to each of the cloud resources to be estimated is calculated as the value of the computing power gain cost of each of the cloud resources to be estimated relative to the target user.

5. The cloud resource cost estimation method according to claim 1, characterized in that: The calculating, based on the value of the target cost type of each of the cloud resources to be estimated relative to the target user, a comprehensive cost of each of the cloud resources to be estimated relative to the target user, includes: When the number of the target cost type is 1, the value of the target cost type of each cloud resource to be estimated relative to the target user is determined as the comprehensive cost of each cloud resource to be estimated relative to the target user; when the number of the target cost types is multiple, for each cloud resource to be estimated, the weighted sum of the values ​​of the target cost type of each cloud resource to be estimated relative to the target user is calculated as the comprehensive cost of each cloud resource to be estimated relative to the target user, and the weight value corresponding to each target cost type is predefined.

6. The cloud resource cost estimation method according to any one of claims 1 to 5, characterized in that: After calculating the comprehensive cost of each of the cloud resources to be estimated relative to the target user based on the value of the target cost type of each of the cloud resources to be estimated relative to the target user, the method further includes: Based on the comprehensive cost of each of the cloud resources to be estimated relative to the target user, the cloud resources required by the target user are determined from among the cloud resources to be estimated.

7. A cloud resource cost estimation device, characterized in that: include: an information acquisition module, used to acquire resource information of each cloud resource to be estimated, user information of a target user, and application scenarios of the cloud resources required by the target user, wherein the resource information of the cloud resource to be estimated includes configuration information, price information, purchase records, usage information, and historical operation data of the cloud resource to be estimated, and the user information of the target user includes user information and historical operation data of the target user; A scenario classification module, configured to determine a target cost type corresponding to the target user based on an application scenario of the cloud resources required by the target user, wherein the target cost type includes at least one of price cost, bandwidth cost, time cost, technology cost, and computing power gain cost; A cost calculation module, configured to obtain a value of the target cost type of each of the cloud resources to be estimated relative to the target user based on the resource information of each of the cloud resources to be estimated and / or the user information of the target user; The cost estimation module is used to calculate the comprehensive cost of each of the cloud resources to be estimated relative to the target user based on the value of the target cost type of each of the cloud resources to be estimated relative to the target user.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the cloud resource cost estimation method according to any one of claims 1 to 6 is implemented.

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

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

Images