Cloud service management method and system based on cloud service adaptation algorithm

Abstract

The invention provides a cloud service management method and system based on a cloud service adaptation algorithm, and the method comprises the following steps: S1, training a cloud service management model based on a convolutional neural network for learning and recognizing the features of different cloud platform APIs, and storing the cloud service management model in a server; and S2, detecting whether an AP I calling request exists or not, and when an API calling request exists, performing feature recognition on the AP I calling request by adopting a cloud service management model, and recognizing the current API calling request cloud platform attribution. According to the method, the features of different cloud platform APIs are automatically recognized through a deep learning model, and a decision tree is constructed to select an optimal adaptation strategy; according to the method, the dependence on professional knowledge and manual configuration errors are reduced, the efficiency and accuracy of the adaptation process are remarkably improved, the possibility of human errors is reduced, and time and human resources are saved.

Description

Technical Field

[0001] The present invention relates to the field of computer science and technology, and in particular to a cloud service management method and system based on a cloud service adaptation algorithm. Background Art

[0002] There are currently a variety of cloud service management tools on the market, typically designed to monitor, analyze, and optimize cloud resources. However, most tools focus on managing a single cloud platform, with limited support for intelligent identification and adaptation of heterogeneous cloud platforms in multi-cloud environments. Existing products typically utilize standardized API integration methods, lacking the ability to deeply learn and adapt to the unique API features of different cloud platforms.

[0003] For example, AWS's CloudWatch and Azure's Monitor services both provide monitoring and management capabilities for their respective platforms, but are limited when it comes to cross-platform operations. Furthermore, third-party tools like Datadog and NewRelic, while supporting multi-cloud environments, rely primarily on predefined integrations and manual configuration rather than intelligent adaptation.

[0004] Although there are a variety of cloud service management tools on the market, these tools still have some significant shortcomings and defects when dealing with heterogeneous cloud platforms in a multi-cloud environment:

[0005] 1. Lack of deep adaptation mechanism:

[0006] Existing products mostly rely on predefined integration methods or manual configuration, lacking in-depth understanding of the API features of different cloud platforms and automatic adaptation capabilities.

[0007] In a multi-cloud environment, especially when different cloud service providers are involved, this approach cannot effectively address the differences and complexity between APIs, resulting in a cumbersome and error-prone integration process.

[0008] 2. Limited cross-platform capabilities:

[0009] While some tools claim to support multi-cloud environments, their actual effectiveness is often limited to basic monitoring and reporting capabilities.

[0010] These tools typically fail to provide advanced features optimized for specific cloud platforms, such as intelligent fault diagnosis and automated resource adjustments.

[0011] 3. Inefficient resource management and optimization:

[0012] Existing tools often adopt general approaches to resource management and optimization, and are unable to perform detailed optimization based on the unique characteristics and performance indicators of different cloud platforms.

[0013] This results in potentially suboptimal resource allocation, failing to fully leverage the features and strengths of each platform.

[0014] 4. User Experience and Operational Complexity

[0015] Managing multiple cloud platforms requires switching between different interfaces and tools, which increases operational complexity and learning costs.

[0016] Users are typically required to have specialized knowledge for each cloud platform, which can be a significant barrier for non-expert users.

[0017] In general, existing cloud service management tools have obvious shortcomings in the intelligent adaptation of heterogeneous cloud platforms in multi-cloud environments and cannot fully meet the growing needs of cross-cloud service management.

[0018] To this end, a cloud service management method and system based on cloud service adaptation algorithm are proposed. Summary of the Invention

[0019] In view of this, the embodiments of the present invention hope to provide a cloud service management method and system based on a cloud service adaptation algorithm to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0020] To solve the above technical problems, a technical solution adopted by this application is to provide a cloud service management method based on a cloud service adaptation algorithm, comprising the following steps:

[0021] S1. Training a cloud service management model based on a convolutional neural network to learn and identify features of different cloud platform APIs, wherein the cloud service management model is stored on a server;

[0022] S2. Detect whether there is an API call request. If there is an API call request, use the cloud service management model to perform feature recognition on the API call request to identify the cloud platform to which the current API call request belongs.

[0023] S3. Based on the recognition results, a decision tree is constructed. The decision tree selects the corresponding cloud platform adaptation strategy based on the prediction output of the cloud service management model.

[0024] S4. Execute the selected cloud platform adaptation strategy to adapt the new API call to the correct cloud platform.

[0025] As a further preferred embodiment of the present technical solution, before training the cloud service management model based on the convolutional neural network, the following steps are further included:

[0026] S01. Data preprocessing:

[0027] Collect API call data from multiple cloud platforms;

[0028] Standardize the data to make the data format consistent;

[0029] S02, Feature Extraction:

[0030] Apply the Text Frequency-Inverse Document Frequency (TF-IDF) technique to extract keywords from API documents as features;

[0031] In order to improve the processing efficiency and reduce the dimension of the feature vector, the principal component analysis (PCA) method is applied, which helps to improve the learning efficiency and accuracy of the subsequent model by eliminating redundant information and emphasizing key features.

[0032] As a further preferred embodiment of the present technical solution: the API call data includes an API endpoint, a request / response format and call parameters.

[0033] As a further preferred embodiment of the present technical solution, the training of the cloud service management model based on the convolutional neural network includes the following steps:

[0034] Use convolutional neural networks to conduct in-depth learning on the extracted features. CNN is particularly suitable for processing hierarchical data and can effectively identify patterns and associations in API features.

[0035] The cloud service management model structure includes:

[0036] An input layer (determined by the number of features), several convolutional layers, pooling layers, fully connected layers, and an output layer for the platform category of classification, such as Figure 3 The figure shows an example diagram of the deep neural network structure of the present invention.

[0037] As a further preferred embodiment of the present technical solution, the training of the cloud service management model based on the convolutional neural network further includes:

[0038] Build a decision tree and formulate a decision tree adaptation strategy based on the output of the cloud service management model (probability distribution of different platforms).

[0039] As a further preferred embodiment of the present technical solution: in the step S02, the following formula is used for feature extraction:

[0040]

[0041] Where t is the term, d is the document, N is the total number of documents, and DF(t) is the number of documents containing the term t.

[0042] As a further preferred embodiment of this technical solution: the output of the cloud service management model includes P AWS 、P Azure and P GCP;

[0043] Among them, P AWS 、P Azure and P GCP They represent the probability of each platform predicted by the cloud service management model;

[0044] The decision tree adaptation strategy includes:

[0045] If P AWS >P Azure And P AWS >P GCP , then select the AWS adaptation strategy;

[0046] If P GCP >P Azure And P GCP >P AWS , then select the GCP adaptation strategy;

[0047] If P Azure >P AWS And P Azure >P GCP , select the Azure adaptation policy.

[0048] To solve the above technical problems, another technical solution adopted by this application is: a cloud service management system based on a cloud service adaptation algorithm, comprising:

[0049] A data collection module, which is used to communicate with multiple cloud platform interfaces and collect data from API calls;

[0050] A data preprocessing module, which is used for feature extraction, model training, model storage, and model tuning;

[0051] A decision tree construction module, which is used to request the API service of the cloud platform in real time to obtain the current service status and configuration, and use the model trained by the preprocessing module to build a decision tree to select the most appropriate cloud service adaptation strategy for the API call;

[0052] The application scheduling module is used to convert intelligent decisions into actual API adaptation operations, so that API calls can be executed smoothly and are compatible with the target cloud service platform.

[0053] To solve the above technical problems, another technical solution adopted in this application is: a computer device, which includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of a cloud service management method and system based on a cloud service adaptation algorithm as described above.

[0054] In order to solve the above technical problems, another technical solution adopted in this application is: a storage medium storing program instructions that can implement a cloud service management method and system based on a cloud service adaptation algorithm as described above.

[0055] The embodiment of the present invention adopts the above technical solution, which has the following advantages:

[0056] 1. Highly automated adaptation process:

[0057] This invention automatically identifies the features of different cloud platform APIs through a deep learning model and constructs a decision tree to select the optimal adaptation strategy, reducing dependence on professional knowledge and manual configuration errors, significantly improving the efficiency and accuracy of the adaptation process, reducing the possibility of human error, and saving time and human resources.

[0058] 2. Intelligent resource management and optimization:

[0059] The present invention can intelligently manage and optimize the resources of different cloud platforms, understand the characteristics of each cloud service through a deep learning model, realize refined resource scheduling, improve resource utilization, reduce costs, and optimize the performance and stability of cloud services.

[0060] 3. Unified multi-cloud platform management:

[0061] The present invention provides a unified interface and framework for managing multiple cloud service providers, simplifies the complexity of cross-platform operations, improves user experience, reduces the requirements for operators, and reduces the complexity of learning and managing multiple cloud platforms.

[0062] 4. Continuous optimization and learning capabilities:

[0063] The algorithm model of the present invention has the ability of continuous learning, can continuously optimize the adaptation strategy according to new data, ensure synchronization with the API update of the cloud platform, ensure the long-term effectiveness of the adaptation algorithm, and improve the flexibility and future compatibility of adaptation decisions.

[0064] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0066] Figure 1 is a flow chart of the method of the present invention;

[0067] Figure 2 Schematic diagram of the system module of the present invention;

[0068] Figure 3 This is an example diagram of the deep neural network structure according to an embodiment of the present invention;

[0069] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0071] It should be clear that the following embodiments of the present disclosure are described through specific concrete examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0072] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this disclosure, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0073] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The illustrations only show components related to the present disclosure and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0074] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples. However, one skilled in the art will appreciate that the aspects described can be practiced without these specific details.

[0075] Figure 1 This is a flow chart of a cloud service management method based on a cloud service adaptation algorithm according to an embodiment of the present invention. It should be noted that if there are substantially the same results, the method of this application is not based on Figure 1 The process sequence shown is limited;

[0076] The core of this invention is the Intelligent Cloud Service Adaptation algorithm (ICSA), which aims to solve the key technical problems of existing cloud service management tools in multi-cloud environments.

[0077] The ICSA algorithm of the present invention directly addresses the shortcomings and defects of the existing technology and provides solutions, specifically including:

[0078] 1. Intelligent Adaptation of Heterogeneous Cloud Platforms:

[0079] Problem: Existing tools lack deep adaptation mechanisms for the API features of different cloud platforms.

[0080] ICSA solution: Through advanced deep learning technology, the ICSA algorithm can automatically identify and adapt to the specific API features of multiple cloud platforms, achieving intelligent adaptation and integration.

[0081] 2. Comprehensive cross-platform functionality:

[0082] Problem: Existing solutions are limited in cross-platform capabilities and cannot provide advanced features.

[0083] ICSA Solution: ICSA algorithm support is not limited to basic monitoring, but also includes optimized management and fault diagnosis for specific cloud platforms, providing comprehensive cloud service management capabilities.

[0084] 3. Efficient Management and Optimization of Cloud Resources

[0085] Problem: Inefficient resource management and optimization for multi-cloud environments.

[0086] ICSA solution: The ICSA algorithm allocates resources and optimizes performance based on the unique characteristics of each cloud platform, improving resource utilization efficiency and service performance.

[0087] 4. User experience and ease of operation:

[0088] Problem: It is complicated for users to switch between multiple platforms, and the platform is not user-friendly enough.

[0089] ICSA solution: Provides a unified user interface and simplified operation logic to reduce the user learning curve and make managing multi-cloud environments simple and easy.

[0090] More specifically, the present invention provides a cloud service management method based on a cloud service adaptation algorithm, the core of which includes:

[0091] A cloud service management model for learning and identifying different cloud platform API characteristics, such as request structure, response format, and parameter types;

[0092] Decision tree logic used to formulate intelligent adaptation strategies based on the output of the cloud service management model to achieve targeted resource management and scheduling.

[0093] The specific implementation includes the following steps:

[0094] S01. Data preprocessing:

[0095] Collect API call data from multiple cloud platforms, including API endpoints, request / response formats, and call parameters;

[0096] Standardize the data to make the data format consistent;

[0097] S02, Feature Extraction:

[0098] Apply the Text Frequency-Inverse Document Frequency (TF-IDF) technique to extract keywords from API documents as features;

[0099] In order to improve processing efficiency and reduce the dimension of feature vectors, the principal component analysis (PCA) method is applied, which helps to improve the learning efficiency and accuracy of subsequent models by eliminating redundant information and emphasizing key features;

[0100] S1. Training a cloud service management model based on a convolutional neural network to learn and identify features of different cloud platform APIs, wherein the cloud service management model is stored on a server;

[0101] Training a cloud service management model based on a convolutional neural network includes the following steps:

[0102] Use convolutional neural networks to conduct in-depth learning on the extracted features. CNN is particularly suitable for processing hierarchical data and can effectively identify patterns and associations in API features.

[0103] The cloud service management model structure includes:

[0104] An input layer (determined by the number of features), several convolutional layers, pooling layers, fully connected layers, and an output layer for platform categories for classification.

[0105] After the cloud service management model training is completed, the decision tree logic is constructed, including:

[0106] Build a decision tree and formulate a decision tree adaptation strategy based on the output of the cloud service management model (probability distribution of different platforms);

[0107] Furthermore, in step S02, the following formula is used for feature extraction:

[0108]

[0109] Where: t is a term, d is a document, N is the total number of documents, and DF(t) is the number of documents containing the term t;

[0110] The output of the cloud service management model includes P AWS 、P Azure and P GCP ;

[0111] Among them, P AWS 、P Azure and P GCP They represent the probability of each platform predicted by the cloud service management model;

[0112] The decision tree adaptation strategy includes:

[0113] If P AWS >P Azure And P AWS >P GCP , then select the AWS adaptation strategy;

[0114] If P GCP >P Azure And P GCP >P AWS , then select the GCP adaptation strategy;

[0115] If P Azure >P AWS And P Azure >P GCP , select the Azure adaptation policy.

[0116] In the above decision tree adaptation strategy, PAWS, PAzure, and PGCP represent the probabilities of each platform predicted by the cloud service management model, AWS represents the AWS platform, Azure represents the Azure platform, and similarly, GCP represents the GCP platform.

[0117] When other platforms are available, other platform codes can be selected according to actual conditions.

[0118] In summary, the algorithm training process of the present invention includes:

[0119] When the program starts, the required libraries and environment parameters are initialized.

[0120] Collect API call data from multiple cloud platforms, including API endpoints, request / response formats, call parameters, etc.

[0121] The collected data is preprocessed, including data cleaning and format standardization, to facilitate effective feature extraction.

[0122] The TF-IDF algorithm is applied to extract the key features of API data, and PCA technology is used to perform feature dimensionality reduction.

[0123] Using the reduced dimensionality features, a deep learning model, usually a convolutional neural network (CNN), is trained to identify and learn the characteristics of different cloud platform APIs.

[0124] The model parameters are optimized iteratively until the model performance reaches the predetermined standard.

[0125] After the model training is completed, the model is stored on a cloud server for subsequent use. The cloud server can be Amazon S3.

[0126] The use process includes the following steps:

[0127] S2. Detect whether there is an API call request. If there is an API call request, use the cloud service management model to perform feature recognition on the API call request to identify the cloud platform to which the current API call request belongs.

[0128] Right now:

[0129] The adaptation process for new API calls includes:

[0130] When a new API call is received, the program will load the previously trained model stored on Amazon S3.

[0131] The program uses this model to perform feature recognition on new API call data to determine which cloud platform it belongs to.

[0132] Based on the recognition results, the program constructs a decision tree, which selects the corresponding cloud platform adaptation strategy based on the model's predicted output.

[0133] The program executes the selected adaptation strategy to adapt the new API call to the correct cloud platform.

[0134] After the adaptation is completed, the program can perform further operations, such as calling APIs or performing data synchronization.

[0135] S3. Based on the recognition results, a decision tree is constructed. The decision tree selects the corresponding cloud platform adaptation strategy based on the prediction output of the cloud service management model.

[0136] In actual operation, testing and verification are also required:

[0137] In both processes, testing and validation are an ongoing step to ensure the accuracy and reliability of trained models and adaptation results of new API calls.

[0138] The program uses a predefined test set to evaluate the trained model to ensure that its adaptability meets actual needs.

[0139] Figure 2 This is a functional module diagram of a cloud service management system based on a cloud service adaptation algorithm according to an embodiment of the present application. Figure 2 As shown, the system of the present invention consists of four modules, each of which has specific tasks and functions. Through the collaborative work between the modules, a complete set of algorithm workflow is realized.

[0140] A data collection module, which is used to communicate with multiple cloud platform interfaces and collect data from API calls;

[0141] Function: This module is responsible for communicating with multiple cloud platforms and collecting API call data. This includes obtaining data from Amazon Cloud, Alibaba Cloud, Microsoft Cloud, Google Cloud, Huawei Cloud, and other private cloud platforms.

[0142] Function: It provides the system with the necessary raw data, which reflects the usage and performance indicators of each cloud service.

[0143] Connection relationship: The collected data will be passed to the data preprocessing module for further processing;

[0144] Improved the breadth and depth of data collected from multi-cloud environments, ensuring the comprehensiveness and diversity of data and providing richer information for subsequent processing.

[0145] A data preprocessing module, which is used for feature extraction, model training, model storage, and model tuning;

[0146] Function: It consists of multiple sub-modules, mainly including feature extraction, model training, model storage and model tuning.

[0147] Feature extraction: Analyze raw API data and extract features useful for model training.

[0148] Model training: Use the extracted features to train a deep learning model, such as a convolutional neural network.

[0149] Model storage: Save the trained model in an appropriate storage system for subsequent use.

[0150] Model tuning: Adjust and optimize the model based on its performance in actual applications.

[0151] Role: Ensure that data collected from various cloud platforms is correctly understood and transformed to make it suitable for intelligent decision-making and adaptation.

[0152] Connection relationship: The processed data and models will be used to build a decision tree to support the decision-making process of the application scheduling module;

[0153] Improved data quality through advanced feature extraction and intelligent data processing, providing more accurate input for model training;

[0154] Model training and storage module: An adaptive learning mechanism is introduced to ensure that the model is continuously optimized over time and adapts to changes in the cloud platform API.

[0155] A decision tree construction module, which is used to request the API service of the cloud platform in real time to obtain the current service status and configuration, and use the model trained by the preprocessing module to build a decision tree to select the most appropriate cloud service adaptation strategy for the API call;

[0156] Functions: Includes "requesting cloud API services" and "using models to build decision trees."

[0157] Request cloud API service: Responsible for real-time requesting the cloud platform's API service to obtain the current service status and configuration.

[0158] Use the model to build a decision tree: Use the model trained by the preprocessing module to build a decision tree to select the most appropriate cloud service adaptation strategy for API calls.

[0159] Function: Intelligently infer and select the optimal service adaptation strategy based on the current cloud service status and historical data patterns.

[0160] Connection relationship: The constructed decision tree will determine which adaptation strategy the application scheduling module selects and applies.

[0161] An application scheduling module, which is used to convert intelligent decisions into actual API adaptation operations, so that API calls can be successfully executed and compatible with the target cloud service platform;

[0162] Function: It consists of two parts: "Adaptation strategy selection" and "Adaptation strategy application".

[0163] Adaptation strategy selection: Select the most suitable adaptation strategy for the current situation based on the recommendation of the decision tree.

[0164] Adaptation strategy application: Apply the selected strategy to the actual cloud service management and adapt the API call.

[0165] Function: This module is responsible for converting intelligent decisions into actual API adaptation operations, ensuring that API calls can be executed smoothly and are compatible with the target cloud service platform.

[0166] Connection relationship: The adaptation results of this module will be fed back to the data collection module, forming a closed loop to continuously optimize system performance;

[0167] The decision tree construction and application scheduling module adopts a data-driven decision tree, which improves the intelligence and accuracy of the adaptation strategy and reduces the risk of resource misconfiguration and waste.

[0168] The working principle of the intelligent cloud service adaptation algorithm (ICSA) of the present invention is to automatically perform data collection, preprocessing, model training and selection and application of adaptation strategies through a series of carefully designed program modules. First, the data collection module obtains API call data from each cloud platform. Then, the data preprocessing module cleans and standardizes these data and extracts key features. Next, the model training module uses these features to train a deep learning model that can identify the API features of each cloud platform and adapt itself. The trained model is stored in the model storage module and continuously optimized by the model tuning module. The decision tree construction module uses the stored model to select the best adaptation strategy for the new API call. Finally, the application scheduling module is responsible for executing these strategies to ensure that the API call can be correctly adapted to the corresponding cloud service.

[0169] For other details about the technical solutions for implementing each module in the system of the above embodiment, please refer to the description of a cloud service management method and system based on a cloud service adaptation algorithm in the above embodiment, which will not be repeated here.

[0170] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For system-related embodiments, since they are generally similar to method-related embodiments, their description is relatively simple. For relevant details, refer to the description of the method-related embodiments.

[0171] An electronic device according to an embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0172] The processor may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of the present disclosure, the processor is configured to execute the computer-readable instructions stored in the memory, causing the electronic device to execute all or part of the steps of the aforementioned cloud service management method based on a cloud service adaptation algorithm and its system in each embodiment of the present disclosure.

[0173] Those skilled in the art should understand that in order to solve the technical problem of how to obtain a good user experience, this embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the scope of protection of this disclosure.

[0174] like Figure 4 The present invention provides a schematic diagram of the structure of an electronic device according to an embodiment of the present invention, which is suitable for implementing the electronic device according to an embodiment of the present invention. Figure 4 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0175] like Figure 4 As shown, the electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0176] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as tapes and hard disks; and communication devices. The communication device allows the electronic device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data. Figure 4 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0177] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by the processor, all or part of the steps of a cloud service management method based on a cloud service adaptation algorithm and its system of the embodiment of the present disclosure are executed.

[0178] The program code implementation includes:

[0179]

[0180]

[0181] For detailed description of this embodiment, please refer to the corresponding description in the aforementioned embodiments, which will not be repeated here.

[0182] According to an embodiment of the present disclosure, a computer-readable storage medium stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the cloud service management method and system based on a cloud service adaptation algorithm described in each embodiment of the present disclosure are executed.

[0183] The above-mentioned computer-readable storage media include, but are not limited to, optical storage media (e.g., CD-ROMs and DVDs), magneto-optical storage media (e.g., MOs), magnetic storage media (e.g., magnetic tapes or mobile hard disks), media with built-in rewritable non-volatile memory (e.g., memory cards), and media with built-in ROM (e.g., ROM cartridges).

[0184] For detailed description of this embodiment, please refer to the corresponding description in the aforementioned embodiments, which will not be repeated here.

[0185] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0186] In the present disclosure, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "including," "comprising," "having," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0187] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0188] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0189] Various changes, substitutions, and modifications may be made to the technology described herein without departing from the teachings defined by the appended claims. Moreover, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of things, means, methods, and actions described above. Currently existing or later developed processes, machines, manufactures, compositions of things, means, methods, or actions that perform substantially the same function or achieve substantially the same results as the corresponding aspects described herein may be utilized. Accordingly, the appended claims include within their scope such processes, machines, manufactures, compositions of things, means, methods, or actions.

[0190] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0191] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A cloud service management method based on a cloud service adaptation algorithm, characterized in that: The following steps are involved: S1. Training a cloud service management model based on a convolutional neural network to learn and identify features of different cloud platform APIs, wherein the cloud service management model is stored on a server; S2. Detect whether there is an API call request. If there is an API call request, use the cloud service management model to perform feature recognition on the API call request to identify the cloud platform to which the current API call request belongs. S3. Based on the recognition results, a decision tree is constructed. The decision tree selects the corresponding cloud platform adaptation strategy based on the prediction output of the cloud service management model. S4. Execute the selected cloud platform adaptation strategy to adapt the new API call to the correct cloud platform.

2. A cloud service management method based on a cloud service adaptation algorithm according to claim 1, characterized in that: Before training the cloud service management model based on the convolutional neural network, the following steps are also included: S01. Data preprocessing: Collect API call data from multiple cloud platforms; Standardize the data to make the data format consistent; S02, Feature Extraction: Apply the text frequency-inverse document frequency technique to extract keywords from API documents as features; The principal component analysis method was applied to eliminate redundant information and emphasize key features.

3. A cloud service management method based on a cloud service adaptation algorithm according to claim 2, characterized in that: The API call data includes API endpoint, request / response format and call parameters.

4. A cloud service management method based on a cloud service adaptation algorithm according to claim 2, characterized in that: The training of the cloud service management model based on the convolutional neural network includes the following steps: Use convolutional neural network to conduct in-depth learning on the extracted features; The cloud service management model structure includes: An input layer, several convolutional layers, pooling layers, fully connected layers, and an output layer for platform categories for classification.

5. A cloud service management method based on a cloud service adaptation algorithm according to claim 4, characterized in that: The training of the cloud service management model based on the convolutional neural network also includes: Build a decision tree and formulate a decision tree adaptation strategy based on the output of the cloud service management model.

6. A cloud service management method based on a cloud service adaptation algorithm according to claim 2, characterized in that: In step S02, the following formula is used for feature extraction: Where t is the term, d is the document, N is the total number of documents, and DF(t) is the number of documents containing the term t.

7. A cloud service management method based on a cloud service adaptation algorithm according to claim 5, characterized in that: The output of the cloud service management model includes P AWS 、P Azure and P GCP ; Among them, P AWS 、P Azure and P GCP They represent the probability of each platform predicted by the cloud service management model; The decision tree adaptation strategy includes: If P AWS >P Azure And P AWS >P GCP , then select the AWS adaptation strategy; If P GCP >P Azure And P GCP >P AWS , then select the GCP adaptation strategy; If P Azure >P AWS And P Azure >P GCP , select the Azure adaptation policy.

8. A cloud service management system based on a cloud service adaptation algorithm, characterized in that: include: A data collection module, which is used to communicate with multiple cloud platform interfaces and collect data from API calls; A data preprocessing module, which is used for feature extraction, model training, model storage, and model tuning; A decision tree construction module, which is used to request the API service of the cloud platform in real time to obtain the current service status and configuration, and use the model trained by the preprocessing module to build a decision tree to select the most appropriate cloud service adaptation strategy for the API call; The application scheduling module is used to convert intelligent decisions into actual API adaptation operations, so that API calls can be executed smoothly and are compatible with the target cloud service platform.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the cloud service management method based on the cloud service adaptation algorithm described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute a cloud service management method based on a cloud service adaptation algorithm as described in any one of claims 1-7.

Images