Cloud platform service quality detection method, device, equipment and storage medium

Abstract

The present application provides a cloud platform service quality detection method, apparatus, equipment and storage medium. The method determines all cloud platforms that meet the cloud service type in a consortium chain according to the cloud service type and obtains cloud platform information; obtains cloud platform usage records in the consortium chain, and determines the cloud platform's historical users based on the usage records; initiates a request to obtain usage satisfaction information from the cloud platform's historical users; receives the usage satisfaction information, and publishes an artificial intelligence training white paper in the consortium chain; after receiving a detection model sent by at least one artificial intelligence model party, performs model verification on the detection model, and determines a target detection model based on the verification results.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a cloud platform service quality detection method, device, equipment and storage medium. Background Art

[0002] In cloud computing environments, cloud storage offers numerous advantages, including large capacity and superior performance. The complexity and uncertainty introduced by global participation in cloud computing further amplify the importance and urgency of research into accounting for cloud-based transaction payments. As a distributed shared ledger and database, blockchain, with its decentralized, tamper-proof, fully traceable, traceable, collectively maintained, and transparent nature, holds promise for addressing the challenges of building a decentralized, tamper-resistant, and traceable, efficient, and trustworthy accounting technology for cloud computing.

[0003] At present, when cloud platform users use the resources provided by cloud platform operators, most of them screen them based on the cloud platform operators' resource acceptance capabilities and price information.

[0004] However, the existing technology lacks a service quality detection method for cloud platforms, and the credibility and reliability of cloud service use are low. Summary of the Invention

[0005] The present application provides a cloud platform service quality detection method, device, equipment and storage medium to solve the technical problems that the existing technology lacks a service quality detection method for cloud platforms and the credibility and reliability of cloud services are low.

[0006] In the first aspect, this application provides a cloud platform service quality detection method, which is applied to the initiator of the detection model establishment, including:

[0007] According to the cloud service type, all cloud platforms that meet the cloud service type are determined in the alliance chain, and cloud platform information is obtained, wherein the cloud platform information includes the cloud platform identification number, the cloud platform basic information set, the cloud platform usage record fault data set and the cloud platform fault repair solution set;

[0008] Obtaining cloud platform usage records in the alliance chain, and determining historical users of the cloud platform based on the usage records;

[0009] Initiate a usage satisfaction information acquisition request to the historical user of the cloud platform, so that the historical user of the cloud platform sends the usage satisfaction information to the detection model establishment initiator after obtaining the usage satisfaction information acquisition request, wherein the satisfaction information includes a homomorphic encryption public key and a satisfaction result encrypted by the homomorphic encryption key of the historical user of the cloud platform;

[0010] Receive the usage satisfaction information, publish an artificial intelligence training white paper in the alliance chain, so that at least one artificial intelligence model party signed in the alliance chain performs artificial intelligence training according to the artificial intelligence training white paper, and sends the trained detection model to the detection model establishment initiator, wherein the artificial intelligence training white paper includes a basic information set corresponding to the cloud platform, a cloud platform usage record fault data set, a cloud platform fault repair solution set, a collection of the satisfaction information, and a preset training acceptance target;

[0011] After receiving the detection model sent by at least one of the artificial intelligence models, the detection model is verified and the target detection model is determined based on the verification result.

[0012] Here, the present application provides a method capable of evaluating and detecting the service quality of a cloud platform. A target detection model for the service quality of a cloud platform is established based on artificial intelligence (AI) and blockchain. Multiple historical users of cloud platforms and multiple cloud platform operators can jointly build a consortium chain. The initiator of establishing the detection model in the consortium chain determines the cloud platform that meets the cloud service type. Based on the historical usage of the cloud platform, combined with AI technology, a target detection model capable of evaluating satisfaction is established. In order to improve data security and prevent satisfaction information from being tampered with, when obtaining usage satisfaction information in historical data, the historical users of the cloud platform in the consortium chain encrypt the usage satisfaction information in advance using their own homomorphic keys. The target detection model is established with high security and accuracy, and can accurately evaluate the service quality of the cloud platform, thereby improving the credibility and reliability of cloud service usage.

[0013] Optionally, performing model verification on the detection model includes:

[0014] According to the cloud platform usage record, first data to be verified is determined, wherein the first data to be verified includes first data to be input and a first result to be verified; the first data to be input is input into the detection model for prediction to obtain a first prediction result; the first prediction result is homomorphically compared with the first result to be verified to determine a verification result.

[0015] Here, after receiving the detection model sent by one or more artificial intelligence model parties, this application can verify the prediction effect of the detection model based on historical data, so as to determine whether the prediction of the detection model is accurate, thereby further improving the accuracy of the cloud platform service quality detection method.

[0016] Optionally, determining the target detection model according to the verification result includes:

[0017] Obtain multiple verification results of the detection model; and determine the target detection model based on the pass rate of the verification results.

[0018] Here, this application determines whether the model can be used as the target detection model for cloud platform service quality detection through the prediction pass rate of the detection model. The higher the pass rate, the higher the accuracy of the detection model, which further improves the accuracy of the cloud platform service quality detection method.

[0019] Optionally, after receiving the detection model sent by at least one of the artificial intelligence models, performing model verification on the detection model, and determining the target detection model based on the verification result, it also includes: obtaining cloud platform information of the cloud platform to be evaluated; inputting the cloud platform information into the target detection model to obtain predicted satisfaction information for the cloud platform to be evaluated.

[0020] Here, the present application can realize the satisfaction detection of the cloud platform to be evaluated that needs to be detected through the target detection model, thereby facilitating users to use cloud platform resources more reliably, and further improving the credibility and reliability of cloud service use.

[0021] Optionally, after receiving the detection model sent by at least one of the artificial intelligence model parties, performing model verification on the detection model, and determining the target detection model based on the verification result, it also includes: determining the second data to be verified based on the cloud platform usage record, wherein the second data to be verified includes the second data to be input and the second result to be verified; removing the verification item data from the second data to be input to obtain the third data to be input; inputting the third data to be input into the detection model for prediction to obtain the second prediction result; performing a homomorphic comparison between the second prediction result and the second result to be verified, and determining the degree of influence of the verification item data on the cloud platform satisfaction based on the comparison result.

[0022] Here, the present application can also eliminate verification item data and input the eliminated data into the target detection model to determine whether the verification item data affects the satisfaction of cloud service users and the extent of the impact, thereby facilitating understanding of various indicators of cloud services and further improving user experience.

[0023] Optionally, the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain or an operator of the cloud platform in the alliance chain.

[0024] Here, the historical users of the cloud platform in the alliance chain or the cloud platform operators in the alliance chain can both conduct service quality inspections on the cloud platform as the cloud platform operator and initiate the establishment of target detection models to meet the needs of different nodes and different users, further improving the user experience.

[0025] Optionally, if the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain, then before determining all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtaining the cloud platform information, it also includes: uploading the desensitized cloud platform usage log in the alliance chain.

[0026] Here, historical users of the cloud platform in the alliance chain desensitize their cloud platform usage logs and upload them to the alliance chain. On the one hand, this protects the security and privacy of user data, and on the other hand, historical data facilitates service quality testing of the cloud platform.

[0027] Optionally, if the initiator of establishing the detection model is a cloud platform operator in the alliance chain, then before determining all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtaining cloud platform information, the process further includes:

[0028] Obtain cloud platform usage records in the alliance chain;

[0029] The cloud platform usage record is verified for correctness.

[0030] Here, the cloud platform operator can perform correctness verification on the cloud platform usage records sent by the cloud platform users, ensuring the accuracy of the data and further improving the credibility and reliability of cloud service use.

[0031] In a second aspect, the present application provides a cloud platform service quality detection device, which is applied to the initiator of the detection model establishment, including:

[0032] A first acquisition module is configured to determine, based on the cloud service type, all cloud platforms that meet the cloud service type in the consortium chain and obtain cloud platform information, wherein the cloud platform information includes an identification number of the cloud platform, a basic information set of the cloud platform, a cloud platform usage record fault data set, and a cloud platform fault repair solution set;

[0033] A second acquisition module is used to obtain cloud platform usage records in the alliance chain and determine the historical users of the cloud platform based on the usage records;

[0034] An initiating module, configured to initiate a usage satisfaction information acquisition request to the historical user of the cloud platform, so that the historical user of the cloud platform sends the usage satisfaction information to the detection model establishment initiator after obtaining the usage satisfaction information acquisition request, wherein the satisfaction information includes a homomorphic encryption public key and a satisfaction result encrypted by the homomorphic encryption key of the historical user of the cloud platform;

[0035] A publishing module is configured to receive the usage satisfaction information and publish an artificial intelligence training white paper in the alliance chain, so that at least one artificial intelligence model party signed in the alliance chain performs artificial intelligence training according to the artificial intelligence training white paper, and sends the trained detection model to the detection model establishment initiator, wherein the artificial intelligence training white paper includes a basic information set corresponding to the cloud platform, a cloud platform usage record fault data set, a cloud platform fault repair solution set, a collection of the satisfaction information, and a preset training acceptance target;

[0036] The model determination module is used to perform model verification on the detection model after receiving the detection model sent by at least one of the artificial intelligence models, and determine the target detection model according to the verification result.

[0037] Optionally, the model determination module is specifically configured to:

[0038] Determining first data to be verified based on the cloud platform usage record, wherein the first data to be verified includes first data to be input and a first result to be verified;

[0039] Inputting the first data to be input into the detection model for prediction to obtain a first prediction result;

[0040] The first prediction result is homomorphically compared with the first result to be verified to determine a verification result.

[0041] Optionally, the model determination module is further specifically configured to:

[0042] Obtain multiple verification results of the detection model;

[0043] The target detection model is determined based on the pass rate of the verification results.

[0044] Optionally, after the model determination module receives the detection model sent by the at least one artificial intelligence model party, it performs model verification on the detection model, and determines the target detection model according to the verification result. The above-mentioned device further includes a detection module for:

[0045] Obtain the cloud platform information of the cloud platform to be evaluated;

[0046] The cloud platform information is input into the target detection model to obtain predicted satisfaction information of the cloud platform to be evaluated.

[0047] Optionally, after the model determination module receives the detection model sent by the at least one artificial intelligence model party, performs model verification on the detection model, and determines the target detection model according to the verification result, the above-mentioned device further includes a verification item data determination module, which is used to:

[0048] Determining second data to be verified based on the cloud platform usage record, wherein the second data to be verified includes second data to be input and a second result to be verified;

[0049] Eliminating the verification item data from the second data to be input to obtain third data to be input;

[0050] Inputting the third data to be input into the detection model for prediction to obtain a second prediction result;

[0051] Perform a homomorphic comparison between the second prediction result and the second result to be verified, and determine the degree of influence of the verification item data on the cloud platform satisfaction based on the comparison result.

[0052] Optionally, the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain or an operator of the cloud platform in the alliance chain.

[0053] Optionally, if the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain, then before the first acquisition module determines all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtains the cloud platform information, the above-mentioned device further includes an uploading module for:

[0054] Upload the desensitized cloud platform usage logs in the alliance chain.

[0055] Optionally, if the initiator of establishing the detection model is a cloud platform operator in the alliance chain, then before the first acquisition module determines all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtains the cloud platform information, the above-mentioned device further includes a verification module for:

[0056] Obtain cloud platform usage records in the alliance chain;

[0057] The cloud platform usage record is verified for correctness.

[0058] In a third aspect, the present application provides a cloud platform service quality detection device, comprising: at least one processor and a memory;

[0059] The memory stores computer-executable instructions;

[0060] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the cloud platform service quality detection method described in the first aspect and various possible designs of the first aspect.

[0061] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer execution instructions. When the processor executes the computer execution instructions, it implements the cloud platform service quality detection method described in the first aspect and various possible designs of the first aspect.

[0062] In a fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the cloud platform service quality detection method described in the first aspect and various possible designs of the first aspect.

[0063] The cloud platform service quality detection method, device, equipment and storage medium provided in the present application, wherein the method establishes a target detection model for the cloud platform service quality based on AI and blockchain, multiple cloud platform historical users and multiple cloud platform operators can jointly build a consortium chain, and the initiator of the detection model establishment in the consortium chain determines the cloud platform that meets the cloud service type, and establishes a target detection model capable of evaluating satisfaction based on the historical usage of the cloud platform in combination with AI technology. In order to improve data security and prevent satisfaction information from being tampered with, when obtaining usage satisfaction information in historical data, the historical users of the cloud platform in the consortium chain encrypt the usage satisfaction information in advance with their own homomorphic keys. The target detection model is established with high security and accuracy, and can accurately evaluate the service quality of the cloud platform, thereby improving the credibility and reliability of cloud service use. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] 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 the description of the prior art. 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 labor.

[0065] Figure 1 A schematic diagram of the cloud platform service quality detection system architecture provided in an embodiment of the present application;

[0066] Figure 2 A flowchart of a cloud platform service quality detection method provided in an embodiment of the present application;

[0067] Figure 3 A schematic diagram of a detection model training process provided in an embodiment of the present application;

[0068] Figure 4 A schematic diagram of the structure of a cloud platform service quality detection device provided in an embodiment of the present application;

[0069] Figure 5A schematic diagram of the structure of a cloud platform service quality detection device provided in an embodiment of the present application.

[0070] The above drawings illustrate specific embodiments of the present disclosure, which will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the present disclosure in any way, but rather to illustrate the concepts of the present disclosure to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0071] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0072] The terms "first," "second," "third," and "fourth," etc., as used in the specification and claims of the present application and in the accompanying drawings, if any, are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products, or apparatus.

[0073] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0074] A consortium blockchain is an inter-institutional blockchain. It targets members of a specific group and a limited number of third parties. It designates multiple pre-selected nodes as bookkeepers, and the generation of each block is determined by all pre-selected nodes. Consortium chains can be applied to cloud service systems.

[0075] Many cloud service consumers worry not only that a single cloud service provider will hinder migration due to service outages or business discontinuity, but also that "platform lock-in" poses further risks. To ensure the openness and fairness of cloud service providers and to ensure the healthy development and operation of cloud platforms, cloud platform users currently lack reliable user reviews and analysis of their chosen cloud platforms. This hinders users from selecting a reliable cloud platform service from a wide variety of cloud platform offerings. Existing technologies lack methods for measuring the quality of cloud platform services, resulting in low trust and reliability in the use of cloud services.

[0076] In order to solve the above technical problems, the embodiments of the present application provide a cloud platform service quality detection method, device, equipment and storage medium. The method establishes a target detection model for the cloud platform service quality based on AI and blockchain. Multiple cloud platform historical users and multiple cloud platform operators can jointly build an alliance chain. The initiator of the detection model establishment in the alliance chain determines the cloud platform that meets the cloud service type, and based on the historical usage of the cloud platform, combines AI technology to establish a target detection model that can evaluate satisfaction. In order to improve data security and prevent satisfaction information from being tampered with, when obtaining usage satisfaction information in historical data, the historical users of the cloud platform in the alliance chain encrypt the usage satisfaction information in advance using their own homomorphic keys.

[0077] Optionally, Figure 1 This is a schematic diagram of a cloud platform service quality detection system architecture provided by the embodiment of this application. Figure 1 As shown, the above architecture includes: a first cloud platform user 101, a first cloud platform operator 102, a second cloud platform user 103, a second cloud platform operator 104, a first artificial intelligence model party 105 and a second artificial intelligence model party 106.

[0078] Among them, the first cloud platform user 101, the first cloud platform operator 102, the second cloud platform user 103, the second cloud platform operator 104, the first artificial intelligence model party 105 and the second artificial intelligence model party 106 are all connected to the same alliance chain and are all nodes in the alliance chain. Any two nodes can communicate through the alliance chain or other communication methods.

[0079] It is understandable that the number and specific structure of the above-mentioned cloud platform users, cloud platform operators and artificial intelligence model parties can be determined according to actual circumstances. Figure 1 This is for illustration only, and the embodiments of the present application do not impose any specific limitation on the number of the above nodes.

[0080] The above-mentioned cloud platform users, cloud platform operators and artificial intelligence model parties can be cloud servers, servers or terminal devices, etc. Any two nodes can communicate through the blockchain\alliance chain network.

[0081] Among them, the above-mentioned cloud platform users, cloud platform operators and artificial intelligence model parties can be set on servers or terminal devices, and the above-mentioned cloud platform users, cloud platform operators and artificial intelligence model parties can also be the servers or terminal devices themselves.

[0082] Optionally, in an embodiment of the present application, multiple cloud platform historical users and multiple cloud platform operators jointly build an alliance chain.

[0083] Optionally, the specific method of building a consortium chain is as follows: each historical user of the cloud platform uploads his or her cloud platform information, such as cloud platform usage logs (especially logs of platform failures, disconnections, etc.), after desensitizing (for example, removing user identity-related information such as name, address, ID number, etc.) and using a private key signed broadcast message to the consortium chain.

[0084] Optionally, the historical usage records of each cloud platform have a unique identifier in the alliance chain, and at least include the basic information set XA of the cloud platform, the cloud platform usage record fault data set XB, and the cloud platform fault repair solution set XC. The XA, XB, and XC data are saved in plain text in the blockchain\alliance chain.

[0085] The basic information set XA of the cloud platform includes information such as storage capacity, charging standards, equipment service life, security service level such as firewall type or compensation standards for information leakage.

[0086] The cloud platform usage record failure dataset XB includes log data such as the total usage time, the time when the platform failure occurred, and the failure repair time. The log data is provided to avoid hacker operations such as discrediting other cloud platforms.

[0087] Among them, Yunping fault repair solution set XC includes the failure causes, repair methods, compensation standards, etc. of cloud platform services.

[0088] Optionally, all participants in the consortium chain can view cloud platform information, such as XA, XB, and XC. This prevents malicious hackers from tampering with information by posing as historical users of a particular cloud platform, potentially leading to unhealthy competition between cloud platforms. Therefore, all broadcasted cloud platform information can be verified by each cloud platform operator against records related to their own cloud platform identifiers to confirm the authenticity of the broadcasted information.

[0089] Alternatively, to avoid the data ownership and management issues associated with fully public access to all cloud platform user information, the final satisfaction information Y used by the cloud platform is held by the cloud platform user and not fully disclosed on the blockchain. When someone needs to view it, they pay a corresponding query fee on the blockchain to obtain the homomorphically encrypted information and homomorphic public key corresponding to Y. Homomorphic comparisons can be performed, but the original text of the final satisfaction information Y used by the cloud platform cannot be decrypted.

[0090] Alternatively, any participant in the consortium chain (be it a cloud platform operator or a cloud platform user) can initiate AI training on the blockchain for cloud platform services that meet certain specific requirements, thereby obtaining a trained object detection model. The obtained object detection model can be used to predict the use of a new cloud platform or analyze key influencing factors.

[0091] It is understood that the structure illustrated in the embodiments of this application does not constitute a specific limitation on the architecture of the cloud platform service quality detection system. In other feasible implementations of this application, the above architecture may include more or fewer components than shown in the figure, or combine or split certain components, or arrange the components differently. The specific configuration can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0092] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0093] The technical solution of the present application is described below using several embodiments as examples, and the same or similar concepts or processes may not be repeated in some embodiments.

[0094] Figure 2 A flow chart of a cloud platform service quality detection method provided in an embodiment of the present application, wherein the execution subject of the embodiment of the present application is the initiator of establishing the detection model, and the initiator of establishing the detection model can be Figure 1 The specific execution subject can be determined according to the actual application scenario. Figure 2 As shown, the method includes the following steps:

[0095] S201: According to the cloud service type, determine all cloud platforms that meet the cloud service type in the alliance chain and obtain cloud platform information.

[0096] The cloud platform information includes the cloud platform identification number, the cloud platform basic information set, the cloud platform usage record fault data set, and the cloud platform fault repair solution set.

[0097] The basic information set XA of the cloud platform includes information such as storage capacity, charging standards, equipment service life, security service level such as firewall type or compensation standards for information leakage.

[0098] The cloud platform usage record failure dataset XB includes log data such as the total usage time, the time when the platform failure occurred, and the failure repair time. The log data is provided to avoid hacker operations such as discrediting other cloud platforms.

[0099] Among them, Yunping fault repair solution set XC includes the failure causes, repair methods, compensation standards, etc. of cloud platform services.

[0100] Optionally, cloud platform information of the cloud platform is filtered according to the cloud service type to obtain cloud platforms that meet the cloud service type.

[0101] Optionally, determine the type of cloud platform service you wish to select and search the consortium chain for relevant cloud platform information. For example, to analyze cloud platform usage services that meet a certain storage capacity requirement, use the relevant keywords to obtain the identification numbers of all cloud platforms that meet the aforementioned criteria: C1, C2, C3, etc., as well as the XA, XB, and XC information of the relevant cloud platforms. Optionally, the cloud platform to be screened is the cloud platform operator.

[0102] Optionally, the cloud service type may be input by the user.

[0103] Optionally, the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain or an operator of the cloud platform in the alliance chain.

[0104] Optionally, if the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain, then before determining all cloud platforms that meet the cloud service type in the alliance chain based on the cloud service type and obtaining the cloud platform information, it also includes: uploading the desensitized cloud platform usage log in the alliance chain.

[0105] Here, historical users of the cloud platform in the alliance chain desensitize their cloud platform usage logs and upload them to the alliance chain. On the one hand, this protects the security and privacy of user data, and on the other hand, historical data facilitates service quality testing of the cloud platform.

[0106] Optionally, if the initiator of establishing the detection model is a cloud platform operator in the alliance chain, then before determining all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtaining the cloud platform information, the following steps are further included:

[0107] Obtain cloud platform usage records in the alliance chain; verify the correctness of cloud platform usage records.

[0108] Here, the cloud platform operator can perform correctness verification on the cloud platform usage records sent by the cloud platform users, ensuring the accuracy of the data and further improving the credibility and reliability of cloud service use.

[0109] S202: Obtain the cloud platform usage record in the alliance chain, and determine the historical users of the cloud platform based on the usage record.

[0110] Among them, historical users of the cloud platform are cloud platform users who have used cloud platform resources before.

[0111] Optionally, there may be one or more cloud platforms, and historical users of the cloud platforms are determined for each cloud platform.

[0112] S203: Initiate a usage satisfaction information acquisition request to the historical users of the cloud platform, so that the historical users of the cloud platform send the usage satisfaction information to the detection model establishment initiator after obtaining the usage satisfaction information acquisition request.

[0113] Among them, the satisfaction information includes the homomorphic encryption public key and the satisfaction result encrypted by the homomorphic encryption key of the historical user of the cloud platform.

[0114] Optionally, in the alliance chain, relevant fees are paid to historical users of the cloud platform for the cloud platform usage records. The historical users of the cloud platform encrypt C1, C2, C3, etc. of the cloud platforms they have used and the corresponding cloud platform usage satisfaction results Y1, Y2, Y3, etc. with their own homomorphic encryption keys and send them together with the homomorphic encryption public key to the initiator of the detection model establishment.

[0115] S204: Receive usage satisfaction information and publish an artificial intelligence training white paper in the alliance chain, so that at least one artificial intelligence model party signed in the alliance chain can perform artificial intelligence training according to the artificial intelligence training white paper, and send the trained detection model to the detection model establishment initiator.

[0116] Among them, the artificial intelligence training white paper includes the basic information set corresponding to the cloud platform, the cloud platform usage record fault data set, the cloud platform fault repair solution set, the collection of satisfaction information and the preset training acceptance goals.

[0117] Optionally, a white paper on AI training is published in the consortium chain, including the corresponding XA, XB, XC sets and the homomorphically encrypted Y set, and includes the corresponding training costs and training acceptance targets.

[0118] Optionally, the utilization rate of a preset specific number of cloud platforms is determined as the acceptance target. The preset specific number can be determined according to actual conditions and is not specifically limited in this embodiment of the present application.

[0119] Optionally, AI model parties, such as AI Big Model A or AI Big Model B, can sign contracts in the alliance chain to conduct AI training. Figure 3 A schematic diagram of a detection model training process provided in an embodiment of the present application is provided. The cloud platform usage data included in the artificial intelligence training white paper is preprocessed. The data includes a basic information set XA of the cloud platform, a cloud platform usage record fault data set XB, a cloud platform fault repair solution set XC, and a corresponding result set Y. After preprocessing, the data is input into a preset model. The preset model can output a prediction result Y'. By performing a homomorphic comparison between Y' and Y, the parameter adjustment can be determined to obtain a detection model. This model can be used for prediction of newly used cloud platforms.

[0120] Optionally, the preset model can be determined according to actual conditions, and the embodiments of the present application do not impose specific restrictions on this. For example, the preset model can adopt the dense Transformer GPT3 model, Pangu model, or other DALL-E, etc., or a sparse MOD Transformer model such as V-MOE.

[0121] Optionally, multiple AI model parties can sign contracts simultaneously, and the party that submits the target detection model that meets the standards first, or the party that is close to the acceptance target, will receive the relevant reward fees.

[0122] S205: After receiving the detection model sent by at least one artificial intelligence model party, perform model verification on the detection model and determine the target detection model based on the verification result.

[0123] Optionally, perform model validation on the detection model, including:

[0124] According to the cloud platform usage record, the first data to be verified is determined, wherein the first data to be verified includes the first data to be input and the first result to be verified; the first data to be input is input into the detection model for prediction to obtain a first prediction result; the first prediction result is homomorphically compared with the first result to be verified to determine the verification result.

[0125] For example, the first data to be verified includes a set of historical cloud platform information and the satisfaction results corresponding to the cloud platform information, namely, the first input data and the first verification result. The first input data is input into the detection model for prediction to obtain a first prediction result. The first prediction result is then homomorphically compared with the first verification result to determine whether the detection model's prediction is accurate.

[0126] Optionally, after receiving the detection model sent by one or more artificial intelligence model parties, the embodiment of the present application can verify the prediction effect of the detection model based on historical data, so as to determine whether the prediction of the detection model is accurate, thereby further improving the accuracy of the cloud platform service quality detection method.

[0127] Optionally, after receiving the detection model sent by at least one artificial intelligence model party, the detection model is verified, and after determining the target detection model based on the verification result, it also includes: determining the second data to be verified based on the cloud platform usage record, wherein the second data to be verified includes the second data to be input and the second result to be verified; removing the verification item data from the second data to be input to obtain the third data to be input; inputting the third data to be input into the detection model for prediction to obtain the second prediction result; performing a homomorphic comparison between the second prediction result and the second result to be verified, and determining the degree of influence of the verification item data on the cloud platform satisfaction based on the comparison result.

[0128] Here, the embodiment of the present application can also eliminate the verification item data and input the eliminated data into the target detection model to determine whether the verification item data affects the satisfaction of cloud service users and the extent of the impact, which facilitates understanding of various indicators of cloud services and further improves user experience.

[0129] Optionally, determining a target detection model based on the verification result includes:

[0130] Obtain multiple verification results of the detection model; and determine the target detection model based on the pass rate of the verification results.

[0131] Optionally, the embodiment of the present application determines whether the model can be used as a target detection model for cloud platform service quality detection by the predicted pass rate of the detection model. The higher the pass rate, the higher the accuracy of the detection model, further improving the accuracy of the cloud platform service quality detection method.

[0132] Optionally, after receiving the detection model sent by at least one artificial intelligence model party, performing model verification on the detection model, and determining the target detection model based on the verification results, it also includes: obtaining the cloud platform information of the cloud platform to be evaluated; inputting the cloud platform information into the target detection model to obtain the predicted satisfaction information of the cloud platform to be evaluated.

[0133] Here, the embodiment of the present application can realize the satisfaction detection of the cloud platform to be evaluated that needs to be detected through the target detection model, thereby facilitating users to use cloud platform resources more reliably, and further improving the credibility and reliability of cloud service use.

[0134] In one possible implementation, a target detection model is obtained by initiating training through the consortium chain. This model can then be used for specialized analysis, such as analyzing which types of cloud platform detection items are key factors for high customer satisfaction. The specific solution is as follows:

[0135] Collect a certain amount of cloud platform service records. Based on the information XA, XB, and XC recorded for each cloud platform, use the target detection model to predict Y'. Compare the probability that Y' is the same as Y. Under normal circumstances, the success rate should exceed the target value set during training. This target value can be determined based on actual conditions.

[0136] Optionally, when testing whether a certain detection item XBn seriously affects user satisfaction, remove the XBn item in XB in all user usage records, and then use the target detection model to predict the result Y'. If the success probability of Y' is similar to Y, then the result of the detection item XBn has little impact on the cloud platform satisfaction.

[0137] Alternatively, users of the cloud platform can make judgments based on their own experience and then verify through detection models to analyze key items.

[0138] Alternatively, when a cloud platform's usage needs require a user satisfaction prediction, simply collect the relevant XA, XB, and XC items for the cloud platform and input them into the target detection model. Based on the model's output, a relatively accurate prediction can be made for the cloud platform. The accuracy of the prediction is related to the accuracy of the model itself.

[0139] Here, an embodiment of the present application provides a method for evaluating and detecting the service quality of a cloud platform, and establishes a target detection model for the service quality of the cloud platform based on AI and blockchain. Multiple historical users of the cloud platform and multiple cloud platform operators can jointly build an alliance chain. The initiator of establishing the detection model in the alliance chain determines the cloud platform that meets the cloud service type, and establishes a target detection model capable of evaluating satisfaction based on the historical usage of the cloud platform and combined with AI technology. In order to improve data security and prevent satisfaction information from being tampered with, when obtaining usage satisfaction information in historical data, the historical users of the cloud platform in the alliance chain encrypt the usage satisfaction information in advance using their own homomorphic keys. The target detection model is established with high security and accuracy, and can accurately evaluate the service quality of the cloud platform, thereby improving the credibility and reliability of cloud service use.

[0140] Figure 4A schematic diagram of the structure of a cloud platform service quality detection device provided in an embodiment of the present application is applied to the initiator of the detection model establishment, such as Figure 4 As shown, the apparatus of the embodiment of the present application includes: a first acquisition module 401, a second acquisition module 402, an initiation module 403, a publishing module 404, and a model determination module 405. The cloud platform service quality detection device here can be a server or a terminal device, or a chip or integrated circuit that implements the functions of the server or terminal device. It should be noted here that the division of the first acquisition module 401, the second acquisition module 402, the initiation module 403, the publishing module 404, and the model determination module 405 is only a division of logical functions. Physically, the two can be integrated or independent.

[0141] The first acquisition module is used to determine all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type, and obtain cloud platform information, wherein the cloud platform information includes the cloud platform identification number, the cloud platform basic information set, the cloud platform usage record fault data set and the cloud platform fault repair solution set;

[0142] The second acquisition module is used to obtain the cloud platform usage records in the alliance chain and determine the cloud platform's historical users based on the usage records;

[0143] An initiating module is used to initiate a usage satisfaction information acquisition request to a historical user of the cloud platform, so that the historical user of the cloud platform sends the usage satisfaction information to the initiator of the detection model establishment after obtaining the usage satisfaction information acquisition request, wherein the satisfaction information includes a homomorphic encryption public key and a satisfaction result encrypted by the homomorphic encryption key of the historical user of the cloud platform;

[0144] A publishing module is used to receive usage satisfaction information and publish an artificial intelligence training white paper in the alliance chain, so that at least one artificial intelligence model party signed in the alliance chain can perform artificial intelligence training according to the artificial intelligence training white paper and send the trained detection model to the detection model establishment initiator. The artificial intelligence training white paper includes a basic information set corresponding to the cloud platform, a cloud platform usage record fault data set, a cloud platform fault repair solution set, a collection of satisfaction information, and preset training acceptance goals;

[0145] The model determination module is used to perform model verification on the detection model after receiving the detection model sent by at least one artificial intelligence model party, and determine the target detection model based on the verification results.

[0146] Optionally, the model determination module is specifically configured to:

[0147] Determine first data to be verified based on the cloud platform usage record, wherein the first data to be verified includes first data to be input and a first result to be verified;

[0148] Inputting the first data to be input into the detection model for prediction to obtain a first prediction result;

[0149] The first prediction result is homomorphically compared with the first result to be verified to determine the verification result.

[0150] Optionally, the model determination module is further specifically configured to:

[0151] Obtain multiple verification results of the detection model;

[0152] The target detection model is determined based on the pass rate of the verification results.

[0153] Optionally, after the model determination module receives the detection model sent by at least one artificial intelligence model party, performs model verification on the detection model, and determines the target detection model according to the verification result, the above-mentioned device further includes a detection module for:

[0154] Obtain the cloud platform information of the cloud platform to be evaluated;

[0155] The cloud platform information is input into the target detection model to obtain the predicted satisfaction information of the cloud platform to be evaluated.

[0156] Optionally, after the model determination module receives the detection model sent by at least one artificial intelligence model party, performs model verification on the detection model, and determines the target detection model according to the verification result, the above-mentioned device further includes a verification item data determination module, which is used to:

[0157] Determine second data to be verified based on the cloud platform usage record, wherein the second data to be verified includes second data to be input and a second result to be verified;

[0158] Eliminate the verification item data from the second data to be input to obtain the third data to be input;

[0159] Inputting the third data to be input into the detection model for prediction to obtain a second prediction result;

[0160] The second prediction result is homomorphically compared with the second result to be verified, and the degree of influence of the verification item data on the cloud platform satisfaction is determined according to the comparison result.

[0161] Optionally, the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain or an operator of the cloud platform in the alliance chain.

[0162] Optionally, if the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain, then before the first acquisition module determines all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtains the cloud platform information, the above-mentioned device further includes an uploading module for:

[0163] Upload the desensitized cloud platform usage logs in the alliance chain.

[0164] Optionally, if the initiator of establishing the detection model is a cloud platform operator in the alliance chain, then before the first acquisition module determines all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtains the cloud platform information, the above-mentioned device further includes a verification module for:

[0165] Obtain cloud platform usage records in the alliance chain;

[0166] Verify the correctness of cloud platform usage records.

[0167] refer to Figure 5 , which shows a schematic diagram of the structure of a cloud platform service quality detection device 500 suitable for implementing an embodiment of the present disclosure. The cloud platform service quality detection device 500 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The cloud platform service quality detection device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0168] like Figure 5 As shown, the cloud platform service quality detection device 500 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (Read Only Memory, referred to as ROM) 502 or the program loaded from the storage device 508 to the random access memory (Random Access Memory, referred to as RAM) 503. Various programs and data required for the operation of the cloud platform service quality detection device 500 are also stored in the RAM 503. The processing device 501, the ROM 502 and the RAM 503 are connected to each other via a bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0169] Typically, the following devices can be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication device 509 can allow the cloud platform service quality detection device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The cloud platform service quality detection device 500 is shown as having various devices, but it should be understood that it is not required to implement or have all the devices shown, and more or fewer devices may be implemented or have instead.

[0170] 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 computer-readable medium, and the computer program includes 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 via the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0171] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0172] The computer-readable medium may be included in the cloud platform service quality detection device; or it may exist independently without being assembled into the cloud platform service quality detection device.

[0173] The computer-readable medium carries one or more programs. When the one or more programs are executed by the cloud platform service quality detection device, the cloud platform service quality detection device executes the method shown in the above embodiment.

[0174] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0175] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0176] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0177] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the applications disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0178] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A cloud platform service quality detection method, characterized in that: Applied to the initiator of establishing the detection model, the method includes: According to the cloud service type, all cloud platforms that meet the cloud service type are determined in the alliance chain, and cloud platform information is obtained, wherein the cloud platform information includes the cloud platform identification number, the cloud platform basic information set, the cloud platform usage record fault data set and the cloud platform fault repair solution set; Obtaining cloud platform usage records in the alliance chain, and determining historical users of the cloud platform based on the usage records; Initiate a usage satisfaction information acquisition request to the historical user of the cloud platform, so that the historical user of the cloud platform sends the usage satisfaction information to the detection model establishment initiator after obtaining the usage satisfaction information acquisition request, wherein the satisfaction information includes a homomorphic encryption public key and a satisfaction result encrypted by the homomorphic encryption key of the historical user of the cloud platform; Receive the usage satisfaction information, publish an artificial intelligence training white paper in the alliance chain, so that at least one artificial intelligence model party signed in the alliance chain performs artificial intelligence training according to the artificial intelligence training white paper, and sends the trained detection model to the detection model establishment initiator, wherein the artificial intelligence training white paper includes a basic information set corresponding to the cloud platform, a cloud platform usage record fault data set, a cloud platform fault repair solution set, a collection of the satisfaction information, and a preset training acceptance target; After receiving the detection model sent by at least one of the artificial intelligence models, the detection model is verified and the target detection model is determined based on the verification result.

2. The method according to claim 1, characterized in that The performing model verification on the detection model includes: Determining first data to be verified based on the cloud platform usage record, wherein the first data to be verified includes first data to be input and a first result to be verified; Inputting the first data to be input into the detection model for prediction to obtain a first prediction result; The first prediction result is homomorphically compared with the first result to be verified to determine a verification result.

3. The method according to claim 2, characterized in that Determining the target detection model according to the verification result includes: Obtain multiple verification results of the detection model; The target detection model is determined based on the pass rate of the verification results.

4. The method according to any one of claims 1 to 3, characterized in that After receiving the detection model sent by the at least one artificial intelligence model party, performing model verification on the detection model, and determining the target detection model according to the verification result, the method further includes: Obtain the cloud platform information of the cloud platform to be evaluated; The cloud platform information is input into the target detection model to obtain predicted satisfaction information of the cloud platform to be evaluated.

5. The method according to any one of claims 1 to 3, characterized in that After receiving the detection model sent by the at least one artificial intelligence model party, performing model verification on the detection model, and determining the target detection model according to the verification result, the method further includes: Determining second data to be verified based on the cloud platform usage record, wherein the second data to be verified includes second data to be input and a second result to be verified; Eliminating the verification item data from the second data to be input to obtain third data to be input; Inputting the third data to be input into the detection model for prediction to obtain a second prediction result; Perform a homomorphic comparison between the second prediction result and the second result to be verified, and determine the degree of influence of the verification item data on the cloud platform satisfaction based on the comparison result.

6. The method according to any one of claims 1 to 3, characterized in that The initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain or an operator of the cloud platform in the alliance chain.

7. The method according to claim 6, characterized in that If the initiator of establishing the detection model is a historical user of the cloud platform in the alliance chain, then before determining all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtaining cloud platform information, the method further includes: Upload the desensitized cloud platform usage logs in the alliance chain.

8. The method according to claim 6, characterized in that If the initiator of establishing the detection model is a cloud platform operator in the alliance chain, then before determining all cloud platforms that meet the cloud service type in the alliance chain according to the cloud service type and obtaining cloud platform information, the method further includes: Obtain cloud platform usage records in the alliance chain; The cloud platform usage record is verified for correctness.

9. A cloud platform service quality detection device, characterized in that: include: at least one processor; as well as 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 platform service quality detection method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the cloud platform service quality detection method according to any one of claims 1 to 8.

Images