Cloud resource configuration method and system based on multi-private cloud management domain classification

Abstract

The application provides a cloud resource configuration method and system based on multi-private cloud management domain classification, obtains cloud resource configuration history data of all private cloud management domains from cloud resource configuration history records of the private cloud management domains respectively, and carries out preprocessing and data correction processing on the cloud resource configuration history data to obtain effective cloud resource configuration record data; then, the effective cloud resource configuration record data is subjected to clustering analysis processing, the similarity and difference between different management domains are identified and analyzed based on cloud resource configuration characteristic information of all private cloud management domains, so that all private cloud management domains are divided into several management domain groups, which facilitates subsequent centralized and unified provision of cloud resource configuration by using the management domain groups; and based on the work log of a newly managed management domain, cloud resource demand attribute information of the newly managed management domain is determined, the newly managed management domain is identified and classified by using the management domain groups, so that a management domain group matched with the newly managed management domain is selected, and accurate and efficient cloud resource demand prediction is carried out based on the region and business type of the newly managed management domain, according to existing data of the newly managed management domain and historical data of the matched management domain group.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of cloud resources, and particularly relates to a cloud resource configuration method and system based on multi-private cloud management domain classification. BACKGROUND

[0002] With the continuous expansion of cloud computing resources by cloud service providers, scientifically and effectively predicting cloud resource demand is crucial for better planning and management of cloud computing resources. In order to accurately and efficiently predict cloud resource demand in a private cloud environment, it is an important topic to classify and analyze different management domains with different cloud resource configuration data. However, the existing methods for predicting private cloud resource demand do not accurately identify and analyze the similarities and differences between different management domains, cannot fully understand the characteristics and trends of different management domains, cannot fully utilize the most matched management domain cloud resource historical data to accurately predict the cloud resource demand of new management domains with less existing data, and are prone to cause low accuracy of cloud resource demand prediction and false prediction, which cannot fully and accurately utilize each management domain for reliable cloud resource configuration. SUMMARY

[0003] The present application relates to the field of cloud resources, and particularly relates to a cloud resource configuration method and system based on multi-private cloud management domain classification.

[0004] The present application is achieved by the following technical solutions:

[0005] The cloud resource configuration method based on multi-private cloud management domain classification comprises:

[0006] Based on the cloud resource configuration history records of the private cloud management domains, cloud resource configuration history data of all private cloud management domains is obtained, and the cloud resource configuration history data is preprocessed; the cloud resource configuration history data after the preprocessing is processed for data correction, so as to obtain effective cloud resource configuration record data;

[0007] The effective cloud resource configuration record data is processed for cluster analysis, so as to obtain cloud resource configuration characteristic information of all private cloud management domains; based on the cloud resource configuration characteristic information, similarity and difference between different management domains are identified and analyzed, and all private cloud management domains are divided into a plurality of management domain groups; wherein all private cloud management domains under each management domain group meet corresponding cloud resource configuration and change trend similarity conditions;

[0008] Based on the working log of the newly managed management domain, cloud resource demand attribute information of the newly managed management domain is determined, the newly managed management domain is identified and classified by using the management domain group, so as to select a management domain group matched with the newly managed management domain; and based on the region and business type of the newly managed management domain and the existing data of the newly managed management domain and the historical data of the matched management domain group, cloud resource demand is predicted.

[0009] Optionally, based on the cloud resource configuration history records of the private cloud management domains, cloud resource configuration history data of all private cloud management domains is obtained, and the cloud resource configuration history data is preprocessed; the cloud resource configuration history data after the preprocessing is processed for data correction, so as to obtain effective cloud resource configuration record data, comprising:

[0010] The cloud resource configuration history records of the private cloud management domains in a preset historical time interval are obtained, the cloud resource configuration history records are analyzed, and all cloud resource configuration effective behaviors of each private cloud management domain occurring in the preset historical time interval are obtained; all cloud resource configuration effective behaviors are analyzed, and configuration history data of each private cloud management domain about different types of cloud resources is determined; wherein the configuration history data at least includes configuration occurrence time and configuration resource quantity of the corresponding type of cloud resource; the different types of cloud resources include computing power cloud resources, memory cloud resources, storage cloud resources and network bandwidth cloud resources; and the configuration history data is sequentially processed for noise removal preprocessing and missing data completion preprocessing;

[0011] Based on the Holt-Winters model, the configuration history data after the noise removal preprocessing and the missing data completion preprocessing is processed for data smoothing; based on the result of the data smoothing, the configuration history data is processed for deviation abnormal data component elimination correction, so as to obtain effective cloud resource configuration record data.

[0012] Optionally, the effective cloud resource configuration record data is subjected to clustering analysis processing to obtain cloud resource configuration characteristic information of each private cloud management domain; based on the cloud resource configuration characteristic information, similarity and difference between different management domains are identified and analyzed, and all private cloud management domains are divided into several management domain groups; wherein all private cloud management domains under each management domain group meet corresponding cloud resource configuration and change trend similarity conditions, including:

[0013] Based on the hybrid algorithm of DBSCAN and Kmeans, the effective cloud resource configuration record data is subjected to clustering analysis processing to obtain demand change trend characteristic information of each private cloud management domain in the configuration process of different types of cloud resources;

[0014] Based on the demand change trend characteristic information, cloud resource type information matched and configured by each private cloud management domain is determined; and based on the matched and configured cloud resource type information, all private cloud management domains are divided into several management domain groups; wherein all private cloud management domains under each management domain group are matched and configured with the same type of cloud resources, and the demand change trend of the cloud resources matched and configured by each private cloud management domain under each management domain group is within a preset range.

[0015] Optionally, based on the work log of the newly managed management domain, cloud resource demand attribute information of the newly managed management domain is determined, the newly managed management domain is identified and classified by using the management domain group, so as to select a management domain group matched with the newly managed management domain; and based on the region and business type of the newly managed management domain, and the existing data of the newly managed management domain and the historical data of the matched management domain group, cloud resource demand prediction is performed, including:

[0016] The work log of the newly managed management domain is analyzed to obtain expected configuration cloud resource type information of the currently executed operation task of the newly managed management domain; the expected configuration cloud resource type information is compared with cloud resource type information that can be provided by each management domain group, and a management domain group matched with the newly managed management domain is selected; and based on the region and business type of the newly managed management domain, and the existing data of the newly managed management domain and the historical data of the matched management domain group, cloud resource demand prediction is performed.

[0017] Optionally, the acquisition process of the work log of the newly managed management domain is subjected to running quality determination, including:

[0018] The acquisition time length of the work log is extracted;

[0019] The acquisition time length of the work log is compared with a preset acquisition time length threshold;

[0020] When the acquisition duration of the work log exceeds a preset acquisition duration threshold, a running parameter for acquiring the work log is called, wherein the running parameter comprises a diary screening accuracy, a diary call garbled code proportion, and a diary call response duration;

[0021] The diary screening accuracy, the diary call garbled code proportion, and the diary call response duration are used to acquire a diary call running evaluation coefficient;

[0022] The diary call running evaluation coefficient is acquired through the following formula:

[0023] Wherein, W represents the diary call running evaluation coefficient; n represents the number of diary calls; P i represents the diary screening accuracy corresponding to the i-th diary call; L i represents the diary call garbled code proportion corresponding to the i-th diary call; T i represents the diary call response duration corresponding to the i-th diary call; T Lmax represents the diary call response duration corresponding to the maximum value of the diary call garbled code proportion; T Lmin represents the diary call response duration corresponding to the minimum value of the diary call garbled code proportion; S represents an adjustment coefficient, and the adjustment coefficient is acquired through the following formula:

[0024] Wherein, S represents the adjustment coefficient; L pmin represents the diary call garbled code proportion corresponding to the minimum value of the diary screening accuracy; L pmax represents the diary call garbled code proportion corresponding to the maximum value of the diary screening accuracy; L min represents the minimum value of the diary call garbled code proportion; L max represents the maximum value of the diary call garbled code proportion;

[0025] The diary call running evaluation coefficient is compared with a preset coefficient threshold;

[0026] When the diary call running evaluation coefficient is lower than the preset coefficient threshold, it is determined that the acquisition process of the work log is abnormal, and an abnormal alarm is performed.

[0027] A cloud resource configuration system based on multi-private cloud management domain classification comprises:

[0028] A historical data acquisition and preprocessing module is configured to acquire cloud resource configuration historical data of all private cloud management domains based on cloud resource configuration historical records of the private cloud management domains, and to preprocess the cloud resource configuration historical data;

[0029] a historical data correction module, configured to perform data correction processing on the cloud resource configuration historical data that has undergone the preprocessing, to obtain effective cloud resource configuration record data;

[0030] a cloud resource configuration feature identification module, configured to perform clustering analysis processing on the effective cloud resource configuration record data, to obtain cloud resource configuration feature information of each private cloud management domain;

[0031] a management domain group division module, configured to identify and analyze the similarities and differences between different management domains based on the cloud resource configuration feature information, and divide all private cloud management domains into a plurality of management domain groups; wherein all private cloud management domains under each management domain group meet corresponding cloud resource configuration and change trend similarity conditions;

[0032] a management domain group selection module, configured to determine cloud resource demand attribute information of a newly managed management domain based on a work log of the newly managed management domain, and identify and classify the newly managed management domain by using the management domain groups, to select a management domain group that matches the newly managed management domain;

[0033] a cloud resource configuration prediction module, configured to perform cloud resource demand prediction based on a region and a business type of the newly managed management domain, and existing data of the newly managed management domain and historical data of the matched management domain group.

[0034] Optionally, the historical data acquisition and preprocessing module is configured to acquire cloud resource configuration historical data of all private cloud management domains based on cloud resource configuration historical records of the private cloud management domains, and perform preprocessing on the cloud resource configuration historical data, including:

[0035] acquire cloud resource configuration historical records of the private cloud management domains in a preset historical time interval, analyze the cloud resource configuration historical records, to obtain all cloud resource configuration effective behaviors of each private cloud management domain in the preset historical time interval, analyze all cloud resource configuration effective behaviors, to determine configuration historical data of each private cloud management domain about different types of cloud resources, wherein the configuration historical data at least includes configuration occurrence time and configuration resource quantity of the corresponding type of cloud resources, the different types of cloud resources include computing power cloud resources, memory cloud resources, storage cloud resources and network bandwidth cloud resources, and the configuration historical data is sequentially subjected to noise removal preprocessing and missing data completion preprocessing;

[0036] the historical data correction module is configured to perform data correction processing on the cloud resource configuration historical data that has undergone the preprocessing, to obtain effective cloud resource configuration record data, including:

[0037] Based on the Holt-Winters model, the configuration history data that has undergone noise removal preprocessing and missing data completion preprocessing is smoothed; then, based on the result of the smoothing, the configuration history data is corrected by removing and eliminating abnormal data components, thereby obtaining effective cloud resource configuration record data.

[0038] Optionally, the cloud resource configuration feature identification module is used to perform cluster analysis on the valid cloud resource configuration record data to obtain cloud resource configuration feature information for each of the private cloud management domains, including:

[0039] Based on a hybrid algorithm of DBSCAN and Kmeans, cluster analysis is performed on the effective cloud resource configuration record data to obtain the demand change trend characteristics of each private cloud management domain in the process of configuring different types of cloud resources.

[0040] The management domain grouping module is used to identify and analyze the similarities and differences between different management domains based on the cloud resource configuration feature information, and to divide all private cloud management domains into several management domain groups; wherein, all private cloud management domains under each management domain group meet the corresponding conditions of similar cloud resource configuration and change trends, including:

[0041] Based on the aforementioned demand change trend characteristics, the cloud resource type information matched and configured for each of the private cloud management domains is determined; then, based on the matched and configured cloud resource type information, all private cloud management domains are divided into several management domain groups; wherein, all private cloud management domains under each management domain group are matched and configured with the same type of cloud resources, and the demand change trend of the cloud resources matched and configured for each private cloud management domain under each management domain group is within a preset quantity range.

[0042] Optionally, the management domain group selection module is used to determine the cloud resource demand attribute information of the newly managed management domain based on the work logs of the newly managed management domain, identify and classify the newly managed management domain using management domain groups, and select management domain groups that match the newly managed management domain, including:

[0043] The work logs of the newly added management domain are analyzed to obtain the expected cloud resource type information of the computing tasks currently being executed by the newly added management domain; the expected cloud resource type information is compared with the cloud resource type information that each of the management domain groups can provide, and the management domain group that matches the newly added management domain is selected.

[0044] Optionally, the process of acquiring work logs for newly added management domains may be subject to operational quality assessment, including:

[0045] extracting an acquisition duration of the work log;

[0046] comparing the acquisition duration of the work log with a preset acquisition duration threshold;

[0047] when the acquisition duration of the work log exceeds the preset acquisition duration threshold, acquiring an operation parameter for acquiring the work log, wherein the operation parameter comprises a diary screening accuracy, a diary acquisition garbled code proportion and a diary acquisition response duration;

[0048] acquiring a diary acquisition operation evaluation coefficient by using the diary screening accuracy, the diary acquisition garbled code proportion and the diary acquisition response duration;

[0049] wherein the diary acquisition operation evaluation coefficient is acquired by the following formula:

[0050] wherein W represents the diary acquisition operation evaluation coefficient; n represents the number of times of diary acquisition; P i represents the diary screening accuracy corresponding to the i-th time of diary acquisition; L i represents the diary acquisition garbled code proportion corresponding to the i-th time of diary acquisition; T i represents the diary acquisition response duration corresponding to the i-th time of diary acquisition; T Lmax represents the diary acquisition response duration corresponding to the maximum value of the diary acquisition garbled code proportion; T Lmin represents the diary acquisition response duration corresponding to the minimum value of the diary acquisition garbled code proportion; S represents an adjustment coefficient, and the adjustment coefficient is acquired by the following formula:

[0051] wherein S represents the adjustment coefficient; L pmin represents the diary acquisition garbled code proportion corresponding to the minimum value of the diary screening accuracy; L pmax represents the diary acquisition garbled code proportion corresponding to the maximum value of the diary screening accuracy; L min represents the minimum value of the diary acquisition garbled code proportion; L max represents the maximum value of the diary acquisition garbled code proportion;

[0052] comparing the diary acquisition operation evaluation coefficient with a preset coefficient threshold;

[0053] when the diary acquisition operation evaluation coefficient is lower than the preset coefficient threshold, determining that the acquisition process of the work log is abnormal, and performing abnormal alarm.

[0054] Compared with the prior art, the present application has the following beneficial effects:

[0055] The cloud resource configuration method and system based on multi-private cloud management domain classification provided in the application obtain cloud resource configuration historical data of all private cloud management domains from cloud resource configuration historical records of the private cloud management domains, and perform preprocessing and data correction processing on the cloud resource configuration historical data to obtain effective cloud resource configuration record data; then, the effective cloud resource configuration record data is subjected to clustering analysis processing, and based on cloud resource configuration characteristic information of all private cloud management domains, the similarity and difference between different management domains are accurately identified and analyzed, so that all private cloud management domains are divided into several management domain groups, which facilitates subsequent centralized and unified provision of cloud resource configuration by the management domain groups; and based on the work log of a newly managed management domain, cloud resource demand attribute information of the newly managed management domain is determined, the newly managed management domain is identified and classified by using the management domain groups, so that a management domain group matched with the newly managed management domain is selected, and based on the region and business type of the newly managed management domain, accurate and efficient cloud resource demand prediction is performed according to existing data of the newly managed management domain and historical data of the matched management domain group. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only constitute some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor. Among them:

[0057] Figure 1 The flowchart of the cloud resource configuration method based on multi-private cloud management domain classification provided by the application.

[0058] Figure 2 The structural schematic diagram of the cloud resource configuration system based on multi-private cloud management domain classification provided by the application. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the specific embodiments of the application will be described in detail below with reference to the drawings. It can be understood that the specific embodiments described herein are only used to explain the application, but not to limit the application. In addition, it should be noted that, in order to facilitate the description, only the parts related to the application are shown in the drawings, but not all the structures. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0060] The terms "comprises", "comprising", "includes", "including", "has", "having" and their conjugates, as used herein, are intended to cover the situation where individual features are added or are inherent to the process, method, article, or apparatus, and also to cover the situation where individual features are excluded or are not inherent to the process, method, article, or apparatus. For example, a process, method, article, or apparatus that comprises a list of steps or elements is not necessarily limited to only those steps or elements but can include additional steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

[0061] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiment, or to a single alternative embodiment. It is explicitly contemplated that embodiments described herein can be combined with each other in their individual aspects.

[0062] See Figure 1 As shown in the accompanying drawings, an embodiment of the present application provides a cloud resource configuration method based on multi-private cloud management domain classification. The cloud resource configuration method based on multi-private cloud management domain classification comprises:

[0063] Based on the cloud resource configuration history records of the respective private cloud management domains, cloud resource configuration history data of all private cloud management domains is obtained, and the cloud resource configuration history data is preprocessed. The cloud resource configuration history data after the preprocessing is subjected to data correction processing, thereby obtaining effective cloud resource configuration record data;

[0064] The effective cloud resource configuration record data is subjected to clustering analysis processing, thereby obtaining cloud resource configuration characteristic information of all private cloud management domains. Based on the cloud resource configuration characteristic information, similarity and difference between different management domains are identified and analyzed, and all private cloud management domains are divided into a plurality of management domain groups. All private cloud management domains under each management domain group satisfy corresponding cloud resource configuration and change trend similarity conditions.

[0065] Based on the working log of a new managed management domain, cloud resource demand attribute information of the new managed management domain is determined, the new managed management domain is identified and classified by using the management domain groups, so as to select a management domain group matched with the new managed management domain. Based on the region and business type of the new managed management domain, and based on the existing data of the new managed management domain and the historical data of the matched management domain group, cloud resource demand is predicted.

[0066] The cloud resource configuration method based on the multi-private cloud management domain classification has the beneficial effects that the cloud resource configuration history data of all private cloud management domains is obtained from the cloud resource configuration history records of the private cloud management domains, the cloud resource configuration history data is preprocessed and data correction processed to obtain effective cloud resource configuration record data, the effective cloud resource configuration record data is subjected to clustering analysis processing, the similarity and difference between different management domains are accurately identified and analyzed based on the cloud resource configuration characteristic information of all private cloud management domains, all private cloud management domains are divided into several management domain groups, and the cloud resource configuration is conveniently provided by the management domain groups; the cloud resource demand attribute information of a newly managed management domain is determined based on the work log of the newly managed management domain, the newly managed management domain is identified and classified by using the management domain groups, a management domain group matched with the newly managed management domain is selected, and the cloud resource demand of the newly managed management domain is accurately and efficiently predicted based on the region and business type of the newly managed management domain and the historical data of the matched management domain group.

[0067] In another embodiment, cloud resource configuration history data of all private cloud management domains is obtained based on the cloud resource configuration history records of the private cloud management domains, and the cloud resource configuration history data is preprocessed; the cloud resource configuration history data subjected to the preprocessing is subjected to data correction processing, thereby obtaining effective cloud resource configuration record data, including:

[0068] The cloud resource configuration history records of the private cloud management domains in a preset historical time interval are obtained, the cloud resource configuration history records are analyzed to obtain all cloud resource configuration effective behaviors of each private cloud management domain in the preset historical time interval; all cloud resource configuration effective behaviors are analyzed to determine the configuration history data of each private cloud management domain about different types of cloud resources; the configuration history data at least includes the configuration time and the configuration resource quantity of the corresponding type of cloud resources; the different types of cloud resources include computing power cloud resources, memory cloud resources, storage cloud resources, and network bandwidth cloud resources; and the configuration history data is subjected to noise removal preprocessing and missing data completion preprocessing in sequence;

[0069] The configuration history data subjected to the noise removal preprocessing and the missing data completion preprocessing is subjected to data smoothing processing based on a Holt-Winters model; the configuration history data is subjected to deviation abnormal data component elimination correction processing based on the result of the data smoothing processing, thereby obtaining effective cloud resource configuration record data.

[0070] The above-mentioned embodiments have the beneficial effects that different private cloud management domains can perform configuration operations on different types of cloud resources, which can include but are not limited to computing power cloud resources, memory cloud resources, storage cloud resources, and network bandwidth cloud resources, etc. Different private cloud management domains usually tend to concentrate on the configuration of one type of cloud resource in actual cloud resource configuration operations. In order to accurately identify the cloud resource configuration characteristics of all private cloud management domains, the cloud resource configuration history records of several private cloud management domains in a preset historical time interval are obtained and analyzed to obtain all cloud resource configuration effective behaviors of each private cloud management domain in the preset historical time interval, wherein the cloud resource configuration effective behavior can be but is not limited to a behavior with a cloud resource configuration duration greater than a preset time length threshold. The cloud resource configuration effective behavior is analyzed to determine the configuration history data of each private cloud management domain on different types of cloud resources. This can quantitatively collect cloud resource configuration tendencies of each private cloud management domain, and provide sufficient and comprehensive data support for subsequent similarity relationship analysis between different private cloud management domains. In addition, the configuration history data is sequentially subjected to noise removal preprocessing and missing data completion preprocessing, which can remove noise interference components in the configuration history data and improve the completeness of the data. Based on the Holt-Winters model, the configuration history data subjected to the noise removal preprocessing and the missing data completion preprocessing is subjected to data smoothing processing. Based on the results of the data smoothing processing, the configuration history data is subjected to deviation abnormal data component elimination correction processing, thereby obtaining effective cloud resource configuration record data, thereby improving data quality and accuracy, and enhancing the reliability and accuracy of subsequent similarity relationship identification between different private cloud management domains.

[0071] In another embodiment, the effective cloud resource configuration record data is subjected to clustering analysis processing to obtain cloud resource configuration characteristic information of all private cloud management domains; based on the cloud resource configuration characteristic information, the similarity and difference between different management domains are identified and analyzed, and all private cloud management domains are divided into several management domain groups; wherein all private cloud management domains under each management domain group satisfy corresponding cloud resource configuration and change trend similarity conditions, including:

[0072] Based on the hybrid algorithm of DBSCAN and Kmeans, the effective cloud resource configuration record data is subjected to clustering analysis processing to obtain demand change trend characteristic information of all private cloud management domains in the configuration process of different types of cloud resources;

[0073] Based on the demand change trend characteristic information, the cloud resource type information matched by each private cloud management domain is determined; and then, based on the matched cloud resource type information, all private cloud management domains are divided into several management domain groups; wherein, all private cloud management domains under each management domain group match the same type of cloud resources, and the demand change trends of the cloud resources matched by all private cloud management domains under each management domain group are within a preset range.

[0074] The above-mentioned embodiments have the beneficial effect that each private cloud management domain can simultaneously manage computing power cloud resources, cloud memory resources, storage cloud resources, and network bandwidth cloud resources, etc. However, in actual cloud resource configuration operations, each private cloud management domain does not necessarily perform equal configuration on all types of cloud resources managed thereunder, i.e., each private cloud management domain can tend to mainly configure one or two types of cloud resources, and at this level, all private cloud management domains can be distinguished in terms of similarity. Therefore, based on the hybrid algorithm of DBSCAN and Kmeans, the effective cloud resource configuration record data is subjected to clustering analysis and processing to obtain demand change trend characteristic information of each private cloud management domain in the configuration process of different types of cloud resources, and based on the demand change trend characteristic information, the cloud resource type information matched by each private cloud management domain is determined, so as to divide all private cloud management domains into several management domain groups; wherein, all private cloud management domains under each management domain group match the same type of cloud resources, and the demand change trends of the cloud resources matched by all private cloud management domains under each management domain group are within a preset range, so as to ensure that all private cloud management domains under the same management domain group tend to mainly configure the same type of cloud resources. Through clustering analysis based on the hybrid algorithm of DBSCAN and Kmeans, the similarity and difference between different private management domains are accurately identified, more accurate management domain characteristics and trend analysis are provided, and resource configuration and performance optimization decisions are optimized. Through classification of private management domains, customized resource allocation schemes can be provided for different private management domains according to the differences in regions and business types, so as to better meet the needs of different management domains and improve cloud resource utilization efficiency and user satisfaction.

[0075] In another embodiment, based on the working log of a new managed management domain, cloud resource demand attribute information of the new managed management domain is determined, the new managed management domain is identified and classified by a management domain group, so as to select a management domain group matched with the new managed management domain; and then, based on the region and business type of the new managed management domain and the historical data of the new managed management domain and the matched management domain group, cloud resource demand prediction is performed, including:

[0076] analyzing the work log of the new managed management domain to obtain expected configuration cloud resource type information of a currently executed operation task of the new managed management domain; comparing the expected configuration cloud resource type information with cloud resource type information that can be provided by each of all management domain groups for configuration, and selecting a management domain group that matches the new managed management domain from the comparison; and performing cloud resource demand prediction based on a region and a business type of the new managed management domain, and existing data of the new managed management domain and historical data of the matched management domain group.

[0077] The above embodiment has the beneficial effect that the new managed management domain has demands for different types of cloud resources such as computing power cloud resources, cloud memory resources, storage cloud resources, and network bandwidth cloud resources during execution of an operation task. In order to ensure that the new managed management domain can obtain suitable cloud resource configuration in each process stage of execution of the operation task, the work log of the new managed management domain is analyzed to obtain expected configuration cloud resource type information of a currently executed operation task. The expected configuration cloud resource type information is compared with cloud resource type information that can be provided by each of all management domain groups for configuration, and a management domain group that matches the new managed management domain is selected from the comparison, so that the selected management domain group can configure suitable cloud resources in the corresponding process stage of execution of the operation task of the new managed management domain. Cloud resource demand prediction is performed based on a region and a business type of the new managed management domain, and existing data of the new managed management domain and historical data of the matched management domain group. The currently executed operation task of the new managed management domain is also monitored to obtain task running process information corresponding to the currently executed operation task. The task running process information is compared with cloud resources in an idle state of each of all private cloud management domains under the matched management domain cluster, to determine private cloud management domains that can configure corresponding types of cloud resources for the new managed management domain, and corresponding cloud resources are extracted from the determined private cloud management domains and configured for the new managed management domain, so as to ensure that the new managed management domain obtains reliable and sustainable cloud resource configuration, improves task running efficiency, and fully utilizes cloud resources of the management domain.

[0078] In another embodiment, a running quality determination is performed on a work log acquisition process of a new managed management domain, including:

[0079] extracting an acquisition duration of the work log;

[0080] comparing the acquisition duration of the work log with a preset acquisition duration threshold;

[0081] when the acquisition duration of the work log exceeds the preset acquisition duration threshold, running parameters for acquiring the work log are called, wherein the running parameters include a diary screening accuracy rate, a diary acquisition garbled code proportion, and a diary acquisition response duration;

[0082] The diary call operation evaluation coefficient is obtained by using the diary screening accuracy, the proportion of messy codes in diary call and the diary call response time length.

[0083] The diary call operation evaluation coefficient is obtained by using the diary screening accuracy, the proportion of messy codes in diary call and the diary call response time length.

[0084] Wherein, W represents the diary call operation evaluation coefficient; n represents the number of diary calls; P i represents the diary screening accuracy corresponding to the i-th diary call; L i represents the proportion of messy codes in diary call corresponding to the i-th diary call; T i represents the diary call response time length corresponding to the i-th diary call; T Lmax represents the diary call response time length corresponding to the maximum value of the proportion of messy codes in diary call; T Lmin represents the diary call response time length corresponding to the minimum value of the proportion of messy codes in diary call; S represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0085] Wherein, S represents the adjustment coefficient; L pmin represents the proportion of messy codes in diary call corresponding to the minimum value of the diary screening accuracy; L pmax represents the proportion of messy codes in diary call corresponding to the maximum value of the diary screening accuracy; L min represents the minimum value of the proportion of messy codes in diary call; L max represents the maximum value of the proportion of messy codes in diary call;

[0086] The diary call operation evaluation coefficient is compared with a preset coefficient threshold value.

[0087] When the diary call operation evaluation coefficient is lower than the preset coefficient threshold value, it is determined that the process of obtaining the work diary is abnormal, and an abnormal alarm is given.

[0088] The beneficial effects of the above embodiments can achieve real-time monitoring of the work log acquisition process in the newly managed management domain by extracting the acquisition duration of the work log and comparing it with the preset acquisition duration threshold. Once the acquisition duration exceeds the threshold, further analysis and judgment processes are triggered immediately to ensure that potential abnormalities can be discovered and handled in a timely manner. When the acquisition duration is abnormal, the scheme not only focuses on a single duration indicator, but also further retrieves the running parameters of the acquisition work log, including the diary filtering accuracy, the diary retrieval garbled code proportion, and the diary retrieval response duration. These parameters collectively constitute a comprehensive evaluation of the running quality of the work log acquisition process, which helps to more accurately identify the problem. By introducing the diary retrieval running evaluation coefficient W, the scheme realizes the quantitative evaluation of the running quality of the work log acquisition process. This coefficient considers multiple running parameters and is calculated through a specific formula, which can more intuitively reflect the running state of the system. The introduction of the adjustment coefficient S makes the calculation of the evaluation coefficient W more flexible and adaptive. The value of S is adjusted according to the changes in the diary filtering accuracy and the diary retrieval garbled code proportion, which can more accurately reflect the running quality of the system in different states. When the diary retrieval running evaluation coefficient is lower than the preset coefficient threshold, the scheme can automatically determine that the acquisition process of the work log is abnormal and issue an abnormal alarm. This helps the operation and maintenance personnel to discover problems in a timely manner and take appropriate measures for fault diagnosis and repair, thereby ensuring the stable operation of the system.

[0089] In summary, the technical scheme effectively improves the running quality and reliability of the work log acquisition process in the newly managed management domain through real-time monitoring, multi-dimensional evaluation, quantitative evaluation, adaptive adjustment, and abnormal alarm.

[0090] Referring to Figure 2 An embodiment of the present application provides a cloud resource configuration system based on multi-private cloud management domain classification. The cloud resource configuration system based on multi-private cloud management domain classification comprises:

[0091] A historical data acquisition and preprocessing module is configured to acquire cloud resource configuration historical data of all private cloud management domains based on cloud resource configuration historical records of the private cloud management domains, and to preprocess the cloud resource configuration historical data;

[0092] A historical data correction module is configured to perform data correction processing on the cloud resource configuration historical data after the preprocessing, thereby obtaining effective cloud resource configuration record data;

[0093] A cloud resource configuration feature recognition module is configured to perform clustering analysis processing on the effective cloud resource configuration record data, thereby obtaining cloud resource configuration feature information of all private cloud management domains;

[0094] The management domain group division module is configured to identify and analyze the similarities and differences between different management domains based on the cloud resource configuration characteristic information, and divide all private cloud management domains into several management domain groups; wherein all private cloud management domains under each management domain group meet the corresponding cloud resource configuration and change trend similarity conditions;

[0095] The management domain group selection module is configured to determine the cloud resource demand attribute information of the newly managed management domain based on the work log of the newly managed management domain, identify and classify the newly managed management domain by using the management domain groups, and select the management domain group matched with the newly managed management domain.

[0096] The cloud resource configuration prediction module is configured to predict the cloud resource demand based on the region and business type of the newly managed management domain, the existing data of the newly managed management domain, and the historical data of the matched management domain group.

[0097] The cloud resource configuration system based on the classification of multiple private cloud management domains has the following beneficial effects: the cloud resource configuration historical data of all private cloud management domains is obtained from the cloud resource configuration historical records of the private cloud management domains, and the cloud resource configuration historical data is preprocessed and corrected to obtain effective cloud resource configuration record data; the effective cloud resource configuration record data is subjected to clustering analysis, the similarities and differences between different management domains are accurately identified and analyzed based on the cloud resource configuration characteristic information of all private cloud management domains, and all private cloud management domains are divided into several management domain groups, so that the cloud resource configuration can be conveniently provided by using the management domain groups; the cloud resource demand attribute information of the newly managed management domain is determined based on the work log of the newly managed management domain, the newly managed management domain is identified and classified by using the management domain groups, the management domain group matched with the newly managed management domain is selected, and the cloud resource demand is accurately and efficiently predicted based on the region and business type of the newly managed management domain, the existing data of the newly managed management domain, and the historical data of the matched management domain group.

[0098] In another embodiment, the historical data acquisition and preprocessing module is configured to obtain the cloud resource configuration historical data of all private cloud management domains based on the cloud resource configuration historical records of the private cloud management domains, and preprocess the cloud resource configuration historical data, including:

[0099] Obtaining cloud resource configuration history records of each private cloud management domain in a preset historical time interval, analyzing the cloud resource configuration history records, obtaining all cloud resource configuration effective behaviors of each private cloud management domain occurring in the preset historical time interval; analyzing all cloud resource configuration effective behaviors, determining configuration history data of each private cloud management domain about different types of cloud resources; wherein the configuration history data at least includes configuration occurrence time and configuration resource quantity of the corresponding type of cloud resources; the different types of cloud resources include computing power cloud resources, memory cloud resources, storage cloud resources and network bandwidth cloud resources; and the configuration history data is sequentially subjected to noise removal preprocessing and missing data completion preprocessing;

[0100] The historical data correction module is used for data correction processing on the cloud resource configuration history data after the preprocessing, so as to obtain effective cloud resource configuration record data, including:

[0101] Based on the Holt-Winters model, the configuration history data after the noise removal preprocessing and the missing data completion preprocessing is subjected to data smoothing processing; and based on the result of the data smoothing processing, the configuration history data is subjected to deviation abnormal data component elimination correction processing, so as to obtain effective cloud resource configuration record data.

[0102] The above embodiments have the beneficial effects that different private cloud management domains can perform configuration operations on different types of cloud resources, which can include but are not limited to computing power cloud resources, memory cloud resources, storage cloud resources, and network bandwidth cloud resources, etc. Different private cloud management domains usually tend to concentrate on the configuration of one type of cloud resource in actual cloud resource configuration operations. In order to accurately identify the cloud resource configuration characteristics of all private cloud management domains, the cloud resource configuration history records of several private cloud management domains in a preset historical time interval are obtained and analyzed to obtain all cloud resource configuration effective behaviors of each private cloud management domain in the preset historical time interval, wherein the cloud resource configuration effective behavior can be but is not limited to a behavior with a cloud resource configuration duration greater than a preset time length threshold. The cloud resource configuration effective behavior is analyzed to determine the configuration history data of each private cloud management domain on different types of cloud resources. This can quantitatively collect cloud resource configuration tendencies of each private cloud management domain and provide sufficient and comprehensive data support for subsequent similarity relationship analysis between different private cloud management domains. In addition, the configuration history data is sequentially subjected to noise removal preprocessing and missing data completion preprocessing, which can remove noise interference components in the configuration history data and improve the completeness of the data. Based on the Holt-Winters model, the configuration history data subjected to the noise removal preprocessing and the missing data completion preprocessing is subjected to data smoothing processing. Based on the results of the data smoothing processing, the configuration history data is subjected to deviation abnormal data component elimination correction processing, thereby obtaining effective cloud resource configuration record data, thereby improving data quality and accuracy and enhancing the reliability and accuracy of subsequent similarity relationship identification between different private cloud management domains.

[0103] In another embodiment, the cloud resource configuration feature identification module is configured to perform clustering analysis processing on the effective cloud resource configuration record data to obtain cloud resource configuration feature information of each private cloud management domain, including:

[0104] Based on the DBSCAN and Kmeans hybrid algorithm, the effective cloud resource configuration record data is subjected to clustering analysis processing to obtain demand change trend feature information of each private cloud management domain in the configuration process of different types of cloud resources.

[0105] The management domain group division module is configured to identify and analyze the similarity and difference between different management domains based on the cloud resource configuration feature information, and divide all private cloud management domains into several management domain groups. Each private cloud management domain in each management domain group satisfies the corresponding cloud resource configuration and change trend similarity condition, including:

[0106] Based on the demand change trend characteristic information, the cloud resource type information matched by each private cloud management domain is determined; and based on the matched cloud resource type information, all private cloud management domains are divided into several management domain groups; wherein all private cloud management domains under each management domain group match the same type of cloud resources, and the demand change trend of the cloud resources matched by each private cloud management domain under each management domain group is within a preset range.

[0107] The above-mentioned embodiments have the beneficial effect that each private cloud management domain can simultaneously manage computing power cloud resources, cloud memory resources, storage cloud resources, and network bandwidth cloud resources, etc. However, in actual cloud resource configuration operations, each private cloud management domain does not necessarily perform equal configuration on all types of cloud resources managed thereunder, i.e. each private cloud management domain can tend to mainly configure one or two types of cloud resources, and at this level, all private cloud management domains can be distinguished in terms of similarity. Therefore, based on the hybrid algorithm of DBSCAN and Kmeans, the effective cloud resource configuration record data is subjected to clustering analysis processing to obtain demand change trend characteristic information of each private cloud management domain in the configuration process of different types of cloud resources, and based on the demand change trend characteristic information, the cloud resource type information matched by each private cloud management domain is determined to divide all private cloud management domains into several management domain groups; wherein all private cloud management domains under each management domain group match the same type of cloud resources, and the demand change trend of the cloud resources matched by each private cloud management domain under each management domain group is within a preset range, which can ensure that all private cloud management domains under the same management domain group tend to concentrate on configuring the same type of cloud resources. Through clustering analysis based on the hybrid algorithm of DBSCAN and Kmeans, the similarity and difference between different private management domains are accurately identified, more accurate management domain characteristics and trend analysis are provided, and resource configuration and performance optimization decisions are optimized. By classifying private management domains, customized resource allocation schemes can be provided for different private management domains according to regional and business type differences, so as to better meet the needs of different management domains and improve cloud resource utilization efficiency and user satisfaction.

[0108] In another embodiment, the management domain group selection module is configured to determine cloud resource demand attribute information of a newly managed management domain based on a work log of the newly managed management domain, and identify and classify the newly managed management domain using a management domain group to select a management domain group matched with the newly managed management domain, including:

[0109] The work log of the new managed management domain is analyzed to obtain expected configuration cloud resource type information of a currently executed operation task of the new managed management domain; and the expected configuration cloud resource type information is compared with cloud resource type information that can be provided by all management domain groups to select a management domain group that matches the new managed management domain.

[0110] The new managed management domain needs different types of cloud resources such as computing power cloud resources, cloud memory resources, storage cloud resources, and network bandwidth cloud resources during execution of an operation task. In order to ensure that the new managed management domain can obtain appropriate cloud resource configuration in each process stage of the operation task, the work log of the new managed management domain is analyzed to obtain expected configuration cloud resource type information of a currently executed operation task; the expected configuration cloud resource type information is compared with cloud resource type information that can be provided by all management domain groups to select a management domain group that matches the new managed management domain, so that the selected management domain group can configure appropriate cloud resources in the corresponding process stage of the operation task of the new managed management domain. Cloud resource demand prediction is further performed based on the region and business type of the new managed management domain and historical data of the new managed management domain and the matched management domain group. The operation task currently executed by the new managed management domain is further monitored to obtain task running process information corresponding to the currently executed operation task, and the task running process information is compared with cloud resources in an idle state of all private cloud management domains under the matched management domain cluster to determine private cloud management domains that can configure corresponding types of cloud resources for the new managed management domain, and corresponding cloud resources are extracted from the determined private cloud management domains and configured for the new managed management domain, so as to ensure that the new managed management domain obtains reliable and sustainable cloud resource configuration, improves task running efficiency, and fully utilizes cloud resources of the management domain.

[0111] In another embodiment, running quality determination is performed on a work log acquisition process of a new managed management domain, including:

[0112] The acquisition duration of the work log is extracted;

[0113] The acquisition duration of the work log is compared with a preset acquisition duration threshold;

[0114] When the acquisition duration of the work log exceeds the preset acquisition duration threshold, running parameters for acquiring the work log are called, wherein the running parameters include a diary screening accuracy, a diary call garbled code proportion, and a diary call response duration;

[0115] The diary screening accuracy, the diary call garbled code proportion, and the diary call response duration are used to obtain a diary call running evaluation coefficient;

[0116] wherein the diary call operation evaluation coefficient is obtained by the following formula:

[0117] wherein W represents the diary call operation evaluation coefficient; n represents the number of diary calls; P i represents the diary screening accuracy corresponding to the i-th diary call; L i represents the proportion of garbled codes in the i-th diary call; T i represents the diary call response time corresponding to the i-th diary call; T Lmax represents the diary call response time corresponding to the maximum proportion of garbled codes; T Lmin represents the diary call response time corresponding to the minimum proportion of garbled codes; S represents an adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0118] wherein S represents the adjustment coefficient; L pmin represents the proportion of garbled codes corresponding to the minimum diary screening accuracy; L pmax represents the proportion of garbled codes corresponding to the maximum diary screening accuracy; L min represents the minimum proportion of garbled codes; L max represents the maximum proportion of garbled codes;

[0119] comparing the diary call operation evaluation coefficient with a preset coefficient threshold;

[0120] when the diary call operation evaluation coefficient is lower than the preset coefficient threshold, it is determined that the diary acquisition process is abnormal, and an abnormal alarm is given.

[0121] The beneficial effects of the above embodiments are that by extracting the acquisition duration of the work log and comparing it with the preset acquisition duration threshold, the real-time monitoring of the work log acquisition process of the newly managed management domain can be realized. Once the acquisition duration exceeds the threshold, further analysis and judgment process is triggered immediately to ensure that potential abnormalities can be discovered and handled in a timely manner. When the acquisition duration is abnormal, the scheme not only focuses on a single duration indicator, but also further retrieves the running parameters of the acquisition work log, including the diary screening accuracy, the diary retrieval garbled code proportion, and the diary retrieval response duration. These parameters together constitute a comprehensive evaluation of the running quality of the work log acquisition process, which helps to more accurately identify the problem. By introducing the diary retrieval running evaluation coefficient W, the scheme realizes the quantitative evaluation of the running quality of the work log acquisition process. This coefficient considers multiple running parameters and is calculated through a specific formula, which can more intuitively reflect the running state of the system. The introduction of the adjustment coefficient S makes the calculation of the evaluation coefficient W more flexible and adaptive. The value of S is adjusted according to the changes of the diary screening accuracy and the diary retrieval garbled code proportion, which can more accurately reflect the running quality of the system in different states. When the diary retrieval running evaluation coefficient is lower than the preset coefficient threshold, the scheme can automatically determine that the acquisition process of the work log is abnormal and perform abnormal alarm. This helps the operation and maintenance personnel to discover problems in a timely manner and take appropriate measures for troubleshooting and repair, thereby ensuring the stable operation of the system.

[0122] In summary, the technical scheme effectively improves the running quality and reliability of the work log acquisition process of the newly managed management domain through real-time monitoring, multi-dimensional evaluation, quantitative evaluation, adaptive adjustment, and abnormal alarm.

[0123] Overall, the cloud resource configuration method and system based on multi-private cloud management domain classification obtain cloud resource configuration historical data of all private cloud management domains from cloud resource configuration historical records of the private cloud management domains, and preprocess and correct the cloud resource configuration historical data to obtain effective cloud resource configuration record data; then, the effective cloud resource configuration record data is subjected to clustering analysis processing, and based on cloud resource configuration feature information of all private cloud management domains, the similarity and difference between different management domains are accurately identified and analyzed, so as to divide all private cloud management domains into several management domain groups, facilitating subsequent centralized and unified provision of cloud resources by the management domain groups; further, based on the work log of the newly managed management domain, cloud resource demand attribute information of the newly managed management domain is determined, the newly managed management domain is identified and classified by using the management domain groups, so as to select a management domain group matched with the newly managed management domain, and based on the region and business type of the newly managed management domain, accurate and efficient cloud resource demand prediction is performed according to existing data of the newly managed management domain and historical data of the matched management domain group.

[0124] The above is only one specific embodiment of the present application, and any improvement made on the basis of the concept of the present application is considered to be within the protection scope of the present application.

Claims

1. A cloud resource allocation method based on multiple private cloud management domain classification, characterized in that, include: Based on the cloud resource configuration history records of each of the multiple private cloud management domains, obtain the cloud resource configuration history data of each of the private cloud management domains, and preprocess the cloud resource configuration history data. The preprocessed historical cloud resource configuration data is then subjected to data correction processing to obtain valid cloud resource configuration record data. Cluster analysis is performed on the valid cloud resource configuration record data to obtain the cloud resource configuration feature information of each private cloud management domain. Based on the cloud resource configuration feature information, the similarity and difference between different management domains are identified and analyzed, and all private cloud management domains are divided into multiple management domain groups. Among them, all private cloud management domains under each management domain group meet the corresponding cloud resource configuration and change trend similarity conditions. Based on the work logs of the newly added management domains, the cloud resource demand attribute information of the newly added management domains is determined. The newly added management domains are identified and classified using management domain groups, thereby selecting management domain groups that match the newly added management domains. Then, based on the location and business type of the newly added management domains, the existing data of the newly added management domains, and the historical data of the matching management domain groups, cloud resource demand is predicted.

2. The cloud resource allocation method based on multi-private cloud management domain classification as described in claim 1, characterized in that: Based on the cloud resource configuration history records of each of the multiple private cloud management domains, obtain the cloud resource configuration history data of each of the private cloud management domains, and preprocess the cloud resource configuration history data. The preprocessed historical cloud resource configuration data is then subjected to data correction processing to obtain valid cloud resource configuration record data, including: The system acquires cloud resource configuration history records for multiple private cloud management domains within a preset historical time interval. It then analyzes these records to obtain all valid cloud resource configuration behaviors occurring within the preset time interval for each private cloud management domain. Further analysis of these valid behaviors determines the configuration history data for different types of cloud resources for each private cloud management domain. This configuration history data includes at least the configuration occurrence time and the number of configured resources for the corresponding type of cloud resource. The different types of cloud resources include computing power cloud resources, memory cloud resources, storage cloud resources, and network bandwidth cloud resources. Finally, the configuration history data undergoes noise removal preprocessing and missing data completion preprocessing. Based on the Holt-Winters model, the configuration history data that has undergone noise removal preprocessing and missing data completion preprocessing is smoothed; then, based on the result of the smoothing, the configuration history data is corrected by removing and eliminating abnormal data components, thereby obtaining effective cloud resource configuration record data.

3. The cloud resource allocation method based on multi-private cloud management domain classification as described in claim 2, characterized in that: Cluster analysis is performed on the valid cloud resource configuration records to obtain cloud resource configuration feature information for each private cloud management domain. Based on the cloud resource configuration feature information, the similarities and differences between different management domains are identified and analyzed, and all private cloud management domains are divided into multiple management domain groups. Each management domain group contains private cloud management domains that meet corresponding conditions regarding similarity in cloud resource configuration and change trends, including: Based on a hybrid algorithm of DBSCAN and Kmeans, cluster analysis is performed on the effective cloud resource configuration record data to obtain the demand change trend characteristics of each private cloud management domain in the process of configuring different types of cloud resources. Based on the aforementioned demand change trend characteristics, the cloud resource type information matched and configured for each of the private cloud management domains is determined; then, based on the matched and configured cloud resource type information, all private cloud management domains are divided into multiple management domain groups; wherein, all private cloud management domains under each management domain group are matched and configured with the same type of cloud resources, and the demand change trend of the cloud resources matched and configured for each private cloud management domain under each management domain group is within a preset quantity range.

4. The cloud resource allocation method based on multi-private cloud management domain classification as described in claim 3, characterized in that: Based on the work logs of the newly added management domains, the cloud resource demand attribute information of the newly added management domains is determined. The newly added management domains are then identified and classified using management domain groups to select management domain groups that match the newly added management domains. Furthermore, based on the geographical location and business type of the newly added management domains, their existing data, and the historical data of the matched management domain groups, cloud resource demand is predicted, including: The work logs of the newly added management domain are analyzed to obtain the expected cloud resource type information of the computing tasks currently being executed by the newly added management domain. The expected cloud resource type information is compared with the cloud resource type information that each management domain group can provide, and a management domain group that matches the newly added management domain is selected. Then, based on the location and business type of the newly added management domain, the existing data of the newly added management domain, and the historical data of the matching management domain group, cloud resource demand is predicted.

5. The cloud resource allocation method based on multi-private cloud management domain classification as described in claim 4, characterized in that: The process of acquiring work logs for newly added management domains is assessed for operational quality, including: Extract the acquisition time of the work log; The acquisition time of the work log is compared with a preset acquisition time threshold; When the acquisition time of the work log exceeds the preset acquisition time threshold, the operation parameters for acquiring the work log are retrieved. The operation parameters include the log filtering accuracy, the proportion of garbled characters in the log retrieval, and the log retrieval response time. The diary retrieval operation evaluation coefficient is obtained by using the diary screening accuracy, the proportion of garbled characters in diary retrieval, and the diary retrieval response time. The evaluation coefficient for log retrieval operation is obtained using the following formula: Where W represents the log retrieval performance evaluation coefficient; n represents the number of log retrievals; P i L represents the accuracy rate of diary filtering during the i-th diary retrieval; i T represents the percentage of garbled characters in the i-th diary retrieval; i T represents the log retrieval response time for the i-th log retrieval; Lmax This indicates the log retrieval response time corresponding to the maximum percentage of garbled characters in the log retrieval; T Lmin The response time for retrieving logs corresponds to the minimum proportion of garbled characters in the log retrieval; S represents the adjustment coefficient, which is obtained using the following formula: Where S represents the adjustment coefficient; L pmin This represents the percentage of garbled characters in the diary retrieval process when the diary filtering accuracy reaches its minimum; L pmax This represents the percentage of garbled characters in the diary retrieval process corresponding to the maximum accuracy of the diary filtering; L min This represents the minimum percentage of garbled characters retrieved from diary entries; L max This indicates the maximum percentage of garbled characters retrieved from the diary. The evaluation coefficients for the log retrieval process are compared with preset coefficient thresholds; When the evaluation coefficient for log retrieval is lower than the preset coefficient threshold, it is determined that there is an anomaly in the process of obtaining the work log, and an anomaly alarm is triggered.

6. A cloud resource allocation system based on multiple private cloud management domain classification, characterized in that, include: The historical data acquisition and preprocessing module is used to acquire the cloud resource configuration history data of each of the multiple private cloud management domains based on their respective cloud resource configuration history records, and to preprocess the cloud resource configuration history data. The historical data correction module is used to perform data correction processing on the preprocessed cloud resource configuration historical data to obtain valid cloud resource configuration record data. The cloud resource configuration feature identification module is used to perform cluster analysis on the valid cloud resource configuration record data to obtain the cloud resource configuration feature information of each private cloud management domain. The management domain grouping module is used to identify and analyze the similarities and differences between different management domains based on the cloud resource configuration feature information, and to divide all private cloud management domains into multiple management domain groups; wherein, all private cloud management domains under each management domain group meet the corresponding cloud resource configuration and change trend similarity conditions. The management domain group selection module is used to determine the cloud resource demand attribute information of the newly managed management domain based on the work log of the newly managed management domain, identify and classify the newly managed management domain using management domain groups, and select management domain groups that match the newly managed management domain. The cloud resource configuration prediction module is used to predict cloud resource demand based on the location and business type of the newly managed domain, the existing data of the newly managed domain, and the historical data of the matched management domain group.

7. The cloud resource allocation system based on multi-private cloud management domain classification as described in claim 6, characterized in that: The historical data acquisition and preprocessing module is used to acquire historical cloud resource configuration data for each of the multiple private cloud management domains based on their respective historical cloud resource configuration records, and to preprocess the historical cloud resource configuration data, including: The system acquires cloud resource configuration history records for multiple private cloud management domains within a preset historical time interval. It then analyzes these records to obtain all valid cloud resource configuration behaviors occurring within the preset time interval for each private cloud management domain. Further analysis of these valid behaviors determines the configuration history data for different types of cloud resources for each private cloud management domain. This configuration history data includes at least the configuration occurrence time and the number of configured resources for the corresponding type of cloud resource. The different types of cloud resources include computing power cloud resources, memory cloud resources, storage cloud resources, and network bandwidth cloud resources. Finally, the configuration history data undergoes noise removal preprocessing and missing data completion preprocessing. The historical data correction module is used to perform data correction processing on the preprocessed cloud resource configuration historical data to obtain valid cloud resource configuration record data, including: Based on the Holt-Winters model, the configuration history data that has undergone noise removal preprocessing and missing data completion preprocessing is smoothed; then, based on the result of the smoothing, the configuration history data is corrected by removing and eliminating abnormal data components, thereby obtaining effective cloud resource configuration record data.

8. The cloud resource allocation system based on multi-private cloud management domain classification as described in claim 6, characterized in that: The cloud resource configuration feature identification module is used to perform cluster analysis on the valid cloud resource configuration record data to obtain cloud resource configuration feature information for each private cloud management domain, including: Based on a hybrid algorithm of DBSCAN and Kmeans, cluster analysis is performed on the effective cloud resource configuration record data to obtain the demand change trend characteristics of each private cloud management domain in the process of configuring different types of cloud resources. The management domain grouping module is used to identify and analyze the similarities and differences between different management domains based on the cloud resource configuration feature information, and to divide all private cloud management domains into multiple management domain groups; wherein, all private cloud management domains under each management domain group meet the corresponding conditions of similar cloud resource configuration and change trends, including: Based on the aforementioned demand change trend characteristics, the cloud resource type information matched and configured for each of the private cloud management domains is determined; then, based on the matched and configured cloud resource type information, all private cloud management domains are divided into multiple management domain groups; wherein, all private cloud management domains under each management domain group are matched and configured with the same type of cloud resources, and the demand change trend of the cloud resources matched and configured for each private cloud management domain under each management domain group is within a preset quantity range.

9. The cloud resource allocation system based on multi-private cloud management domain classification as described in claim 8, characterized in that: The management domain group selection module is used to determine the cloud resource demand attribute information of the newly added management domain based on the work logs of the newly added management domain, identify and classify the newly added management domain using management domain groups, and select management domain groups that match the newly added management domain, including: The work logs of the newly added management domain are analyzed to obtain the expected cloud resource type information of the computing tasks currently being executed by the newly added management domain; the expected cloud resource type information is compared with the cloud resource type information that each of the management domain groups can provide, and the management domain group that matches the newly added management domain is selected.

10. The cloud resource allocation system based on multi-private cloud management domain classification as described in claim 9, characterized in that: The process of acquiring work logs for newly added management domains is assessed for operational quality, including: Extract the acquisition time of the work log; The acquisition time of the work log is compared with a preset acquisition time threshold; When the acquisition time of the work log exceeds the preset acquisition time threshold, the operation parameters for acquiring the work log are retrieved. The operation parameters include the log filtering accuracy, the proportion of garbled characters in the log retrieval, and the log retrieval response time. The diary retrieval operation evaluation coefficient is obtained by using the diary screening accuracy, the proportion of garbled characters in diary retrieval, and the diary retrieval response time. The evaluation coefficient for log retrieval operation is obtained using the following formula: Where W represents the log retrieval performance evaluation coefficient; n represents the number of log retrievals; P i L represents the accuracy rate of diary filtering during the i-th diary retrieval; i T represents the percentage of garbled characters in the i-th diary retrieval; i T represents the log retrieval response time for the i-th log retrieval; Lmax This indicates the log retrieval response time corresponding to the maximum percentage of garbled characters in the log retrieval; T Lmin The response time for retrieving logs corresponds to the minimum proportion of garbled characters in the log retrieval; S represents the adjustment coefficient, which is obtained using the following formula: Where S represents the adjustment coefficient; L pmin This represents the percentage of garbled characters in the diary retrieval process when the diary filtering accuracy reaches its minimum; L pmax This represents the percentage of garbled characters in the diary retrieval process corresponding to the maximum accuracy of the diary filtering; L min This represents the minimum percentage of garbled characters retrieved from diary entries; L max This indicates the maximum percentage of garbled characters retrieved from the diary. The evaluation coefficients for the log retrieval process are compared with preset coefficient thresholds; When the evaluation coefficient for log retrieval is lower than the preset coefficient threshold, it is determined that there is an anomaly in the process of obtaining the work log, and an anomaly alarm is triggered.

Images