Cloud computing power analysis method and cloud computing power platform and system

Abstract

The invention provides a cloud computing power analysis method and a cloud computing power platform and system, and the method comprises the steps: effectively achieving the obtaining of an optimal cloud computing power resource when a target task is achieved through constructing a cloud computing power resource center, thereby guaranteeing the efficiency of completing the target task, saving the resources, improving the adaptability to different target tasks, and achieving the purpose of achieving the optimal cloud computing power resource. By dynamically updating the cloud computing power resources according to the execution process until the target task is completed, the standard of the target task can be effectively guaranteed to be reached within the expected completion time, and the accuracy and effectiveness of task completion are effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing power data processing, and particularly relates to a cloud computing power parsing method, a cloud computing power platform and a system. Background Art

[0002] At present, with the rapid development of information technology, cloud computing has become an important infrastructure for modern enterprises and research institutions to process massive data and run complex applications. In many fields such as big data analysis, artificial intelligence training, and scientific computing, the demand for computing power has shown an explosive growth;

[0003] However, in the existing cloud computing environment, the management and allocation of computing power resources face many problems. On the one hand, the computing power requirements of different users and applications vary greatly in terms of type, scale, and time. On the other hand, cloud service providers often have various types and specifications of computing devices. How to effectively integrate the computing power of these devices to meet the diverse needs of different users has become an urgent problem to be solved;

[0004] Therefore, in order to overcome the above technical problems, the present invention provides a cloud computing power parsing method, a cloud computing power platform and a system. Summary of the Invention

[0005] The present invention provides a cloud computing power parsing method, a cloud computing power platform and a system, which can effectively realize the acquisition of the best cloud computing power resources when achieving the target task by constructing a cloud computing power resource center, so as to ensure the efficiency of completing the target task and save resources, improve the adaptability to different target tasks, and effectively ensure the accuracy and effectiveness of task completion by dynamically updating the cloud computing power resources according to the execution process until the target task is completed, and can effectively ensure that the standard of the target task is reached within the expected completion time.

[0006] A cloud computing power parsing method includes:

[0007] Step 1: Construct a cloud computing power resource management center. At the same time, based on the user terminal, input the target task and obtain the task requirement information of the target task;

[0008] Step 2: Evaluate the available cloud computing power resources in the cloud computing power resource management center according to the task requirement information;

[0009] Step 3: Analyze the available cloud computing power resources to obtain the best cloud computing power resources, and execute the target task input by the user terminal based on the best cloud computing power resources;

[0010] Step 4: Collect the execution process and dynamically update the cloud computing power resources according to the execution process until the target task is completed.

[0011] Preferably, for a cloud computing power parsing method, in step 1, a cloud computing power resource management center is constructed, including:

[0012] Read a number of cloud computing power resources. At the same time, respectively extract the resource characteristics of each cloud computing power resource and the resource label of the cloud computing power resource;

[0013] Read the feature types included in the resource characteristics, and determine the feature labels according to the feature types;

[0014] Generate a horizontal record chain according to the feature labels, and at the same time, generate a vertical record chain according to the resource labels;

[0015] Respectively map the data of a number of cloud computing power resources in the horizontal record chain and the vertical record chain according to the feature labels and the resource labels to generate a cloud computing power resource comprehensive node;

[0016] Analyze the cloud computing power resource comprehensive node, determine the splitting mark for the cloud computing power resource comprehensive node, and split and store the cloud computing power resource comprehensive node according to the splitting mark to construct a cloud computing power resource management center.

[0017] Preferably, for a cloud computing power parsing method, analyze the cloud computing power resource comprehensive node, determine the splitting mark for the cloud computing power resource comprehensive node, and split and store the cloud computing power resource comprehensive node according to the splitting mark, including:

[0018] Read the cloud computing power resource comprehensive node, determine the target similarity between the horizontal record chain of any cloud computing power resource in the cloud computing power resource comprehensive node and the horizontal record chains of the remaining cloud computing power resources, and mark the first position of any cloud computing power resource in the vertical record chain;

[0019] Mark the first target cloud computing power resource when the target similarity reaches a preset condition among the remaining cloud computing power resources, and locate the second position of the first target cloud computing power resource in the vertical record chain;

[0020] Perform a splitting mark on the cloud computing power resource comprehensive node according to the first position and the corresponding second position to obtain multiple sub-cloud computing power resource comprehensive nodes;

[0021] Construct a storage interval, store each sub-cloud computing power resource comprehensive node in the corresponding storage interval, and add a resource label to the storage interval.

[0022] Preferably, for a cloud computing power parsing method, in step 1, based on the user terminal, input a target task and obtain the task requirement information of the target task, including:

[0023] Based on the user terminal, determine the target task, and determine the target task upload request according to the target task;

[0024] Perform eligibility verification on the target task upload request based on the cloud computing power platform, and read the target task upload request after passing the eligibility verification to determine the target task;

[0025] Read the target task and extract the task requirement keywords;

[0026] Determine the task requirement information of the target task according to the task requirement keywords.

[0027] Preferably, for a cloud computing power analysis method, in step 2, evaluate the available cloud computing power resources in the cloud computing power resource management center according to the task requirement information, including:

[0028] Read the task requirement information to determine the requirement dimensions in the task requirement information and the requirement criteria under each requirement dimension;

[0029] Input the requirement dimensions and the requirement criteria under each requirement dimension into the cloud computing power resource management center for matching, and judge the second target cloud computing power resources that meet the requirement criteria;

[0030] Read the working status of the second target cloud computing power resources in real time;

[0031] Select the third target cloud computing power resources in the working status of the second target cloud computing power resources, where the third target cloud computing power resources are the available cloud computing power resources.

[0032] Preferably, for a cloud computing power analysis method, in step 3, analyze the available cloud computing power resources to obtain the optimal cloud computing power resources, and execute the target task input by the user terminal based on the optimal cloud computing power resources, including:

[0033] Read the target task to determine the execution steps for completing the target task, and divide the target task according to the execution steps to obtain multiple sub-target tasks;

[0034] Read the resource requirement criteria for each sub-target task;

[0035] Perform pooling management on the available cloud computing power resources to obtain a target resource pool, where the target resource pool includes a set of configurations of the available cloud computing power resources;

[0036] Match according to the resource requirement criteria of each sub-target task in the target resource pool to obtain the target configuration sequence corresponding to each sub-target task;

[0037] Sort the target configuration sequences corresponding to each sub-target task according to the execution order of the execution steps, and perform permutation and combination on the target configuration sequences corresponding to each sub-target task according to the sorting result to obtain multiple configuration combinations for completing the target task;

[0038] Select the target configuration combination from multiple configuration combinations as the optimal cloud computing power resource, and execute the target task according to the optimal cloud computing power resource.

[0039] Preferably, a cloud computing power analysis method, which selects the target configuration combination from multiple configuration combinations as the optimal cloud computing power resource, and executes the target task according to the optimal cloud computing power resource, includes:

[0040] Obtain the task parameters for executing the target task, and simulate the task parameters for executing the target task in a computer. At the same time, simulate and execute the target task in the computer based on multiple configuration combinations respectively to obtain the completion efficiency of each configuration combination;

[0041] Select the two configuration combinations with the top completion efficiency rankings, and use the configuration combination with the first completion efficiency as the optimal cloud computing power resource. At the same time, use the configuration combination with the second completion efficiency as the alternative cloud computing power resource;

[0042] Execute the target task input by the user terminal according to the optimal cloud computing power resource, and when the optimal cloud computing power resource cannot execute, start the alternative cloud computing power resource.

[0043] Preferably, in step 4 of a cloud computing power analysis method, collect the execution process and dynamically update the cloud computing power resource according to the execution process until the target task is completed, including:

[0044] When executing the target task based on the optimal cloud computing power resource, collect the execution process of executing the target task in real time to determine the real-time progress of executing the target task;

[0045] Determine the remaining execution amount and execution duration of the target task according to the real-time progress of the execution task;

[0046] Obtain the execution speed of the optimal cloud computing power resource, and determine the remaining time to complete the target task according to the execution speed of the optimal cloud computing power resource and the remaining execution amount of the target task;

[0047] Obtain the expected completion time to complete the target task, and calculate the target difference time between the expected completion time and the execution duration;

[0048] Compare the remaining time with the target difference time to determine whether it is necessary to update the cloud computing power resource;

[0049] When the remaining time is less than or equal to the target difference time, it is determined that there is no need to update the cloud computing power resource;

[0050] Otherwise, it is determined that it is necessary to update the cloud computing power resource, retrieve the cloud computing power resource that meets the target difference time in the cloud computing power resource management center, and at the same time, update the current optimal cloud computing power resource according to the retrieval result.

[0051] A cloud computing power platform, comprising: steps for executing any one of the described cloud computing power parsing methods.

[0052] A cloud computing power parsing system, comprising:

[0053] A construction module, configured to construct a cloud computing power resource management center. Meanwhile, based on the input of a target task by a user terminal, task requirement information of the target task is obtained;

[0054] An evaluation module, configured to evaluate available cloud computing power resources in the cloud computing power resource management center according to the task requirement information;

[0055] An analysis module, configured to analyze the available cloud computing power resources to obtain the optimal cloud computing power resources, and execute the target task input by the user terminal based on the optimal cloud computing power resources;

[0056] An update module, configured to collect the execution process and dynamically update the cloud computing power resources according to the execution process until the target task is completed.

[0057] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0058] By constructing a cloud computing power resource center, it is effectively realized to obtain the optimal cloud computing power resources when achieving the target task, thereby ensuring the efficiency of completing the target task and the purpose of saving resources, improving the adaptability to different target tasks. By dynamically updating the cloud computing power resources according to the execution process until the target task is completed, it can effectively ensure that the standard of the target task is achieved within the expected completion time, and effectively ensure the accuracy and effectiveness of task completion.

[0059] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained through the structures specifically pointed out in this application document.

[0060] Next, through the drawings and embodiments, the technical solutions of the present invention will be further described in detail. Description of the Drawings

[0061] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0062] Figure 1 It is a flowchart of the steps of a cloud computing power parsing method in an embodiment of the present invention;

[0063] Figure 2 It is a flowchart of step 1 in a cloud computing power parsing method in an embodiment of the present invention;

[0064] Figure 3 This is a structural diagram of a cloud computing power analysis system in an embodiment of the present invention. Specific implementation manners

[0065] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0066] Embodiment 1:

[0067] This embodiment provides a cloud computing power analysis method, as Figure 1 shown, including:

[0068] Step 1: Build a cloud computing power resource management center. At the same time, based on the user terminal, input a target task and obtain the task requirement information of the target task;

[0069] Step 2: Evaluate the available cloud computing power resources in the cloud computing power resource management center according to the task requirement information;

[0070] Step 3: Analyze the available cloud computing power resources to obtain the best cloud computing power resources, and execute the target task input by the user terminal based on the best cloud computing power resources;

[0071] Step 4: Collect the execution process and dynamically update the cloud computing power resources according to the execution process until the target task is completed.

[0072] In this embodiment, the cloud computing power resource management center is applicable to one or more of the following: technology development, technology consulting, technology services, technology transfer in the fields of data technology, network technology, intelligent technology, electromechanical technology, and computer technology; application software services, basic software services; contract energy management; sales of electromechanical equipment, communication equipment, building materials, metal materials, instruments and meters, electronic products, computer software and hardware and auxiliary equipment; computer information system integration; investment operation management of transmission network infrastructure, database processing; design and construction of construction projects, security projects, decoration projects, and electronic intelligence projects; exhibition display planning; value-added telecommunications services; broadband user premise network services.

[0073] In this embodiment, the cloud computing power resource management center is an area used to manage different cloud computing power resources. By the cloud computing power resource management center, different cloud computing power resources can be retrieved for different target tasks to achieve the maximization of the utilization of cloud computing power resources.

[0074] In this embodiment, executing the target task input by the user terminal based on the optimal cloud computing power resources means matching the computing power resources that can complete the target task in the cloud computing power resource management center, and then using the matching computing power resources as available computing power resources, determining the optimal computing power resources from the available computing power resources, so as to complete the target task through the optimal cloud computing power resources, which helps to complete the target task in an efficient and resource-saving manner.

[0075] In this embodiment, the collection execution process refers to the process data when completing the target task, including the execution progress and so on.

[0076] In this embodiment, dynamically updating the cloud computing power resources according to the execution process means judging whether the remaining tasks can be completed within the specified time through the execution process. If they cannot be completed within the specified time, then re-determine the cloud computing power resources that meet the requirements in the cloud computing power resource management center for updating to ensure the smooth completion of the target task.

[0077] In this embodiment, the target task is the task that needs to be completed (for example: the data scale and processing in data processing, the model architecture and data volume in artificial intelligence training, etc.), and the target task requirements are the requirements for completing the target task, such as: the expected completion time, the calculation accuracy requirements, etc.

[0078] The working principle and beneficial effects of the above technical solution are: by constructing a cloud computing power resource center, it effectively realizes the acquisition of the optimal cloud computing power resources when achieving the target task, thus ensuring the efficiency of completing the target task and the purpose of saving resources, improving the adaptability to different target tasks. By dynamically updating the cloud computing power resources according to the execution process until the target task is completed, it can effectively ensure meeting the standards of the target task within the expected completion time and effectively ensure the accuracy and effectiveness of task completion.

[0079] Embodiment 2:

[0080] Based on Embodiment 1, this embodiment provides a cloud computing power parsing method. As Figure 2 shown, in step 1, constructing a cloud computing power resource management center includes:

[0081] S101: Read a number of cloud computing power resources. At the same time, respectively extract the resource characteristics and resource labels of each cloud computing power resource;

[0082] S102: Read the feature types included in the resource characteristics and determine the feature labels according to the feature types;

[0083] S103: Generate a horizontal record chain according to the feature labels. At the same time, generate a vertical record chain according to the resource labels;

[0084] S104: Respectively perform data association mapping on several cloud computing power resources according to the feature tags and resource tags in the horizontal record chain and the vertical record chain to generate a comprehensive node of cloud computing power resources;

[0085] S105: Analyze the comprehensive node of cloud computing power resources, determine the splitting mark for the comprehensive node of cloud computing power resources, and split and store the comprehensive node of cloud computing power resources according to the splitting mark to construct a cloud computing power resource management center.

[0086] In this embodiment, the resource characteristics represent information such as the type and value of cloud computing power resources.

[0087] In this embodiment, the resource tag is a marking symbol for distinguishing cloud computing power resources.

[0088] In this embodiment, the feature type is used to represent the classification results of multiple different attributes in the resource characteristics. For example, the computing power, storage capacity, and network bandwidth of cloud computing power resources, etc. One attribute corresponds to one feature category, and one feature category corresponds to one feature tag.

[0089] In this embodiment, the horizontal record chain is used to record the feature tags of cloud computing power resources, and the vertical record chain is used to record the resource tags of cloud computing power resources. By performing data association mapping on the feature tags and resource tags in the horizontal record chain and the vertical record chain, a comprehensive node of cloud computing power resources can be effectively generated.

[0090] The working principle and beneficial effects of the above technical solution are: By determining the resource characteristics and resource tags of each cloud computing power resource, data association mapping of different cloud computing power resources is realized according to the resource characteristics and resource tags, and then the comprehensive cloud computing power resources are analyzed to realize the splitting and storage of the comprehensive node of cloud computing power resources, providing a reliable guarantee for cloud computing power parsing.

[0091] Embodiment 3:

[0092] Based on Embodiment 2, this embodiment provides a cloud computing power parsing method, which analyzes the comprehensive node of cloud computing power resources, determines the splitting mark for the comprehensive node of cloud computing power resources, and splits and stores the comprehensive node of cloud computing power resources according to the splitting mark, including:

[0093] Read the comprehensive node of cloud computing power resources, determine the target similarity between the horizontal record chain of any cloud computing power resource in the comprehensive node of cloud computing power resources and the horizontal record chains of the remaining cloud computing power resources, and mark the first position of any cloud computing power resource in the vertical record chain;

[0094] Mark the first target cloud computing power resource when the target similarity reaches a preset condition among the remaining cloud computing power resources, and locate the second position of the first target cloud computing power resource in the vertical record chain;

[0095] Split and label the cloud computing power resource integration node according to the first position and the corresponding second position to obtain multiple sub-cloud computing power resource integration nodes;

[0096] Construct a storage interval, store each sub-cloud computing power resource integration node in the corresponding storage interval, and add resource labels to the storage interval.

[0097] In this embodiment, the target similarity is used to characterize the similarity degree between the horizontal record chain of any cloud computing power resource and the horizontal record chains of other cloud computing power resources. The larger the value, the more similar.

[0098] In this embodiment, the first position refers to the specific position information corresponding to different cloud computing power resources in the vertical record chain.

[0099] In this embodiment, the preset condition is set in advance.

[0100] In this embodiment, the first target cloud computing power resource refers to the cloud computing power resource whose target similarity with the reference cloud computing power resource among other cloud computing power resources reaches the preset condition when analyzing the similarity of other cloud computing power resources with any cloud computing power resource as the reference, and it is not unique.

[0101] In this embodiment, the second position refers to the specific position of other cloud computing power resources in the vertical record chain when the determined target similarity reaches the preset condition.

[0102] In this embodiment, the sub-cloud computing power resource integration node refers to different cloud computing power resource integration nodes obtained by splitting and labeling the cloud computing power resource integration node.

[0103] In this embodiment, the resource label refers to a marking symbol for distinguishing different sub-cloud computing power resource integration nodes.

[0104] The working principle and beneficial effects of the above technical solution are: by analyzing the cloud computing power resource integration node, the positions of different cloud computing power resources in the horizontal record chain and the vertical record chain are determined. Finally, the cloud computing power resource integration node is split and labeled according to the determined positions, so as to lock multiple sub-cloud computing power resource integration nodes. Finally, the obtained multiple sub-cloud computing power resource integration nodes are stored in the constructed storage interval, ensuring the accurate and reliable integration of cloud computing power resources and providing guarantee and convenience for cloud computing power analysis.

[0105] Embodiment 4:

[0106] Based on Embodiment 1, this embodiment provides a cloud computing power parsing method. In step 1, a target task is input based on the user terminal, and the task requirement information of the target task is obtained, including:

[0107] Determine the target task based on the user terminal, and determine the target task upload request according to the target task;

[0108] Based on the cloud computing power platform, perform qualification verification on the target task upload request, and when the qualification verification is passed, read the target task upload request to determine the target task;

[0109] Read the target task and extract the task requirement keywords;

[0110] Determine the task requirement information of the target task according to the task requirement keywords.

[0111] In this embodiment, the target task upload request is related to the type of the target task and the business that can be processed, and is the introduction parameter of the target task sent to the cloud computing power platform.

[0112] In this embodiment, the qualification verification refers to verifying the compliance and permissions of the target task upload request through the cloud computing power platform.

[0113] In this embodiment, the task requirement keywords refer to the data fragments obtained after parsing the target task, which can represent the purpose or specific processing business of the target task.

[0114] The working principle and beneficial effects of the above technical solution are: by performing qualification verification on the target task upload request of the user terminal and parsing the target task upload request after the qualification verification is passed, the task requirement information of the target task of the user terminal can be accurately and effectively determined according to the parsing result, so as to facilitate the allocation of cloud computing power resources according to the task requirement information and ensure the processing effect and reliability of the target task of the user terminal.

[0115] Embodiment 5:

[0116] Based on Embodiment 1, this embodiment provides a cloud computing power parsing method. In step 2, evaluate the available cloud computing power resources in the cloud computing power resource management center according to the task requirement information, including:

[0117] Read the task requirement information, determine the requirement dimensions in the task requirement information and the requirement standards under each requirement dimension;

[0118] Input the requirement dimensions and the requirement standards under each requirement dimension into the cloud computing power resource management center for matching, and judge the second target cloud computing power resources that meet the requirement standards;

[0119] Read the working status of the second target cloud computing power resources in real time;

[0120] Extract the third target cloud computing power resources in the working status of the second target cloud computing power resources that are in a non-working state. Among them, the third target cloud computing power resources are the available cloud computing power resources.

[0121] In this embodiment, the demand dimension refers to different aspects of parsing the task. Among them, the demand standard corresponding to each demand dimension is the execution condition and the realization purpose of executing and completing the task corresponding to the current demand dimension.

[0122] In this embodiment, the second target cloud computing power resources are used to represent the cloud computing power resources that can execute the task demand information in line with the demand dimension and the demand standard under the demand dimension.

[0123] In this embodiment, the third target cloud computing power resources are the cloud computing power resources corresponding to the non-working state in the second target cloud computing power resources.

[0124] The working principle and beneficial effects of the above technical solution are as follows: By parsing the task demand information, the demand dimension corresponding to the task demand information and the demand standard under each demand dimension are accurately and effectively determined. Secondly, according to the demand dimension and the demand standard, the second target cloud computing power resources that meet the demand standard are matched from the cloud computing power resource management center, and the working status of the second target cloud computing power resources is determined in real time, so as to effectively obtain the third target cloud computing power resources in the non-working state from the second target cloud computing power resources. Finally, the determination of the available cloud computing power resources is realized, which provides convenience and guarantee for the determination of the best cloud computing power resources.

[0125] Embodiment 6:

[0126] On the basis of Embodiment 1, this embodiment provides a cloud computing power parsing method. In step 3, the available cloud computing power resources are analyzed to obtain the best cloud computing power resources, and the target task input by the user terminal is executed based on the best cloud computing power resources, including:

[0127] Read the target task, determine the execution steps for completing the target task, and divide the target task according to the execution steps to obtain multiple sub-target tasks;

[0128] Read the resource demand standard for each sub-target task;

[0129] Pool and manage the available cloud computing power resources to obtain a target resource pool, where the target resource pool includes the configuration composition set of the available cloud computing power resources;

[0130] Match according to the resource demand standard of each sub-target task in the target resource pool to obtain the target configuration sequence corresponding to each sub-target task;

[0131] Sort the target configuration sequences corresponding to each sub - target task according to the execution order of the execution steps, and perform permutations and combinations on the target configuration sequences corresponding to each sub - target task according to the sorting result to obtain multiple configuration combinations for completing the target task;

[0132] Select the target configuration combination from the multiple configuration combinations as the optimal cloud computing power resource, and execute the target task according to the optimal cloud computing power resource.

[0133] In this embodiment, the sub - target task is the result of splitting the target task according to the execution steps, and one execution step corresponds to one sub - target task.

[0134] In this embodiment, the pooling management of available cloud computing power resources is the result of centralizing and managing available cloud computing power resources such as CPUs and GPUs, that is, forming a target resource pool.

[0135] The working principle and beneficial effects of the above - mentioned technical solution are as follows: By parsing the target task, the execution steps of the target task are determined, so as to divide the target task according to the execution steps to obtain multiple sub - target tasks. Secondly, the resource requirement standards for each sub - target task are determined and matched with the target resource pool after pooling the available cloud computing power resources, so as to lock the target configuration sequence corresponding to each sub - target task, which provides a guarantee for determining the cloud computing power resource corresponding to the target task. Finally, the target configuration sequences corresponding to each sub - target task are permuted and combined according to the execution order of the execution steps, so as to accurately and reliably determine the optimal cloud computing power resource, thus ensuring the reliability, accuracy and efficiency of the execution of the target task.

[0136] Embodiment 7:

[0137] Based on Embodiment 6, this embodiment provides a cloud computing power analysis method. Select the target configuration combination from the multiple configuration combinations as the optimal cloud computing power resource, and execute the target task according to the optimal cloud computing power resource, including:

[0138] Obtain the task parameters for executing the target task, simulate the task parameters for executing the target task in a computer, and at the same time, simulate the execution of the target task in the computer based on the multiple configuration combinations respectively to obtain the completion efficiency of each configuration combination;

[0139] Select the top two configuration combinations in terms of completion efficiency ranking, use the configuration combination with the first - ranked completion efficiency as the optimal cloud computing power resource, and at the same time, use the configuration combination with the second - ranked completion efficiency as the alternative cloud computing power resource;

[0140] Execute the target task input by the user terminal according to the optimal cloud computing power resource, and when the optimal cloud computing power resource cannot be executed, start the alternative cloud computing power resource.

[0141] In this embodiment, the task parameters refer to parameters such as the amount of calculation and processing speed required to complete the target task.

[0142] In this embodiment, the alternative cloud computing power resource is used as a candidate resource for the optimal cloud computing power resource. Secondly, according to the sorting result, by analogy, when the alternative cloud computing power resource is used as the optimal cloud computing power resource and the optimal cloud computing power resource cannot be executed, the configuration combination ranked third in efficiency is determined, and so on until the execution of the target task is completed.

[0143] The working principle and beneficial effects of the above technical solution are: by determining the completion efficiency, the determination of the optimal cloud computing power resource and the alternative cloud computing power resource can be effectively realized, which can ensure the effectiveness and accuracy of the execution of the target task, and thus ensure the efficient completion of the target task.

[0144] Embodiment 8:

[0145] Based on Embodiment 1, this embodiment provides a cloud computing power analysis method. In step 4, collect the execution process and dynamically update the cloud computing power resource according to the execution process until the target task is completed, including:

[0146] When executing the target task based on the optimal cloud computing power resource, collect the execution process of the target task in real time and determine the real-time progress of the target task execution;

[0147] Determine the remaining execution amount and execution duration of the target task according to the real-time progress of the execution task;

[0148] Obtain the execution speed of the optimal cloud computing power resource, and determine the remaining time to complete the target task according to the execution speed of the optimal cloud computing power resource and the remaining execution amount of the target task;

[0149] Obtain the expected completion time to complete the target task, and calculate the target difference time between the expected completion time and the execution duration;

[0150] Compare the remaining time with the target difference time to determine whether it is necessary to update the cloud computing power resource;

[0151] When the remaining time is less than or equal to the target difference time, it is determined that there is no need to update the cloud computing power resource;

[0152] Otherwise, it is determined that it is necessary to update the cloud computing power resource, and the cloud computing power resource that meets the target difference time is retrieved in the cloud computing power resource management center. At the same time, the current optimal cloud computing power resource is updated according to the retrieval result.

[0153] In this embodiment, the remaining time to complete the target task determined according to the execution speed of the optimal cloud computing power resource and the remaining execution amount of the target task can be: remaining execution amount / execution speed = remaining time to complete the target task.

[0154] In this embodiment, retrieving the cloud computing power resource that meets the target difference time in the cloud computing power resource management center means determining the cloud computing power resource in the cloud computing power resource management center that can complete the task within the target difference time.

[0155] The working principle and beneficial effects of the above technical solution are: by collecting the execution process in real time, effectively mastering the real-time progress of completing the target task, and then effectively determining the remaining time to complete the target task. By determining the target difference time between the expected completion time and the execution duration and comparing it with the remaining time, effectively realizing the measurement of whether to update the cloud computing power resource, which is beneficial to ensuring the smooth progress of the target task.

[0156] Embodiment 9:

[0157] This embodiment provides a cloud computing power platform, including: performing the steps of a cloud computing power analysis method as described in any one of Embodiments 1 to 8.

[0158] The working principle and beneficial effects of the above technical solution are: by constructing a cloud computing power resource center, effectively realizing the acquisition of the optimal cloud computing power resource when achieving the target task, thereby ensuring the efficiency of completing the target task and the purpose of saving resources, improving the adaptability to different target tasks. By dynamically updating the cloud computing power resource according to the execution process until the target task is completed, it can effectively ensure meeting the standards of the target task within the expected completion time, and effectively ensure the accuracy and effectiveness of task completion.

[0159] Embodiment 10:

[0160] This embodiment provides a cloud computing power analysis system, as Figure 3 shown, including:

[0161] A construction module, used to construct a cloud computing power resource management center. At the same time, based on the input of the target task by the user terminal, obtain the task requirement information of the target task;

[0162] An evaluation module, used to evaluate the available cloud computing power resources in the cloud computing power resource management center according to the task requirement information;

[0163] An analysis module, used to analyze the available cloud computing power resources to obtain the optimal cloud computing power resource, and execute the target task input by the user terminal based on the optimal cloud computing power resource;

[0164] An update module, used to collect the execution process and dynamically update the cloud computing power resource according to the execution process until the target task is completed.

[0165] The working principle and beneficial effects of the above technical solution are as follows: By constructing a cloud computing power resource center, it can effectively achieve the acquisition of the best cloud computing power resources when achieving the target task, thereby ensuring the efficiency of completing the target task and the purpose of saving resources, improving the adaptability to different target tasks, and dynamically updating the cloud computing power resources according to the execution process until the target task is completed, which can effectively ensure meeting the standards of the target task within the expected completion time and effectively ensure the accuracy and effectiveness of task completion.

[0166] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications therein.

Claims

1. A cloud computing power parsing method, characterized in that, Including: Step 1: Build a cloud computing power resource management center. Meanwhile, based on the user terminal, input a target task and obtain the task requirement information of the target task; Step 2: Evaluate available cloud computing power resources in the cloud computing power resource management center according to the task requirement information; Step 3: Analyze the available cloud computing power resources to obtain the optimal cloud computing power resources, and execute the target task input by the user terminal based on the optimal cloud computing power resources; Step 4: Collect the execution process and dynamically update the cloud computing power resources according to the execution process until the target task is completed.

2. The cloud computing power parsing method according to claim 1, characterized in that In Step 1, building the cloud computing power resource management center includes: Read several cloud computing power resources. Meanwhile, respectively extract the resource characteristics and resource labels of each cloud computing power resource; Read the feature types included in the resource characteristics and determine the feature labels according to the feature types; Generate a horizontal record chain according to the feature labels, and generate a vertical record chain according to the resource labels; Respectively map the data of several cloud computing power resources to the horizontal record chain and the vertical record chain according to the feature labels and resource labels to generate a comprehensive cloud computing power resource node; Analyze the comprehensive cloud computing power resource node, determine the splitting mark for the comprehensive cloud computing power resource node, and split and store the comprehensive cloud computing power resource node according to the splitting mark to build the cloud computing power resource management center.

3. The cloud computing power parsing method according to claim 2, wherein, Analyzing the comprehensive cloud computing power resource node, determining the splitting mark for the comprehensive cloud computing power resource node, and splitting and storing the comprehensive cloud computing power resource node according to the splitting mark includes: Read the comprehensive cloud computing power resource node, determine the target similarity between the horizontal record chain of any one cloud computing power resource in the comprehensive cloud computing power resource node and the horizontal record chains of the remaining cloud computing power resources, and mark the first position of any one cloud computing power resource in the vertical record chain; Mark the first target cloud computing power resource when the target similarity reaches the preset condition among the remaining cloud computing power resources, and locate the second position of the first target cloud computing power resource in the vertical record chain; Perform a splitting mark on the comprehensive cloud computing power resource node according to the first position and the corresponding second position to obtain multiple sub-comprehensive cloud computing power resource nodes; Build a storage interval, store each sub-comprehensive cloud computing power resource node in the corresponding storage interval, and add resource labels to the storage interval.

4. A cloud computing power parsing method according to claim 1, characterized in that In Step 1, based on the user terminal, input a target task and obtain the task requirement information of the target task, including: Determine the target task based on the user terminal and determine the target task upload request according to the target task; Based on the cloud computing power platform, verify the eligibility of the target task upload request, and when the eligibility verification is passed, read the target task upload request to determine the target task; Read the target task and extract the task requirement keywords; Determine the task requirement information of the target task according to the task requirement keywords.

5. A cloud computing power parsing method according to claim 1, characterized in that In Step 2, evaluating available cloud computing power resources in the cloud computing power resource management center according to the task requirement information includes: Read the task requirement information, determine the requirement dimensions in the task requirement information and the requirement standards under each requirement dimension; Input the requirement dimension and the requirement criteria under each requirement dimension into the cloud computing power resource management center for matching to determine the second target cloud computing power resources that meet the requirement criteria; Read the working status of the second target cloud computing power resources in real time; Select the third target cloud computing power resources in the working status of the second target cloud computing power resources, where the third target cloud computing power resources are the available cloud computing power resources.

6. The cloud computing power parsing method according to claim 1, characterized in that, In step 3, analyze the available cloud computing power resources to obtain the optimal cloud computing power resources and execute the target task input by the user terminal based on the optimal cloud computing power resources, including: Read the target task to determine the execution steps for completing the target task, divide the target task according to the execution steps to obtain multiple sub-target tasks; Read the resource requirement criteria for each sub-target task; Pool and manage the available cloud computing power resources to obtain a target resource pool, where the target resource pool includes the configuration composition set of the available cloud computing power resources; Match according to the resource requirement criteria of each sub-target task in the target resource pool to obtain the target configuration sequence corresponding to each sub-target task; Sort the target configuration sequences corresponding to each sub-target task according to the execution order of the execution steps, and perform permutation and combination on the target configuration sequences corresponding to each sub-target task according to the sorting result to obtain multiple configuration combinations for completing the target task; Select the target configuration combination as the optimal cloud computing power resources from the multiple configuration combinations and execute the target task according to the optimal cloud computing power resources.

7. A cloud computing power parsing method according to claim 6, characterized in that, Select the target configuration combination as the optimal cloud computing power resources from the multiple configuration combinations and execute the target task according to the optimal cloud computing power resources, including: Obtain the task parameters for executing the target task, simulate the task parameters for executing the target task in the computer, and at the same time, simulate and execute the target task in the computer based on the multiple configuration combinations respectively to obtain the completion efficiency of each configuration combination; Select the top two configuration combinations in terms of completion efficiency, use the configuration combination with the first completion efficiency as the optimal cloud computing power resources, and at the same time, use the configuration combination with the second completion efficiency as the alternative cloud computing power resources; Execute the target task input by the user terminal according to the optimal cloud computing power resources, and when the optimal cloud computing power resources cannot be executed, start the alternative cloud computing power resources.

8. A cloud computing power parsing method according to claim 1, characterized in that In step 4, collect the execution process and dynamically update the cloud computing power resources according to the execution process until the target task is completed, including: When executing the target task based on the optimal cloud computing power resources, collect the execution process of the target task in real time to determine the real-time progress of the target task; Determine the remaining execution amount and execution duration of the target task according to the real-time progress of the execution task; Obtain the execution speed of the optimal cloud computing power resources, and determine the remaining time for completing the target task according to the execution speed of the optimal cloud computing power resources and the remaining execution amount of the target task; Obtain the expected completion time for completing the target task and calculate the target difference time between the expected completion time and the execution duration; Compare the remaining time with the target difference time to determine whether it is necessary to update the cloud computing power resources; When the remaining time is less than or equal to the target difference time, it is determined that there is no need to update the cloud computing power resources; Otherwise, it is determined that the cloud computing power resources need to be updated, and the cloud computing power resources that meet the target difference time are retrieved from the cloud computing power resource management center. Meanwhile, the current optimal cloud computing power resources are updated according to the retrieval result.

9. A cloud computing power platform, characterized in that, Including: To execute the steps of a cloud computing power parsing method according to any one of claims 1 to 8.

10. A cloud computing power parsing system, characterized in that, Including: A construction module for constructing a cloud computing power resource management center. Meanwhile, based on the input of the user terminal for a target task, the task requirement information of the target task is obtained; An evaluation module for evaluating available cloud computing power resources in the cloud computing power resource management center according to the task requirement information; An analysis module for analyzing the available cloud computing power resources to obtain the optimal cloud computing power resources, and executing the target task input by the user terminal based on the optimal cloud computing power resources; An update module for collecting the execution process and dynamically updating the cloud computing power resources according to the execution process until the target task is completed.

Images