Batch task allocation method, device and equipment
By extracting the characteristics of batch tasks and servers, using auction algorithms to calculate the value and benefits of the tasks to the server, and distribute tasks based on quotations, solving the problem of uneven task distribution in traditional allocation methods and improving system efficiency.
Patent Information
- Application Number
- CN202411739989.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-29
- Publication Date
- 2025-03-18
AI Technical Summary
In the traditional batch task allocation method, random allocation of tasks and servers may lead to uneven distribution of tasks, resulting in failure or extension of tasks, affecting system efficiency.
By extracting the characteristics of batch tasks and servers, using auction algorithms to calculate the value and benefits of the task to the server, and assigning tasks based on quotations to ensure that the tasks are allocated to the appropriate server.
Improve server usage and batch tasks execution efficiency, avoiding the problem of task failure and extension.
Smart Images
Figure CN119645602A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method, device and equipment for allocating batch tasks. Background Art
[0002] In recent years, with the rapid development of social economy, the amount of data tasks that major banks, as the center of financial services, need to process has increased exponentially. In this case, how to enable major banks and other financial structures to effectively process batch tasks more quickly and accurately has become an important research topic.
[0003] However, in the traditional batch task allocation process, batch tasks and servers are randomly allocated. In actual use, this allocation method may result in uneven task distribution. For example, if tasks with specific requirements (such as tasks with high memory requirements and long running time) cannot be allocated to appropriate servers, task failure may occur. Once the above situation occurs, the running time of batch tasks will be greatly increased, affecting the operating efficiency of the entire system. Summary of the invention
[0004] The main purpose of the embodiments of the present application is to provide a batch task allocation method, device and equipment, which can extract batch task characteristics and server characteristics, calculate the corresponding value according to the auction algorithm, and then calculate the revenue. In this way, the batch task can quote the server based on the revenue, and finally allocate the server based on the quotation, thereby improving the utilization rate of the server and improving the execution efficiency of the batch tasks.
[0005] In a first aspect, an embodiment of the present application provides a batch task allocation method, comprising:
[0006] Obtain N target tasks and M target servers to be assigned; both N and M are positive integers greater than 0;
[0007] Determining value weights of the N target tasks to the M target servers;
[0008] Calculate the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers;
[0009] Calculating the quotes of the N target tasks for the M target servers according to the revenue values of the N target tasks for the M target servers;
[0010] The quotations of the N target tasks for the M target servers are used to allocate the N target tasks to the M target servers on demand to obtain an allocation result.
[0011] Optionally, determining the value weights of the N target tasks to the M target servers includes:
[0012] Extracting K operation features of the N target tasks according to the historical operation records of the N target tasks; wherein K is a positive integer greater than 0;
[0013] Determining the value weights of the K operating features in the N target tasks according to the influence of the K operating features on each target task;
[0014] Extracting K current operating characteristics of the M target servers;
[0015] Determining value weights of K operating characteristics in the M target servers according to the capabilities of the M target servers to accept tasks;
[0016] The value weights of the N target tasks to the M target servers are calculated according to the value weights of the K operating characteristics of the N target tasks and the value weights of the K operating characteristics in the M target servers.
[0017] Optionally, calculating the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers includes:
[0018] According to the auction algorithm, the revenue values of the N target tasks to the M target servers are calculated by utilizing the value weights of the N target tasks to the M target servers.
[0019] Optionally, after allocating the N target tasks to the M target servers on demand using the quotations of the N target tasks for the M target servers and obtaining the allocation result, the method further includes:
[0020] Determining whether the allocation result satisfies a preset allocation stop condition;
[0021] If yes, the allocation result is taken as the final allocation result;
[0022] If not, the calculation of the quotations of the N target tasks for the M target servers and subsequent steps are re-executed until the obtained allocation result meets the preset stop allocation condition, and the final allocation result is determined.
[0023] In a second aspect, the embodiment of the present application further provides a batch task allocation device, including:
[0024] An acquisition unit, used to acquire N target tasks and M target servers to be assigned; both N and M are positive integers greater than 0;
[0025] A determination unit, used to determine the value weights of the N target tasks to the M target servers;
[0026] A first calculation unit, configured to calculate the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers;
[0027] A second calculation unit, configured to calculate the quotation of the N target tasks for the M target servers according to the revenue values of the N target tasks for the M target servers;
[0028] The allocation unit is used to allocate the N target tasks to the M target servers on demand using the quotations of the N target tasks for the M target servers to obtain an allocation result.
[0029] Optionally, the determining unit includes:
[0030] A first extraction subunit is used to extract K operation features of the N target tasks according to the historical operation records of the N target tasks; K is a positive integer greater than 0;
[0031] A first determining subunit is used to determine the value weights of the K operating features in the N target tasks according to the influence of the K operating features on each target task;
[0032] A second extraction subunit is used to extract K current operation characteristics of the M target servers;
[0033] A second determining subunit is used to determine the value weights of K operating characteristics in the M target servers according to the capabilities of the M target servers to accept tasks;
[0034] The calculation subunit is used to calculate the value weights of the N target tasks to the M target servers according to the value weights of the K operating characteristics of the N target tasks and the value weights of the K operating characteristics in the M target servers.
[0035] Optionally, the first computing unit is specifically configured to:
[0036] According to the auction algorithm, and according to the value weights of the N target tasks to the M target servers, the revenue values of the N target tasks to the M target servers are calculated.
[0037] Optionally, the device further comprises:
[0038] The judging unit is used to judge whether the allocation result satisfies a preset stop allocation condition; if so, the allocation result is used as the final allocation result; if not, the second calculation unit and the allocation unit are re-called and executed to determine the final allocation result.
[0039] The embodiment of the present application also provides a batch task allocation device, including: a processor, a memory, and a system bus;
[0040] The processor and the memory are connected via the system bus;
[0041] The memory is used to store one or more programs, and the one or more programs include instructions. When the instructions are executed by the processor, the processor executes any one of the implementations of the above-mentioned batch task allocation method.
[0042] An embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes any one of the implementations of the above-mentioned batch task allocation method.
[0043] The present application provides a method, device and equipment for allocating batch tasks. First, N target tasks and M target servers to be allocated are obtained; wherein N and M are both positive integers greater than 0. Then, the value weights of the N target tasks to the M target servers are determined. Then, according to the value weights of the N target tasks to the M target servers, the revenue values of the N target tasks to the M target servers are calculated. Then, according to the revenue values of the N target tasks to the M target servers, the quotation of the N target tasks to the M target servers is calculated. Then, the quotation of the N target tasks to the M target servers can be used to allocate the N target tasks to the M target servers on demand to obtain the allocation result. Thus, the utilization rate of each target server can be improved, and the execution efficiency of each target batch task can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0045] Figure 1 A flowchart of a batch task allocation method provided in an embodiment of the present application;
[0046] Figure 2An example diagram of the value weights of N target tasks to the M target servers provided in an embodiment of the present application;
[0047] Figure 3 One of the example diagrams of the quotation of N target tasks to M target servers provided in the embodiment of the present application;
[0048] Figure 4 The second example diagram of the quotation of N target tasks to M target servers provided in the embodiment of the present application;
[0049] Figure 5 Figure 3 of an example of quotations of N target tasks for M target servers provided in an embodiment of the present application;
[0050] Figure 6 A schematic diagram of the composition of a batch task allocation device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0051] In traditional batch scheduling systems in the financial field, random allocation is used when assigning servers to batch tasks. That is, for scheduling systems with multiple servers, the management end will randomly assign batch tasks to any scheduling server for processing. This allocation method may result in uneven machine resource allocation during actual use, resulting in batch tasks not being able to run and complete in the shortest time. For example, random allocation may cause a large number of tasks to be assigned to the same server, resulting in a significant increase in batch task processing time. In addition, this allocation method will also lead to a mismatch between batch task characteristics and server usage. For example, for tasks that require larger batch processing scales, higher memory is required, but the existing random allocation method cannot allocate tasks on demand. If the server memory is insufficient, batch tasks may fail to run.
[0052] To solve the above defects, the embodiment of the present application provides a batch task allocation method, firstly, obtaining N target tasks and M target servers to be allocated; wherein N and M are both positive integers greater than 0, then determining the value weights of the N target tasks to the M target servers, then calculating the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers, and then calculating the quotation of the N target tasks to the M target servers according to the revenue values of the N target tasks to the M target servers, and then using the quotation of the N target tasks to the M target servers, the N target tasks can be allocated to the M target servers on demand to obtain the allocation result. Thus, the utilization rate of each target server can be improved, and the execution efficiency of each target batch task can be improved.
[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0054] First embodiment
[0055] See also Figure 1 , is a flow chart of a batch task allocation method provided in this embodiment, the method comprising the following steps:
[0056] S101: Obtain N target tasks and M target servers to be assigned; wherein N and M are both positive integers greater than 0.
[0057] In this embodiment, the batch tasks of any bank that are reasonably allocated by this embodiment are defined as target tasks, and the servers allocated to the target tasks by the allocation method adopted by this embodiment are defined as target servers. It should be noted that this application does not limit the number of target tasks and target servers, and will be described later by taking N target tasks and M target servers as examples, where N and M are both positive integers greater than 0, and the values of the two can be the same or different. After obtaining the N target tasks and M target servers to be allocated by using the existing or future data acquisition method, the subsequent step S102 can be continued.
[0058] Furthermore, this application does not limit the content and acquisition method of the target tasks. For example, the N target tasks to be assigned may refer to a large number of batch tasks that financial institutions such as banks need to process to ensure the smooth operation of their daily operations. For example, the content of the target task may be any of the following common batch processing tasks:
[0059] 1. Account Settlement:
[0060] At the end of each day, all account transaction records are processed, including deposits, withdrawals, transfers, etc.
[0061] Interest is calculated and the account balance is updated.
[0062] 2. Loan processing:
[0063] Calculate and process interest and principal payments on loans.
[0064] Dealing with overdue loans and defaults.
[0065] 3. Transaction processing:
[0066] Process transaction records from ATM, POS and other channels.
[0067] Processing of international transactions and foreign exchange.
[0068] 4. Report generation:
[0069] Generate financial statements regularly, including balance sheet, income statement, etc.
[0070] Generate regulatory reports to meet regulatory agency requirements.
[0071] 5. Risk management:
[0072] Monitor market risk, credit risk and operational risk.
[0073] Conduct stress testing and risk assessments.
[0074] 6. Compliance inspection:
[0075] Ensure all transactions and operations comply with regulations and internal policies.
[0076] Conduct Know Your Customer (KYC) checks.
[0077] 7. Data backup and recovery:
[0078] Back up critical data regularly to prevent data loss.
[0079] Test your data recovery procedures to ensure quick recovery in an emergency.
[0080] 8. Customer Service:
[0081] Process batch customer requests, such as account enquiries, reporting loss, password reset, etc.
[0082] Automated customer notifications, such as account balance change alerts.
[0083] 9. Funds Allocation:
[0084] Transfer funds between different accounts and branches.
[0085] Manage liquidity and ensure sufficient funds.
[0086] 10. Credit card processing:
[0087] Process credit card applications, approvals, and billing.
[0088] Manage credit limits and risk on your credit cards.
[0089] 11. Portfolio Management:
[0090] Monitor and adjust portfolios to optimize returns and risks.
[0091] Processing investment transactions and settlements.
[0092] 12. System maintenance and upgrade:
[0093] Perform system maintenance and software upgrades regularly.
[0094] Ensure the security and stability of the system.
[0095] S102: Determine the value weights of the N target tasks to the M target servers.
[0096] In this embodiment, after obtaining N target tasks and M target servers to be assigned through step S101, further, K operation features of the N target tasks can be extracted based on the historical operation records of the N target tasks, where K is a positive integer greater than 0.
[0097] Among them, this application does not limit the content and extraction method of the running characteristics of the target task. For example, the running characteristics of the target task may include but are not limited to running time, CPU occupancy, memory occupancy and other characteristics.
[0098] Then, the value weights of the K operating features in the N target tasks can be determined according to the degree of influence of the K operating features on each target task. For example, when the value of K is 3, and the three operating features of the N target tasks are the running time, CPU occupancy rate, and memory occupancy rate, the value weights of the three operating features in the target tasks can be shown in Table 1 below:
[0099]
[0100] Table 1
[0101] It should be noted that this application does not limit the value weights of the K operating features in N target tasks. For example, they can range from 1 to 10 to represent different weights. As shown in Table 1, target task 1 is only sensitive to memory occupancy, so the feature weight is higher, which is 10, and the weights of the other two features are 1.
[0102] Then, the current K operating characteristics of the M target servers can be extracted. In addition, the present application does not limit the content and extraction method of the operating characteristics of the target server. For example, the operating characteristics of the target server may include but are not limited to the number of received tasks, CPU occupancy, memory occupancy, disk usage, and other characteristics.
[0103] Then, the value weights of the K operating characteristics of the M target servers can be determined based on the ability of the M target servers to accept tasks. For example, when the value of K is 3, and the three operating characteristics of the target server are the number of received tasks, CPU occupancy, and memory occupancy, the value weights of the three operating characteristics of the target server can be shown in Table 2 below:
[0104]
[0105]
[0106] Table 2
[0107] It should be noted that this application does not limit the value weights of the K operating features in the M target servers, but it must ensure that the value weights are in the same dimension as the value weights of the K operating features in the N target tasks. For example, they can also range from 1 to 10 to represent different weights. As shown in Table 2, target server 1 currently has a large number of running tasks and a high CPU occupancy rate. Its ability to run tasks with long running times and excessive CPU occupancy is poor, so the weights of these two features are relatively low, both 1, and the other feature weight is 10.
[0108] Finally, the value weights of N target tasks to M target servers can be calculated based on the value weights of K operating features of N target tasks and the value weights of K operating features in M target servers. For example, when the value weights of 3 operating features in the target task are as shown in Table 1, and the value weights of 3 operating features in the target server are as shown in Table 2, the corresponding weights are multiplied and summed to obtain the value weights of N target tasks to M target servers as shown in Table 3 below:
[0109]
[0110] Table 3
[0111] According to the calculation results shown in Table 3, the value weights of the N target tasks to the M target servers can be determined as follows: Figure 2 shown.
[0112] S103: Calculate the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers.
[0113] In this embodiment, after determining the value weights of N target tasks to M target servers through step S102, the revenue values of the N target tasks to the M target servers can be further calculated according to the auction algorithm using the value weights of the N target tasks to the M target servers to execute the subsequent step S104.
[0114] Among them, the essence of the auction algorithm is to imitate the auction process in economic transactions. It is an algorithm that can obtain the best allocation plan in limited calculations.
[0115] Specifically, according to the auction algorithm, based on the value weights of the N target tasks to the M target servers determined in step S102, the formula for calculating the revenue value of the N target tasks to the M target servers is as follows:
[0116] profit=value-price
[0117] Wherein, profit represents revenue; value represents the value weights of the N target tasks to the M target servers determined in step S102; and price represents the bid price.
[0118] It is understandable that before the first bid, the starting prices of the M target servers are all 0.
[0119] Target task 1 bids for the first time. Since the prices of the M target servers are all 0 at present, the value of profit for target task 1 is all value, that is, the value weights of the N target tasks to the M target servers determined in step S102.
[0120] S104: Calculate the quotation of the N target tasks for the M target servers according to the revenue values of the N target tasks for the M target servers.
[0121] S105: using the quotations of the N target tasks for the M target servers, allocating the N target tasks to the M target servers on demand to obtain an allocation result.
[0122] In this embodiment, after calculating the revenue values of the N target tasks to the M target servers in step S103, the bids of the N target tasks to the M target servers can be further calculated according to the auction algorithm. The specific calculation formula is as follows:
[0123] price old +ε≤price new ≤price old +π+ε
[0124] Among them, according to Figure 2It can be seen that the benefits of target task 1 selecting target server 1, target server 2, and target server M are 102, 30, and 120 respectively, and the auction algorithm gives each task self-interest, that is, it always selects the target server with the highest benefit. This is also an important guarantee for obtaining the optimal solution through the auction algorithm. Based on self-interest, target task 1 selects target server M, quotes target server M, and increases its price. Among them, referring to the above formula, the price increase is between ε and π+ε, that is, each quotation is at least ε higher than the original, and at most π+ε higher than the original. Among them, the values of ε and π are not limited, and can be set according to actual conditions and experience values. For example, ε=10, π=100, etc. can be selected. In this way, target task 1 increases the price of target server M to 120+ε (when ε=10, 120+ε=130), such as Figure 3 shown.
[0125] On this basis, target task 2 starts to quote. It selects the revenues of target server 1, target server 2, and target server M as 30, 201, and 80 respectively (that is, when ε=10, 120+ε=130, then 210-(120+ε)=210-130=80). Due to the price increase of target task 1, the price of target server M is already higher than the value that server M can provide to task 2. Therefore, target task 2 no longer considers server M, but selects target server 2 with the highest revenue and increases its price to 201+ε (when ε=10, 201+ε=211). Figure 4 shown.
[0126] On this basis, target task N starts to quote. It selects the benefits of target server 1, target server 2, and target server M as 12, -190 (that is, when ε=10, 201+ε=211, then 21-(201+ε)=21-211=-190), and -100 (that is, when ε=10, 120+ε=130, then 30-(120+ε)=30-130=-100). According to self-interest, target task N selects target server 1 and increases its price to 12+ε (when ε=10, 12+ε=22), as shown in Figure 1. Figure 5 As shown in the figure, this ensures that all target tasks are assigned by the server and the assigned results are obtained.
[0127] Furthermore, in order to improve the allocation effect, an optional implementation method is to determine whether the obtained allocation result meets the preset stop allocation condition. If so, the allocation result can be used as the final allocation result; if not, the above steps S104-S105 can be re-executed to recalculate the quotation of N target tasks for M target servers, and then the N target tasks are allocated to M target servers on demand according to the quotation, until the obtained allocation result meets the preset stop allocation condition, then the final allocation result can be determined.
[0128] The present application does not limit the specific content of the preset stop allocation condition. According to the auction algorithm, it can be set to that all N target tasks are allocated to the target server, or the maximum revenue of each target task after being allocated to the corresponding target server is not greater than 0. For example, based on Figure 5 In the example in , the overall satisfaction of the allocation result is 120+201+12=333, which is the highest overall value among all allocation schemes. At the same time, from the business meaning, target task 1 has the problem of high memory usage, and the memory usage rate of target server M is low, which meets the running conditions of target task 1; target task 2 has the problem of CPU ratio task and long running time. Target server 2 currently has a small number of running tasks and a low CPU ratio, which meets the running conditions of task 2; target task N has no requirements for running time, CPU ratio, and memory occupancy rate. Although target server 1 has a slightly larger number of running tasks and a high CPU ratio, it still meets the running conditions of task n. Therefore, from the business results, the optimal allocation of the three tasks is met.
[0129] In this way, by executing the above steps S101-S105, batch task features and server features are extracted, calculated according to the auction algorithm, and batch tasks are assigned to corresponding servers for processing according to revenue matching. This method reasonably allocates server resources and improves server utilization and batch task execution efficiency.
[0130] In summary, the batch task allocation method provided in this embodiment first obtains N target tasks and M target servers to be allocated; wherein N and M are both positive integers greater than 0, then determines the value weights of the N target tasks to the M target servers, then calculates the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers, and then calculates the quotation of the N target tasks to the M target servers according to the revenue values of the N target tasks to the M target servers, and then uses the quotation of the N target tasks to the M target servers to allocate the N target tasks to the M target servers on demand to obtain the allocation result. Thus, the utilization rate of each target server can be improved, and the execution efficiency of each target batch task can be improved.
[0131] Second embodiment
[0132] This embodiment will introduce a batch task allocation device. For related content, please refer to the above method embodiment.
[0133] See also Figure 6 , is a schematic diagram of the composition of a batch task allocation device provided in this embodiment, the device comprising:
[0134] The acquisition unit 601 is used to acquire N target tasks and M target servers to be assigned; both N and M are positive integers greater than 0;
[0135] A determination unit 602 is used to determine the value weights of the N target tasks to the M target servers;
[0136] A first calculation unit 603 is used to calculate the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers;
[0137] A second calculation unit 604 is used to calculate the quotation of the N target tasks to the M target servers according to the revenue values of the N target tasks to the M target servers;
[0138] The allocation unit 605 is configured to allocate the N target tasks to the M target servers on demand using the quotations of the N target tasks for the M target servers to obtain an allocation result.
[0139] In an implementation of this embodiment, the determining unit 602 includes:
[0140] A first extraction subunit is used to extract K operation features of the N target tasks according to the historical operation records of the N target tasks; K is a positive integer greater than 0;
[0141] A first determining subunit is used to determine the value weights of the K operating features in the N target tasks according to the influence of the K operating features on each target task;
[0142] A second extraction subunit is used to extract K current operation characteristics of the M target servers;
[0143] A second determining subunit is used to determine the value weights of K operating characteristics in the M target servers according to the capabilities of the M target servers to accept tasks;
[0144] The calculation subunit is used to calculate the value weights of the N target tasks to the M target servers according to the value weights of the K operating characteristics of the N target tasks and the value weights of the K operating characteristics in the M target servers.
[0145] In an implementation of this embodiment, the first calculating unit 603 is specifically configured to:
[0146] According to the auction algorithm, and according to the value weights of the N target tasks to the M target servers, the revenue values of the N target tasks to the M target servers are calculated.
[0147] In an implementation of this embodiment, the device further includes:
[0148] The judging unit is used to judge whether the allocation result satisfies a preset stop allocation condition; if so, the allocation result is used as the final allocation result; if not, the second calculation unit and the allocation unit are re-called and executed to determine the final allocation result.
[0149] In summary, the batch task allocation device provided by the present embodiment first obtains N target tasks and M target servers to be allocated, wherein N and M are both positive integers greater than 0, and then determines the value weights of the N target tasks to the M target servers, and then calculates the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers, and then calculates the quotation of the N target tasks to the M target servers according to the revenue values of the N target tasks to the M target servers, and then can use the quotation of the N target tasks to the M target servers to allocate the N target tasks to the M target servers on demand, and obtain the allocation result. Thereby, the utilization rate of each target server can be improved, and the execution efficiency of each target batch task can be improved.
[0150] Furthermore, an embodiment of the present application also provides a batch task allocation device, comprising: a processor, a memory, and a system bus;
[0151] The processor and the memory are connected via the system bus;
[0152] The memory is used to store one or more programs, and the one or more programs include instructions. When the instructions are executed by the processor, the processor executes any one of the implementation methods of the above-mentioned batch task allocation method.
[0153] Furthermore, an embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes any one of the implementation methods of the above-mentioned batch task allocation method.
[0154] It can be known from the description of the above implementation mode that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., including several instructions for enabling a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.
[0155] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0156] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0157] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A batch task allocation method, characterized in that: include: Obtain N target tasks and M target servers to be assigned; Both N and M are positive integers greater than 0; Determining value weights of the N target tasks to the M target servers; Calculate the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers; Calculating the quotes of the N target tasks for the M target servers according to the revenue values of the N target tasks for the M target servers; The quotations of the N target tasks for the M target servers are used to allocate the N target tasks to the M target servers on demand to obtain an allocation result.
2. The method according to claim 1, characterized in that Determining the value weights of the N target tasks to the M target servers includes: Extracting K operation features of the N target tasks according to the historical operation records of the N target tasks; wherein K is a positive integer greater than 0; Determining the value weights of the K operating features in the N target tasks according to the influence of the K operating features on each target task; Extracting K current operating characteristics of the M target servers; Determining value weights of K operating characteristics in the M target servers according to the capabilities of the M target servers to accept tasks; The value weights of the N target tasks to the M target servers are calculated according to the value weights of the K operating characteristics of the N target tasks and the value weights of the K operating characteristics in the M target servers.
3. The method according to claim 1, characterized in that The calculating, according to the value weights of the N target tasks to the M target servers, the revenue values of the N target tasks to the M target servers comprises: According to the auction algorithm, the revenue values of the N target tasks to the M target servers are calculated by utilizing the value weights of the N target tasks to the M target servers.
4. The method according to claim 1, characterized in that: After allocating the N target tasks to the M target servers on demand using the quotations of the N target tasks to the M target servers and obtaining the allocation results, the method further includes: Determining whether the allocation result satisfies a preset allocation stop condition; If yes, the allocation result is taken as the final allocation result; If not, the calculation of the quotations of the N target tasks for the M target servers and subsequent steps are re-executed until the obtained allocation result meets the preset stop allocation condition, and the final allocation result is determined.
5. A batch task allocation device, characterized in that: include: An acquisition unit, used for acquiring N target tasks and M target servers to be assigned; Both N and M are positive integers greater than 0; A determination unit, used to determine the value weights of the N target tasks to the M target servers; A first calculation unit, configured to calculate the revenue values of the N target tasks to the M target servers according to the value weights of the N target tasks to the M target servers; A second calculation unit, configured to calculate the quotation of the N target tasks for the M target servers according to the revenue values of the N target tasks for the M target servers; The allocation unit is used to allocate the N target tasks to the M target servers on demand using the quotations of the N target tasks for the M target servers to obtain an allocation result.
6. The device according to claim 5, characterized in that The determining unit comprises: A first extraction subunit is used to extract K operation features of the N target tasks according to the historical operation records of the N target tasks; K is a positive integer greater than 0; A first determining subunit is used to determine the value weights of the K operating features in the N target tasks according to the influence of the K operating features on each target task; A second extraction subunit is used to extract K current operation characteristics of the M target servers; A second determining subunit is used to determine the value weights of K operating characteristics in the M target servers according to the capabilities of the M target servers to accept tasks; The calculation subunit is used to calculate the value weights of the N target tasks to the M target servers according to the value weights of the K operating characteristics of the N target tasks and the value weights of the K operating characteristics in the M target servers.
7. The device according to claim 5, characterized in that The first computing unit is specifically configured to: According to the auction algorithm, and according to the value weights of the N target tasks to the M target servers, the revenue values of the N target tasks to the M target servers are calculated.
8. The device according to claim 5, characterized in that The device also includes: The judging unit is used to judge whether the allocation result satisfies a preset stop allocation condition; if so, the allocation result is used as the final allocation result; if not, the second calculation unit and the allocation unit are re-called and executed to determine the final allocation result.
9. A batch task allocation device, characterized in that: include: Processor, memory, system bus; The processor and the memory are connected via the system bus; The memory is used to store one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by the processor, the processor executes the method according to any one of claims 1 to 4.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the method according to any one of claims 1 to 4.