CN117669928A - Task running method, device, equipment and storage medium - Google Patents
Task running method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117669928A CN117669928A CN202311551627.1A CN202311551627A CN117669928A CN 117669928 A CN117669928 A CN 117669928A CN 202311551627 A CN202311551627 A CN 202311551627A CN 117669928 A CN117669928 A CN 117669928A
- Authority
- CN
- China
- Prior art keywords
- node
- task
- nodes
- completion time
- running
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000013486 operation strategy Methods 0.000 claims abstract description 64
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims description 5
- 230000003111 delayed effect Effects 0.000 abstract description 11
- 238000004364 calculation method Methods 0.000 description 16
- 230000000977 initiatory effect Effects 0.000 description 5
- 238000011144 upstream manufacturing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a task operation method, a device, equipment and a storage medium, wherein the task operation method comprises the following steps: acquiring a task submitted by a user, wherein the task comprises a plurality of task nodes; under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node; and operating the task nodes of the node list to be operated based on the node operation strategy. According to the method and the device, the task can be scheduled according to the emergency degree and the preset priority, the problem that task processing is delayed is effectively avoided, and timeliness of task processing and overall completion efficiency are improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a task running method, device, apparatus, and storage medium.
Background
The current running strategies of tasks or a series of tasks with mutual dependency relations in the market mainly aim at scheduling task starting strategies. Such a task initiation strategy focuses on initiating tasks in a certain order. However, existing task initiation strategies are often difficult to adapt to task scheduling with varying degrees of urgency, which can easily lead to delayed processing of some important tasks.
Therefore, there is a need to propose a solution for tasks that is easily delayed.
Disclosure of Invention
The main purpose of the application is to provide a task operation method, a device, equipment and a storage medium, which aim to solve the problem that the task processing is easy to be delayed in the existing task operation scheme.
In order to achieve the above object, the present application provides a task operation method, including:
acquiring a task submitted by a user, wherein the task comprises a plurality of task nodes;
under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node;
and operating the task nodes of the node list to be operated based on the node operation strategy.
Optionally, before the step of moving the task node into the node list to be operated and generating the node operation policy, the method further includes:
determining a predetermined completion time of the task;
and reversely pushing and calculating the preset completion time of the task nodes according to the preset completion time of the task.
Optionally, the step of generating the node operation policy based on the task nodes in the node list to be operated includes:
predicting to obtain overtime task nodes and overtime time thereof based on the historical completion time and the preset completion time of the task nodes in the node list to be operated;
and determining nodes with timeout time smaller than the timeout task node in the running node queue and/or nodes without preset finishing time as pause nodes to generate the node running strategy.
Optionally, the step of running the task node of the to-be-run node list based on the node running policy includes:
and transferring the pause node to a pause node queue based on the node operation strategy, and transferring the overtime task node to the operation node queue so as to operate the overtime task node.
Optionally, after the step of running the task node of the to-be-run node list based on the node running policy, the method further includes:
monitoring and counting the running time and the running progress percentage of the running task nodes;
predicting the completion time of the running task node according to the running duration and the running progress percentage;
Dividing the running task nodes into nodes without overtime risks and nodes with overtime risks according to the completion time;
and transferring the node resources without the overtime risk to the node with the overtime risk.
Optionally, after the step of running the task node of the to-be-run node list based on the node running policy, the method further includes:
determining suspicious nodes according to the current running process and the estimated resource consumption condition of the nodes in the running node queue, wherein the suspicious nodes are nodes of which the current running process and the estimated resource consumption condition of the nodes do not accord with a preset threshold value;
and transferring the in-doubt node to an in-doubt node queue and removing the running resource of the in-doubt node.
Optionally, in the case that the task node in the task is determined to be a preset state node, the step of moving the task node into the node to be run list includes:
under the condition that the task node in the task is a preset state node, determining whether the task node meets a preset node enqueuing strategy, wherein the node enqueuing strategy is obtained based on the remaining slot positions of a to-be-operated node list, the historical completion time of the task node and the preset completion time;
And under the condition that the task node meets a node enqueuing strategy, moving the task node into the node list to be operated.
The embodiment of the application also provides a task running device, which comprises:
the acquisition module is used for acquiring tasks submitted by users, wherein the tasks comprise a plurality of task nodes;
the system comprises a moving-in module, a node operation module and a task processing module, wherein the moving-in module is used for moving a task node in the task into a node list to be operated and generating a node operation strategy under the condition that the task node in the task is determined to be a preset state node, and the node operation strategy is generated based on the historical completion time and the preset completion time of the task node;
and the operation module is used for operating the task nodes of the node list to be operated based on the node operation strategy.
The embodiment of the application also provides task running equipment, which comprises a memory, a processor and a task running program which is stored in the memory and can run on the processor, wherein the task running program realizes the steps of the task running method when being executed by the processor.
The embodiments of the present application also provide a computer-readable storage medium having a task execution program stored thereon, which when executed by a processor, implements the steps of the task execution method as described above.
The task running method, the device, the equipment and the storage medium provided by the embodiment of the application are used for acquiring the task submitted by the user, wherein the task comprises a plurality of task nodes; under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node; and operating the task nodes of the node list to be operated based on the node operation strategy. By generating a node operation strategy according to the historical completion time and the preset completion time of the task node under the condition that the task node is a preset state node, the emergency degree of the task node can be analyzed and the priority and the execution sequence of the node can be determined; by operating the task nodes in the node list to be operated according to the node operation strategy, the task can be ensured to be scheduled according to the preset priority, the problem that the task processing is delayed is effectively avoided, and the timeliness and the overall completion efficiency of the task processing are improved.
Drawings
FIG. 1 is a schematic diagram of functional modules of a terminal device to which a task running device of the present application belongs;
FIG. 2 is a flow chart of an exemplary embodiment of a task execution method of the present application;
FIG. 3 is a flow chart of another exemplary embodiment of a task execution method of the present application;
FIG. 4 is a flow chart of yet another exemplary embodiment of a task execution method of the present application;
FIG. 5 is another flow chart of a task node of the list of nodes to be executed after the task node is executed according to an exemplary embodiment of the task execution method of the present application;
fig. 6 is a schematic diagram of a task operation system according to an exemplary embodiment of the task operation method of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The main solutions of the embodiments of the present application are: acquiring a task submitted by a user, wherein the task comprises a plurality of task nodes; under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node; and operating the task nodes of the node list to be operated based on the node operation strategy. By generating a node operation strategy according to the historical completion time and the preset completion time of the task node under the condition that the task node is a preset state node, the emergency degree of the task node can be analyzed and the priority and the execution sequence of the node can be determined; by operating the task nodes in the node list to be operated according to the node operation strategy, the task can be ensured to be scheduled according to the preset priority, the problem that the task processing is delayed is effectively avoided, and the timeliness and the overall completion efficiency of the task processing are improved.
Specifically, referring to fig. 1, fig. 1 is a schematic diagram of functional modules of a terminal device to which a task running device of the present application belongs. The task execution device may be a device independent of the terminal device, capable of executing tasks, and may be carried on the terminal device in the form of hardware or software. The terminal equipment can be an intelligent mobile terminal with a data processing function such as a mobile phone and a tablet personal computer, and can also be a fixed terminal equipment or a server with a data processing function.
In this embodiment, the terminal device to which the task running device belongs includes at least an output module 110, a processor 120, a memory 130, and a communication module 140.
The memory 130 stores an operating system and a task running program, and the task running device can store the acquired task composed of a plurality of task nodes submitted by a user, determine whether the task nodes are the result of preset state nodes, a list of nodes to be run, and information such as a node running strategy obtained based on the historical completion time and the preset completion time of the task nodes in the memory 130; the output module 110 may be a display screen or the like. The communication module 140 may include a WIFI module, a mobile communication module, a bluetooth module, and the like, and communicates with an external device or a server through the communication module 140.
Wherein the task execution program in the memory 130, when executed by the processor, performs the steps of:
acquiring a task submitted by a user, wherein the task comprises a plurality of task nodes;
under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node;
and operating the task nodes of the node list to be operated based on the node operation strategy.
Further, the task execution program in the memory 130, when executed by the processor, further performs the steps of:
determining a predetermined completion time of the task;
and reversely pushing and calculating the preset completion time of the task nodes according to the preset completion time of the task.
Further, the task execution program in the memory 130, when executed by the processor, further performs the steps of:
predicting to obtain overtime task nodes and overtime time thereof based on the historical completion time and the preset completion time of the task nodes in the node list to be operated;
and determining nodes with timeout time smaller than the timeout task node in the running node queue and/or nodes without preset finishing time as pause nodes to generate the node running strategy.
Further, the task execution program in the memory 130, when executed by the processor, further performs the steps of:
and transferring the pause node to a pause node queue based on the node operation strategy, and transferring the overtime task node to the operation node queue so as to operate the overtime task node.
Further, the task execution program in the memory 130, when executed by the processor, further performs the steps of:
monitoring and counting the running time and the running progress percentage of the running task nodes;
predicting the completion time of the running task node according to the running duration and the running progress percentage;
dividing the running task nodes into nodes without overtime risks and nodes with overtime risks according to the completion time;
and transferring the node resources without the overtime risk to the node with the overtime risk.
Further, the task execution program in the memory 130, when executed by the processor, further performs the steps of:
determining suspicious nodes according to the current running process and the estimated resource consumption condition of the nodes in the running node queue, wherein the suspicious nodes are nodes of which the current running process and the estimated resource consumption condition of the nodes do not accord with a preset threshold value;
And transferring the in-doubt node to an in-doubt node queue and removing the running resource of the in-doubt node.
Further, the task execution program in the memory 130, when executed by the processor, further performs the steps of:
under the condition that the task node in the task is a preset state node, determining whether the task node meets a preset node enqueuing strategy, wherein the node enqueuing strategy is obtained based on the remaining slot positions of a to-be-operated node list, the historical completion time of the task node and the preset completion time;
and under the condition that the task node meets a node enqueuing strategy, moving the task node into the node list to be operated.
According to the scheme, the task submitted by the user is obtained, wherein the task comprises a plurality of task nodes; under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node; and operating the task nodes of the node list to be operated based on the node operation strategy. By generating a node operation strategy according to the historical completion time and the preset completion time of the task node under the condition that the task node is a preset state node, the emergency degree of the task node can be analyzed and the priority and the execution sequence of the node can be determined; by operating the task nodes in the node list to be operated according to the node operation strategy, the task can be ensured to be scheduled according to the preset priority, the problem that the task processing is delayed is effectively avoided, and the timeliness and the overall completion efficiency of the task processing are improved.
Based on the above terminal device architecture, but not limited to the above architecture, the method embodiments of the present application are presented.
Referring to fig. 2, fig. 2 is a flow chart illustrating an exemplary embodiment of a task running method of the present application. The task operation method comprises the following steps:
step S10, acquiring a task submitted by a user, wherein the task comprises a plurality of task nodes.
The execution main body of the method of the embodiment may be a task operation device, or may be a task operation terminal device or a server, and the task operation device is exemplified by the task operation device, and the task operation device may be integrated on a device such as a smart phone or a computer with a data processing function.
Specifically, after a user submits a task, the task submitted by the user is acquired through a task running device. In this embodiment, the task submitted by the user includes a plurality of task nodes, where the plurality of task nodes may include a series of task nodes with a dependency relationship, and may further include task nodes without a dependency relationship.
Further, in an embodiment, after acquiring the task submitted by the user, the method may further include:
and importing the tasks into an operation task list and/or a task list to be operated according to the number of the remaining slots of the operation task pool.
Specifically, according to the number of the remaining slots of the running task pool, the tasks corresponding to the number of the remaining slots are imported into the running task list, and the remaining tasks are imported into the to-be-running task list.
More specifically, if the number of the remaining slots in the running task pool is greater than or equal to the number of tasks submitted by the user, importing all the tasks into a running task list; if the number of the residual slots in the running task pool is smaller than the number of the tasks submitted by the user, selecting the tasks with the number corresponding to the number of the residual slots, and importing the selected tasks into a running task list; and importing the rest tasks into a task list to be operated.
Step S20, under the condition that the task node in the task is determined to be a preset state node, the task node is moved into a node list to be operated and a node operation strategy is generated, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node.
Specifically, for a plurality of task nodes, it is determined whether the task node is a preset state node. The task nodes may be divided into various status nodes, for example, may be divided into: a task node having a dependency relationship, a task node having no dependency relationship, a task node having a dependency relationship with itself in an upstream state, a task node not having a dependency relationship with itself in a completion state, and the like.
In this embodiment, the preset state node is set to be a task node in which all the upstream nodes having a dependency relationship with itself are the completion state, and a task node having no dependency relationship. More specifically, for a plurality of task nodes, it is determined whether the task node is a task node whose upstream nodes having a dependency relationship with themselves are all in a completed state, or a task node having no dependency relationship.
In other embodiments, the preset state node may also be set to other state nodes. The specific situation can be set according to the actual requirement.
Further, in an embodiment, the step of determining whether the task node is a preset state node may include:
and determining whether the task node in the running task list and/or the task node in the task list to be run is a preset state node or not.
Specifically, whether the task node imported into the running task list is a preset state node is determined, and whether the task node imported into the to-be-running task list is a preset state node is determined, wherein the preset state node can comprise a task node with a finished state of an upstream node with a self-dependency relationship, a task node without a dependency relationship and the like.
In this embodiment, under the condition that the task node in the task is determined to be a node in a preset state, the task node in the preset state is moved into a node list to be operated and a node operation policy is generated, wherein the node operation policy is generated based on the historical completion time and the preset completion time of the task node.
In this embodiment, the task node that moves into the to-be-executed node list may include: a task node having a predetermined completion time, a task node having no predetermined completion time, a task node having a historical completion time, and/or a task node having no historical completion time, etc. The preset completion time refers to the time when the task node is scheduled to complete operation, namely, the task node is set to complete operation before the preset completion time; the historical completion time refers to the time elapsed for the task node operation to complete, which is counted based on the task history index.
And generating a corresponding node operation strategy according to the historical completion time and/or the preset completion time of the task node which is moved into the node list to be operated.
By way of example, assuming that the task nodes moved into the to-be-run node list include task nodes provided with scheduled completion times and having historical completion times, task nodes without scheduled completion times and without historical completion times, task nodes with historical completion times and without scheduled completion times, a corresponding node operation policy is generated according to the task nodes, wherein the node operation policy is:
(1) The task nodes with the preset completion time are preferentially met, and the task nodes with the preset completion time and the historical completion time are ordered according to the sequence of the preset completion time;
(2) Then considering task nodes with historical completion time but without preset completion time, after the sequencing in the step (1) is completed, reversely pushing the starting operation time of the task nodes according to the preset completion time and the historical completion time of the sequenced task nodes, and acquiring the time interval between the task nodes based on the starting operation time of each task node; comparing the acquired time interval with the historical completion time of each residual task node, and inserting the residual task node into a corresponding time interval position if the acquired time interval is greater than or equal to the historical completion time of the residual task node; if the acquired time interval is smaller than the historical completion time of the remaining task nodes, after the current ordering, randomly arranging the processing sequence of the remaining task nodes with the historical completion time but without the scheduled completion time;
(3) Finally, after the ordering of step (2) is completed, task nodes without a predetermined completion time and without a historical completion time are randomly arranged.
And step S30, operating the task nodes of the node list to be operated based on the node operation strategy.
Specifically, task nodes in the node list to be operated are sequentially operated according to the generated node operation strategy, so that the delay of the processing of important tasks is avoided.
According to the scheme, the task submitted by the user is obtained, wherein the task comprises a plurality of task nodes; under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node; and operating the task nodes of the node list to be operated based on the node operation strategy. By generating a node operation strategy according to the historical completion time and the preset completion time of the task node under the condition that the task node is a preset state node, the emergency degree of the task node can be analyzed and the priority and the execution sequence of the node can be determined; by operating the task nodes in the node list to be operated according to the node operation strategy, the task can be ensured to be scheduled according to the preset priority, the problem that the task processing is delayed is effectively avoided, and the timeliness and the overall completion efficiency of the task processing are improved.
Further, referring to fig. 3, fig. 3 is a schematic flow chart of another exemplary embodiment of the task running method of the present application. Based on the embodiment shown in fig. 2, in this embodiment, before the step of moving the task node into the node list to be executed and generating the node running policy, the task running method may further include:
step S210, determining the scheduled completion time of the task;
step S220, the preset completion time of the task nodes is calculated in a back-pushing mode according to the preset completion time of the task.
Specifically, for a task for which a user has set a predetermined completion time, the predetermined completion time of the task submitted by the user is determined. And according to the preset completion time of the task, reversely pushing and calculating the preset completion time of a plurality of task nodes included in the task.
For example, the user sets the predetermined completion time to be 12 pm for task 1, wherein the task is composed of 3 task nodes, namely task node 1, task node 2 and task node 3. And counting the historical completion time of each task node to be 20 minutes according to the task historical indexes. At this time, according to the preset completion time of the task submitted by the user, the preset completion time of 3 task nodes included in the task is calculated by combining the historical completion time of each task node in a back-pushing way, and the preset completion time is respectively as follows:
The historical completion time of the task node 1 is 11 points for 20 minutes;
the historical completion time of the task node 2 is 11 points for 40 minutes;
the historical completion time of the task node 3 is 12 points.
Further, in an embodiment, the step of generating the node operation policy based on the task node in the node to be operated list may include:
step S201, predicting and obtaining a task node that has timed out and a timeout time thereof based on the historical completion time and the predetermined completion time of the task node in the node list to be operated.
Specifically, for task nodes in the node list to be operated, predicting and obtaining overtime task nodes and corresponding overtime time according to the historical completion time and the preset completion time of the task nodes.
More specifically, according to the historical completion time of task nodes in the node list to be operated and the ordering conditions of all task nodes in the node list to be operated, predicting the completion time of the task nodes; comparing the predicted completion time with the preset completion time of the task node, and if the predicted completion time is greater than the preset completion time, determining the corresponding task node as a overtime task node; and determining the overtime time of the overtime task node according to the preset completion time and the predicted completion time of the overtime task node.
Step S202, determining nodes with timeout time smaller than the timeout task node in the running node queue and/or nodes without preset completion time as pause nodes to generate the node running strategy.
Specifically, counting the overtime time of task nodes in an operation node queue, and determining the node with the overtime time smaller than the overtime time of the overtime task nodes in the operation node queue as a pause node; and/or determining the node which does not set the preset completion time in the operation node queue as a pause node so as to complete the generation of the node operation strategy.
Further, based on the above-described embodiment, in an embodiment, the step S30, running the task node of the node list to be run based on the node running policy may include:
step S301, transferring the suspended node to a suspended node queue based on the node operation policy, and transferring the overtime task node to the operation node queue to operate the overtime task node.
Specifically, the suspended node is transferred to a suspended node queue according to a node operation policy, and operation resources of the suspended node are removed and the node is suspended. And moving the overtime task node into an operation node queue, endowing the overtime task node with operation resources and starting to operate the overtime task node.
Further, the pause node transferred to the pause node queue is in a subsequent link to participate in the generation and operation of the node operation strategy together with the task node in the node list to be operated.
According to the scheme, the overtime task node can be obtained in a prediction mode by analyzing the historical completion time and the preset completion time of the task node, so that overtime tasks can be found and processed in time, and task delay is avoided. By determining and moving out the pause node, the overtime task node is moved into the operation node queue to replace the operation of the pause node, so that the overtime node can be ensured to be processed in time, and meanwhile, the phenomenon that the task cannot be completed in time due to the fact that the pause node continuously occupies resources is avoided, and therefore the overall completion efficiency of the task is improved.
Further, based on the above-described embodiment, the step of moving the task node into the node to be run list in the case where it is determined that the task node in the task is a preset state node may include:
step S203, determining whether a task node in the task meets a preset node enqueuing strategy or not under the condition that the task node in the task is a preset state node, wherein the node enqueuing strategy is obtained based on the remaining slot positions of a to-be-operated node list, the historical completion time of the task node and the preset completion time;
And step S204, moving the task node into the node list to be operated under the condition that the task node meets a node enqueuing strategy.
Specifically, under the condition that the task node is determined to be a preset state node, determining whether the task node accords with a preset node enqueuing strategy according to the remaining slot positions of the node list to be operated, the historical completion time of the task node and the preset completion time. And under the condition that the task node meets the node enqueuing strategy, the task node is moved into a node list to be operated.
For example, the node enqueue policy may be set to:
determining the emergency degree of the task nodes according to the historical completion time of the task nodes and the scheduled completion time, and sequencing the task nodes according to the emergency degree of the task nodes;
and then, determining the remaining slots of the current node list to be operated, selecting the front N-bit task nodes in the ordered task nodes according to the number N of the remaining slots, and moving the selected front N-bit task nodes into the node list to be operated.
Further, referring to fig. 4, fig. 4 is a schematic flow chart of a further exemplary embodiment of the task running method of the present application. Based on the above-described embodiment, after the task node of the node list to be executed based on the node execution policy in the above-described step S30, the method may further include:
S40, monitoring and counting the running time and the running progress percentage of the running task nodes;
s50, predicting the completion time of the running task node according to the running time and the running progress percentage.
Specifically, for the running task nodes, the running time length and the running progress percentage of the running task nodes are monitored and counted. The operation progress percentage refers to the ratio of the current operation progress of the task node relative to the total task operation progress. And predicting the completion time of the corresponding running task node according to the counted running time and running progress percentage.
S60, dividing the running task nodes into nodes without overtime risks and nodes with overtime risks according to the completion time;
and S70, transferring the node resources without the overtime risk to the node with the overtime risk.
Specifically, according to the predicted completion time of the task node, the running task node is divided into a node without timeout risk and a node with timeout risk. More specifically, comparing the predicted completion time of the running task node with the preset completion time of the running task node, and dividing the running task node with the predicted completion time exceeding the preset completion time into nodes with overtime risks; the running task nodes whose predicted completion time does not exceed the predetermined completion time are divided into nodes without risk of timeout. And transferring the node resources without the overtime risk to the nodes with the overtime risk so as to realize the adjustment of the node resources in the operation node queue.
According to the method and the device, the running time and the running progress percentage of the task nodes are monitored and counted, the completion time of the task nodes is predicted, the nodes with overtime risks and the nodes without overtime risks are divided, the node resources in the running node queues are adjusted, and the running efficiency and the completion time of the task can be optimized.
Optionally, referring to fig. 5, fig. 5 is another schematic flow chart implemented after the task node of the node list to be executed is executed according to an exemplary embodiment of the task execution method of the present application. After the task node of the node list to be executed is executed based on the node execution policy in step S30, the method may further include:
step S80, determining suspicious nodes according to the current running process and the estimated resource consumption condition of the nodes in the running node queue, wherein the suspicious nodes are nodes of which the current running process and the estimated resource consumption condition of the nodes do not accord with a preset threshold value;
step S90, transferring the in-doubt node to an in-doubt node queue and removing the running resource of the in-doubt node.
Specifically, the overall operation condition of the task node can be accurately estimated by comprehensively considering the historical performance consumption of the task node and the operation capability of the machine. And determining the node of which the current running process and the resource consumption do not accord with the preset threshold value as the suspicious node according to the current running process and the resource consumption estimated condition of the node in the running node queue. And transferring the determined in-doubt node to the in-doubt node list and removing the running resources of the in-doubt node, thereby preventing the in-doubt node from causing adverse effects on other normally running task nodes and preventing the running of the in-doubt node from wasting excessive cluster resources.
More specifically, a threshold value is preset, wherein the threshold value may be set according to historical running process and resource consumption data. For example, according to the historical running process and the average value of the resource consumption, the threshold value coefficient is multiplied to obtain a set threshold value and stored. And then, comparing the current running process and the estimated resource consumption condition of the nodes in the running node queue with a preset threshold value. If the current running process and the estimated resource consumption condition of the node are greater than a preset threshold value, the node is determined to be an in-doubt node. And transferring the determined in-doubt node to an in-doubt node list and removing the running resource of the in-doubt node.
And finally, sending out an alarm prompt, and waiting for a manager to analyze and process the suspicious nodes in the suspicious node list.
According to the method, the device and the system, through the analysis of the combination of the performance consumption and the machine operation performance, the suspicious node is determined according to the current operation process and the estimated condition of the resource consumption, the suspicious node is transferred to the suspicious node queue, the operation resource is removed, the suspicious node can be effectively managed and processed, and the normal operation of the task node and the effective utilization of the cluster resource are ensured.
Referring to fig. 6, fig. 6 is a schematic diagram of a task running system according to an exemplary embodiment of the task running method of the present application. Based on the above-described embodiments, this embodiment also proposes a task running system, which at least includes: a task list to be operated, a task pool to be operated, a node list to be operated, an operation node queue, a pause node list, a doubtful node list, a decision center, a statistics center, a resource pool and the like.
After a user submits a new task to the task running system of the embodiment, the task submitted by the user is obtained through the task running system, wherein the task comprises a plurality of task nodes. The tasks submitted by the user comprise a series of task nodes without preset finishing time and/or task nodes with preset finishing time. The task nodes without dependency relationship and/or the task nodes with dependency relationship (i.e. the dependency nodes) are included in the plurality of task nodes.
And tracing/back-pushing according to the task history indexes counted in advance to calculate the preset completion time of the dependent node based on the task node with the preset completion time in the task. If a certain task node has a plurality of downstream nodes with preset completion time, the earliest time is used as the preset completion time of the task node.
And then, according to the number of the residual slots of the running task pool, importing the tasks submitted by the user into a running task list and/or a task list to be run of the running task pool. And when the running task pool has new residual slots, importing the new tasks submitted by the user or the tasks in the task list to be run into the running task list.
Determining whether the task node imported into the running task list is a preset state node, and determining whether the task node imported into the to-be-run task list is a preset state node, wherein the preset state node can comprise a task node with a finished state as an upstream node with a self-dependency relationship, a task node without a dependency relationship and the like.
Under the condition that a task node is a preset state node, namely the task node is an operable node, determining whether the task node meets a preset node enqueuing strategy, wherein the node enqueuing strategy is obtained based on the remaining slot positions of a to-be-operated node list, the historical completion time of the task node and the preset completion time; and under the condition that the task node meets a node enqueuing strategy, moving the task node into the node list to be operated.
And generating a corresponding node operation strategy for the task node which is moved into the node list to be operated according to the historical completion time and/or the preset completion time of the task node.
For example, based on a policy set in a decision center by an administrator to ensure the minimum average delay rate/minimum average delay time, the decision center analyzes the urgency degree of task nodes and determines the priority and execution sequence of the nodes according to the historical completion time and/or the preset completion time of the task nodes in the list of the nodes to be operated, so as to generate a corresponding node operation policy. The minimum average delay rate is to delay as few nodes as possible, and the minimum average delay time is to delay as little time as possible.
In the process of generating the node operation strategy, the method can further comprise predicting and obtaining overtime task nodes and overtime time thereof based on the historical completion time and the preset completion time of the task nodes in the node list to be operated; and determining nodes with timeout time smaller than the timeout task node in the operation node queue and/or nodes without preset finishing time as pause nodes, and generating a corresponding node operation strategy.
And operating the task nodes of the node list to be operated based on the generated node operation strategy. And transferring the pause node to a pause node queue according to the generated node operation strategy, removing operation resources of the pause node and pausing operation of the node. And moving the overtime task node into an operation node queue, endowing the overtime task node with operation resources and starting to operate the overtime task node.
Further, the pause node transferred to the pause node queue is preferentially participated in the generation of the node operation strategy again together with the task node in the node list to be operated in the subsequent link, and operation is resumed.
In addition, if all nodes are found to be in the estimated overtime state in the running list, the strategy center is used for inputting the prepared machine resources; and if all the task nodes are not in the overtime state, withdrawing the input machine resources. Based on the present embodiment, hardware resources can be fully utilized and resources can be dynamically added and subtracted.
For task nodes running in the running node queue, monitoring and counting the running time length and the running progress percentage of the running task nodes; and predicting the completion time of the running task node according to the running time length and the running progress percentage.
And transmitting the counted running progress condition of the task node and the predicted completion time to a counting center. Dividing the running task nodes into nodes without overtime risks and nodes with overtime risks according to the predicted completion time through a statistical center; and transmitting the node dividing result to a decision center, and providing data support for the decision center.
A policy is generated by the decision center to transfer node resources without a timeout risk to nodes with a timeout risk. And transmitting the generated strategy to a resource pool so as to realize the effect of transferring the node resources in the operation node queue according to the strategy. The resource pool is also used for counting the running utilization rate of the current resource and transmitting data such as the running utilization rate to a counting center.
Further, after the task node of the node list to be executed based on the generated node execution policy, the method may further include:
determining suspicious nodes according to the current running process and the estimated resource consumption condition of the nodes in the running node queue, wherein the suspicious nodes are nodes of which the current running process and the estimated resource consumption condition of the nodes do not accord with a preset threshold value; and transferring the in-doubt node to an in-doubt node queue and removing the running resource of the in-doubt node.
After all the runnable nodes in the task are finished, the task is marked to be finished, and the historical finishing time of each node of the task and the task itself is updated, and task indexes such as resource consumption condition, delay rate and the like of each node are updated. And transmitting the updated task index to a statistical center.
According to the scheme, the node operation strategy is generated according to the historical completion time and the preset completion time of the task node under the condition that the task node is the preset state node, so that the emergency degree of the task node can be analyzed, and the priority and the execution sequence of the node can be determined; by operating the task nodes in the node list to be operated according to the node operation strategy, the task can be ensured to be scheduled according to the preset priority, the problem that the task processing is delayed is effectively avoided, and the timeliness and the overall completion efficiency of the task processing are improved.
Illustratively, assume an example scenario, specifically as follows:
time: 9 am at the end of a month
Task 1 customizes the lifting task for an individual. Task 1 is actively initiated by an employee to fulfill a temporarily proposed demand by a customer without a scheduled completion time. Being a temporary initiation, there is no historical completion time and delay rate. Task 1 totals 5 task nodes, which are: the node 1 relies on verification calculation (calculation class) - > node 2 external input circulation (circulation class) - > node 3 data calculation (calculation class) - > node 4qc quality verification task (calculation class) - > node 5 result data circulation export (circulation class).
Task 2 is a daily warehouse-in task. The timing is automatically initiated to complete the task of importing a large data cluster into a daily dependency table, wherein the data is T+1 basic data of each day. The predetermined completion time is 11 pm per day. The total historical completion time of all task nodes in the whole task is 1 hour, and the historical completion time of each task node is 20 minutes. The total of 3 task nodes are: node 1 relies on the check computation (computation class) - > node 2 external input stream (data stream class) - > node 3qc quality check task (computation class).
Task 3 is a monthly product output task. And (3) automatically initiating at fixed time to finish the data calculation and external output tasks of financial products of a company in the current month. The total historical completion time for all task nodes within a task is 5 hours. The historical completion time for each task node was 1 hour and 15 minutes. The predetermined completion time is 4 pm on the day. The total of 4 task nodes are: node 1 relies on the verification calculation (calculation class) - > node 2 data calculation (calculation class) - > node 3qc quality verification task (calculation class) - > node 4 result data stream export (stream class).
The present example defines a running pool slot number of 1 for tasks and nodes. Assume that each node in personal extraction task 1 consumes one hour.
The scheduled completion time of each task node is calculated according to the dependence backward pushing of the scheduling node as follows:
task 2: node 1 relies on a check calculation (calculation class) to obtain a preset completion time of 10:20- > node 2 external input flow (flow class) to obtain a preset completion time of 10:40- > node 3qc quality check task (calculation class) to obtain a preset completion time of 11:00.
Task 3: node 1 relies on the check computation (computation class) to schedule a completion time 12:15- > node 2 data calculation (calculation class) scheduled completion time 13:30- > node 3qc quality check task (computational class) scheduled completion time 14:45- > node 4 results data stream derivation (stream class) scheduled completion time is 16:00.
the implementation case one: based on the prior art, the following is the following according to the normal scheduling condition without interference:
09:00-09:20 task 2 node 1
09:20-10:35 task 3 node 1
10:35-11:35 task 1 node 1
11:35-11:55 task 2 node 2
11:55-13:10 task 3 node 2
13:10-14:10 task 1 node 2
14:10-14:30 task 2 node 3 (task 2 completed, timeout 3 hours 30 minutes)
14:30-15:45 task 3 node 3
15:45-16:45 task 1 node 3
16:45-18:00 task 3 node 4 (task 3 completed, timeout 2 hours)
16:45-17:45 task 1 node 4
17:45-18:45 task 1 node 5 (task 1 complete)
Summarizing: both tasks with the predetermined completion time timed out, 3 hours 30 minutes and 2 hours respectively.
And the implementation condition II: the task scheduling is performed based on the task running scheme of the application as follows:
09:00-09:20 task 2 node 1 dependency check computation (computation class)
09:20-10:35 task 3 node 1 dependency check computation (computation class)
09:20-09:40 task 2 node 2 external input stream (stream class)
10:35-10:55 task 2 node 3qc quality check task (computational class). Here, it is predicted that task 2 node 3 will timeout and is therefore scheduled preferentially. Task 2 is complete and not timed out.
10:35-11:35 task 1 node 2 external input stream (stream class)
10:55-11:55 task 1 node 1 dependency check computation (computation class)
11:55-13:10 task 3 node 2 data computation (computation class)
13:10-13:30 task 1 node 3 data computation (computation class). Here, the node 3 according to the predicted task 3 does not timeout, and there is still room for 30 minutes, and the originally scheduled task 1 is still maintained. However, after running to 13:30, it is predicted that task 3 node 3 enters a timeout state and should preempt the queue preferentially, thus causing task 1 node 3 to enter a pause state.
13:30-14:45 task 3 node 3qc quality check task (computing class)
14:45-15:25 task 1 node 3 resumes from the suspended state, continuing to run.
14:45-16:00 task 3 node 4 result data stream export (stream class). Task 3 is complete and not timed out.
15:25-16:25 task 1 node 4qc quality check task (computational class)
16:25-17:25 task 1 node 5 result data stream export (stream class). Task 1 is complete.
Summarizing: neither task has timed out with a predetermined completion time. Task 1 without the scheduled completion time is also completed 1 hour and 20 minutes earlier than the normal scheduling method.
In conclusion, the problem that task processing is delayed is effectively avoided based on the scheme of the application, and timeliness of task processing and overall completion efficiency are improved. In this example, the delay rate of the mission operation scheme of the present application is reduced from 100% to 0% compared to the prior art.
In addition, the embodiment of the application also provides a task running device, which comprises:
the acquisition module is used for acquiring tasks submitted by users, wherein the tasks comprise a plurality of task nodes;
the system comprises a moving-in module, a node operation module and a task processing module, wherein the moving-in module is used for moving a task node in the task into a node list to be operated and generating a node operation strategy under the condition that the task node in the task is determined to be a preset state node, and the node operation strategy is generated based on the historical completion time and the preset completion time of the task node;
And the operation module is used for operating the task nodes of the node list to be operated based on the node operation strategy.
The present embodiment realizes the principle and implementation process of task operation, please refer to the above embodiments, and will not be described herein.
In addition, the embodiment of the application also provides task running equipment, which comprises a memory, a processor and a task running program which is stored in the memory and can run on the processor, wherein the task running program realizes the steps of the task running method when being executed by the processor.
Because the task running program is executed by the processor, all the technical schemes of all the embodiments are adopted, and therefore, the task running program at least has all the beneficial effects brought by all the technical schemes of all the embodiments, and is not described in detail herein.
In addition, the embodiment of the application also provides a computer readable storage medium, wherein a task running program is stored on the computer readable storage medium, and the task running program realizes the steps of the task running method when being executed by a processor.
Because the task running program is executed by the processor, all the technical schemes of all the embodiments are adopted, and therefore, the task running program at least has all the beneficial effects brought by all the technical schemes of all the embodiments, and is not described in detail herein.
Compared with the prior art, the task running method, the device, the equipment and the storage medium provided by the embodiment of the application are used for acquiring the task submitted by the user, wherein the task comprises a plurality of task nodes; under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node; and operating the task nodes of the node list to be operated based on the node operation strategy. By generating a node operation strategy according to the historical completion time and the preset completion time of the task node under the condition that the task node is a preset state node, the emergency degree of the task node can be analyzed and the priority and the execution sequence of the node can be determined; by operating the task nodes in the node list to be operated according to the node operation strategy, the task can be ensured to be scheduled according to the preset priority, the problem that the task processing is delayed is effectively avoided, and the timeliness and the overall completion efficiency of the task processing are improved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as above, including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to perform the method of each embodiment of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (10)
1. A task operation method, characterized in that the task operation method comprises:
acquiring a task submitted by a user, wherein the task comprises a plurality of task nodes;
under the condition that the task node in the task is a preset state node, moving the task node into a node list to be operated and generating a node operation strategy, wherein the node operation strategy is generated based on the historical completion time and the preset completion time of the task node;
and operating the task nodes of the node list to be operated based on the node operation strategy.
2. The task execution method according to claim 1, further comprising, before the step of moving the task node into a list of nodes to be executed and generating a node execution policy:
determining a predetermined completion time of the task;
and reversely pushing and calculating the preset completion time of the task nodes according to the preset completion time of the task.
3. The task execution method according to claim 1, wherein the step of generating a node execution policy based on task nodes in the to-be-executed node list includes:
predicting to obtain overtime task nodes and overtime time thereof based on the historical completion time and the preset completion time of the task nodes in the node list to be operated;
And determining nodes with timeout time smaller than the timeout task node in the running node queue and/or nodes without preset finishing time as pause nodes to generate the node running strategy.
4. A task execution method according to claim 3, wherein the step of executing the task node of the to-be-executed node list based on the node execution policy includes:
and transferring the pause node to a pause node queue based on the node operation strategy, and transferring the overtime task node to the operation node queue so as to operate the overtime task node.
5. The task execution method according to claim 1, further comprising, after the step of executing the task node of the to-be-executed node list based on the node execution policy:
monitoring and counting the running time and the running progress percentage of the running task nodes;
predicting the completion time of the running task node according to the running duration and the running progress percentage;
dividing the running task nodes into nodes without overtime risks and nodes with overtime risks according to the completion time;
And transferring the node resources without the overtime risk to the node with the overtime risk.
6. The task execution method according to claim 1, further comprising, after the step of executing the task node of the to-be-executed node list based on the node execution policy:
determining suspicious nodes according to the current running process and the estimated resource consumption condition of the nodes in the running node queue, wherein the suspicious nodes are nodes of which the current running process and the estimated resource consumption condition of the nodes do not accord with a preset threshold value;
and transferring the in-doubt node to an in-doubt node queue and removing the running resource of the in-doubt node.
7. The task operation method according to claim 1, wherein in the case where it is determined that a task node in the task is a preset state node, the step of moving the task node into a to-be-operated node list includes:
under the condition that the task node in the task is a preset state node, determining whether the task node meets a preset node enqueuing strategy, wherein the node enqueuing strategy is obtained based on the remaining slot positions of a to-be-operated node list, the historical completion time of the task node and the preset completion time;
And under the condition that the task node meets a node enqueuing strategy, moving the task node into the node list to be operated.
8. A task execution device, characterized in that the task execution device comprises:
the acquisition module is used for acquiring tasks submitted by users, wherein the tasks comprise a plurality of task nodes;
the system comprises a moving-in module, a node operation module and a task processing module, wherein the moving-in module is used for moving a task node in the task into a node list to be operated and generating a node operation strategy under the condition that the task node in the task is determined to be a preset state node, and the node operation strategy is generated based on the historical completion time and the preset completion time of the task node;
and the operation module is used for operating the task nodes of the node list to be operated based on the node operation strategy.
9. A task execution device, characterized in that the terminal device comprises a memory, a processor and a task execution program stored on the memory and executable on the processor, which task execution program when executed by the processor implements the steps of the task execution method according to any one of claims 1-7.
10. A computer-readable storage medium, on which a task execution program is stored, which when executed by a processor, implements the steps of the task execution method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311551627.1A CN117669928A (en) | 2023-11-20 | 2023-11-20 | Task running method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311551627.1A CN117669928A (en) | 2023-11-20 | 2023-11-20 | Task running method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117669928A true CN117669928A (en) | 2024-03-08 |
Family
ID=90085512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311551627.1A Pending CN117669928A (en) | 2023-11-20 | 2023-11-20 | Task running method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117669928A (en) |
-
2023
- 2023-11-20 CN CN202311551627.1A patent/CN117669928A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11836654B2 (en) | On-demand resource scheduling | |
| Yu et al. | Deadline scheduling as restless bandits | |
| Cheng et al. | Adaptive scheduling of parallel jobs in spark streaming | |
| EP3920490B1 (en) | Adaptive resource allocation method and apparatus | |
| US9135581B1 (en) | Resource constrained task scheduling | |
| CN111338791A (en) | Method, device and equipment for scheduling cluster queue resources and storage medium | |
| Wang et al. | A throughput optimal algorithm for map task scheduling in mapreduce with data locality | |
| CN105022668B (en) | Job scheduling method and system | |
| US10095546B2 (en) | Batch processing of oversubscribed system based on subscriber usage patterns | |
| CN113342497A (en) | Task scheduling method and device, terminal equipment and computer storage medium | |
| Balla et al. | Reliability enhancement in cloud computing via optimized job scheduling implementing reinforcement learning algorithm and queuing theory | |
| CN111913799A (en) | Video stream online analysis task scheduling method and computer equipment | |
| CN113608852B (en) | Task scheduling method, scheduling module, reasoning node and collaborative operation system | |
| Chatterjee et al. | Work capacity of freelance markets: Fundamental limits and decentralized schemes | |
| CN115794323A (en) | Task scheduling method, device, server and storage medium | |
| Fourneau et al. | Multiple class g-networks with restart | |
| CN117135130A (en) | Server control method, device, electronic equipment and storage medium | |
| Hirth et al. | Task scheduling on crowdsourcing platforms for enabling completion time slas | |
| CN104735134B (en) | A kind of method and apparatus serviced for providing calculating | |
| CN117669928A (en) | Task running method, device, equipment and storage medium | |
| CN111176815B (en) | Task scheduling method and device of operating system | |
| US20220171664A1 (en) | Parallel execution controller for partitioned segments of a data model | |
| CN114327925A (en) | Power data real-time calculation scheduling optimization method and system | |
| CN113076181A (en) | Data processing flow optimization method, system and storage medium | |
| Zhang et al. | A high priority random task fuzzy scheduling algorithm for CPS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |