CN-122019106-A - Device scheduling method, device, storage medium and program product

CN122019106ACN 122019106 ACN122019106 ACN 122019106ACN-122019106-A

Abstract

The invention discloses a device scheduling method, a device, a storage medium and a program product. The method comprises the steps of responding to a task request sent by a user, analyzing the task request to obtain a plurality of subtasks and target resources corresponding to the subtasks, wherein the target resources are used for representing hardware resource requirements corresponding to the subtasks, screening a plurality of candidate terminal devices meeting the target resources corresponding to the subtasks from a plurality of terminal devices according to any subtask, respectively determining the confidence coefficient of the plurality of candidate terminal devices according to the current state information of the plurality of candidate terminal devices, wherein the current state information comprises current computing power, current workload, network delay and current electric quantity, determining target terminal devices corresponding to the subtasks according to the confidence coefficient of the plurality of candidate terminal devices, and sending the subtasks to the target terminal devices for processing. The efficiency of equipment scheduling is improved.

Inventors

WANG GUOWEI
DU BING

Assignees

北京鸿湖数安科技发展有限公司

Dates

Publication Date: 20260512
Application Date: 20260210

Claims (10)

1. A device scheduling method, applied to a server, comprising: Responding to a task request sent by a user, analyzing the task request to obtain a plurality of subtasks and target resources corresponding to the subtasks, wherein the target resources are used for representing hardware resource requirements corresponding to the subtasks; For any subtask, screening a plurality of candidate terminal devices meeting target resources corresponding to the subtask from a plurality of terminal devices, wherein the plurality of terminal devices are all terminal devices in the same local area network; the confidence degrees of the candidate terminal devices are respectively determined according to the current state information of the candidate terminal devices, wherein the current state information comprises current computing power, current workload, network delay and current electric quantity; determining target terminal equipment corresponding to the subtasks according to the confidence degrees of the candidate terminal equipment; and sending the subtasks to the target terminal equipment for processing.
2. The method of claim 1, wherein the screening a plurality of candidate terminal devices that satisfy the target resource corresponding to the subtask from the plurality of terminal devices includes: traversing the plurality of terminal devices; for any traversed terminal equipment, matching the current state information of the terminal equipment with the target resource, and determining whether the current state information of the terminal equipment meets the target resource; If yes, after the terminal equipment is determined to be the candidate terminal equipment, continuing to traverse the plurality of terminal equipment; If not, continuing to traverse the plurality of terminal devices until the traversing is finished.
3. The method of claim 1, wherein the determining the confidence levels of the plurality of candidate terminal devices according to the current state information of the plurality of candidate terminal devices, respectively, comprises: normalizing the current calculation power of any candidate terminal equipment to obtain a calculation power factor, and Normalizing the network delay of the candidate terminal equipment to obtain a network condition factor, and Normalizing the current electric quantity of the candidate terminal equipment to obtain an electric quantity condition factor, and Normalizing the current workload of the candidate terminal equipment to obtain a load balancing factor; And carrying out weighted summation on the power calculation factor, the network state factor, the electric quantity condition factor and the load balancing factor to obtain the confidence coefficient of the candidate terminal equipment.
4. The method of claim 3, wherein normalizing the computing power of the candidate terminal device to obtain a computing power factor comprises: Normalizing the current calculation force by using a preset normalization function to obtain the calculation force factor; the normalizing processing is performed on the network delay of the candidate terminal equipment to obtain a network condition factor, which comprises the following steps: normalizing the network delay of the candidate terminal equipment by using a preset normalization function to obtain a first intermediate factor, and subtracting the first intermediate factor from a specified value to obtain the network condition factor; the normalizing processing is performed on the current workload of the candidate terminal equipment to obtain a load balancing factor, which comprises the following steps: And carrying out normalization processing on the current workload of the candidate terminal equipment by using a preset normalization function to obtain a second intermediate factor, and subtracting the appointed numerical value from the second intermediate factor to obtain the load balancing factor.
5. The method of claim 3, wherein normalizing the power of the candidate terminal device to obtain a power condition factor includes: if the equipment type of the candidate terminal equipment is a plug-in equipment type, setting the electric quantity condition factor to the appointed numerical value; If the equipment type of the candidate terminal equipment is the non-plug-in equipment type, carrying out normalization processing on the current electric quantity of the candidate terminal equipment by utilizing a preset normalization function to obtain the electric quantity condition factor.
6. The method of claim 1, wherein the determining the target terminal device corresponding to the subtask according to the confidence levels of the plurality of candidate terminal devices comprises: traversing the plurality of candidate terminal devices according to the order of the confidence coefficient from high to low; determining the expected load of the candidate terminal equipment according to the task parameters of the task and the current state information of the terminal equipment aiming at any traversed candidate terminal equipment, wherein the task parameters are used for representing the resource consumption corresponding to the subtasks; If the predicted load is smaller than a specified threshold, determining the candidate terminal equipment as the target terminal equipment; And if the predicted load is not smaller than the specified threshold, continuing to traverse the plurality of candidate terminal devices according to the order of the confidence level from large to small until the target terminal device is determined or the traversing is finished.
7. A device scheduling apparatus for use in a server, the apparatus comprising: the analysis module is used for responding to a task request sent by a user, analyzing the task request to obtain a plurality of subtasks and target resources corresponding to the subtasks, wherein the target resources are used for representing hardware resource requirements corresponding to the subtasks; The screening module is used for screening a plurality of candidate terminal devices meeting target resources corresponding to any subtask from a plurality of terminal devices, wherein the plurality of terminal devices are all terminal devices in the same local area network; The confidence degree determining module is used for determining the confidence degrees of the plurality of candidate terminal devices according to the current state information of the plurality of candidate terminal devices, wherein the current state information comprises current computing power, current workload, network delay and current electric quantity; a target terminal device determining module, configured to determine a target terminal device corresponding to the subtask according to the confidence degrees of the plurality of candidate terminal devices; and the sending module is used for sending the subtasks to the target terminal equipment for processing.
8. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the device scheduling method of any one of claims 1-6.
9. A computer readable storage medium storing computer instructions for causing a processor to implement the device scheduling method of any one of claims 1-6 when executed.
10. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the device scheduling method according to any one of claims 1-6.

Description

Device scheduling method, device, storage medium and program product Technical Field The present invention relates to the field of data processing technologies, and in particular, to a device scheduling method, apparatus, device, storage medium, and program product. Background Under the background of deep integration of industrial Internet, intelligent manufacturing, cloud computing and Internet of things technologies, equipment scheduling is used as a core technology for connecting physical equipment and business requirements, and is widely applied to multiple scenes such as production line operation and maintenance, data center management, edge computing node management and control, intelligent logistics and the like. The scheduling precision and efficiency directly determine the equipment utilization rate, the production operation and maintenance cost and the service quality. In the actual landing of the equipment scheduling, the efficient circulation of the information such as the equipment state, the task requirement and the like is realized by depending on the information sharing platform, and a plurality of pain points existing in the current information sharing platform become key bottlenecks for restricting the improvement of the equipment scheduling efficiency. Along with the rapid iteration of 5G, edge computing, artificial intelligence and digital twin technology, the equipment in various scenes presents the remarkable characteristics of isomerization, distribution, scale and dynamics, the complexity and challenges faced by equipment scheduling are continuously upgraded, and the pain point problem of the existing information sharing platform is further amplified. In the prior art, equipment scheduling is performed manually, so that the efficiency of equipment scheduling is low. Disclosure of Invention The embodiment of the invention provides a device scheduling method, a device, equipment, a storage medium and a program product, which are used for solving the problem that the prior art is difficult to realize. According to a first aspect of an embodiment of the present invention, there is provided a device scheduling method, applied to a server, the method including: Responding to a task request sent by a user, analyzing the task request to obtain a plurality of subtasks and target resources corresponding to the subtasks, wherein the target resources are used for representing hardware resource requirements corresponding to the subtasks; For any subtask, screening a plurality of candidate terminal devices meeting target resources corresponding to the subtask from a plurality of terminal devices, wherein the plurality of terminal devices are all terminal devices in the same local area network; the confidence degrees of the candidate terminal devices are respectively determined according to the current state information of the candidate terminal devices, wherein the current state information comprises current computing power, current workload, network delay and current electric quantity; determining target terminal equipment corresponding to the subtasks according to the confidence degrees of the candidate terminal equipment; and sending the subtasks to the target terminal equipment for processing. According to another aspect of the embodiment of the present invention, there is provided a device scheduling apparatus, applied to a server, the apparatus including: the analysis module is used for responding to a task request sent by a user, analyzing the task request to obtain a plurality of subtasks and target resources corresponding to the subtasks, wherein the target resources are used for representing hardware resource requirements corresponding to the subtasks; The screening module is used for screening a plurality of candidate terminal devices meeting target resources corresponding to any subtask from a plurality of terminal devices, wherein the plurality of terminal devices are all terminal devices in the same local area network; The confidence degree determining module is used for determining the confidence degrees of the plurality of candidate terminal devices according to the current state information of the plurality of candidate terminal devices, wherein the current state information comprises current computing power, current workload, network delay and current electric quantity; a target terminal device determining module, configured to determine a target terminal device corresponding to the subtask according to the confidence degrees of the plurality of candidate terminal devices; and the sending module is used for sending the subtasks to the target terminal equipment for processing. According to another aspect of an embodiment of the present invention, there is provided an electronic apparatus including: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to ena