Granted Patent B2

US 12,608,238 · App. 18/014,125 · Granted Apr 21, 2026

Inventors: Shiying Jin (Shenzhen, CN); Zhenyu Wang (Shenzen, CN); Bingtao Han (Shenzhen, CN); Yaofeng Tu (Shenzhen, CN); Hong Gao (Shenzhen, CN)

Assignee: ZTE Corporation

G06F9/5055G06F9/4881

Abstract

Claims (83)

1 . A resource scheduling method, comprising:

acquiring an intelligent application processing request;

acquiring current resource usage information;

matching an intelligent application instance according to the intelligent application processing request; and

creating a task according to the resource usage information and the intelligent application instance, to process the intelligent application processing request;

wherein prior to creating a task according to the resource usage information and the intelligent application instance, the method further comprises:

acquiring at least two corresponding intelligent application models according to the current concurrent intelligent application instances;

acquiring a number of to-be-processed requests corresponding to each respective intelligent application model in the cache queue;

acquiring priority information of the intelligent application model;

acquiring, according to the number of the to-be-processed requests corresponding to each respective intelligent application models, weight information corresponding to the respective intelligent application model;

adjusting a priority of the respective intelligent application model according to the priority information and the weight information; and

adjusting an instance concurrency number corresponding to the respective intelligent application model according to the priority of the respective intelligent application model and the number of the to-be-processed requests.

2 . The resource scheduling method of claim 1 , wherein prior to matching an intelligent application instance according to the intelligent application processing request, the method further comprises:

acquiring at least one intelligent application model according to the intelligent application processing request; and

creating at least one intelligent application instance according to the intelligent application model, a resource demand corresponding to the intelligent application model, and the resource usage information.

3 . The resource scheduling method of claim 2 , wherein creating at least one intelligent application instance according to the intelligent application model, a resource demand corresponding to the intelligent application model, and the resource usage information comprises:

acquiring a first estimated resource amount according to the resource demand corresponding to the intelligent application model;

acquiring a current idle resource amount according to resource usage information;

comparing the first estimated resource amount with the idle resource amount; and

creating at least one intelligent application instance according to the intelligent application model in response to the first estimated resource amount being not greater than the idle resource amount.

4 . The resource scheduling method of claim 3 , wherein creating a task according to the resource usage information and the intelligent application instance comprises:

acquiring state information of the intelligent application instance;

acquiring current task concurrency information;

creating a task according to the intelligent application instance, the state information of the intelligent application instance and the task concurrency information.

5 . The resource scheduling method of claim 3 , wherein prior to creating a task according to the resource usage information and the intelligent application instance, the method further comprises:

acquiring a corresponding intelligent application model according to the intelligent application instance;

acquiring a number of to-be-processed requests corresponding to the intelligent application model in a cache queue; and

adjusting an instance concurrency number of the intelligent application model according to the number of to-be-processed requests.

6 . The resource scheduling method of claim 2 , wherein creating a task according to the resource usage information and the intelligent application instance comprises:

acquiring state information of the intelligent application instance;

acquiring current task concurrency information;

creating a task according to the intelligent application instance, the state information of the intelligent application instance and the task concurrency information.

7 . The resource scheduling method of claim 2 , wherein prior to creating a task according to the resource usage information and the intelligent application instance, the method further comprises:

acquiring a corresponding intelligent application model according to the intelligent application instance;

acquiring a number of to-be-processed requests corresponding to the intelligent application model in a cache queue; and

adjusting an instance concurrency number of the intelligent application model according to the number of to-be-processed requests.

8 . The resource scheduling method of claim 1 , wherein prior to matching an intelligent application instance according to the intelligent application processing request, the method further comprises:

prioritizing intelligent application models in a model database to acquire priority information;

acquiring one of the intelligent application models according to the intelligent application processing request and the priority information;

creating at least one intelligent application instance according to the intelligent application model, a resource demand corresponding to the intelligent application model, and the resource usage information.

9 . The resource scheduling method of claim 8 , wherein creating a task according to the resource usage information and the intelligent application instance comprises:

acquiring state information of the intelligent application instance;

acquiring current task concurrency information;

creating a task according to the intelligent application instance, the state information of the intelligent application instance and the task concurrency information.

10 . The resource scheduling method of claim 1 , wherein creating a task according to the resource usage information and the intelligent application instance comprises:

acquiring state information of the intelligent application instance;

acquiring current task concurrency information;

creating a task according to the intelligent application instance, the state information of the intelligent application instance and the task concurrency information.

11 . The resource scheduling method of claim 10 , wherein creating a task according to the intelligent application instance, the state information of the intelligent application instance and the task concurrency information comprises:

acquiring a task concurrency number according to the task concurrency information;

comparing the task concurrency number with a maximum task concurrency number;

creating a task according to the intelligent application instance and the state information of the intelligent application instance in response to the task concurrency number being not greater than the maximum task concurrency number.

12 . The resource scheduling method of claim 11 , wherein prior to comparing the task concurrency number with the maximum task concurrency number, the method further comprises:

acquiring a current wait task number; and

adjusting the maximum task concurrency number according to a current maximum task concurrency number, a maximum number of tasks in the system and a preset adjustment factor in response to the current wait task number being greater than a preset wait task number threshold.

13 . The resource scheduling method of claim 1 , wherein prior to creating a task according to the resource usage information and the intelligent application instance, the method further comprises:

acquiring a corresponding intelligent application model according to the intelligent application instance;

acquiring a number of to-be-processed requests corresponding to the intelligent application model in a cache queue; and

adjusting an instance concurrency number of the intelligent application model according to the number of to-be-processed requests.

14 . An electronic device, comprising: a memory, a processor, and a program stored in the memory and executable by the processor which, when executed by the processor, causes the processor to perform a resource scheduling method, the resource scheduling method comprising:

acquiring an intelligent application processing request;

acquiring current resource usage information;

matching an intelligent application instance according to the intelligent application processing request; and

creating a task according to the resource usage information and the intelligent application instance, to process the intelligent application processing request;

wherein prior to creating a task according to the resource usage information and the intelligent application instance, the method further comprises:

acquiring at least two corresponding intelligent application models according to the current concurrent intelligent application instances;

acquiring a number of to-be-processed requests corresponding to each respective intelligent application model in the cache queue;

acquiring priority information of the intelligent application model;

acquiring, according to the number of the to-be-processed requests corresponding to each respective intelligent application models, weight information corresponding to the respective intelligent application model;

adjusting a priority of the respective intelligent application model according to the priority information and the weight information; and

adjusting an instance concurrency number corresponding to the respective intelligent application model according to the priority of the respective intelligent application model and the number of the to-be-processed requests.

15 . A non-transitory computer-readable storage medium configured for computer-readable storage, wherein the storage medium stores at least one program which, when executed by at least one processor, causes the at least one processor to perform a resource scheduling method, the resource scheduling method comprising:

acquiring an intelligent application processing request;

acquiring current resource usage information;

matching an intelligent application instance according to the intelligent application processing request; and

creating a task according to the resource usage information and the intelligent application instance, to process the intelligent application processing request;

wherein prior to creating a task according to the resource usage information and the intelligent application instance, the method further comprises:

acquiring at least two corresponding intelligent application models according to the current concurrent intelligent application instances;

acquiring a number of to-be-processed requests corresponding to each respective intelligent application model in the cache queue;

acquiring priority information of the intelligent application model;

acquiring, according to the number of the to-be-processed requests corresponding to each respective intelligent application models, weight information corresponding to the respective intelligent application model;

adjusting a priority of the respective intelligent application model according to the priority information and the weight information; and

adjusting an instance concurrency number corresponding to the respective intelligent application model according to the priority of the respective intelligent application model and the number of the to-be-processed requests.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (12)