Granted Patent B2

US 12,596,570 · App. 17/807,145 · Granted Apr 7, 2026

Inventors: Joseph W. Dain (Tucson, AZ); Simon Lorenz (Biebertal, DE); Piyush Chaudhary (Highland, NY); Gero Friedrich Wolf Schmidt (Mainz, DE); Qais Noorshams (Frankfurt, DE); Gregory T. Kishi (Oro Valley, AZ)

Assignee: International Business Machines Corporation

G06F9/4881

Abstract

Claims (54)

1 . A method for managing computer jobs in a queue comprising:

extracting current metadata from a new job received for processing;

providing the extracted current metadata from said new job to a self-learning artificial intelligence (AI) system for determining when a similar enriched metadata exists in a database, wherein availability of enriched data is determined by researching said database according to labels used to classify contents of said enriched data;

further comprising generating enriched metadata from said extracted current metadata and updating said database;

determining a job score associated with said received new job by said self-learning AI system based on said extracted current metadata and the generated enriched metadata;

determining a storage footprint for said new job based on said extracted current metadata;

determining whether said new job can be grouped and labelled similarly for processing with a plurality of pending jobs disposed on a queue;

analyzing information about job groupings and an overall storage footprint of the plurality of pending jobs disposed on the queue to provide an optimal solution by said self-learning AI system for processing the plurality of pending jobs,

wherein said provided optimal solution includes both speed and cost considerations of storage and groupings of said plurality of pending jobs;

adding said new job to said queue and sorting said queue based on said provided optimal solution,

wherein the adding of said job to said queue comprises a placement of said new job on said queue is based on a combination of said provided optimal solution, said determined score of the new job, said determined storage footprint, said determined grouping of the new job with the pending jobs disposed on said queue for processing, and said similar enriched metadata;

process said new job and the pending jobs according to the placement of said new job on the queue.

2 . The method of claim 1 , wherein said queue is updated after sorting and said updated queue is sent to a scheduler for further job processing.

3 . The method of claim 2 , wherein said job score is determined from at least one of a job priority, previous job completion record, and/or job complexity.

4 . The method of claim 1 , wherein said similar jobs are also grouped together for processing when said queue is being sorted and updated.

5 . The method of claim 4 , wherein the queue is also sorted based on a plurality of prefetch and data evict needs of each job.

6 . The method of claim 5 , wherein said new job is grouped with other jobs on said queue based on prefetch and data evict needs of said jobs in said queue.

7 . The method of claim 1 , further comprising:

updating and resorting said queue every time one of said jobs on said queue is completed.

8 . The method of claim 7 , wherein after said job completion, evicting data from said storage and determining whether said new job received may be regrouped based on said data eviction in said queue.

9 . The method of claim 8 , further comprising determining an order of said new job received in said queue after any job is completed in said queue by re-determining said score associated with said new job as appropriate and said new job's storage footprint.

10 . The method of claim 8 , wherein said queue is updated and provided to a scheduler for further data and job processing.

11 . A computer system, comprising: one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method for managing computer jobs in a queue comprising:

extracting current metadata from a new job received for processing;

providing the extracted current metadata from said new job to a self-learning artificial intelligence (AI) system for determining when a similar enriched metadata exists in a database, wherein availability of enriched data is determined by researching said database according to labels used to classify contents of said enriched data;

further comprising generating enriched metadata from said extracted current metadata and updating said database;

determining a job score associated with said received new job by said self-learning AI system based on said extracted current metadata and the generating enriched metadata;

determining a storage footprint for said received new job based on said extracted current metadata;

determining whether said new job can be grouped and labelled similarly for processing with a plurality of pending jobs disposed on a queue;

analyzing information about job groupings and an overall storage footprint to provide an

optimal solution by said self-learning AI system for processing of the plurality of pending jobs disposed on the queue, wherein said optimal solution includes both speed and cost considerations and groupings of said plurality of pending jobs;

adding said new job to said queue and sorting said queue based on said provided optimal solution,

wherein the adding of said job to said queue comprises a placement of said new job on said queue is based on a combination of said provided optimal solution and said determined score of the new job, and said determined storage footprint, and said determined grouping of the new job with the pending jobs disposed on said queue for processing and said similar enriched metadata;

process said new job and the pending jobs according to the placement of said new job on the queue.

12 . The computer system of claim 11 , wherein said queue is updated after sorting and said updated queue is sent to a scheduler for further job processing.

13 . The computer system of claim 11 , wherein said job score is determined from at least one of a job priority, previous job completion record, and/or job complexity.

14 . The computer system of claim 11 , wherein said storage footprint is a cache footprint.

15 . The computer system of claim 11 , wherein said similar jobs are also grouped together for processing when said queue is being sorted and updated.

16 . A computer program product, comprising: one or more non-transitory computer-readable storage media and program instructions stored on at least one or more tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:

extracting current metadata from a new job received for processing;

providing the extracted current metadata from said new job to a self-learning artificial intelligence (AI) system for determining when a similar enriched metadata exists in a database, wherein availability of enriched data is determined by researching said database according to labels used to classify contents of said enriched data;

further comprising generating enriched metadata from said extracted current metadata and updating said database;

determining a job score associated with said received new job by said self-learning AI system based on said extracted current metadata and the generated enriched metadata, wherein availability of said enriched data is determined by researching said database according to labels used to classify contents of said enriched data;

further comprising generating enriched metadata from said extracted current metadata and updating said database;

determining a storage footprint for said new job based on said extracted current metadata;

determining whether said new job can be grouped and labelled similarly for processing with a plurality of pending jobs disposed on a queue;

analyzing information about job groupings and an overall storage footprint of the plurality of pending jobs disposed on the queue to provide an optimal solution by said self-learning AI system for processing the plurality of pending jobs, wherein provided said optimal solution includes both speed and cost considerations of storage and groupings of said

plurality of pending jobs;

adding said new job to said queue and sorting said queue based on said provided optimal solution,

wherein the adding of said job to said queue comprises a placement of said new job on said queue is based on a combination of said provided optimal solution, said determined score of the new job, said determined storage footprint, and said determined grouping of the new job with the pending jobs disposed on said queue for processing, and said similar enriched metadata;

process said new job and the pending jobs according to the placement of said new job on the queue.

17 . The computer program product of claim 16 , wherein said queue is updated after sorting and said updated queue is sent to a scheduler for further job processing.

18 . The computer program product of claim 16 , wherein said job score is determined from at least one of a job priority, previous job completion record, and/or job complexity.

19 . The computer program product of claim 16 , wherein said storage footprint is a cache footprint.

Assignments (1)

Continuity (1)

References Cited (25)