System and method for process scheduling

• US 10,692,135 B2
• Filed: 08/08/2012
• Issued: 06/23/2020
• Est. Priority Date: 01/07/2003
• Status: Active Grant

• Current Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Original Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Inventors: Loucaides, Alex, Clayden, Daniel, Carter, Phillip, Addison, Mark
• Primary Examiner(s): Vyas, Abhishek
• Application Number:
  US13/569,617
• Publication Number:
  US 20130013532A1
• Time in Patent Office: 2,876 Days
• Field of Search: 705 35
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

A method for scheduling processing of an instrument. The method receives instrument information, selects an instrument category for the instrument based on the instrument information, the selected instrument category having a calculation set, assigns the instrument to a job corresponding to the calculation set of the selected instrument category; and sends the job to a computing resource. In another aspect, the method also receives a purpose identifier, and chooses the calculation set from two or more calculation sets of the selected instrument category based on the purpose identifier. In another aspect, the calculation set includes two or more calculation sub-sets, each calculation sub-set having a job priority, and the method includes assigning the instrument to two or more jobs corresponding to each of the two or more calculation sub-sets.

Claims

1. A non-transitory computer-readable medium storing instructions for causing a computer to implement a method for scheduling processing of an instrument, the method comprising:

receiving a processing request, the processing request including instrument information and a context that relates to the instrument information;

creating a hashmap that applies a hash function to the context to obtain a 32-bit hash value that provides an internal address used to associate the context with a valuation pool;

selecting an instrument type of the instrument based on the received instrument information, wherein the received instrument information includes a computational complexity of the instrument;

assigning an information set control from a plurality of instrument set controls associated with the instrument type based on a computational intensity of computing a valuation for the instrument and the context of the instrument;

assigning a calculation control associated with a plurality of calculation types based on the assigned information set control;

separating, based on a cached configuration of the scheduler, the instrument into jobs and assigning the instrument to a job corresponding to a calculation control;

placing each job into a pool scheduling queue, determining a corresponding valuation pool queue for each job in the pool scheduling queue by using the context to retrieve the valuation pool via the hashmap, and placing each job into the corresponding valuation pool queue, each valuation pool queue having corresponding processing engines; and

selecting jobs from the valuation pool queue and transmitting each job to one of the multiple processing engines corresponding to the valuation pool queue for processing.

2. The non-transitory computer readable medium of claim 1, wherein the method further comprises creating a previously presented job when the job corresponding to the calculation control does not exist.

3. The non-transitory computer readable medium of claim 1, wherein the instrument information includes the computational intensity of computing the valuation for the instrument.

4. The non-transitory computer readable medium of claim 1, wherein the method further comprises transmitting the job to the processing engine in an order according to a job priority based on the calculation control.

5. The non-transitory computer readable medium of claim 1, wherein the calculation control includes at least one financial calculation.

6. The non-transitory computer readable medium of claim 1, wherein the processing engines operate across one or more CPUs.

7. The non-transitory computer readable medium of claim 1, wherein at least one processing engine is associated with the calculation control.

8. The non-transitory computer readable medium of claim 1, wherein the calculation control includes at least two calculation sub-sets, each calculation sub-set having a job priority, and wherein the method further comprises assigning the instrument to at least two jobs corresponding to each of the at least two calculation sub-sets.

9. The non-transitory computer readable medium of claim 8, wherein the transmitter transmits the at least two jobs to the processing engines in an order according to the job priority.

10. A method for scheduling processing of an instrument across multiple processing engines, the method comprising:

receiving a processing request, the processing request including instrument information and a context that relates to the instrument information;

creating a hashmap that applies a hash function to the context to obtain a 32-bit hash value that provides an internal address used to associate the context with a valuation pool;

selecting an instrument type of the instrument based on the received instrument information, wherein the received instrument information includes a computational complexity of the instrument;

assigning an information set control from a plurality of instrument set controls associated with the instrument type based on a computational intensity of computing a valuation for the instrument and a context of the instrument;

assigning a calculation control associated with a plurality of calculation types based on the assigned information set control;

separating the instrument into jobs and assigns the instrument to a job corresponding to a calculation control;

placing each job into a pool scheduling queue, determining a corresponding valuation pool queue for each job in the pool scheduling queue by using the context to retrieve the valuation pool via the hashmap, and placing each job into the corresponding valuation pool queue, each valuation pool queue having corresponding processing engines; and

selecting jobs from the valuation pool queue for transmitting each job to one of the multiple processing engines corresponding to the valuation pool queue for processing.

11. The method of claim 10, wherein assigning the calculation control further comprises creating a previously presented job when the job corresponding to the calculation control does not exist.

12. The method of claim 10, wherein the instrument information includes the computational intensity of computing the valuation for the instrument.

13. The method of claim 10, further comprising transmitting the job to the processing engines in an order according to a job priority based on the calculation tool.

14. The method of claim 10, wherein the calculation control includes at least one financial calculation.

15. The method of claim 10, wherein the processing engines operate across one or more CPUs.

16. The method of claim 10, wherein at least one processing engine is associated with the calculation control.

17. The method of claim 10, wherein the calculation control includes at least two calculation sub-sets, each calculation sub-set having a job priority, and wherein the method further comprises assigning the instrument to at least two jobs corresponding to each of the at least two calculation sub-sets.

18. The method of claim 10, further comprising transmitting at least two jobs to the processing engine in an order according to the job priority.

19. A system for scheduling processing of an instrument across multiple processing engines, the system comprising:

a central processing unit configured to;

receive a processing request, the processing request including instrument information and a context that relates to the instrument information;

create a hashmap that applies a hash function to the context to obtain a 32-bit hash value that provides an internal address used to associate the context with a valuation pool;

select an instrument type of the instrument based on the received instrument information, wherein the received instrument information includes a computational complexity of the instrument;

assign an information set control from a plurality of instrument set controls associated with the instrument type based on a computational intensity of computing a valuation for the instrument and a context of the instrument;

assign a calculation control associated with a plurality of calculation types based on the assigned information set control;

separate, based on a cached configuration of the system, the instrument into jobs and assign a portion of the instrument to a job corresponding to a calculation control;

place each job into a pool scheduling queue, determine a corresponding valuation pool queue for each job in the pool scheduling queue by using the context to retrieve the valuation pool via the hashmap, and place each job into the corresponding valuation pool queue, each valuation pool queue having corresponding processing engines; and

select jobs from the valuation pool queue and transmit each job to one of the multiple processing engines corresponding to the valuation pool queue for processing.

20. The system of claim 19, wherein the valuation pool queue comprises a plurality of valuation pools stored in the hashmap.