Resource allocation in distributed processing systems

• US 10,153,984 B2
• Filed: 06/30/2017
• Issued: 12/11/2018
• Est. Priority Date: 09/29/2014
• Status: Active Grant

• Current Assignee: Pearson Education Incorporated (Pearson plc)
• Original Assignee: Pearson Education Incorporated (Pearson plc)
• Inventors: Dronen, Jr., Nicholas A., Foltz, Peter W., Garner, Holly, Loring, Miles T., Kapoor, Vishal
• Primary Examiner(s): Lai, Michael C
• Application Number:
  US15/640,101
• Publication Number:
  US 20170300360A1
• Time in Patent Office: 529 Days
• Field of Search: 709224, 709226
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: H04L 47/783 Distributed allocation of resources, e.g. bandwidth brokers

Abstract

A distributed processing system is disclosed herein. The distributed processing system includes a server, a database server, and an application server that are interconnected via a network, and connected via the network to a plurality of independent processing units. The independent processing units can include an analysis engine that is machine-learning-capable, and thus uniquely completes its processing tasks. The server can provide one or several pieces of data to one or several of the independent processing units, can receive analysis results from these one or several independent processing units, and can update the result based on a value characterizing the machine learning of the independent processing unit.

Claims

1. A system for automated management of a plurality of independent processing units, the system comprising:

a first independent processing unit comprising a first analysis engine;

a second independent processing unit comprising a second analysis engine; and

at least one server communicating coupled with the first independent processing unit and the second independent processing unit, the at least one server configured to;

select a task for a first evaluation by the first independent processing unit and a second evaluation by the second independent processing unit;

receive a first evaluation of the task from the first independent processing unit;

retrieve a first accuracy parameter characterizing an accuracy of previous evaluations from the first independent processing unit;

receive the second evaluation of the task from the second independent processing unit;

retrieve a second accuracy parameter characterizing an accuracy of previous evaluations from the second independent processing unit;

generate a combined evaluation of the task based on the first evaluation, the second evaluation, the first accuracy parameter, and the second accuracy parameter; and

update the first accuracy parameter based on a difference between the combined evaluation and the first evaluation.

2. The system of claim 1, wherein the combined evaluation is generated based on the first evaluation, the second evaluation, and the first accuracy parameter.

3. The system of claim 1, wherein the at least one server is further configured to generate a discrepancy value indicating a difference between the first evaluation and the combined evaluation.

4. The system of claim 3, wherein the first accuracy parameter is updated based on the discrepancy value.

5. The system of claim 4, wherein the at least one server is further configured to automatically select training material in response to the updated first accuracy parameter.

6. The system of claim 5, wherein the at least one server is further configured to deliver the training material to the first independent processing unit.

7. The system of claim 1, wherein the at least one server is further configured to:

select the first independent processing unit for generation of the first evaluation; and

provide analysis criteria to the first independent processing unit in electronic format, wherein the analysis criteria are convertible to visual format.

8. A method for automated management of a plurality of independent processing units, the method comprising:

selecting with one or more servers a task for a first evaluation by a first independent processing unit and for a second evaluation by a second independent processing unit;

receiving at the one or more servers the first evaluation of the task from the first independent processing unit;

retrieving a first accuracy parameter characterizing an accuracy of evaluations previously received from the first independent processing unit;

receiving the second evaluation of the task from the second independent processing unit;

retrieving a second accuracy parameter characterizing an accuracy of previous evaluations from the second independent processing unit;

generating with the one or more servers a combined evaluation of the task based on the first evaluation, the second evaluation, the first accuracy parameter, and the second accuracy parameter; and

updating with the one or more servers the first accuracy parameter based on a difference between the combined evaluation and the first evaluation.

9. The method of claim 8, wherein the combined evaluation is generated based on the first evaluation, the second evaluation, and the first accuracy parameter.

10. The method of claim 8, generating a discrepancy value indicating a difference between the first evaluation and the combined evaluation.

11. The method of claim 10, wherein the first accuracy parameter is updated based on the discrepancy value.

12. The method of claim 11, further comprising automatically selecting training material in response to the updated first accuracy parameter.

13. The method of claim 12, further comprising delivering the training material to the first independent processing unit.

14. The method of claim 8, further comprising:

selecting the first independent processing unit for generation of the first evaluation; and

providing analysis criteria to the first independent processing unit in electronic format, wherein the analysis criteria are convertible to visual format.