Computer system, edge device control method, and program

• US 10,637,928 B2
• Filed: 11/30/2016
• Issued: 04/28/2020
• Est. Priority Date: 11/30/2016
• Status: Active Grant

• Current Assignee: Optim LLC
• Original Assignee: Optim LLC
• Inventors: Sugaya, Shunji
• Primary Examiner(s): Won, Michael
• Application Number:
  US15/574,924
• Publication Number:
  US 20190289075A1
• Time in Patent Office: 1,245 Days
• Field of Search: 709220, 709223, 709230
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: H04L 12/66 Arrangements for connecting between networks having differing types of switching systems, e.g. gateways
• CPC Class Codes: H04L 41/0853 by actively collecting configuration information or by backing up configuration information
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network
• CPC Class Codes: H04W 4/38 for collecting sensor information

Abstract

It is an object to provide a computer system, an edge device control method, and a program for improving a processing speed by effectively utilizing edge devices existing in a network. A computer system for controlling edge devices 100 connected to a gateway 200 to perform machine learning detects edge devices 100 connected to the gateway 200, determines a combination of the detected edge devices 100, acquires processing performances of the detected edge devices 100, determines programs for edge device 100 and a program for machine learning based on the determined combination and the acquired processing performances, transmits the determined programs for edge device 100 to the edge devices 100 in accordance with the acquired processing performances, causes the edge devices 100 to execute the programs for edge device 100 in accordance with the acquired processing performances, and causes a predetermined computer to execute the program for machine learning.

Claims

1. A computer system for controlling edge devices connected to a gateway to perform machine learning, the computer system comprising:

a detection unit that detects edge devices connected to the gateway;

a combination determining unit that determines a combination type of the detected edge devices from among a plurality of combination types each indicating a combination of one or more edge devices;

an acquiring unit that acquires processing performances of the detected edge devices;

a program determining unit that determines programs for edge device and a program for machine learning based on the determined combination type and the acquired processing performances;

a transmitting unit that transmits the determined programs for edge device to the edge devices in accordance with the acquired processing performances; and

an executing unit that causes the edge devices to execute the programs for edge device in accordance with the acquired processing performances, and causes a predetermined computer to execute the program for machine learning,

wherein the determined programs transmitted to an edge device satisfying a predetermined condition among the detected edge devices include a program for machine learning to be executed by the edge device satisfying the predetermined condition, and

wherein the determined programs transmitted to an edge device satisfying no predetermined condition among the detected edge devices include no program for machine learning.

2. The computer system according to claim 1, further comprising:

a downloading unit that controls the edge device to download a teacher data corresponding to the data; and

a control unit that causes the edge device to perform machine learn on the data using the teacher data.

3. The computer system according to claim 1, wherein in a case where the acquired processing performance is high, the executing unit causes the edge device to execute a program for machine learning that can be activated by the edge device among the programs for edge device.

4. The computer system according to claim 1, wherein in a case where the acquired processing performance is high, the executing unit causes the edge device to execute a program for machine learning that can be activated by the edge device among the programs for edge device, together with the program for machine learning executed in the predetermined computer.

5. The computer system according to claim 1, wherein the predetermined condition includes a condition that the processing performance of the edge device is equal to or higher than a predetermined performance.

6. An edge device control method for controlling edge devices connected to a gateway to perform machine learning, the computer system comprising:

detecting edge devices connected to the gateway;

determining a combination type of the detected edge devices from among a plurality of combination types each indicating a combination of one or more edge devices;

acquiring processing performances of the detected edge devices;

determining programs for edge device and a program for machine learning based on the determined combination type and the acquired processing performances;

transmitting the determined programs for edge device to the edge devices in accordance with the acquired processing performances; and

causing the edge devices to execute the programs for edge device in accordance with the acquired processing performances, and causing a predetermined computer to execute the program for machine learning,

wherein the determined programs transmitted to an edge device satisfying a predetermined condition among the detected edge devices include a program for machine learning to be executed by the edge device satisfying the predetermined condition, and

wherein the determined programs transmitted to an edge device satisfying no predetermined condition among the detected edge devices include no program for machine learning.

7. The edge device control method according to claim 6, wherein the predetermined condition includes a condition that the processing performance of the edge device is equal to or higher than a predetermined performance.

8. A program, stored on a non-transitory recording medium, for causing a computer system for controlling edge devices connected to a gateway to perform machine learning, to execute to:

detect edge devices connected to the gateway;

determine a combination type of the detected edge devices from among a plurality of combination types each indicating a combination of one or more edge devices;

acquire processing performances of the detected edge devices;

determine programs for edge device and a program for machine learning based on the determined combination type and the acquired processing performances;

transmit the determined programs for edge device to the edge devices in accordance with the acquired processing performances; and

cause the edge devices to execute the programs for edge device in accordance with the acquired processing performances, and cause a predetermined computer to execute the program for machine learning,

wherein the determined programs transmitted to an edge device satisfying a predetermined condition among the detected edge devices include a program for machine learning to be executed by the edge device satisfying the predetermined condition, and

wherein the determined programs transmitted to an edge device satisfying no predetermined condition among the detected edge devices include no program for machine learning.

9. The program according to claim 8, wherein the predetermined condition includes a condition that the processing performance of the edge device is equal to or higher than a predetermined performance.