US 11,863,399 B2
System, method, and control apparatus
Anan Sawabe, Tokyo (JP); Takanori Iwai, Tokyo (JP); and Kosei Kobayashi, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Appl. No. 17/642,341
Filed by NEC Corporation, Tokyo (JP)
PCT Filed Sep. 30, 2019, PCT No. PCT/JP2019/038457
§ 371(c)(1), (2) Date Mar. 11, 2022,
PCT Pub. No. WO2021/064769, PCT Pub. Date Apr. 8, 2021.
Prior Publication US 2022/0303190 A1, Sep. 22, 2022
Int. Cl. H04L 41/16 (2022.01); H04L 43/16 (2022.01); G06F 18/21 (2023.01)
CPC H04L 41/16 (2013.01) [G06F 18/2185 (2023.01); H04L 43/16 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A system comprising:
one or more apparatuses each including a memory storing instructions and one or more processors configured to execute the instructions, wherein
the one or more apparatuses are configured to:
obtain work-related information related to human work in network operation;
train a machine learning based controller for controlling communication in a communication network, based on the work-related information;
select the machine learning based controller when the communication network is congested over a certain level; and
select a reinforcement learning based controller configured to control communication in the communication network when the communication network is not congested over the certain level, and
the reinforcement learning is learning what kind of action realizes a greatest reward according to a state of the communication network.