US 12,282,805 B2
Apparatus and method for managing trust-based delegation consensus of blockchain network using deep reinforcement learning
Jong-Moon Chung, Seoul (KR); Yun Yeong Goh, Incheon (KR); and Ju Sik Yun, Seoul (KR)
Assigned to INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY, Seoul (KR)
Filed by INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY, Seoul (KR)
Filed on Oct. 20, 2022, as Appl. No. 18/048,125.
Claims priority of application No. 10-2021-0144312 (KR), filed on Oct. 27, 2021.
Prior Publication US 2023/0139892 A1, May 4, 2023
Int. Cl. H04L 67/10 (2022.01); G06F 9/50 (2006.01)
CPC G06F 9/5072 (2013.01) [H04L 67/10 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An apparatus for managing delegation consensus of a blockchain network, the apparatus having: one or more processors; and a memory storing one or more programs executed by the one or more processors,
wherein the processors
obtain state information including trust of each delegated node in a current epoch of the blockchain network,
determine an action including a delegation rate by performing a neural network operation on the state information,
create, according to the determined action, a local trust opinion (LTO) matrix representing a mutual subjective evaluation of each delegated node, and
select, based on the trust calculated using the LTO matrix, K delegated nodes according to the determined delegation rate among N nodes,
wherein the processors calculate the trust of each delegated node by calculating an average subjective trust value and trust similarity for each delegated node based on the LTO matrix.