US 11,748,835 B2
Systems and methods for monetizing data in decentralized model building for machine learning using a blockchain
Sathyanarayanan Manamohan, Bangalore (IN); Vishesh Garg, Bangalore (IN); and Krishnaprasad Lingadahalli Shastry, Bangalore (IN)
Assigned to Hewlett Packard Enterprise Development LP, Spring, TX (US)
Filed by HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP, Houston, TX (US)
Filed on Jan. 27, 2020, as Appl. No. 16/773,397.
Prior Publication US 2021/0233192 A1, Jul. 29, 2021
Int. Cl. H04L 9/32 (2006.01); G06F 16/22 (2019.01); G06N 20/20 (2019.01); G06Q 20/06 (2012.01); G06F 16/23 (2019.01); G06N 20/00 (2019.01); G06Q 20/38 (2012.01); G06Q 50/26 (2012.01); H04L 9/40 (2022.01); G06Q 30/018 (2023.01); G06Q 10/10 (2023.01); G06Q 20/40 (2012.01); G06Q 30/0207 (2023.01); G06Q 40/04 (2012.01)
CPC G06Q 50/265 (2013.01) [G06F 16/2246 (2019.01); G06F 16/2255 (2019.01); G06F 16/2315 (2019.01); G06F 16/2365 (2019.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G06Q 10/10 (2013.01); G06Q 20/0655 (2013.01); G06Q 20/388 (2013.01); G06Q 20/401 (2013.01); G06Q 30/0185 (2013.01); G06Q 30/0215 (2013.01); G06Q 40/04 (2013.01); H04L 9/3236 (2013.01); H04L 63/0435 (2013.01); G06Q 2220/00 (2013.01); G06Q 2220/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A first computing node to operate in a blockchain network, comprising:
a processor; and
a non-transitory storage medium storing instructions executable on the processor to:
train, at the first computing node, a machine learning model as part of distributed machine learning performed by a plurality of computing nodes including the first computing node;
output a model parameter produced by the training of the machine learning model from the first computing node to a second computing node of the plurality of computing nodes for merging of the model parameter from the first computing node with model parameters from other computing nodes of the plurality of computing nodes;
receive, at the first computing node from the second computing node, a merged parameter produced by the merging of the model parameter from the first computing node with the model parameters from the other computing nodes;
update, at the first computing node, the machine learning model using the merged parameter;
encrypt a raw data record extracted from the machine learning model being trained;
create a secure cryptographic hash of the encrypted raw data record;
build a hash tree based at least on the secure cryptographic hash of the encrypted raw data record, and register a corresponding hash tree root in a distributed ledger of the blockchain network;
submit a claim for a reward represented by a height of the hash tree;
provide a hash tree proof to each of the other computing nodes in the blockchain network, the hash tree proof verifying the height of the hash tree in response to a verification challenge from a computing node of the plurality of computing nodes;
calculate an amount of individual data points contributed by the first computing node based upon the height of the hash tree, the calculated amount of individual data points comprising a share of a monetization reward for the training of the machine learning model at the first computing node; and
receive the share of the monetization reward.