US 11,889,819 B2
Methods and apparatus to adaptively optimize feed blend and medicinal selection using machine learning to optimize animal milk production and health
James Brennan Worth, Aurora, CO (US)
Assigned to Substrate AI SA, Madrid (ES)
Filed by SUBSTRATE AI SA, Madrid (ES)
Filed on Sep. 29, 2021, as Appl. No. 17/488,706.
Prior Publication US 2023/0101777 A1, Mar. 30, 2023
Int. Cl. A01K 29/00 (2006.01); A23K 10/00 (2016.01); G06N 20/00 (2019.01); G06F 18/21 (2023.01)
CPC A01K 29/005 (2013.01) [A23K 10/00 (2016.05); G06F 18/217 (2023.01); G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A method, comprising: training a machine learning model associated with a set of hyperparameters to receive an indication associated with a health status of a managed livestock and a value associated with a bioproduct quality of the managed livestock and output, based on the set of hyperparameters, a feed selection configured to increase a likelihood of collectively improving the health status of the managed livestock and the bioproduct quality of the managed livestock, the set of hyperparameters including at least one of a discount factor associated with a weight of future rewards in the machine learning model, or a threshold value to balance between exploration and exploitation within the machine learning model; receiving, at a first time, a first value of the bioproduct quality and a first indication of the health status of the managed livestock; generating a set of input vectors based on the first value of the bioproduct quality and the first indication of the health status of the managed livestock; providing the set of input vectors to the machine learning model to generate a first output indicating a first feed selection to be used to feed the managed livestock, the first feed selection configured to, upon consumption, collectively improve the health status of the managed livestock and the bioproduct quality of the managed livestock based on the first value and the first indication; receiving, at a second time, at least one of a second value of the bioproduct quality or a second indication of the health status of the managed livestock; and automatically adjusting at least one hyperparameter from the set of hyperparameters in response to receiving the second value of the bioproduct quality or the second indication of the health status such that that the machine learning model is configured to generate a second output indicating a second feed selection to be used to feed the managed livestock, the second feed selection configured to, upon consumption, collectively improve the health status of the managed livestock and the bioproduct quality of the managed livestock based on the second value and the second indication.