US 12,282,303 B2
Deep causal learning for continuous testing, diagnosis, and optimization
Gilles J. Benoit, Minneapolis, MN (US); Brian E. Brooks, St. Paul, MN (US); Peter O. Olson, Andover, MN (US); and Tyler W. Olson, Woodbury, MN (US)
Assigned to 3M Innovative Properties Company, St. Paul, MN (US)
Appl. No. 17/431,533
Filed by 3M INNOVATIVE PROPERTIES COMPANY, St. Paul, MN (US)
PCT Filed Sep. 11, 2019, PCT No. PCT/IB2019/057673
§ 371(c)(1), (2) Date Aug. 17, 2021,
PCT Pub. No. WO2020/188331, PCT Pub. Date Sep. 24, 2020.
Claims priority of provisional application 62/818,816, filed on Mar. 15, 2019.
Prior Publication US 2022/0121971 A1, Apr. 21, 2022
Int. Cl. G05B 13/04 (2006.01); B60W 40/064 (2012.01); B60W 40/08 (2012.01); B60W 40/105 (2012.01); G05B 13/02 (2006.01); G05B 19/4065 (2006.01); G05B 19/418 (2006.01); G05B 23/02 (2006.01); G06F 18/21 (2023.01); G06N 5/043 (2023.01); G06N 5/046 (2023.01); G06N 7/01 (2023.01); G06Q 10/0631 (2023.01); G06Q 10/0639 (2023.01); G06Q 10/087 (2023.01); G06Q 30/0202 (2023.01)
CPC G05B 13/042 (2013.01) [B60W 40/064 (2013.01); B60W 40/08 (2013.01); B60W 40/105 (2013.01); G05B 13/021 (2013.01); G05B 13/024 (2013.01); G05B 13/0265 (2013.01); G05B 13/041 (2013.01); G05B 19/4065 (2013.01); G05B 19/41835 (2013.01); G05B 23/0229 (2013.01); G05B 23/0248 (2013.01); G06F 18/2193 (2023.01); G06N 5/043 (2013.01); G06N 5/046 (2013.01); G06N 7/01 (2023.01); G06Q 10/06315 (2013.01); G06Q 10/06395 (2013.01); G06Q 30/0202 (2013.01); G05B 2219/36301 (2013.01); G06Q 10/087 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for multivariate learning and optimization, comprising:
memory; and
a processor coupled to the memory, the processor configured to:
receive one or more assumptions for a randomized multivariate comparison of process decisions, the process decisions to be provided to users of a system;
repeatedly generate self-organized experimental units (SOEUs) based on the one or more assumptions;
inject the SOEUs into the system to generate quantified inferences about the process decisions;
identify, responsive to injecting the SOEUs, at least one confidence interval within the quantified inferences;
compute the at least one confidence interval by statistical testing on d-scores, which are defined as differences between measured effects when a variable is activated and when it is deactivated; and
iteratively modify the SOEUs based on the at least one confidence interval to identify at least one causal interaction of the process decisions within the system.