	US 11,704,388 B2
	Disaggregation system
Christian Macaro, Munich (DE); Fedor Reva, Guadalajara (ES); and Rocco Claudio Cannizzaro, Cary, NC (US)
Assigned to SAS Institute Inc., Cary, NC (US)
Filed by SAS Institute Inc., Cary, NC (US)
Filed on Jul. 12, 2022, as Appl. No. 17/862,510.
Claims priority of provisional application 63/308,570, filed on Feb. 10, 2022.
Claims priority of provisional application 63/289,559, filed on Dec. 14, 2021.
Prior Publication US 2023/0185883 A1, Jun. 15, 2023
Int. Cl. G06F 17/11 (2006.01); G06F 18/2413 (2023.01); G06Q 10/0635 (2023.01); G06F 18/2411 (2023.01); G06F 18/23213 (2023.01)

CPC G06F 18/24137 (2023.01) [G06F 17/11 (2013.01); G06F 18/23213 (2023.01); G06F 18/2411 (2023.01); G06Q 10/0635 (2013.01)]

30 Claims

1. A non-transitory computer-readable medium having stored thereon computer-readable instructions that when executed by a computing device cause the computing device to:

(A) compute a first value for a known variable using a predefined density distribution function;

(B) compute a second value for an unknown variable using the computed first value, a predefined correlation value, and a predefined aggregate value, wherein the predefined correlation value indicates a correlation between the known variable and the unknown variable;

(C) repeat (A) and (B) until a predefined number of solution vectors is computed, wherein a solution vector is the computed first value and the computed second value;

(D) compute a centroid vector from solution vectors computed by repeating (A) and (B) in (C);

(E) determine a predefined number of closest solution vectors to the computed centroid vector from the solution vectors;

(F) select a first solution vector from the predefined number of closest solution vectors;

(G) define a first aggregate value that is a value of the known variable in the selected first solution vector;

(H) compute a third value for a second known variable using a second predefined density distribution function;

(I) compute a fourth value for a second unknown variable using the computed third value, a second predefined correlation value, and the defined first aggregate value, wherein the second predefined correlation value indicates a correlation between the second known variable and the second unknown variable;

(J) repeat (H) and (I) until the predefined number of solution vectors is computed to define second solution vectors, wherein a second solution vector is the computed third value and the computed fourth value;

(K) compute a second centroid vector from the defined second solution vectors;

(L) determine a second predefined number of closest solution vectors to the computed second centroid vector from the defined second solution vectors;

(M) define a second aggregate value that is a value of the unknown variable in the selected first solution vector;

(N) compute a fifth value for a third known variable using a third predefined density distribution function;

(O) compute a sixth value for a third unknown variable using the computed fifth value, a third predefined correlation value, and the defined second aggregate value, wherein the third predefined correlation value indicates a correlation between the third known variable and the third unknown variable;

(P) repeat (N) and (O) until the predefined number of solution vectors is computed to define third solution vectors, wherein a third solution vector is the computed fifth value and the computed sixth value;

(Q) compute a third centroid vector from the defined third solution vectors;

(R) determine a third predefined number of closest solution vectors to the computed third centroid vector from the defined third solution vectors; and

(S) output the determined second predefined number of closest solution vectors and the determined third predefined number of closest solution vectors as disaggregated solutions given the predefined aggregate value.