US 11,875,292 B2
Image-based decomposition for fast iterative solve of complex linear problems
Devanand R, Bangalore (IN); Narayan Nandeda, Ujjain (IN); and Tushar Shekhar, Bangalore (IN)
Assigned to Blue Yonder Group, Inc., Scottsdale, AZ (US)
Filed by Blue Yonder Group, Inc., Scottsdale, AZ (US)
Filed on Feb. 20, 2023, as Appl. No. 18/111,749.
Application 18/111,749 is a continuation of application No. 17/745,305, filed on May 16, 2022, granted, now 11,605,039.
Application 17/745,305 is a continuation of application No. 16/886,684, filed on May 28, 2020, granted, now 11,334,827, issued on May 17, 2022.
Claims priority of provisional application 62/895,866, filed on Sep. 4, 2019.
Claims priority of provisional application 62/856,360, filed on Jun. 3, 2019.
Prior Publication US 2023/0196238 A1, Jun. 22, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/0631 (2023.01); G06Q 10/04 (2023.01); G06V 10/75 (2022.01)
CPC G06Q 10/06315 (2013.01) [G06Q 10/04 (2013.01); G06Q 10/06313 (2013.01); G06V 10/752 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system of solving a supply chain planning problem modeled as a linear programming problem, comprising:
a computer, comprising a processor and memory, the computer further comprising an image rendering engine, an image processing engine, a decomposition module, and a solver;
the image rendering engine configured to:
generate pixels of a supply chain problem image, the pixels representing links between constraints and variables of the linear programming problem;
the image processing engine configured to:
identify one or more contours of the supply chain problem image using a machine-learning model trained using a convolutional neural network and contour-labeled images received from the image rendering engine;
the decomposition module configured to:
determine a partition comprising at least two components linked by a first contour is more balanced than a partition comprising the at least two components linked by a second contour; and
the solver configured to:
formulate at least two decomposed subproblems sharing one or more complicating constraints associated with at least one of the one or more contours; and
solve the at least two decomposed subproblems to generate a solution to the supply chain planning problem.