US-12619938-B2 - System and method for automatic parameter tuning of campaign planning with hierarchical linear programming objectives

Abstract

A system and method are disclosed for campaign planning and include modeling the use of campaign operations and campaignable resources of a supply chain network including a production line to produce products using campaign operations and campaignable resources as campaign planning problems, defining an evaluation function comprising a weighted sum of features evaluated from the campaign planning problem, initializing weights to build a consumption profile and evaluation function, determining fitness values that indicate a level of variability, evaluating reward values based on the fitness values, selecting a sub-sample of the top fitness values having the best associated objective function, repeating the generating, the evaluating and the selecting steps to adjust the weights until a stopping criterion is met indicating an optimal solution has been reached, and determining a campaign plan for the use of the campaign operations and campaignable resource.

Inventors

• Devanand R

Assignees

• Blue Yonder Group, Inc.

Dates

Publication Date

20260505

Application Date

20240129

Claims (20)

1. 1 . A system of campaign planning, comprising: a computer, comprising one or more processors and a memory, configured to: initialize weights to build a weighted consumption profile; define an evaluation function comprising a vector of weights for a campaign planning problem; initialize or invoke one or more LP optimization solvers to run in parallel to reduce an amount of time for determining the weights of the evaluation function; generate evaluated fitness values based on sample weight vectors; compute a reward value based on the evaluation function; select top fitness values to evaluate weight mean and variance; repeat the generate, the compute and the select to adjust the weights in each iteration until a stopping criteria is met indicating an optimal solution has been reached; determine a campaign plan for a use of one or more campaign operation and one or more campaignable resource; and instruct automated robotic production machinery to produce products according to the determined campaign plan.
2. 2 . The system of claim 1 , wherein the computer is further configured to: receive an input weight vector at each of the one or more processors for parallel processing.
3. 3 . The system of claim 1 , wherein the computer is further configured to: receive a sample size comprising a number of random weights that are generated and evaluated at each of the iterations.
4. 4 . The system of claim 1 , wherein the computer is further configured to: sort sample vectors by generated output; and select top sample vectors according to a threshold.
5. 5 . The system of claim 1 , wherein the computer is further configured to: compensate a memory overhead in the computer to speed up computational time.
6. 6 . The system of claim 1 , wherein the computer is further configured to: in response to determining that a solution is trapped in a local optima, search for new feasible space.
7. 7 . The system of claim 1 , wherein the computer is further configured to: perform an LPOPT call within a given time bucket for each required KPI of the campaign plan.
8. 8 . A computer-implemented method of campaign planning, comprising: initializing, by a computer comprising one or more processors and a memory, weights to build a weighted consumption profile; defining, by the computer, an evaluation function comprising a vector of weights for a campaign planning problem; initializing or invoking, by the computer, one or more LP optimization solvers to run in parallel to reduce an amount of time for determining the weights of the evaluation function; generating, by the computer, evaluated fitness values based on sample weight vectors; computing, by the computer, a reward value based on the evaluation function; selecting, by the computer, top fitness values to evaluate weight mean and variance; repeating, by the computer, the generate, the compute and the select to adjust the weights in each iteration until a stopping criteria is met indicating an optimal solution has been reached; determining, by the computer, a campaign plan for a use of one or more campaign operation and one or more campaignable resource; and instructing, by the computer, automated robotic production machinery to produce products according to the determined campaign plan.
9. 9 . The computer-implemented method of claim 8 , further comprising: receiving, by the computer, an input weight vector at each of the one or more processors for parallel processing.
10. 10 . The computer-implemented method of claim 8 , further comprising: receiving, by the computer, a sample size comprising a number of random weights that are generated and evaluated at each of the iterations.
11. 11 . The computer-implemented method of claim 8 , further comprising: sorting, by the computer, sample vectors by generated output; and selecting, by the computer, top sample vectors according to a threshold.
12. 12 . The computer-implemented method of claim 8 , further comprising: compensating, by the computer, a memory overhead in the computer to speed up computational time.
13. 13 . The computer-implemented method of claim 8 , further comprising: in response to determining that a solution is trapped in a local optima, searching, by the computer, for new feasible space.
14. 14 . The computer-implemented method of claim 13 , further comprising: performing, by the computer, an LPOPT call within a given time bucket for each required KPI of the campaign plan.
15. 15 . A non-transitory computer-readable medium embodied with software for campaign planning, the software when executed: initializes weights to build a weighted consumption profile; defines an evaluation function comprising a vector of weights for a campaign planning problem; initializes or invokes one or more LP optimization solvers to run in parallel to reduce an amount of time for determining the weights of the evaluation function; generates evaluated fitness values based on sample weight vectors; computes a reward value based on the evaluation function; selects top fitness values to evaluate weight mean and variance; repeats the generates, the computes and the selects to adjust the weights in each iteration until a stopping criteria is met indicating an optimal solution has been reached; determines a campaign plan for a use of one or more campaign operation and one or more campaignable resource; and instructs automated robotic production machinery to produce products according to the determined campaign plan.
16. 16 . The non-transitory computer-readable medium of claim 15 , wherein the software when executed further: receives an input weight vector at each of the one or more processors for parallel processing.
17. 17 . The non-transitory computer-readable medium of claim 15 , wherein the software when executed further: receives a sample size comprising a number of random weights that are generated and evaluated at each of the iterations.
18. 18 . The non-transitory computer-readable medium of claim 15 , wherein the software when executed further: sorts sample vectors by generated output; and selects top sample vectors according to a threshold.
19. 19 . The non-transitory computer-readable medium of claim 15 , wherein the software when executed further: compensates a memory overhead in the computer to speed up computational time.
20. 20 . The non-transitory computer-readable medium of claim 15 , wherein the software when executed further: in response to determining that a solution is trapped in a local optima, searches for new feasible space.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent application Ser. No. 18/137,707, filed Apr. 21, 2023, entitled “System and Method for Automatic Parameter Tuning of Campaign Planning with Hierarchical Linear Programming Objectives,” which is a continuation of U.S. patent application Ser. No. 17/728,808, filed Apr. 25, 2022, entitled “System and Method for Automatic Parameter Tuning of Campaign Planning with Hierarchical Linear Programming Objectives,” now U.S. Pat. No. 11,657,356, which is a continuation of U.S. patent application Ser. No. 16/510,302, filed Jul. 12, 2019, entitled “System and Method for Automatic Parameter Tuning for Campaign Planning with Hierarchical Linear Programming Objectives,” now U.S. Pat. No. 11,315,059, which claims the benefit under 35 U.S.C. § 119(e) to U.S. Provisional Application No. 62/741,922, filed Oct. 5, 2018, entitled “System and Method for Automatic Parameter Tuning for Campaign Planning with Hierarchical Linear Programming Objectives.” U.S. patent application Ser. No. 18/137,707, U.S. Pat. Nos. 11,657,356, 11,315,059, and U.S. Provisional Application No. 62/741,922 are assigned to the assignee of the present application. TECHNICAL FIELD The present disclosure relates generally to supply chain management and specifically to systems and methods for automatic parameter tuning of campaign planning with hierarchical linear programming objectives. BACKGROUND A supply chain for manufactured items typically involves the procurement of raw materials, transforming the raw materials into finished goods, and preparing the finished goods for distribution to warehouses, retailers, and customers. A supply chain planner determines the flow and distribution of items in the supply chain to meet a demand for the finished goods, while ensuring compliance with business objectives and constraints. In addition, manufacturing operations face resource constraints where certain resources, referred to as campaignable resources, require significant setup times or costs between different operations. However, formulating a supply chain plan that includes campaignable resources requires the use of one or more iterative heuristic solving techniques that use manually-selected parameters for evaluating campaign selections. Although these manually-selected parameters greatly influence the overall solution output, current methods are unable to calculate these values, and therefore, these values are instead left up to users' intuition. Deciding these parameters manually, based on a users' intuition, is not effective for campaign planning problems and a user cannot determine whether changes to the parameters would improve the solution output. In addition, the iterative process of testing changes to the parameters and re-solving the campaign planning problem often leads to local solutions with poor plan quality and high computation time. The inability to efficiently calculate parameter values that are suitable for evaluating campaign selections is undesirable. BRIEF DESCRIPTION OF THE DRAWINGS A more complete understanding of the present invention may be derived by referring to the detailed description when considered in connection with the following illustrative figures. In the figures, like reference numbers refer to like elements or acts throughout the figures. FIG. 1 illustrates an exemplary supply chain network, according to an embodiment; FIG. 2 illustrates the supply chain planner of FIG. 1 in greater detail, according to an embodiment; FIG. 3 illustrates an exemplary supply chain network model representing a simplified supply chain, according to an embodiment; FIG. 4 illustrates an exemplary method of cross-entropy campaign planning, according to a first embodiment; FIG. 5 illustrates an exemplary method of cross-entropy campaign planning, in accordance with a second embodiment; FIG. 6 illustrates an exemplary method of cross-entropy campaign planning weight learning, according to an embodiment; FIG. 7 illustrates an exemplary plot of evaluation value convergence for successive iterations of cross-entropy based selection of big bucket campaign planning according to the method of FIG. 6, according to an embodiment; FIG. 8 illustrates an exemplary method of modified cross-entropy campaign planning method comprising multiple cross-entropy campaign planning sub-methods executed on multiple parallel instances of a campaign planner, in accordance with an embodiment; and FIG. 9 illustrates a chart comparing expert-based weight selection and cross-entropy-based weight selection for production planning using big bucket campaign planning of an exemplary dataset representing a global supply chain network, according to an embodiment. DETAILED DESCRIPTION Aspects and applications of the invention presented herein are described below in the drawings and detailed description of the invention. Unless specifically noted, it is intended that the words and phrases in the specif