Fulfilment machine for optimizing shipping

Patent metadata

Field	Value
Publication number	US-11301791-B2
Application number	US-201816005166-A
Country	US
Kind code	B2
Filing date	Jun 11, 2018
Priority date	Jun 11, 2018
Publication date	Apr 12, 2022
Grant date	Apr 12, 2022

Abstract

A computer implemented method and system of setting values of parameters of nodes in an omnichannel distribution system, the method comprising is provided. Input parameters are received from a computing device. Historical data related to the network of nodes is received from a data repository. A synthetic scenario is determined based on the received input parameters and the historical data. Each node is clustered into a corresponding category. For each category of nodes, key parameters are identified. A range of each key parameter is determined based on the synthetic scenario. A number of simulations N to perform with data sampled from the synthetic scenario within the determined range of each key parameter is determined. For each of the N simulations, a multi-objective optimization is performed to determine a cost factor of the parameter settings. The parameter settings with a lowest cost factor are selected.

First claim

What is claimed is:

1. A computing device comprising:
a processor;
a network interface coupled to the processor to enable communication over a network;
a storage device for content and programming coupled to the processor;
a program stored in the storage device, wherein an execution of the program by the processor configures the computing device to perform acts comprising:
receiving input parameters;
receiving historical data related to a network of nodes, from a data repository;
determining a synthetic scenario based on the received input parameters and the historical data;
reducing a load on a memory stack of the computing device and a computational load on the processor by clustering each node into a corresponding category of a plurality of categories;
for each category of nodes:
identifying key parameters;
determining a range of each key parameter based on the synthetic scenario comprising:
determining a maximum and a minimum setting for the key parameter from a synthetic network status data;
extending at least one of the maximum and the minimum setting by a predetermined sigma variation; and
basing the range of the key parameter between the maximum and the minimum, including the extension by the predetermined sigma variation;

sampling data from the synthetic scenario within the determined range of each key parameter;
further reducing the computational load on the processor by determining a number of simulations N to perform with the data sampled from the synthetic scenario based on the range of each key parameter, a determination of a computational resources available, and a desired computing accuracy;
for each of the N simulations, performing a multi-objective optimization to determine a cost factor of the parameter settings and storing the cost factor in the storage device; and
selecting the parameter settings with a lowest cost factor.

2. The computing device of claim 1 , wherein the data sampled from the synthetic scenario within the determined range of each key parameter is obtained by applying Orthogonal Latin Hypercube Sampling (OLHS) on the synthetic scenario based on the key parameters.

3. The computing device of claim 1 , wherein determining the synthetic scenario comprises:
creating a synthetic demand status data based on the historical data and the input parameters; and
creating a synthetic network status data based on the historical data, the input parameters, and the synthetic demand status.

4. The computing device of claim 1 , wherein:
the historical data includes:
raw demand data of one or more products offered by the network of nodes; and
raw node data of each node in the network of nodes;

the synthetic demand status is based on the raw demand data; and
the synthetic network status is based on the raw node data.

5. The computing device of claim 1 , wherein the determination of the number of simulations N to perform is based on at least one of: (i) a time limit for the N simulations, and (ii) a predetermined accuracy for the simulations.

6. The computing device of claim 1 , wherein the clustering of each node into a corresponding category of a plurality of categories is based on one or more features of the node.

7. The computing device of claim 1 , wherein the key parameters are identified from the input parameters.

8. The computing device of claim 1 , wherein the key parameters are identified by receiving the key parameters from a business rules database over the network.

9. The computing device of claim 1 , wherein the cost factor is based on at least one of: (i) a fulfilment cost for a predetermined time period, and (ii) a capacity utilization of the omnichannel distribution system for the predetermined time period.

10. The computing device of claim 1 , wherein execution of the program by the processor further configures the computing device to perform acts comprising, for each category of nodes, upon determining that a delta of the cost factor between a present simulation and a prior simulation of the N simulations is below a predetermined threshold:
identifying the present simulation as having the lowest cost factor; and
not performing any additional simulations for the category even if all N simulations have not yet been performed.

11. The computing device of claim 1 , wherein determining the synthetic scenario comprises using machine learning to learn from the historical data.

12. A non-transitory computer readable storage medium tangibly embodying a computer readable program code having computer readable instructions that, when executed, causes a computer device to carry out a method of setting values of parameters of a network of nodes in an omnichannel distribution system, the method comprising:
receiving input parameters from a computing device of a user;
receiving historical data related to the network of nodes, from a data repository;
determining a synthetic scenario based on the received input parameters and the historical data;
reducing a load on a memory and a computational load on the computer device by clustering each node into a corresponding category of a plurality of categories;
for each category of nodes:
identifying key parameters;
determining a range of each key parameter based on the synthetic scenario comprising:
determining a maximum and a minimum setting for the key parameter from a synthetic network status data;
extending at least one of the maximum and the minimum setting by a predetermined sigma variation; and
basing the range of the key parameter between the maximum and the minimum, including the extension by the predetermined sigma variation;

sampling data from the synthetic scenario within the determined range of each key parameter;
reducing the computational load on the computer device by determining a number of simulations N to perform with the data sampled from the synthetic scenario based on the range of each key parameter, a determination of a computational resources available, and a desired computing accuracy;
for each of the N simulations, performing a multi-objective optimization to determine a cost factor of the parameter settings and storing the cost factor in the storage device; and
selecting the parameter settings with a lowest cost factor.

13. The non-transitory computer readable storage medium of claim 12 , wherein the data sampled from the synthetic scenario within the determined range of each key parameter is obtained by applying Orthogonal Latin Hypercube Sampling (OLHS) on the synthetic scenario based on the key parameters.

14. The non-transitory computer readable storage medium of claim 12 , wherein determining the synthetic scenario comprises:
creating a synthetic demand status data based on the historical data and the input parameters; and
creating a synthetic network status data based on the historical data, the input parameters, and the synthetic demand status.

15. The non-transitory computer readable storage medium of claim 14 , wherein determining the range of a key parameter comprises:
determining a maximum and a minimum setting for the key parameter from the synthetic network status data; and
basing the range of the key parameter between the determined maximum and the minimum settings.

16. The non-transitory computer readable storage medium of claim 12 , wherein the determination of the number of simulations N to perform is based on at least one of: (i) a time limit for the N simulations, and (ii) a predetermined accuracy for the simulations.

17. The non-transitory computer readable storage medium of claim 12 , wherein the co

Assignees

• IBM

Inventors

• Zhu Yada
• Liu Xuan
• Quanz Brian Leo
• Deshpande Ajay Ashok
• Koc Ali
• Cao Lei
• Li Yingjie

Classifications

• G06Q10/067

  Enterprise or organisation modelling · CPC title

• G06Q10/06315 Primary

  Needs-based resource requirements planning or analysis · CPC title