Methods and apparatus for generating planograms

Patent metadata

Field	Value
Publication number	US-12086867-B2
Application number	US-202217589752-A
Country	US
Kind code	B2
Filing date	Jan 31, 2022
Priority date	Jan 31, 2022
Publication date	Sep 10, 2024
Grant date	Sep 10, 2024

Abstract

In some examples, a system may be configured to, based on the data characterizing the shelf portion of a shelf-peg modular, the item data and the draw strategy data, implement a first set of modular placement optimization operations that generate a first modular dataset of the shelf portion of the shelf-peg modular. Furthermore, the system may be configured to, based at least on data characterizing the peg portion of the shelf-peg modular, and the modular data of the shelf portion, determine dimensional information of the peg portion. As such, the system may be configured to, based on the data characterizing the peg portion of the shelf-peg modular, the dimensional information of the peg portion, the item data, the first modular dataset, and the draw strategy data, implement a second set of modular placement optimization operations that generate a second modular dataset of the peg portion of the shelf-peg modular.

First claim

What is claimed is:

1. A system comprising:
a memory resource storing instructions; and
one or more processors coupled to the memory resource, the one or more processors configured to execute the instructions to:
provide a service application to a computing device which may be utilized to generate, by the service application, a user-interface (UI) that includes at least one or more interactive features that enable the user to implement a set of input data which includes at least one or more of constraint data or user defined parameters, wherein the input data is transmitted to the one or more processors;
obtain modular data of a shelf-peg modular, item data of a group of items associated with an item type of the shelf-peg modular, and draw strategy data, wherein the draw strategy includes a sequencing elasticity parameter, a blockiness parameter, a blockiness elasticity parameter, a striping parameter, and an item placement flexibility parameter;
extract, from the modular data, data characterizing a shelf portion of the shelf-peg modular and data characterizing a peg portion of the shelf-peg modular;
based on the data characterizing the shelf portion, the item data, and the draw strategy data, implement a first set of modular placement optimization operations, by a shelf optimization engine, that generate a first modular dataset of the shelf portion of the shelf-peg modular;
based on data characterizing the peg portion, the modular data of the shelf portion, the item data, the first modular dataset, and the draw strategy data, determine dimensional information of the peg portion;
based on the data characterizing the peg portion of the shelf-peg modular, the dimensional information of the peg portion, the item data, the first modular dataset, and the draw strategy data, implement a second set of modular placement optimization operations that generate a second modular dataset of the peg portion of the shelf-peg modular;
determine, by the shelf optimization engine, a score of the first and the second modular dataset based on a sum average of a ranking of each item of the item data in the corresponding first and second modular dataset;
in response to determining the score of the first and the second modular dataset, generate a planogram data structure based on a highest score of the first and second modular dataset; and
generate, by the service application provided to the computing device, a graphical representation of the planogram data structure.

2. The system of claim 1 , wherein the first set of modular placement optimization operations includes:
determining, from the group of items, a combination of items to place onto the shelf portion of the shelf-peg modular and, for each item of the combination of items, a placement position on the shelf portion of the shelf-peg modular, and a number of facings; and
generating the first modular dataset, the first modular dataset identifying the combination of items and characterizing the corresponding placement position of each of the group of items and the number of facings for each of the group of items.

3. The system of claim 2 , wherein the item data identifies the group of items and characterizes, for each of the group of items, a corresponding rank, a corresponding sequence, and corresponding set of attributes.

4. The system of claim 3 , wherein the combination of items is associated with a particular attribute.

5. The system of claim 3 , wherein the first set of modular placement optimization operations includes:
determining whether to implement a set of re-run operations based on whether the first modular dataset satisfies a rank criterion.

6. The system of claim 5 , wherein the first set of modular placement optimization operations includes:
implementing the set of re-run operations that generates a third modular dataset based on the first modular dataset not satisfying the rank criterion.

7. The system of claim 6 , wherein the one or more processors are configured to execute the instructions further to:
generate a score for the first modular dataset and the third modular dataset; and
based on the score of the first modular dataset and the score of the third modular dataset, transmit, to a computing device of a user, the modular dataset with the highest score.

8. The system of claim 1 , further comprising:
a communications interface configured to communicate with a computing device operated by a user, the one or more processors being further coupled to the communications interface; and
wherein the one or more processors are configured to execute the instructions further to:
obtain, from the computing device, user input, the user input including data characterizing the draw strategy data.

9. The system of claim 1 , wherein the one or more processors are configured to execute the instructions further to:
obtain constraint data, the first set of modular placement optimization operations being further based on the constraint data.

10. The system of claim 1 , wherein the item data is associated with a cluster of stores.

11. A computer-implemented method comprising:
providing a service application to a computing device which may be utilized to generate, by the service application, a user-interface (UI) that includes at least one or more interactive features that enable the user to implement a set of input data which includes at least one or more constraints or user defined parameters, wherein the input data is transmitted to a processor;
obtaining, by the processor, modular data of a shelf-peg modular, item data of a group of items associated with an item type of the shelf-peg modular, and draw strategy data, wherein the draw strategy includes a sequencing elasticity parameter, a blockiness parameter, a blockiness elasticity parameter, a striping parameter, and an item placement flexibility parameter;
extracting, by the processor and from the modular data, data characterizing a shelf portion of the shelf-peg modular and data characterizing a peg portion of the shelf-peg modular;
based on the data characterizing the shelf portion, the item data, and the draw strategy data, implementing, by a shelf optimization engine, a first set of modular placement optimization operations that generate a first modular dataset of the shelf portion of the shelf-peg modular;
based on data characterizing the peg portion, the modular data of the shelf portion, the item data, the first modular dataset, and the draw strategy data, determining, by the processor, dimensional information of the peg portion;
based on the data characterizing the peg portion of the shelf-peg modular, the dimensional information of the peg portion, the item data, the first modular dataset, and the draw strategy data, implementing, by the processor, a second set of modular placement optimization operations that generate a second modular dataset of the peg portion of the shelf-peg modular;
determining, by the shelf optimization engine, a score of the first and the second modular dataset based on a sum average of a ranking of each item of the item data in the corresponding first and second modular dataset;
in response to determining the score of the first and the second modular dataset, generating a planogram data structure based on a highest score of the first and second modular dataset; and
generating by the service application provided to the computing device a graphical representation of the planogram data structure.

12. The computer-implemented method of claim 11 , wherein the first set of modular placement optimization operations includes:
determining, from the group of items, a combination of items to place onto the shelf portion of the shel

Assignees

• Walmart Apollo Llc

Inventors

• Yang Yijia
• Batham Mohit

Classifications

• G06Q30/0639 Primary

  Locating goods or services, e.g. based on physical position of the goods or services within a shopping facility · CPC title

• G06Q10/08724 Primary

  by shelf level inventory management, e.g. planograms · CPC title

• G06Q30/0603

  Catalogue creation or management · CPC title

• G06Q10/087 Primary

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title