System and method for automatic planogram generation and optimization

Patent metadata

Field	Value
Publication number	US-2024257045-A1
Application number	US-202318103206-A
Country	US
Kind code	A1
Filing date	Jan 30, 2023
Priority date	Jan 30, 2023
Publication date	Aug 1, 2024
Grant date	—

Abstract

Systems and methods for automatic planogram generation and optimization are disclosed. In some embodiments, an exemplary method includes: based on recommended assortment information regarding future products to be displayed in a retailer store, determining a plurality of candidate layouts each of which corresponds to a two-dimensional arrangement of the future products; for each candidate layout, computing an objective function based on current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score; generating, from the plurality of candidate layouts, an optimal layout that optimizes the objective function; generating a planogram based on the optimal layout for the retailer store; and transmitting the planogram to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram.

First claim

What is claimed is:

1 . A system, comprising:
a non-transitory memory having instructions stored thereon; and at least one processor operatively coupled to the non-transitory memory, and configured to read the instructions to:
obtain current product location information regarding current products being displayed in a retailer store,
obtain recommended assortment information regarding future products to be displayed in the retailer store,
based on the recommended assortment information, determine a plurality of candidate layouts each of which corresponds to a two-dimensional arrangement of the future products to be displayed in the retailer store,
for each of the plurality of candidate layouts, compute an objective function based on the current product location information, a set of parameters and at least one of: a minimum area ratio, a first unprotected rank, a combined propensity score, or a contiguity score,
generate, from the plurality of candidate layouts, an optimal layout that optimizes the objective function,
generate a planogram based on the optimal layout for the retailer store, and
transmit the planogram to a computing device associated with the retailer store for placing at least some of the future products in the retailer store according to the planogram.

2 . The system of claim 1 , wherein:
the future products to be displayed in the retailer store are classified into a plurality of product groups; each candidate layout of the plurality of candidate layouts comprises a same number of unit cells arranged in a same manner; each candidate layout of the plurality of candidate layouts comprises a plurality of coded layout portions each of which includes a plurality of unit cells and corresponds to a respective one of the plurality of product groups; and each of the plurality of coded layout portions represents a location in the candidate layout allocated to the respective one of the plurality of product groups.

3 . The system of claim 2 , wherein:
the future products are classified based on at least one of: product type, product brand, product price, or product packet size; and each of the plurality of coded layout portions is coded in the candidate layout based on at least one of: color, grayscale, filled pattern, filled texture, filled gradient, or filled picture.

4 . The system of claim 2 , wherein the objective function for each candidate layout is computed based on:
computing the minimum area ratio representing a level of equitability of space allocation for the plurality of product groups; computing the first unprotected rank representing a level of protection of top products in the plurality of product groups; computing the combined propensity score representing a deviation of the candidate layout from a current layout of current products; and computing the contiguity score representing a level of blockiness of the plurality of coded layout portions in the candidate layout.

5 . The system of claim 4 , wherein:
the set of parameters comprises: a first weight associated with the minimum area ratio, a second weight associated with the first unprotected rank, a third weight associated with the combined propensity score, and a fourth weight associated with the contiguity score; and the objective function is computed based on a weighted sum of the minimum area ratio, the first unprotected rank, the combined propensity score and the contiguity score, with their respective associated weights.

6 . The system of claim 4 , wherein the minimum area ratio is computed based on:
computing, for each of the plurality of coded layout portions in the candidate layout, an area ratio between an area allocated to the coded layout portion according to the candidate layout and an area required to store all recommended products in a product group corresponding to the coded layout portion; and computing the minimum area ratio for the candidate layout based on a minimum of all area ratios of all of the plurality of coded layout portions.

7 . The system of claim 4 , wherein the first unprotected rank is computed based on:
ranking the future products in the plurality of product groups based on a predetermined model; for each of the plurality of coded layout portions in the candidate layout,
(a) determining top N ranked products across the plurality of product groups, wherein N is a positive integer whose value is initialized to be one, and
(b) comparing a first area allocated to the coded layout portion according to the candidate layout and a second area required to store a subset of the top N ranked products in a product group corresponding to the coded layout portion;
increasing the value of N by one and repeating the above steps of (a) and (b) for each of the plurality of coded layout portions in the candidate layout, until a first value of N is found to enable the first area to be smaller than the second area for any one of the plurality of coded layout portions in the candidate layout; and determining the first unprotected rank for the candidate layout based on the first value of N.

8 . The system of claim 4 , wherein the combined propensity score is computed based on:
for each unit cell,
determining a first coded layout portion where the unit cell is located in the candidate layout,
determining a second coded layout portion where the unit cell is located in the current layout,
assigning a first propensity score to the unit cell when the first coded layout portion and the second coded layout portion correspond to one same product group, and
assigning a second propensity score to the unit cell when the first coded layout portion and the second coded layout portion correspond to two different product groups, respectively, wherein the first propensity score and the second propensity score are generated based on an image smoothing of the current layout; and
computing the combined propensity score for the candidate layout based on a summation of all propensity scores assigned to all unit cells in the candidate layout.

9 . The system of claim 4 , wherein the contiguity score is computed based on:
computing a total quantity of contiguity cell pairs in the candidate layout, wherein each of the contiguity cell pairs includes two unit cells that are contiguous to each other and belonging to a same coded layout portion in the candidate layout; and computing the contiguity score for the candidate layout based on the total quantity.

10 . The system of claim 4 , wherein:
the optimal layout minimizes or maximizes the objective function among all of the plurality of candidate layouts based on at least one of:
a maximization of the minimum area ratio,
a maximization of the first unprotected rank,
a maximization of the combined propensity score, or
a maximization of the contiguity score; and
each of the plurality of candidate layouts is determined subject to at least the following two conditions:
each unit cell is assigned to one and only one of the plurality of coded layout portions in the candidate layout, and
each unit cell is assigned to a same coded layout portion as at least two other unit cells contiguous to the unit cell in the candidate layout.

11 . A computer-implemented method, comprising:
obtaining current product location information regarding current products being displayed in a retailer store; obtaining recommended assortment information regarding future products to be displayed in the retailer store; based on the recommended assortment information, determining a plurality of candidate layouts each of which corresponds to a two-dimensional arrangement of the future products to be displayed in the retailer store

Assignees

• Walmart Apollo Llc

Inventors

• Wang Jiewen
• Kuhn Kenneth
• Vabbilisetty Saipraveen

Classifications

• G06Q10/087 Primary

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