Methods and apparatuses for recommending substitutions made during order fulfillment processes

Patent metadata

Field	Value
Publication number	US-12367518-B2
Application number	US-202418654301-A
Country	US
Kind code	B2
Filing date	May 3, 2024
Priority date	Jan 24, 2020
Publication date	Jul 22, 2025
Grant date	Jul 22, 2025

Abstract

A system is configured to train a customer understanding model to generate a preference score for substitution items. The customer understanding model generates a preference score for each of a plurality of related substitution items based on order data including data indicative of at least one item ordered and location data indicating a location of a first store. The customer understanding model ranks each of the substitution items based on the preference score. Order data is transmitted including substitution data identifying each of the substitution items and corresponding rank. Performance data associated with a set of operations implemented based on the order data and the substitution data is obtained. An updated customer understanding model is trained based on the performance data and iteratively modified based on the updated training dataset and updated performance metrics generated from second performance data.

First claim

What is claimed is:

1. A system comprising:
a processor; and
a non-transitory memory, storing instructions that, when executed, cause the processor to:
train a customer understanding model to generate customer attributes for a user based on past behavior;
receive, via a communications interface, order data associated with a first user including data indicative of at least one item ordered and location data indicating a location of a first store;
implement the customer understanding model to generate customer attributes for the first user;
generate a preference score for each of a plurality of related substitution items, wherein the preference score is generated based on a combination of the customer attributes and item attributes for each item in the plurality of related substitution items;
generate a relevance score for each of the plurality of related substitution items;
generate a substitution score based on the preference score and the relevance score;
rank each of the plurality of related substitution items based on the substitution scores;
transmit, via the communications interface, the order data and substitution data identifying each of the plurality of related substitution items and corresponding rank;
obtain, via the communications interface, performance data associated with a set of operations implemented based on the order data and the substitution data;
train an updated customer understanding model based on an updated training dataset including the performance data; and
iteratively modify the updated customer understanding model based on the updated training dataset and updated performance metrics generated from second performance data associated with implementation of the updated customer understanding model.

2. The system of claim 1 , wherein the customer understanding model is trained using historical behavior on a corresponding network platform.

3. The system of claim 2 , wherein the performance data includes acceptance data characterizing whether a substitution item is accepted as a replacement for the at least one item ordered, and wherein the processor is further configured to execute the instructions to apply the updated customer understanding model to obtain revised preference scores for the plurality of related substitution items.

4. The system of claim 1 , wherein the customer understanding model is trained using a training dataset including customer purchase behavior over a first predetermined time period and a second predetermined time period.

5. The system of claim 4 , wherein the customer purchase behavior includes customer attribute data determined by identifying a number of purchases of items that include one or more characteristics of a corresponding item attribute data.

6. The system of claim 1 , wherein the processor is further configured to select a preferred group of substitution items from the plurality of related substitution items based on the substitution scores and send the preferred group to a store order management device.

7. The system of claim 1 , wherein the processor is further configured to execute the instructions to generate an overall substitution score for each of the plurality of related substitution items.

8. The system of claim 7 , wherein the overall substitution score is generated based on a relevance score, a preference score, a score parameter, an item attribute, and a customer attribute.

9. A computer-implemented method, comprising:
training a customer understanding model to generate customer attributes for a user based on past behavior;
receiving, via a communications interface, order data associated with a first user including data indicative of at least one item ordered and location data indicating a location of a first store;
implementing the customer understanding model to generate customer attributes for the first user;
generating a preference score for each of a plurality of related substitution items, wherein preference score is generated based on a combination of the customer attributes and item attributes for each item in the plurality of related substitution items;
generating a relevance score for each of the plurality of related substitution items;
generating a substitution score score based on the preference score and the relevance score;
ranking each of the plurality of related substitution items based on the substitution score;
transmitting, via the communications interface, the order data and substitution data identifying each of the plurality of related substitution items and corresponding rank;
obtaining, via the communications interface, performance data associated with a set of operations implemented based on the order data and the substitution data;
training an updated customer understanding model based on an updated training dataset including the performance data; and
iteratively modifying the updated customer understanding model based on the updated training dataset and updated performance metrics generated from second performance data associated with implementation of the updated customer understanding model.

10. The computer-implemented method of claim 9 , wherein the customer understanding model is trained using historical behavior on a corresponding network platform.

11. The computer-implemented method of claim 10 , comprising applying the updated customer understanding model to obtain revised preference scores for the plurality of related substitution items, wherein the performance data includes acceptance data characterizing whether a substitution item is accepted as a replacement for the at least one item ordered.

12. The computer-implemented method of claim 9 , wherein the customer understanding model is trained using a training dataset including customer purchase behavior over a first predetermined time period and a second predetermined time period.

13. The computer-implemented method of claim 12 , wherein the customer purchase behavior includes customer attribute data determined by identifying a number of purchases of items that include one or more characteristics of a corresponding item attribute data.

14. The computer-implemented method of claim 9 , comprising selecting a preferred group of substitution items from the plurality of related substitution items based on the substitution scores and send the preferred group to a store order management device.

15. The computer-implemented method of claim 9 , comprising generating an overall substitution score for each of the plurality of related substitution items.

16. The computer-implemented method of claim 15 , wherein the overall substitution score is generated based on a relevance score, a preference score, a score parameter, an item attribute, and a customer attribute.

17. A non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, cause a device to perform operations comprising:
training a customer understanding model to generate customer attributes for a user based on past behavior;
receiving, via a communications interface, order data associated with a first user including data indicative of at least one item ordered and location data indicating a location of a first store;
implementing the customer understanding model to generate customer attributes for the first user;
generating a preference score for each of a plurality of related substitution items, wherein preference score is generated based on a combination of the customer attributes and item attributes for each item in the plurality of related substitution items;
generate a relevance score for e

Assignees

• Walmart Apollo Llc

Inventors

• Cho Hyun Duk
• Bhatt Swati
• Kalidindi Vidya Sagar
• Motwani Kamiya
• Kumar Sushant
• Achan Kannan

Classifications

• G06Q30/0635

  replenishment orders; recurring orders · CPC title

• G06Q30/0641 Primary

  utilising user interfaces specially adapted for shopping · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q30/0629 Primary

  by pre-processing results, e.g. ranking or ordering results · CPC title