US 11,386,455 B2Granted

Methods and apparatus for providing a unified serving platform across multiple tenants and touchpoints

AssigneeWalmart Apollo, LLC

InventorsShirpaa Manoharan, Kannan Achan, Evren Korpeoglu, Sushant Kumar

Life of this patent

Estimating the term…

Loading patent…

Abstract

This application relates to apparatus and methods for providing a unified serving platform that allows for the reusability of machine learning models across a plurality of websites to determine personalized content. For example, a computing device trains a machine learning model with session data identifying browsing events and transaction data identifying purchasing events for a plurality of users. The computing device receives and stores session data and transaction data associated with a first website for the customer. The computing device may then receive a request for content to display to the customer on a second website. The computing device generates label data based on the session data and transaction data associated with the first website, and executes the trained machine learning model with the label data. Based on execution of the trained machine learning model, the computing device generates content to display on the second website, and transmits the content.

Claims16

Dependent claims

A system comprising:

a memory device;
and
a computing device communicatively coupled to the memory device and configured to:
obtain, from the memory device, session data identifying browsing events of a plurality of users for a first marketplace;
obtain, from the memory device, transaction data identifying purchase transactions of at least a portion of the plurality of users for the first online marketplace;
generate user profile data for each of the plurality of users based on the session data and the purchase transactions associated with the first marketplace;
train a machine learning model with the user profile data for each of the plurality of users to determine content to display to the plurality of users;
receive, from a different computing device, a content request for content to display to a first user on a second marketplace, the second marketplace different from the first marketplace wherein the first user is one of the plurality of users;
obtain, from the memory device, at least a portion of at least one of session data and transaction data for the first user, wherein the at least one of the session data and the transaction data for the first user is associated with the first marketplace;
generate a user profile for the first user based on the at least one of the session data and the transaction data for the first user associated with the first marketplace;
determine content to display to the first user based on applying the trained machine learning model to at least a portion of the generated user profile for the first user, wherein determining the content to display to the first user further comprises:
determining whether the generated user profile data for the plurality of users includes user profile data for the first user and determining default content to display to the first user based on the determination of whether the generated user profile data for the plurality of users includes user profile data for the first user;
transmit the content to the different computing device for display on the second marketplace;
receive from the different computing device, data from a real-time event;
update the trained machine learning model based on the real-time event data;
update content to display to the first user based on the updated trained machine learning model;
transmit the updated content;
determine a conversion rate based on the content;
and
determine the trained machine learning model is trained when the conversion rate is beyond a threshold value.

17 more elements

A method by a computing device comprising:

obtaining, from a memory device, session data identifying browsing events of a plurality of users for a first marketplace;
obtaining, from the memory device, transaction data identifying purchase transactions of at least a portion of the plurality of users for the first online marketplace;
generating user profile data for each of the plurality of users based on the session data and the purchase transactions associated with the first marketplace;
training a machine learning model with the user profile data for each of the plurality of users to determine content to display to the plurality of users;
receiving, from a different computing device, a content request for content to display to a first user on a second marketplace, the second marketplace different from the first marketplace, wherein the first user is one of the plurality of users;
obtaining, from the memory device, at least a portion of at least one of session data and transaction data for the first user, wherein the at least one of the session data and the transaction data for the first user is associated with the first marketplace;
generating a user profile for the first user based on the at least one of the session data and the transaction data for the first user associated with the first marketplace;
determining content to display to the first user based on applying the trained machine learning model to at least a portion of the generated user profile for the first user, wherein determining the content to display to the first user comprises:
determining whether the generated user profile data for the plurality of users includes user profile data for the first user and determining default content to display to the first user based on the determination of whether the generated user profile data for the plurality of users includes user profile data for the first user;
transmitting the content to the different computing device for display on the second marketplace;
determining a conversion rate based on the content;
and
determining the trained machine learning model is trained when the conversion rate is beyond a threshold value.

10 more elements

A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause a device to perform operations comprising:

obtaining, from a memory device, session data identifying browsing events of a plurality of users for a first marketplace;
obtaining, from the memory device, transaction data identifying purchase transactions of at least a portion of the plurality of users for the first online marketplace;
generating user profile data for each of the plurality of users based on the session data and the purchase transactions associated with the first marketplace;
training a machine learning model with the user profile data for each of the plurality of users to determine content to display to the plurality of users;
receiving, from a different computing device, a content request for content to display to a first user on a second marketplace, the second marketplace different from the first marketplace, wherein the first user is one of the plurality of users;
obtaining, from the memory device, at least a portion of at least one of session data and transaction data for the first user, wherein the at least one of the session data and the transaction data for the first user is associated with the first marketplace;
generating a user profile for the first user based on the at least one of the session data and the transaction data for the first user associated with the first marketplace;
determining content to display to the first user based on applying the trained machine learning model to at least a portion of the generated user profile for the first user, wherein determining the content to display to the first user comprises:
determining whether the generated user profile data for the plurality of users includes user profile data for the first user and determining default content to display to the first user based on the determination of whether the generated user profile data for the plurality of users includes user profile data for the first user;
transmitting to the different computing device the content for display on the second marketplace;
determining a conversion rate based on the content;
and
determining the trained machine learning model is trained when the conversion rate is beyond a threshold value.

10 more elements

Dependencies are inferred from the claim text.