US 11,455,655 B2Granted

Methods and apparatus for electronically providing item recommendations for advertisement

AssigneeWalmart Apollo, LLC

InventorsZeinab Taghavi Nasr Abadi, Habibur Rahman, Najmeh Forouzandehmehr, Xilun Chen, Jianpeng Xu, Anant Maheshwari, Sriram Guna Sekhar Kollipara

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

This application relates to apparatus and methods for automatically determining and providing recommendations of items to advertise customers. In some examples, a computing device generates feature data based on historical website interaction data, historical transaction data, and item categorical data. The computing device trains each of a plurality of machine learning models based on the generated feature data. The computing device may then receive a plurality of recommended items to advertise in association with an anchor item. The computing device may execute the trained machine learning process to generate prediction data associated with a future time period. The prediction data may identify a number of times each recommended item may be purchased during the future time period. The computing device may then rank the plurality of recommended items based on the prediction data. In some examples, the computing device filters the plurality of recommended items based on item categories.

Claims18

Dependent claims

A system comprising:

a user device including at least one processor, a memory coupled to the at least one processor, and a display;
and
a computing device including at least one processor and a memory coupled to the at least one processor, the at least one processor configured to generate recommendations during said session by executing instructions that cause the at least one processor to:
receive, from the user device during a current user session, session activity data of a user associated with the user device, the session activity data comprising an anchor item, the anchor item being identified based on a webpage being displayed on the display of the user device including the anchor item;
obtain, from a database, historical session activity data associated with one or more other users received during other user sessions;
obtain, from the database, a plurality of recommended items pertaining to the anchor item;
generate, for each recommended item of the plurality of recommended items, feature data comprising features based on the session activity data;
update the feature data based on the historical session activity data;
determine an item type of the anchor item and the plurality of recommended items;
train a machine learning process using the updated feature data;
execute the trained machine learning process;
generate prediction data for each of the recommended items based on output from the execution of the trained machine learning process;
generate a ranking of the plurality of recommended items based on the prediction data;
generate categorical attribute embeddings based on the session activity data;
filter the ranking of the plurality of recommended items based on the categorical attribute embeddings, wherein filtering the ranking of the plurality of recommended items comprises:
determining a distance value between a category of each recommended item of the plurality of recommended items and the categorical attribute embeddings;
transmit the plurality of recommended items and the ranking of the plurality of recommended items to the user device;
and
display, during the current user session, the plurality of recommended items and the ranking on the webpage being displayed on the display of the user device.

16 more elements

A method comprising:

receiving, from a user device during a current user session, session activity data of a user associated with the user device, the session activity data comprising an anchor item, the anchor item being identified based on a webpage being displayed on a display of the user device including the anchor item;
obtaining, from a database, historical session activity data associated with one or more other users received during other user sessions;
obtaining, from the database, a plurality of recommended items pertaining to the anchor item;
generating, for each recommended item of the plurality of recommended items, feature data comprising features based on the session activity data;
updating the feature data using the historical session activity data;
determining an item type of the anchor item and the plurality of recommended items;
training a machine learning process using the updated feature data;
executing trained machine learning process;
generating prediction data for each of the recommended items based on output from the execution of the trained machine learning process;
generating a ranking of the plurality of recommended items based on the prediction data;
generating categorical attribute embeddings based on the session activity data;
filtering the ranking of the plurality of recommended items based on the categorical attribute embeddings, wherein filtering the ranking of the plurality of recommended items comprises:
determining a distance value between a category of each recommended item of the plurality of recommended items and the categorical attribute embeddings;
transmitting the plurality of recommended items and the ranking of the plurality of recommended items to the user device;
and
displaying, during the current user session, the plurality of recommended items and the ranking on the webpage being displayed on the display of the user device.

13 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:

receiving, from a user device during a current user session, session activity data of a user associated with the user device, the session activity data comprising an anchor item, the anchor item being identified based on a webpage being displayed on a display of the user device including the anchor item;
obtaining, from a database, historical session activity data associated with one or more other users received during other user sessions;
obtaining, from the database, a plurality of recommended items pertaining to the anchor item;
generating, for each recommended item of the plurality of recommended items, feature data comprising features based on the session activity data;
updating the feature data using on the historical session activity data;
determining an item type of the anchor item and the plurality of recommended items;
training a machine learning process using the updated feature data;
executing the trained machine learning process;
generating prediction data for each of the recommended items based on output from the execution of the trained machine learning process;
generating a ranking of the plurality of recommended items based on the prediction data;
generating categorical attribute embeddings based on the session activity data;
filtering the ranking of the plurality of recommended items based on the categorical attribute embeddings;
determining a distance value between a category of each recommended item of the plurality of recommended items and the categorical attribute embeddings by using one of cosine similarity and mean similarity;
transmitting the plurality of recommended items and the ranking of the plurality of recommended items to the user device;
and
displaying, during the current user session, the plurality of recommended items and the ranking on the webpage being displayed on the display of the user device.

13 more elements

Dependencies are inferred from the claim text.