Systems and methods for predicting user segments in real-time

Patent metadata

Field	Value
Publication number	US-10643236-B2
Application number	US-201615274458-A
Country	US
Kind code	B2
Filing date	Sep 23, 2016
Priority date	Sep 23, 2016
Publication date	May 5, 2020
Grant date	May 5, 2020

Abstract

Systems and methods can include one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of storing a plurality of user segments for users of an ecommerce website, recording an online browsing trail of a user during an online browsing session on the ecommerce website, the online browsing trail comprising a sequence of one or more actions by the user of the ecommerce website during the online browsing session, and predicting, in real-time, a first user segment for the user from the plurality of user segments during the online browsing session based on the sequence of the one or more actions of the user in the online browsing trail during the online browsing session as recorded by the one or more non-transitory storage modules.

First claim

What is claimed is:

1. A system comprising:
one or more processors; and
one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of:
storing a plurality of user segments for users of an ecommerce website;
recording an online browsing trail of a user during an online browsing session on the ecommerce website, the online browsing trail comprising a sequence of one or more actions by the user of the ecommerce website during the online browsing session;
predicting, in real-time, a first user segment for the user from the plurality of user segments during the online browsing session based on the sequence of the one or more actions of the user in the online browsing trail during the online browsing session, as recorded by the one or more non-transitory storage devices;
correlating the first user segment for the user, as predicted, with at least one product of a plurality of products, the at least one product of the plurality of products comprising a first user preference of a plurality of user preferences associated with the first user segment, as predicted;
determining, for each respective product of the plurality of products, one or more respective user preferences of the plurality of user preferences;
mapping each respective product of the plurality of products to a vector space comprising a plurality of axes, wherein:
two or more products of the plurality of products determined to be more similar to one another are closer together on the vector space than two or more products of the plurality of products determined to be less similar to one another; and

coordinating a display of at least two products of the plurality of products on a subsequent webpage of the ecommerce website during the online browsing session, wherein:
a first product of the at least two products is associated with the first user preference associated with the first user segment, as predicted; and
a second product of the at least two products is proximate to the first product of the at least two products on the vector space.

2. The system of claim 1 , wherein:
predicting, in real-time, the first user segment for the user during the online browsing session comprises:
predicting, in real-time, a respective probability that the online browsing trail pertains to each respective user segment of the plurality of user segments; and

the first user segment for the user comprises:
a highest probability that the online browsing trail pertains to the first user segment of the plurality of user segments, the highest probability being relative to respective probabilities of other user segments of the plurality of user segments.

3. The system of claim 2 , wherein predicting, in real-time, the respective probability that the online browsing trail pertains to each respective user segment of the plurality of user segments comprises:
predicting, in real-time, a probability (P) using a formula comprising:

log
⁢

⁢

P
⁡

(

segment
=

k
|
Θ

,
browseTrail

)

=

∑
t
z

⁢

⁢

log
⁢

⁢

P
⁡

(

i
t

,

i

t
+
1

|

Θ
k

)

,

 where:
the probability (P) is the respective probability that the online browsing trail pertains to each respective user segment of the plurality of user segments;
k is a segment of the plurality of user segments;
Θ is a learned model;
t is the online browsing trail;
i t is a product of a previous webpage in the online browsing trail on the ecommerce website;
i t+1 is a product of a current webpage in the online browsing trail of the ecommerce website; and
z is a number of pairs of i t and i t+1 being evaluated.

4. The system of claim 2 , wherein:
the respective probability is normalized by a duration of the online browsing session.

5. The system of claim 1 , wherein:
predicting, in real-time, the first user segment for the user comprises:
predicting, in real-time, the first user segment for the user during the online browsing session based on a proximity of webpages of the ecommerce website on the online browsing trail during the sequence of the one or more actions by the user of the ecommerce website during the online browsing session.

6. The system of claim 1 , wherein:
predicting, in real-time, the first user segment for the user from the plurality of user segments during the online browsing session based on the sequence of the one or more actions of the user in the online browsing trail during the online browsing session comprises:
predicting, in real-time, the first user segment for the user from the plurality of user segments and at least a second user segment of the plurality of user segments during the online browsing session based on the sequence of the one or more actions of the user in the online browsing trail during the online browsing session;

the first user segment comprises a demographic of the user, the demographic of the user comprising one or more of an age of the user or a gender of the user; and
the second user segment comprises a purpose of the online browsing session of the user, the purpose of the online browsing session comprising one or more of:
browsing for a different person of a particular age;
browsing for the different person of a particular gender;
browsing for home delivery of a product;
browsing for store-pickup of the product; or
browsing to buy the product from the ecommerce web site during the online browsing session.

7. The system of claim 1 , wherein:
predicting, in real-time, the first user segment for the user during the online browsing session based on the sequence of the one or more actions of the user in the online browsing trail during the online browsing sessio

Assignees

• Wal Mart Stores Inc
• Walmart Apollo Llc

Inventors

• Ali Afroza
• Achan Kannan
• Rapaka Venkata Syam Prakash

Classifications

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06Q30/0256

  User search · CPC title

• H04L67/306

  User profiles · CPC title

• G06Q30/0253

  During e-commerce, i.e. online transactions · CPC title

• G06Q30/0251

  Targeted advertisements · CPC title