Systems and methods for determining user personas for a user

Patent metadata

Field	Value
Publication number	US-11776016-B2
Application number	US-202217587485-A
Country	US
Kind code	B2
Filing date	Jan 28, 2022
Priority date	Jan 28, 2022
Publication date	Oct 3, 2023
Grant date	Oct 3, 2023

Abstract

This application relates to apparatus and methods for automatically determining and providing personalized user personas of a customer for specific platforms (e.g., applications). In some examples, a computing device receives a persona request identifying a user and a platform. In response, the computing device obtains user data associated with the user and a plurality of potential user personas from a database. For each of the plurality of potential user personas, the computing device then determines a combination score for the user based on the user data. The combination score indicates user's affinity to a corresponding potential user persona within the platform. The computing device selects at least one potential user persona of the plurality of potential user personas as a final user persona for the user and the platform based on the corresponding combination score.

First claim

What is claimed is:

1. A system comprising:
a database configured to:
store historical user data representative of one or more prior interactions between one or more users and one or more platforms; and
store item data representative of one or more items each having one or more associated features in the database;

a first processor configured to:
receive a persona request identifying a first user and a first platform;
receive user session data representative of interactions between the first user and the first platform occurring during a concurrent session;
obtain the historical user data associated with the one or more users and the one or more platforms from the database;
obtain a plurality of potential user personas from the database, each of the plurality of potential user personas including data characterizing a particular product category of a plurality of product categories;
generate one or more embeddings based on the user session data, the historical user data, and the plurality of potential user personas;
train a first model to generate a platform-specific sub-score, wherein the first model is trained using at least the one or more embeddings generated based on the historical user data;
train a second model to generate a user-specific sub-score, wherein the second model is trained using at least the one or more embeddings generated based on the historical user data and the plurality of potential user personas;
for each of the plurality of potential user personas, determine a combination score for the user based on at least the user session data and each of the plurality of potential user personas, the combination score indicates affinity to a corresponding potential user persona for the first platform, wherein the combination score is generated by aggregating outputs of the first and second models;
select at least one potential user persona of the plurality of potential user personas as a final user persona for the user and the platform based on the a corresponding combination score; and
transmit, over one or more networks, the final user persona to a second processor configured to (i) generate item recommendation data identifying and characterizing one or more item recommendations based on the final user persona and (ii) transmit, over the one or more networks and to a second computing device, instructions configured to cause the second computing device to generate an interface including the one or more item recommendations;
receive additional session data representative of one or more additional interactions between the first user and the first platform in response to generation of the interface;
generate one or more updated embeddings representative of the additional session data; and
retrain at least one of the first model or the second model based on the one or more embeddings and the one or more updated embeddings.

2. The system of claim 1 , wherein the second model includes a user-persona model configured to determine, for each of the plurality of potential user personas, a user-persona score for the user indicating a likelihood of the user interacting with the corresponding potential user persona, and wherein the user-persona model is configured to receive one or more embeddings representative of user-persona engagement data, user engagement data, and catalog data.

3. The system of claim 1 , wherein the first model includes a user-platform model configured to determine a user-platform score for the user indicating a likelihood of the user interacting with the platform, and wherein the user platform model is configured to receive one or more embeddings representative of a user, a platform, and a persona.

4. The system of claim 1 , wherein at least one of the first model or the second model includes a user-persona-platform model configured to determine, for each of the plurality of potential user personas, a user-persona-platform score for the user indicating a likelihood of the user interacting with the items associated with the corresponding potential user persona within the platform, and wherein the user-persona-platform model is configured to aggregate sub-platform embeddings belonging to a corresponding potential user persona.

5. The system of claim 1 , wherein the plurality of potential user personas is one or more of internet-based personas, lifestyle-based personas, need-based personas, and family-based personas.

6. The system of claim 1 , wherein determining the combination score is further based on catalog data including a plurality of items for sale on the platform.

7. A computer-implemented method comprising:
receiving, by a processor, a persona request identifying a first user and a first platform;
receiving, by the processor, user session data representative of interactions between the first user and the first platform occurring during a concurrent session;
obtaining, by the processor, historical user data associated with the user from a database, the user data including user session data identifying and characterizing interactions between the user and the platform and user transaction data identifying and characterizing one or more transactions of the user;
obtaining, by the processor, a plurality of potential user personas from the database, each of the plurality of potential user personas including data characterizing a particular product category of a plurality of product categories;
generating one or more embeddings based on the user session data, the historical user data, and the plurality of potential user personas;
training a first model to generate a platform-specific sub-score, wherein the first model is trained using at least the one or more embeddings generated based on the historical user data;
training a second model to generate a user-specific sub-score, wherein the second model is trained using at least the one or more embeddings generated based on the historical user data and the plurality of potential user personas;
for each of the plurality of potential user personas, determining, by the processor, a combination score for the user based on at least the user session data and each of the plurality of potential user personas, the combination score indicates affinity to a corresponding potential user persona for the first platform, wherein the combination score is generated by aggregating outputs of the first and second models;
selecting, by the processor, at least one potential user persona of the plurality of potential user personas as a final user persona for the user and the platform based on the a corresponding combination score; and
transmitting, by the processor and over one or more networks, the final user persona to a computing system configured to (i) generate item recommendation data identifying and characterizing one or more item recommendations based on the final user persona and (ii) transmit, over the one or more networks and to a second computing device, instructions configured to cause the second computing device to generate an interface including the one or more item recommendations;
receiving additional session data representative of one or more additional interactions between the first user and the first platform in response to generation of the interface;
generating one or more updated embeddings representative of the additional session data; and
retraining at least one of the first model or the second model based on the one or more embeddings and the one or more updated embeddings.

8. The computer-implemented method of claim 7 , wherein the second model includes a user persona model configured to determine, for each of the plurality of potential user personas, a user-persona score for the user indicating a likelihood of the user interacting with items associated

Assignees

• Walmart Apollo Llc

Inventors

• Rajasekaran Rishi
• Gupta Sneha
• Arora Yokila
• Sridhar Rahul
• Kumar Sushant
• Korpeoglu Evren
• Achan Kannan

Classifications

• G06Q30/0269 Primary

  based on user profile or attribute · CPC title

• G06Q30/0631

  Recommending goods or services · CPC title

• G06Q30/0255

  based on user history · CPC title