Granted Patent B2

US 12,418,499 · App. 18/439,055 · Granted Sep 16, 2025

Inventors: Jessica Anna Sarceda (Scottsdale, AZ); Stephen Derek Ost (Scottsdale, AZ)

Assignee: Paradox, Inc.

H04L51/02G06F16/3329G06F16/3334G06F40/35H04L67/306

Abstract

Claims (60)

1. A method, comprising:

receiving, by a computing system, user activity data from a user of a user device interacting with content hosted by a third-party computing system via one or more integrations injected into code of an application executing on the user device, the application presenting the content to the user;

learning, by the computing system, attributes of the user based on the user activity data;

causing, by the computing system, the application to render a web page for display to the user via the user device, the web page comprising a chat interface at least partially overlaying the content of the web page;

establishing, by the computing system, a communication session between the user and an intelligent assistant associated with the computing system via a chat interface of the application;

continuing, by the computing system, to learn additional attributes of the user based on updated user activity data received via messages sent by the user to the intelligent assistant via the communication session between the user and the intelligent assistant and one or more of user browsing activity on the web page or location information derived from communications with the user;

receiving, by the computing system, a message from the user to the intelligent assistant; and

dynamically causing, by the computing system, the application to render customized content in the web page for the user based on the learned attributes and the learned additional attributes of the user by:

determining, by the computing system, that the message comprises a key word triggering retrieval of content relevant to the message,

based on the determining, retrieving, by the computing system, the relevant content that is associated with the key word and relevant to the user based on the learned attributes and the learned additional attributes of the user, and

causing, by the computing system, the application to render customized content in the web page, the customized content comprising the content determined to be relevant to the user based on the message alongside the chat interface.

2. The method of claim 1 , wherein the user activity data comprises at least one of: internet protocol (IP) information, campaign data, pages of a website viewed, time spent on each webpage, browser language, cursor movements, portions of the application viewed, or time spent on each portion of the application.

3. The method of claim 1 , wherein learning, by the computing system, the attributes of the user further comprises:

generating a plurality of tags corresponding to the learned attributes.

4. The method of claim 3 , wherein retrieving, by the computing system, the relevant content is further based on a match between the plurality of tags and content tags associated with the relevant content.

5. The method of claim 1 , wherein the communication session is established in response to the user interacting with an intelligent assistant prompt displayed within the content hosted by the third-party computing system.

6. The method of claim 1 , wherein determining, by the computing system, that the message comprises the key word triggering retrieval of the relevant content comprises:

analyzing, by a natural language processing module of the computing system, the message from the user to identify the key word.

7. The method of claim 1 , further comprising:

prompting, by the intelligent assistant, the user to upload a document, and wherein the learned attributes of the user is further based on analysis of the uploaded document.

8. A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by a processor, causes a computing system to perform operations comprising:

receiving, by the computing system, user activity data from a user of a user device interacting with content hosted by a third-party computing system via one or more integrations injected into code of an application executing on the user device, the application presenting the content to the user;

learning, by the computing system, attributes of the user based on the user activity data;

causing, by the computing system, the application to render a web page for display to the user via the user device, the web page comprising a chat interface at least partially overlaying the content of the web page;

establishing, by the computing system, a communication session between the user and an intelligent assistant associated with the computing system via a chat interface of the application;

continuing, by the computing system, to learn additional attributes of the user based on updated user activity data received via messages sent by the user to the intelligent assistant via the communication session between the user and the intelligent assistant and one or more of user browsing activity on the web page or location information derived from communications with the user;

receiving, by the computing system, a message from the user to the intelligent assistant; and

dynamically causing, by the computing system, the application to render customized content in the web page for the user based on the learned attributes and the learned additional attributes of the user by:

determining, by the computing system, that the message comprises a key word triggering retrieval of content relevant to the message,

based on the determining, retrieving, by the computing system, the relevant content that is associated with the key word and relevant to the user based on the learned attributes and the learned additional attributes of the user, and

causing, by the computing system, the application to render customized content in the web page, the customized content comprising the content determined to be relevant to the user based on the message alongside the chat interface.

9. The non-transitory computer readable medium of claim 8 , wherein the user activity data comprises at least one of: internet protocol (IP) information, campaign data, pages of a website viewed, time spent on each webpage, browser language, cursor movements, portions of the application viewed, or time spent on each portion of the application.

10. The non-transitory computer readable medium of claim 8 , wherein learning, by the computing system, the attributes of the user further comprises:

generating a plurality of tags corresponding to the learned attributes.

11. The non-transitory computer readable medium of claim 10 , wherein retrieving, by the computing system, the relevant content is further based on a match between the plurality of tags and content tags associated with the relevant content.

12. The non-transitory computer readable medium of claim 8 , wherein the communication session is established in response to the user interacting with an intelligent assistant prompt displayed within the content hosted by the third-party computing system.

13. The non-transitory computer readable medium of claim 8 , wherein determining, by the computing system, that the message comprises the key word triggering retrieval of the relevant content comprises:

analyzing, by a natural language processing module of the computing system, the message from the user to identify the key word.

14. The non-transitory computer readable medium of claim 8 , further comprising:

prompting, by the intelligent assistant, the user to upload a document, and wherein the learned attributes of the user is further based on analysis of the uploaded document.

15. A system, comprising:

a processor; and

a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:

receiving user activity data from a user of a user device interacting with content hosted by a third-party computing system via one or more integrations injected into code of an application executing on the user device, the application presenting the content to the user;

learning attributes of the user based on the user activity data;

causing the application to render a web page for display to the user via the user device, the web page comprising a chat interface at least partially overlaying the content of the web page;

establishing a communication session between the user and an intelligent assistant associated with the system via a chat interface of the application;

continuing to learn additional attributes of the user based on updated user activity data received via messages sent by the user to the intelligent assistant via the communication session between the user and the intelligent assistant and one or more of user browsing activity on the web page or location information derived from communications with the user;

receiving a message from the user to the intelligent assistant; and

dynamically causing the application to render customized content in the web page for the user based on the learned attributes and the learned additional attributes of the user by:

determining that the message comprises a key word triggering retrieval of content relevant to the message,

based on the determining, retrieving the relevant content that is associated with the key word and relevant to the user based on the learned attributes and the learned additional attributes of the user, and

causing the application to render customized content in the web page, the customized content comprising the content determined to be relevant to the user based on the message alongside the chat interface.

16. The system of claim 15 , wherein the user activity data comprises at least one of: internet protocol (IP) information, campaign data, pages of a website viewed, time spent on each webpage, browser language, cursor movements, portions of the application viewed, or time spent on each portion of the application.

17. The system of claim 15 , wherein learning the attributes of the user further comprises:

generating a plurality of tags corresponding to the learned attributes.

18. The system of claim 17 , wherein retrieving the relevant content is further based on a match between the plurality of tags and content tags associated with the relevant content.

19. The system of claim 15 , wherein the communication session is established in response to the user interacting with an intelligent assistant prompt displayed within the content hosted by the third-party computing system.

20. The system of claim 15 , wherein the operations further comprise:

prompting, by the intelligent assistant, the user to upload a document, and wherein the learned attributes of the user is further based on analysis of the uploaded document.

Assignments (3)

Continuity (3)

References Cited (27)