IP Library Granted Patent US 12710971
Granted Patent B2
US 12710971 · App. 18/322,134 · Granted Aug 18, 2026

Digital character interactions with media items in a conversational session

Inventors: Vacit Arat (La Cañada Flintridge, CA); Rick King (Kiowa, CO); Arnav Mukherjee (Lexington, MA); Bobbi Jolean Sheffield (Rockwall, TX)
Assignee: HIA Technologies, Inc.
G06F9/453G06F3/167G06T13/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12710971
App. No.
18/322,134
Granted
Aug 18, 2026
Kind
B2
Abstract

A computing system is configured to perform operations including: (i) causing a graphical user interface (GUI) of a content authoring tool for creating a visual conversation application to be presented via a first device, the GUI comprising one or more media interactions for a digital character configured to interact with a user in a conversational session of the visual conversation application, (ii) receiving, from the first device, an indication of a media item to be presented in the conversational session, (iii) receiving, from the first device, an indication of a media interaction of the one or more media interactions, the media interaction comprising a type of engagement of the digital character with the media item, and (iv) causing the conversational session to be presented via a second device, wherein the digital character is configured to engage with the media item in accordance with the media interaction during the conversational session.

Claims (56)

1 . A computing system comprising:

a network interface;

at least one processor;

at least one non-transitory computer-readable medium; and

program instructions stored on the at least one non-transitory computer-readable medium that are executable by the at least one processor such that the computing system is configured to:

cause a graphical user interface (GUI) of a content authoring tool for creating a visual conversation application to be presented via a first computing device, the GUI comprising one or more selectable media interactions for configuring digital character interactions with media items, wherein the digital character is configured to interact with a user of a second computing device in a conversational session of the visual conversation application;

receive, from the first computing device, an indication of a media item to be presented in the conversational session of the visual conversation application, wherein the media item is not a digital character;

receive, from the first computing device, an indication of a given media interaction of the one or more selectable media interactions, wherein the given media interaction comprises a type of engagement of the digital character with the media item;

receive, from the first computing device, an indication of a given portion of the media item that defines the given portion of the media item as a target location for the given media interaction; and

cause the conversational session to be presented via the visual conversation application on the second computing device, wherein the visual conversation application is configured to, during the conversational session:

present the digital character and the media item;

while the digital character and the media item are being presented, receive, from the user of the second computing device, a query that is directed to the digital character;

select the given media interaction as being responsive to the query; and

cause the digital character to respond to the query directed to the digital character by engaging with the media item in accordance with the given media interaction, wherein the engagement with the media item in accordance with the given media interaction is directed to the given portion of the media item, and wherein the given portion of the media item includes information relevant to the query.

2 . The computing system of claim 1 , wherein the GUI further comprises a set of media items comprising the media item, and wherein the program instructions that are executable by the at least one processor such that the computing system is configured to receive the indication of the media item comprise program instructions that are executable by the at least one processor such that the computing system is configured to:

receive the indication of the media item based on a user of the first computing device selecting the media item from the set of media items via the first computing device.

3 . The computing system of claim 1 , wherein the given media interaction comprises a verbal type of engagement of the digital character with the media item.

4 . The computing system of claim 1 , wherein the given media interaction comprises a visual type of engagement of the digital character with the media item.

5 . The computing system of claim 1 , wherein the media item comprises a representation of one or both of textual content or image content.

6 . The computing system of claim 5 , wherein the media item comprises a representation of a slide presentation.

7 . The computing system of claim 6 , wherein the given media interaction comprises the digital character editing content that is displayed by the media item.

8 . The computing system of claim 1 , wherein the media item comprises video content.

9 . The computing system of claim 8 , wherein the given media interaction comprises the digital character manipulating playback of the video content.

10 . The computing system of claim 1 , wherein the given media interaction comprises the digital character acting out an action that is described in the media item.

11 . The computing system of claim 1 , wherein the given portion of the media item comprises a sub-media item of the media item that takes the form of an individually displayed element within the media item.

12 . The computing system of claim 1 , further comprising program instructions stored on the at least one non-transitory computer-readable medium that, when executed by the at least one processor, cause the computing system to:

cause the GUI of the content authoring tool to include a grid that is overlaying the media item, wherein the grid includes a plurality of selectable regions;

wherein the indication of the given portion of the media item comprises an indication of a user selection of a given selectable region of the plurality of selectable regions that corresponds to the given portion of the media item.

13 . A non-transitory computer-readable medium, wherein the non-transitory computer-readable medium is provisioned with program instructions that, when executed by at least one processor, cause a computing system to:

cause a graphical user interface (GUI) of a content authoring tool for creating a visual conversation application to be presented via a first computing device, the GUI comprising one or more selectable media interactions for configuring digital character interactions with media items, wherein the digital character is configured to interact with a user of a second computing device in a conversational session of the visual conversation application;

receive, from the first computing device, an indication of a media item to be presented in the conversational session of the visual conversation application, wherein the media item is not a digital character;

receive, from the first computing device, an indication of a given media interaction of the one or more selectable media interactions, wherein the given media interaction comprises a type of engagement of the digital character with the media item;

receive, from the first computing device, an indication of a given portion of the media item that defines the given portion of the media item as a target location for the given media interaction; and

cause the conversational session to be presented via the visual conversation application on the second computing device, wherein the visual conversation application is configured to, during the conversational session:

present the digital character and the media item;

while the digital character and the media item are being presented, receive, from the user of the second computing device, a query that is directed to the digital character;

select the given media interaction as being responsive to the query; and

cause the digital character to respond to the query directed to the digital character by engaging with the media item in accordance with the given media interaction, wherein the engagement with the media item in accordance with the given media interaction is directed to the given portion of the media item, and wherein the given portion of the media item includes information relevant to the query.

14 . The non-transitory computer-readable medium of claim 13 , wherein the GUI further comprises a set of media items comprising the media item, and wherein the program instructions that, when executed by the at least one processor, cause the computing system to receive the indication of the media item comprise program instructions that, when executed by the at least one processor, cause the computing system to:

receive the indication of the media item based on a user of the first computing device selecting the media item from the set of media items via the first computing device.

15 . The non-transitory computer-readable medium of claim 13 , wherein the given media interaction comprises a verbal type of engagement of the digital character with the media item.

16 . The non-transitory computer-readable medium of claim 13 , wherein the given media interaction comprises a visual type of engagement of the digital character with the media item.

17 . A method carried out by a computing system, the method comprising:

causing a graphical user interface (GUI) of a content authoring tool for creating a visual conversation application to be presented via a first computing device, the GUI comprising one or more selectable media interactions for configuring digital character interactions with media items, wherein the digital character is configured to interact with a user of a second computing device in a conversational session of the visual conversation application;

receiving, from the first computing device, an indication of a media item to be presented in the conversational session of the visual conversation application, wherein the media item is not a digital character;

receiving, from the first computing device, an indication of a given media interaction of the one or more selectable media interactions, wherein the given media interaction comprises a type of engagement of the digital character with the media item;

receiving, from the first computing device, an indication of a given portion of the media item that defines the given portion of the media item as a target location for the given media interaction; and

causing the conversational session to be presented via the visual conversation application on the second computing device, wherein the visual conversation application is configured to, during the conversational session:

present the digital character and the media item;

while the digital character and the media item are being presented, receive, from the user of the second computing device, a query that is directed to the digital character;

select the given media interaction as being responsive to the query; and

cause the digital character to respond to the query directed to the digital character by engaging with the media item in accordance with the given media interaction, wherein the engagement with the media item in accordance with the given media interaction is directed to the given portion of the media item, and wherein the given portion of the media item includes information relevant to the query.

18 . The method of claim 17 , wherein the GUI further comprises a set of media items comprising the media item, and wherein receiving the indication of the media item comprises:

receiving the indication of the media item based on a user of the first computing device selecting the media item from the set of media items via the first computing device.

19 . The method of claim 17 , wherein the given media interaction comprises a verbal type of engagement of the digital character with the media item.

20 . The method of claim 17 , wherein the given media interaction comprises a visual type of engagement of the digital character with the media item.