# US 2026/0100921 A1 · Artificial intelligence (ai)-based user interfaces

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0100921 A1
- Document ID: US20260100921A1
- Status: Published application
- Kind: A1
- Application number: 18/908,545
- Filed: 2024-10-07
- Published: 2026-04-09
- Earliest claimed: 2024-10-07
- Assignees: Zoom Video Communications, Inc.
- Applicants: Zoom Video Communications, Inc.
- Inventors: Zheng Chen; Pengcheng He; Xuedong David Huang; Mark Kawano; Bo Yan
- Web page: https://patentgrep.com/patent/US20260100921A1

## CPC

- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

One example method includes receiving, via a graphical user interface (“GUI”) of an artificial intelligence (“AI”) user interface (“AI-UI”) of an AI assistant, user input corresponding to one or more components of the GUI; determining, by the AI-UI using a trained ML model, one or more tasks based on the user inputs; invoking, by the AI assistant, one or more services to perform the one or more tasks; and presenting, in the AI-UI, outputs of the one or more tasks.

## Claims

### Claim 1

A method comprising:
receiving, via a graphical user interface (“GUI”) of an artificial intelligence (“AI”) user interface (“AI-UI”) of an AI assistant, user input corresponding to one or more components of the GUI;
determining, by the AI-UI using a trained ML model, one or more tasks based on the user inputs;
invoking, by the AI assistant, one or more services to perform the one or more tasks; and
presenting, in the AI-UI, outputs of the one or more tasks.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more services comprises an external application, and wherein invoking the one or more services comprises invoking the external application.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the one or more tasks comprises generating a prompt to a large language model (“LLM”) based on the user input and receiving an identification of the one or more tasks from the LLM.

### Claim 4 (depends on 1)

The method of claim 1, wherein presenting the outputs of the one or more tasks comprises modifying the GUI based on the outputs.

### Claim 5 (depends on 1)

The method of claim 1, wherein presenting the outputs of the one or more tasks comprises generating and outputting one or more text messages in a conversational user interface (“CUI”) of the AI-UI.

### Claim 6 (depends on 5)

The method of claim 5, wherein the one or more text messages comprise a request for more information.

### Claim 7 (depends on 1)

The method of claim 1, wherein the user input comprises a request for assistance regarding a component of the one or more components of the GUI.

### Claim 8

A system comprising:
a communications interface;
a non-transitory computer-readable medium; and
one or more processors configured to execute processor-executable instructions stored in the non-transitory computer-readable medium to:
receive, via a graphical user interface (“GUI”) of an artificial intelligence (“AI”) user interface (“AI-UI”) of an AI assistant, user input corresponding to one or more components of the GUI;
determine, by the AI-UI using a trained ML model, one or more tasks based on the user inputs;
invoke, by the AI assistant, one or more services to perform the one or more tasks; and
present, in the AI-UI, outputs of the one or more tasks.

### Claim 9 (depends on 8)

The system of claim 8, wherein the one or more services comprises an external application, and wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to invoke the external application.

### Claim 10 (depends on 8)

The system of claim 8, wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to generate a prompt to a large language model (“LLM”) based on the user input and receiving an identification of the one or more tasks from the LLM.

### Claim 11 (depends on 8)

The system of claim 8, wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to modify the GUI based on the outputs.

### Claim 12 (depends on 8)

The system of claim 8, wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to generate and output one or more text messages in a conversational user interface (“CUI”) of the AI-UI.

### Claim 13 (depends on 12)

The system of claim 12, wherein the one or more text messages comprise a request for more information.

### Claim 14 (depends on 8)

The system of claim 8, wherein the user input comprises a request for assistance regarding a component of the one or more components of the GUI.

### Claim 15

A non-transitory computer-readable medium comprising processor-executable instructions configured to cause one or more processors to:
receive, via a graphical user interface (“GUI”) of an artificial intelligence (“AI”) user interface (“AI-UI”) of an AI assistant, user input corresponding to one or more components of the GUI;
determine, by the AI-UI using a trained ML model, one or more tasks based on the user inputs;
invoke, by the AI assistant, one or more services to perform the one or more tasks; and
present, in the AI-UI, outputs of the one or more tasks.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more services comprises an external application, and wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to invoke the external application.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to generate a prompt to a large language model (“LLM”) based on the user input and receiving an identification of the one or more tasks from the LLM.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to modify the GUI based on the outputs.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to generate and output one or more text messages in a conversational user interface (“CUI”) of the AI-UI.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein the one or more text messages comprise a request for more information.
