# US 2026/0039611 A1 · Advanced communications system

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

- Number: US 2026/0039611 A1
- Document ID: US20260039611A1
- Status: Published application
- Kind: A1
- Application number: 19/352,379
- Filed: 2025-10-07
- Published: 2026-02-05
- Earliest claimed: 2023-07-28
- Assignees: Rolling Square
- Applicants: Rolling Square
- Inventors: Carlo Edoardo FERRARIS
- Web page: https://patentgrep.com/patent/US20260039611A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- H04L 51/046: Interoperability with other network applications or services
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A hands-free communications system that evaluates user utterances by performing speech to text conversions, evaluating the text, and connecting the user to other users or artificial intelligence (AI) agents. Instant, real-time communications channels are created between the user and the other users and/or AI agents via voice commands.

## Claims

### Claim 1

A method, comprising:
receiving a user's speech input from a user a user headset;
converting the speech input to text;
parsing the text for a command phrase;
sending the text to an artificial intelligence (AI) assistant;
wherein the AI assistant evaluates the text and performs one of the following:
based on a determination that the text is requesting an action that the AI assistant can address, the AI assistant responding to the user via the user headset;
based on a determination that the text can be addressed by a particular AI agent, the AI assistant creating an audio communication session between the user headset and the particular AI agent;
based on a determination that the text is requesting a contact in the user's contact list, the AI assistant creating an audio communication session between the user headset and the user headset.
