US 12406663

Analysis of U.S. Patent 12,406,663

Washington, D.C. - An analysis of United States Patent 12,406,663, titled "Routing of user commands across disparate ecosystems," reveals a system for integrating voice commands from a vehicle with various smart home or Internet of Things (IoT) ecosystems. The patent, issued to Cerence Operating Co., outlines a method for a vehicle's assistant to intelligently route user commands to the correct external system, such as a home automation platform.

Patent Number	12,406,663
Title	Routing of user commands across disparate ecosystems
Assignee	Cerence Operating Co.
Inventors	Prateek Kathpal, Brian Arthur Rubin
Filing Date	December 17, 2021
Issue Date	September 2, 2025
Abstract	A system for routing commands issued by a passenger of a vehicle to a Smart Home and/or an Internet of Things (IoT) ecosystem via a connection manager. Issued commands are obtained from utterances using speech recognition and analyzed using natural language understanding and natural language processing. Using the output of the natural understanding analysis, the connection manager determines where to send the command by identifying a target Smart Home and/or IoT ecosystem.

As of April 26, 2026, a search of the dockets for the Court of Appeals for the Federal Circuit (CAFC) for the year 2026 did not reveal any cases involving US Patent 12,406,663.

Overview of Independent Claims:

This patent contains three independent claims which form the core of the invention.

Independent Claim 1 describes a system within a vehicle that can process a user's spoken commands. This system includes a "recognition module" with hardware processors that receives utterances from the vehicle's speakers. This module is designed to identify a specific command and determine which of the user's existing smart home systems (the "target ecosystem") the command is intended for. A key component is a natural language understanding (NLU) module that interprets the meaning of the spoken words to identify the correct ecosystem. The claim specifies that a "connection manager" then sends the command to that target ecosystem. A crucial feature of this claim is the system's ability to learn and improve; it receives feedback from the smart home system about the command and uses this feedback to update its NLU models.

Independent Claim 3 outlines a method, or a series of steps, for routing these commands. The process begins with receiving a spoken command in the vehicle, along with "contextual data" such as the vehicle's location or the time of day. The spoken words are converted to text. The system then determines the correct smart home ecosystem for the command by analyzing both the text and the contextual information. For example, a command like "turn on the lights" might be routed to the user's home lighting system if the vehicle is nearing the user's house in the evening. The command is then sent to the target system, and the method includes receiving a confirmation that the command was successfully carried out.

Independent Claim 12 describes a broader system that accomplishes a similar goal. It details a recognition module within a vehicle that processes voice commands from an occupant. This system uses contextual data associated with the command to identify the correct "target ecosystem," which is defined as a non-vehicle system in the user's home that can execute commands remotely. A "connection manager" is then responsible for routing the command to that identified ecosystem. This claim emphasizes the integration of the in-vehicle system with external smart home environments.