Unified Speech Assistant for In-Vehicle Device Command Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In vehicles equipped with multiple entertainment systems, existing speech assistants often confuse users by requiring additional interactions to relay commands to specific devices, limiting the ability to execute commands on intended systems, such as playing media on rear-seat entertainment systems from the head unit.
Innovation Solution
A computer-implemented method that receives sound waves, performs speech recognition to determine user commands, identifies the user's location, selects the target device based on this location, and relays instructions to execute the command on the appropriate device, enabling a holistic in-vehicle speech assistant to manage all devices seamlessly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If each entertainment system has its own speech assistant, then each device can independently execute commands, but the user experience deteriorates due to confusion and inability to execute commands across multiple devices
Solution Approach 1:
The patent merges multiple device-specific speech assistants into a single unified speech assistant that can control multiple entertainment systems. The head unit acts as a central controller that receives voice commands and relays them to the appropriate target device (rear-seat entertainment system, co-driver entertainment system, etc.), eliminating the need for users to interact with multiple separate assistants and simplifying the user experience while maintaining broad command execution capability
2Adaptability or versatility
If a speech assistant on the head unit is used to relay commands to rear-seat devices, then command execution across devices is enabled, but additional interactions are required which complicates the technical solution and user experience
Solution Approach 1:
The unified speech assistant system performs self-service by automatically determining the appropriate target device for a given voice command. The system uses location information, device capabilities, and command context to autonomously route commands to the correct entertainment system without requiring users to manually select devices or perform additional interactions, thereby reducing both technical complexity and user effort
3Measurement precision
If manual device selection is required for each command, then precise device targeting is achieved, but the ease of operation deteriorates due to additional button presses and interactions
Solution Approach 1:
The system performs preliminary actions by pre-configuring device locations, capabilities, and associations before user interaction. When a voice command is received, the speech assistant already has the necessary information about which devices are available, their locations, and their capabilities, allowing it to automatically and accurately determine the intended target device without requiring users to manually select or navigate through device options
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution allows a unified speech assistant to execute commands on all vehicle devices, simplifying user interactions and ensuring that commands are directed to the correct device, enhancing user experience by eliminating the need for additional button presses and improving command execution across various entertainment systems.
Implementation Method 1
receive sound waves at a microphone, wherein the sound waves bears a user voice call for a command
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Given a method of providing in-vehicle media entertainment to passengers of a vehicle, it is an objective of the present invention to improve interaction of in-vehicle speech assistance. The objective is solved by a computer-implemented method (400) for controlling a device of a plurality of devices (130) available in a vehicle (101), the method comprising steps: receive (410) sound waves at a microphone, wherein the sound waves bears a user voice call for a command, such as a media player command; determine (420) at least one instruction by performing at least a speech recognition of a digital representation of the sound waves; determine (430) at least one user location; select (440) at least one target device by correlating the user location with at least one location of the plurality of devices; relay (450) the instruction to the at least one target device; and execute (460) the instruction on the at least one target device.