Voice Interface Focus Session for Device Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face the burden of explicitly specifying a target device in voice commands for electronic devices with voice interfaces, which can be tedious and cumbersome, especially when the target device is unknown or ambiguous.
Innovation Solution
A voice-activated electronic device and voice assistant system that determines or assigns a target device for voice inputs when a specification is absent or ambiguous, by establishing focus sessions and using criteria such as recent voice command history and time thresholds to automatically direct voice requests to the appropriate device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system requires explicit target device specification in every voice command, then the precision of device identification is improved, but the ease of operation deteriorates
Solution Approach 1:
The system performs preliminary actions by establishing focus sessions and maintaining device context in advance. When a user issues a voice command without explicit device specification, the system uses the previously established focus session or recent device context to automatically determine the target device, eliminating the need for repeated explicit specifications while maintaining accurate device identification
Solution Approach 2:
The system serves itself by maintaining internal state (focus sessions, device context) that automatically resolves ambiguous voice commands. The voice interface device uses its own stored context to identify target devices without requiring additional user input, making the system self-sufficient in disambiguating commands
2Ease of operation
If the system accepts ambiguous voice commands without explicit device specification, then the ease of operation is improved, but the reliability of command execution deteriorates
Solution Approach 1:
The system uses feedback mechanisms by monitoring voice command patterns, focus session states, and device context to dynamically determine target devices. The system continuously updates its understanding of user intent based on recent interactions and uses this feedback to accurately resolve ambiguous commands without explicit device specifications
Solution Approach 2:
The system performs preliminary actions by establishing and maintaining focus sessions that pre-determine the context for subsequent voice commands. This preliminary context establishment ensures that when ambiguous commands are received, the system has already prepared the necessary information to reliably execute the correct device
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
A method at a first electronic device with one or more microphones, a speaker, one or more processors, and memory storing one or more programs for execution by the one or more processors, the first electronic device being a member of a local group of connected electronic devices communicatively coupled to a common network service, comprises: receiving a first voice command including a request for a first operation; determining a first target device for the first operation from among the local group of connected electronic devices, wherein the first target device is the first electronic device; establishing a focus session with respect to the first target device; causing the first operation to be performed by the first target device via operation of the common network service; receiving a second voice command including a request for a second operation; determining that the second voice command does not include an explicit designation of a second target device; determining that the second operation can be performed by the first target device; causing the second operation to be performed by the first target device via operation of the common network service; receiving a third voice command including a request for a third operation and an explicit designation of a third target device among the local group of connected electronic devices, wherein the third target device is a second electronic device member of the local group of connected electronic devices, the second electronic device different from the first electronic device; maintaining the focus session with respect to the first target device; and causing the third operation to be performed by the third target device via operation of the common network service.