Voice Assistant Device Alias Matching for Intent Disambiguation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice-based digital assistants face challenges in accurately controlling multiple home devices of the same type due to difficulties in disambiguating user intent, leading to cumbersome and computationally expensive interactions.
Innovation Solution
Implementing a method that uses a name list for multiple devices, where each device is assigned a unique alias, allowing users to control them through voice commands by performing speech-to-text conversion and intent deduction based on the recognized aliases, thereby simplifying the interaction process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If interactive questions and answers are used to disambiguate user intent, then control accuracy is improved, but interaction time and computational cost increase
Solution Approach 1:
The system performs preliminary actions by proactively pushing device status information (name, type, location, current state) to the user's portable device before the voice command is given. This allows the user's device to pre-load the context data needed for accurate intent disambiguation, eliminating the need for time-consuming interactive questions during the actual control operation.
Solution Approach 2:
The user's portable device serves as an intermediary between the voice-based assistant and the home devices. It receives and stores device context information, then uses this cached data to rapidly disambiguate user intent by matching the voice command against the pre-loaded device list, avoiding direct real-time interaction loops between the assistant and user.
2Measurement precision
If interactive questions and answers are used to disambiguate user intent, then control accuracy is improved, but computational cost increases
Solution Approach 1:
The system performs preliminary actions by pushing device context information to the user's portable device in advance. This distributes the computational burden of maintaining device state data to the user's device, reducing the computational cost on the voice-based assistant system while enabling accurate intent disambiguation through local context matching.
Solution Approach 2:
The user's portable device acts as an intermediary that caches device context information locally. This eliminates the need for the voice-based assistant to perform expensive real-time computations for intent disambiguation, as the portable device can rapidly match commands against pre-loaded device data, significantly reducing overall computational cost.
3Measurement precision
If explicit location descriptors are required in voice commands, then device identification accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The system implements self-service by automatically providing the user with a list of available devices and their contexts on their portable device. The user simply needs to select or refer to a device by name or simple descriptor, and the system handles the complex task of matching the command to the correct device using the pre-pushed context information, eliminating the need for users to construct complex location descriptors.
Solution Approach 2:
The system performs preliminary actions by pushing comprehensive device context data to the user's portable device before the interaction. This pre-loading of device information enables the user to issue simple voice commands without needing to remember or specify detailed location descriptors, as the system already has the context needed for accurate device identification.
Data Source
AI summary
System and method for controlling a home assistant device include: receiving an audio input; performing speech-to-text conversion on the audio input to obtain a textual string; searching a name list of multiple home devices to determine whether the textual string includes a respective alias of at least one home device in the name list; in accordance with a determination that the textual string includes a first alias corresponding to a first home device of a first device type, generating a first actionable intent to operate the first home device of the first device type; and in accordance with a determination that the textual string includes a second alias corresponding to a second home device of the first device type that is distinct from the first home device, generating a second actionable intent to operate the second home device of the first device type.