Voice Command Processing via Device Topology Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional voice command processing techniques struggle to interpret complex voice utterances and lack sufficient understanding of smart devices and their relationships within a smart home network, often requiring additional information from users.
Innovation Solution
A computer-implemented method that processes voice utterances by receiving data indicative of a voice command, accessing a device topology representation to define smart devices and their locations, and determining transcriptions and actions based on this representation, using personalized language models to improve interpretation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional voice command processing techniques are used, then the system can process simple voice commands, but it cannot interpret complex voice utterances and lacks understanding of device relationships
Solution Approach 1:
The system performs preliminary actions by constructing a device topology representation that maps devices and their relationships before processing voice commands. This pre-established contextual framework enables the system to interpret complex voice utterances accurately without requiring additional information from users during command processing.
Solution Approach 2:
The device topology representation serves as an intermediary structure that bridges the gap between voice utterances and device control. It contains contextual information about device relationships, locations, and associations, allowing the system to resolve ambiguous references in complex voice commands without requesting clarification.
2Ease of operation
If conventional voice processing is used, then the system can operate with simple command structures, but it requires additional information from users for complex commands
Solution Approach 1:
By pre-constructing the device topology representation with all device relationships and contextual information, the system eliminates the need for follow-up clarification questions during voice command processing. Users can issue complex commands in a single interaction, reducing communication rounds and saving time.
3Measurement precision
If the system lacks device topology understanding, then the processing logic remains simple, but interpretation accuracy decreases
Solution Approach 1:
The system segments the complex processing task into two distinct components: (1) constructing a device topology representation that captures device relationships and contextual information, and (2) using this representation to interpret voice commands. This segmentation allows the system to maintain manageable complexity while achieving high interpretation accuracy.
Data Source
AI summary
Example aspects of the present disclosure are directed to processing voice commands or utterances. For instance, data indicative of a voice utterance can be received. A device topology representation can be accessed. The device topology representation can define a plurality of smart devices associated with one or more structures. The device topology representation can further define a location of each of the plurality of devices within the associated structures. A transcription of the voice utterance can be determined based at least in part on the device topology representation. One or more selected devices and one or more actions to be performed by the one or more selected devices can be determined based at least in part on the determined transcription and the device topology representation.