Voice Domain Determination for Multi-Device Home Network Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current home network systems can only recognize and respond to user utterance sounds for functions provided by a single terminal device, unable to combine and process functions from multiple devices, and struggle with utterances outside programmed dialogues or when the user changes domains during conversation.
Innovation Solution
An electronic device with a processor that determines the appropriate domain and context for processing user utterance sounds based on confidence scores, using stored domain and context information to generate system responses, and updates information for external devices in the network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the system uses a single terminal device for voice recognition and response, then the system complexity is low, but the system cannot process functions from multiple devices or handle unprogrammed utterances
Solution Approach 1:
The patent implements a domain determination mechanism that enables a single voice recognition system to handle multiple domains (weather, news, entertainment, etc.) and integrate functions from multiple terminal devices. The processor determines the appropriate domain based on user utterance and routes to corresponding processing modules, allowing the system to provide universal service across diverse functions without requiring separate systems for each function.
Solution Approach 2:
The patent introduces a domain determination module as an intermediary between voice recognition and function execution. This mediator analyzes the user utterance, determines the appropriate domain, and routes the request to the corresponding processing module. This intermediary layer enables complex multi-device coordination while maintaining a unified interface for users, effectively managing system complexity through modular architecture.
2Adaptability or versatility
If the system uses fixed programmed dialogues, then the system reliability is high, but the system cannot recognize or process user utterances outside the programmed dialogues
Solution Approach 1:
The patent implements dynamic domain determination that adapts to different user utterances in real-time. Instead of relying on fixed dialogue scripts, the system analyzes each utterance to determine the appropriate domain dynamically. This dynamic approach allows the system to handle unprogrammed utterances by routing them to relevant domain-specific processing modules, maintaining reliability through structured domain handling while achieving versatility through adaptive recognition.
Solution Approach 2:
The patent changes the parameter of dialogue processing from fixed script matching to dynamic domain-based routing. By transforming the system from relying on predetermined dialogue parameters to using domain classification parameters, the system can accommodate various types of utterances including unprogrammed ones, while maintaining reliability through consistent domain processing rules.
3Adaptability or versatility
If the system maintains a single domain context during dialogue, then the processing is simple, but the system cannot handle domain changes during user conversation
Solution Approach 1:
The patent segments the dialogue processing system into multiple independent domain-specific modules. Each domain (weather, news, entertainment, etc.) is handled by a separate processing module, allowing the system to switch between domains during conversation without requiring complex cross-domain context management. This segmentation enables flexible domain transitions while keeping each module's context management relatively simple.
Solution Approach 2:
The patent adds a domain dimension to the dialogue processing architecture. Instead of managing complex multi-dimensional context within a single domain, the system uses domain as a separate dimension for organizing processing logic. This dimensional separation allows the system to handle domain changes by switching processing modules rather than managing complex context transitions within a monolithic system.
Data Source
AI summary
An electronic device and a method for controlling the same are provided. The electronic device includes a storage configured to store domain information that is categorized for dialog subjects, a speaker configured to output a system response based on a user utterance sound, and a processor configured to detect a domain, among the domain information, based on the user utterance sound, determine one among the detected domain and a previous domain as a domain to be used to process the user utterance sound, based on a confidence between the user utterance sound and the detected domain, and process the user utterance sound to generate the system response, based on the determined domain.