Multi-Voice Assistant Switching for Richer Response Information
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices with multiple voice assistants face difficulties in seamlessly switching and integrating these assistants, leading to user inconvenience and limited response information from a single voice command.
Innovation Solution
An electronic apparatus and method that enables easy switching and integration of multiple voice assistants by determining the appropriate assistant based on user input, application context, and history, and displaying response information from multiple assistants simultaneously.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If multiple voice assistants are integrated in an electronic device, then the variety and accuracy of response information is improved, but the device complexity and difficulty of management increases
Solution Approach 1:
The patent introduces a voice assistant manager as an intermediary component that mediates between multiple voice assistants and the user. This manager receives user voice inputs, determines which voice assistant(s) should process them based on predefined rules or machine learning models, and coordinates their responses. This intermediary structure allows multiple voice assistants to coexist without requiring direct user management of each assistant, thus maintaining information completeness while reducing perceived complexity for users.
Solution Approach 2:
The voice assistant manager serves multiple functions: it acts as a router to distribute voice commands to appropriate assistants, a conflict resolver to handle overlapping responses, and a learning system that adapts to user preferences. This multi-functional design consolidates what would otherwise require separate management systems for each voice assistant, reducing overall system complexity while maintaining the benefits of multiple assistants.
2Loss of information
If multiple voice assistants operate simultaneously, then the information coverage and response accuracy is improved, but the ease of operation deteriorates due to switching difficulties
Solution Approach 1:
The system implements self-service through automated voice assistant selection and switching. The voice assistant manager continuously monitors user interactions, voice patterns, and context to automatically determine which assistant should handle each command, eliminating the need for users to manually switch between assistants. The system also provides self-explanation capabilities, informing users why a particular assistant was selected, thereby maintaining ease of operation while achieving comprehensive information coverage through multiple assistants.
Solution Approach 2:
The patent implements dynamic voice assistant selection where the system adapts to changing user needs, contexts, and preferences in real-time. The voice assistant manager dynamically adjusts which assistants are active, how they are weighted, and how their responses are synthesized based on current situational factors. This dynamic approach allows seamless transitions between assistants without requiring user intervention, maintaining operational simplicity while leveraging the full information coverage of multiple assistants.
3Productivity
If a single voice assistant is used, then the device complexity is reduced, but the productivity and information variety from voice commands is limited
Solution Approach 1:
The patent segments the voice assistant system into distinct functional modules: a voice assistant manager that handles high-level decision-making, individual voice assistant modules that specialize in specific domains or functions, and a response synthesis module that integrates outputs. This segmentation allows the system to leverage the specialized capabilities of multiple assistants for improved productivity and information variety while managing complexity through modular architecture, where each component has a defined responsibility and can be independently optimized or replaced.
Data Source
AI summary
An electronic apparatus includes: a display; a memory configured to store a plurality of assistance instructions respectively corresponding to a plurality of voice assistants; and at least one processor operatively connected to the display and the memory, wherein the at least one processor is configured to, based on a user voice command, generate response information by using the at least one voice assistant and control the display to display the generated response information, based on a predetermined voice command received during a first voice assistant operation, activate a second voice assistant operation corresponding to the predetermined voice command.