Voice Assistant Server Routing Across Multiple Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face inconvenience when multiple devices with voice assistants are present, as they need to remember different keywords to activate each device, leading to confusion and inefficiency, especially as the number of devices increases in IoT environments.
Innovation Solution
A voice assistant system where multiple devices communicate with a server apparatus to record and transmit user speech data, allowing the server to perform voice recognition and select the appropriate device for output based on predetermined criteria such as usage state and output unit performance, eliminating the need for specific keywords.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If each device has its own unique voice assistant with device-specific keywords, then each device can independently perform voice assistant functions, but users need to memorize multiple different keywords for different devices, increasing operational complexity
Solution Approach 1:
The patent implements a universal keyword system where a single keyword (e.g., 'Hey Siri') can activate the voice assistant on multiple different devices simultaneously. The server apparatus receives speech data from multiple devices and performs unified voice recognition, allowing one keyword to serve multiple functions across different device types and manufacturers.
Solution Approach 2:
The patent introduces a server apparatus as an intermediary between multiple devices and the voice recognition system. The server receives speech data from various devices, performs centralized voice recognition processing, and returns results to the appropriate devices. This intermediary eliminates the need for each device to have its own unique keyword system while maintaining device independence.
2Adaptability or versatility
If multiple devices are present in a user's room, then more devices are available for voice assistant functions, but users hesitate in determining which device to use, increasing decision time and reducing efficiency
Solution Approach 1:
The patent enables the system to automatically determine which device should receive the voice assistant response without user intervention. The server apparatus analyzes speech data from multiple devices, identifies the appropriate target device based on predetermined standards (such as device proximity, current usage state, or output capabilities), and routes the response accordingly. This self-service mechanism eliminates the need for users to manually select a device.
3Ease of operation
If a unified keyword system is implemented across multiple devices, then users can easily activate voice assistants without memorizing multiple keywords, but determining which device should process the speech and output the response becomes more complex
Solution Approach 1:
The patent extracts the complex device selection logic from the individual devices and centralizes it in the server apparatus. Each device simply needs to transmit speech data when activated by the universal keyword, while the server handles the sophisticated logic of determining which device should process the speech and output the response based on various criteria such as device state, proximity, and capabilities.
Data Source
AI summary
A voice assistant system includes a server apparatus performing voice assistant and a plurality of devices, in which the server apparatus and the devices are communicatively connected to each other. The plurality of devices each records the same user's speech through a microphone, and then transmits recorded data of the same user's speech to the server apparatus. The server apparatus receives the recorded data transmitted from each of the plurality of devices, and then voice-recognizes two or more of the received recorded data in accordance with a predetermined standard to thereby interpret the contents of the user's speech to perform the voice assistant.