Multi-Virtual Assistant Framework for Voice Query Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in accessing optimal virtual assistant services across different categories due to the limitations of default virtual assistants on their devices, including impracticality of carrying multiple devices, battery life issues, and the need for multiple devices to access diverse information sources effectively.
Innovation Solution
A communication apparatus that captures user voice queries and sends them to multiple virtual assistant services via a network, receiving and comparing responses based on preference rules to identify the most relevant and accurate answer, which is then outputted, eliminating the need for multiple devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If users carry multiple computing devices to access different virtual assistant services, then access to diverse information sources is improved, but device portability and user convenience deteriorate
Solution Approach 1:
The patent combines multiple virtual assistant services into a single computing device by implementing a framework that can simultaneously interact with multiple virtual assistant services (e.g., Siri, Google Assistant, Alexa) through one device. This merging approach allows users to access diverse information sources without carrying multiple devices, resolving the contradiction between versatility and portability.
Solution Approach 2:
The computing device is designed with universal capabilities to interface with multiple different virtual assistant services through a common framework. This multi-functionality enables the single device to perform the roles of multiple specialized devices, allowing users to access various information sources while maintaining device portability.
2Adaptability or versatility
If users carry multiple computing devices to access different virtual assistant services, then access to diverse information sources is improved, but battery consumption increases
Solution Approach 1:
By merging multiple virtual assistant service interactions into a single computing device, the system eliminates the need to power multiple separate devices simultaneously. The single device framework manages communications with multiple virtual assistant services, reducing overall battery consumption while maintaining access to diverse information sources.
3Ease of operation
If a single default virtual assistant service is used, then device simplicity is maintained, but response quality and accuracy for specific categories deteriorate
Solution Approach 1:
The system implements dynamic service selection where the framework can adaptively choose which virtual assistant service to use based on the query category and performance metrics. This dynamic approach allows the system to maintain simplicity for the user while internally optimizing for response quality by routing different types of queries to the most appropriate virtual assistant service.
Solution Approach 2:
The framework incorporates feedback mechanisms that evaluate the performance of different virtual assistant services across various categories. Based on this feedback, the system learns and adapts to select the most accurate service for each query type, thereby improving response quality while maintaining a simple user interface that requires no user configuration.
4Adaptability or versatility
If multiple virtual assistant services are integrated into one device, then access to diverse information sources is improved, but system complexity increases
Solution Approach 1:
The patent introduces an intermediary framework that acts as a mediator between the user and multiple virtual assistant services. This framework layer handles the complexity of managing multiple service connections, authentication, and response integration, while presenting a simple unified interface to the user. The intermediary absorbs the system complexity, allowing the device to access diverse information sources without exposing complexity to the user.
Data Source
AI summary
Microphone data indicative of a user spoken phrase is captured utilizing the microphone at a communication apparatus. At least a portion of the microphone data is sent to a set of computing devices. A response phrase determined at a virtual assistant service is received from each of the computing devices. A preferred response phrase is identified among the set of received response phrases according to a preference rule. The preferred response phrase is caused to be output via a speaker at the communication apparatus.


