Voice Assistant Failover Using Cached Audio Request Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In situations where multiple automated assistants are present on the same device or nearby devices, a user's request may be incorrectly directed to an assistant that fails to handle it, leading to suboptimal or inaccurate responses.
Innovation Solution
An automated assistant can detect failures in other assistants and offer to handle the request, either automatically or upon user request, by caching user input and processing it to provide a fulfilling response.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple automated assistants are running on the same device or nearby devices, then the system provides more assistant options and capabilities, but the risk of request misdirection and assistant failure increases
Solution Approach 1:
The patent introduces a failover detection mechanism that acts as an intermediary between multiple automated assistants. When one assistant fails to properly handle a request, the failover mechanism detects this failure and redirects the request to an alternative assistant, ensuring reliable request handling while maintaining multiple assistant options.
Solution Approach 2:
The system implements feedback loops where automated assistants monitor each other's performance and request handling outcomes. When a failure is detected in one assistant, this feedback triggers a failover to another assistant, creating a self-correcting system that maintains reliability despite having multiple assistants.
2Reliability
If an automated assistant continuously monitors for failures in other assistants, then the system reliability improves, but the computational resources and processing time increase
Solution Approach 1:
Instead of continuous monitoring, the failover detection mechanism operates periodically or event-driven. The assistant monitors for failures at specific intervals or when triggered by certain conditions, reducing computational overhead while maintaining adequate detection capability.
Solution Approach 2:
The system performs preliminary failure detection by analyzing request outcomes and assistant responses. By detecting failures through outcome analysis rather than continuous monitoring, the system reduces processing resources while maintaining reliability.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Techniques are described herein for detecting and handling failures in other automated assistants. A method includes: executing a first automated assistant in an inactive state at least in part on a computing device operated by a user; while in the inactive state, determining, by the first automated assistant, that a second automated assistant failed to fulfill a request of the user; in response to determining that the second automated assistant failed to fulfill the request of the user, the first automated assistant processing cached audio data that captures a spoken utterance of the user comprising the request that the second automated assistant failed to fulfill, or features of the cached audio data, to determine a response that fulfills the request of the user; and providing, by the first automated assistant to the user, the response that fulfills the request of the user.