Voice Assistant Transient Error Handling via Feedback and Retry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice-controlled electronic devices often fail to effectively communicate transient errors to users, leading to frustration as they either do not respond or instruct users to try again without resolving the issue, resulting in a less than satisfying user experience.
Innovation Solution
The system provides conversational exchanges with users by informing them of errors and continuing to attempt to fulfill requests, using audio and visual cues to keep users informed, and by attempting alternative methods to complete tasks, such as searching for music or processing orders, thereby reducing confusion and system load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the device does not respond to transient errors or simply instructs users to try again, then the system remains simple, but user experience deteriorates due to frustration and confusion
Solution Approach 1:
The system provides real-time feedback to users about transient errors by communicating the error status and continuing to attempt request fulfillment. This feedback loop keeps users informed about the system's state without requiring them to initiate multiple requests, thereby improving user experience while managing complexity through automated error handling.
Solution Approach 2:
The system automatically handles transient errors by detecting them and continuing to attempt request fulfillment without user intervention. This self-service approach resolves errors in the background while keeping users informed, improving reliability without significantly increasing user-facing complexity.
2Reliability
If the device communicates transient errors and continues attempting to fulfill requests, then user experience improves through clear status updates, but system load increases due to repeated processing attempts
Solution Approach 1:
The system performs a limited number of retry attempts for transient errors rather than indefinitely repeating requests. This partial action approach balances user experience improvement through error communication with system load management by setting reasonable limits on retry frequency and duration.
Solution Approach 2:
The system implements periodic retry attempts with appropriate intervals rather than continuous immediate retries. This periodic approach allows the system to communicate errors to users while managing load through timed retry cycles, preventing overwhelming system resources while maintaining persistent attempt to fulfill requests.
3Reliability
If the device provides detailed error communication and continues retrying, then user engagement improves through clear status updates, but response time increases due to multiple processing attempts
Solution Approach 1:
The system communicates error status to users immediately when transient errors are detected, rather than waiting for all retry attempts to complete. This preliminary communication keeps users engaged and informed about the system's state without requiring them to wait for the full retry process, thereby reducing perceived response time while maintaining engagement.
Solution Approach 2:
The system maintains continuous attempt to fulfill requests in the background while providing periodic status updates to users. This continuity ensures that useful action (request fulfillment) persists without interruption, while scheduled communications provide engagement without significantly extending overall response time.
Data Source
AI summary
This patent application is directed to interaction between a voice-controlled device and a language processing system that processes user requests. The requests can be requests for information or they can be requests to control a device, such as “Turn on the bedroom light.” The disclosure includes various embodiments for trying to resolve system errors in a manner that provides an improved customer experience. The improvements described include the capability of the overall system to recognize that an error has occurred while attempting to fulfill a request that was submitted as part of a recognized spoken utterance. Instead of simply doing nothing, or of playing a message to the customer to try again later, the system would now let the user know it was still processing the request while making another attempt at fulfilling the request. This requires the system to retain the entire utterance until it is determined that the request has been fulfilled or that the request cannot be fulfilled, so that the customer does not have to repeat the request a second (or third) time. The feedback to the customer can be audio, visual, or a combination. For example, the Echo could play an audio message “please stand by, I'm still working on your request” while at the same time, the colored ring could turn green to indicate all is well and processing is continuing.