Computational Assistant Delay Feedback to Prevent Duplicate Utterances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computational assistants often fail to inform users when task completion will be delayed, leading to duplicate utterances and increased processing requirements, power consumption, and ambiguity in user interactions.
Innovation Solution
A computational assistant outputs a synthesized voice message informing users when task completion will not be immediate, preventing duplicate utterances and reducing processing requirements and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the computational assistant performs tasks without informing users of delays, then the system operates automatically with minimal user intervention, but users may restate utterances causing duplicate task performance and increased processing requirements
Solution Approach 1:
The system provides feedback to users by outputting synthesized voice data that informs them when task completion will not be immediate. This feedback loop prevents users from restating utterances by keeping them informed about task status, thereby eliminating duplicate task performance and improving processing efficiency while maintaining automatic operation
2Reliability
If the computational assistant waits for task completion before responding, then processing accuracy is maintained, but user interaction time increases and users may become uncertain about system functionality
Solution Approach 1:
The system performs preliminary action by informing users in advance that task completion will not be immediate. By outputting synthesized voice data that communicates expected delay before the task actually completes, the system maintains processing accuracy while reducing user uncertainty and perceived waiting time, allowing users to understand the system is still working
3Reliability
If the computational assistant processes all user utterances, then no tasks are missed, but power consumption and processing requirements increase
Solution Approach 1:
The system uses feedback to prevent redundant processing by informing users when a task is already being performed. The synthesized voice output that communicates task status prevents users from restating utterances, thereby maintaining complete task completion while reducing duplicate processing and lowering power consumption
Solution Approach 2:
The system provides self-service by automatically monitoring its own task status and communicating this information to users through synthesized voice output. This self-monitoring and communication capability eliminates the need for users to repeatedly ask about task status, reducing unnecessary processing and energy consumption while ensuring no tasks are missed
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach reduces duplicate task performance and ambiguity by informing users of delayed responses, thus optimizing user interactions and resource utilization.
Implementation Method 1
receive, via a microphone, acoustic input that corresponds to a user utterance
Implementation Method 2
output, with one or more speakers, synthesized voice data that informs the requesting user
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; identifying, based on the utterance, a task to be performed by the computational assistant; responsive to determining, by the computational assistant, that complete performance of the task will take more than a threshold amount of time, outputting, for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs a user of the computing device that complete performance of the task will not be immediate; and performing, by the computational assistant, the task.