Conversation Recovery via Alternative Topic Recommendation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems often result in undesirable user experiences when they are unable to understand user inputs or perform requested actions, leading to unresponsive actions and error messages.
Innovation Solution
The system engages users by determining likely user intent and querying them about performing alternative actions, recommending topics based on context analysis, and providing users with options to continue the conversational exchange.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the speech processing system strictly follows user input interpretation, then processing accuracy is improved, but user experience deteriorates when the system cannot understand or perform requested actions
Solution Approach 1:
The system implements feedback by querying the user about alternative actions when the original intent cannot be satisfied. The error message includes a question asking the user if they would like to perform an alternative action, creating a feedback loop that improves user experience while maintaining processing accuracy for understood inputs
Solution Approach 2:
The system changes the parameter of response generation by dynamically selecting between different response types based on intent satisfaction. When original intent cannot be satisfied, the system transitions from providing only error messages to providing error messages with alternative action recommendations, changing the nature of the system's response parameter
2Ease of operation
If the system provides detailed error messages and alternative actions, then user experience is improved, but system complexity increases
Solution Approach 1:
The system performs preliminary action by pre-generating alternative actions and their descriptions before presenting them to the user. The error message component is prepared in advance with alternative actions already identified and described, reducing the complexity of real-time decision-making while improving user experience
Solution Approach 2:
The error message acts as an intermediary between the system's intent satisfaction failure and the user. Instead of directly failing, the system uses the error message as a mediator to communicate the failure and simultaneously offer alternative actions, reducing system complexity by handling multiple functions through a single intermediary component
3Productivity
If the system recovers from errors by suggesting alternative actions, then productivity is improved, but loss of information increases as original user intent may be abandoned
Solution Approach 1:
The system applies preliminary anti-action by anticipating the potential loss of original user intent and counteracting it through the error message design. The error message explicitly states that the alternative action is being suggested because the original intent cannot be satisfied, preserving the information about what the user originally wanted while enabling recovery through alternatives
Data Source
Figure 1A
Figure 1B
Figure 2A
AI summary
Techniques for performing conversation recovery of a system/user exchange are described. In response to determining that an action responsive to a user input cannot be performed, a system may determine a topic to recommend to a user. The topic may be unrelated to the original substance of the user input. The system may have access to various data representing a context in which a user provides an input to the system. The system may use these inputs and various data at runtime to make a determination regarding whether a user should be recommended a topic, as well as what that topic should be. The system may cause a question be output to the user, with the question asking the user about the topic, for example whether the user would like a song played, whether the user would like to hear information about a particular individual (e.g., artist), whether the user would like to know about a particular skill (e.g., a skill having a significantly high popularity among users of the system), or whether the user would like to know about some other topic. If the user responds affirmatively to the recommended topic, the system may pass the user experience off to an appropriate component of the system (e.g., one that is configured to perform an action related to the topic). If the user responds negatively, does not respond at all, or the system is unsure whether the user's response was affirmative or negative, the system may cease interaction with the user, thereby enabling the user to interact with the system as the user desires.