Electronic Device Response Handling with Extended Intent Database
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AI-based voice assistant systems struggle with ambiguous user intents, leading to reduced performance and user dissatisfaction due to incorrect responses, and require extensive training data to handle all potential questions, which is costly and time-consuming.
Innovation Solution
An electronic device extends its database by analyzing previous responses to ambiguous user intents and uses this extended database to provide appropriate responses, improving user experience even when the intent is unclear.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system uses a traditional database to provide answers to user queries, then the system can provide accurate responses to clear intents, but the system fails to handle ambiguous intents and provides error-handling phrases instead of desirable answers
Solution Approach 1:
The system performs preliminary analysis of responses by extracting intent information from previously provided responses and storing it in an extended database. This preliminary action enables the system to handle ambiguous intents in future queries without requiring real-time analysis during user interaction.
Solution Approach 2:
The system uses feedback from previously provided responses to improve its handling of ambiguous intents. By analyzing past responses and extracting intent information, the system learns from previous interactions and uses this knowledge to better handle similar ambiguous queries in the future.
2Adaptability or versatility
If the system predicts all potential questions to understand all intents of utterances, then the system can comprehensively handle user queries, but it requires a great amount of cost and time to learn all utterances
Solution Approach 1:
The system performs self-service by automatically analyzing its own previously provided responses to extract intent information and build the extended database. This self-service approach eliminates the need for manual training data collection and processing, significantly reducing the time and cost required to handle diverse intents.
Solution Approach 2:
The system continuously analyzes and adds to the extended database with each interaction, enabling ongoing learning without requiring periodic retraining. This continuous action allows the system to progressively expand its capability to handle ambiguous intents while maintaining performance.
3Device complexity
If the system provides error-handling phrases for ambiguous intents, then the system maintains simplicity in processing, but it reduces user experience and system performance
Solution Approach 1:
The extended database serves multiple functions: it stores intent information from clear queries, provides responses to ambiguous intents, and maintains the original database for clear query handling. This multi-functionality allows the system to improve user experience without significantly increasing processing complexity.
Data Source
AI summary
An electronic device includes: a memory including instructions and a processor electrically connected to the memory and configured to execute the instructions. When the instructions are executed by the processor, the processor is configured to: receive a voice signal corresponding to an utterance; match the voice signal with at least one of a plurality of defined intents; and when the at least one and the voice signal do not match, provide a response corresponding to the utterance based on an extended database (DB) that includes a result of analyzing responses provided in response to utterances matched to the at least one.