Voice Dialog Device Emotion Estimation Discrepancy Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice dialog systems face challenges in accurately estimating user emotions due to discrepancies between different estimation methods, leading to uncertain response creation.
Innovation Solution
A voice dialog device with multiple estimation units that recognize user voice and facial expressions, and a response unit that makes inquiries to resolve discrepancies by confirming the accuracy of emotion estimation results, using past estimation history and weighting methods to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple estimation units estimate emotion by different methods, then the comprehensiveness of emotion recognition is improved, but the reliability of emotion estimation deteriorates due to discrepancies between different methods
Solution Approach 1:
The system introduces feedback by making the estimation unit inquire with the user when discrepancies occur between different estimation methods. The user's response serves as feedback to confirm or correct the estimated emotion, thereby resolving the reliability issue while maintaining the comprehensiveness benefit of multiple estimation methods
Solution Approach 2:
The inquiry mechanism acts as an intermediary between the multiple estimation units and the final emotion determination. When discrepancies arise, the intermediary inquiry process mediates by seeking user confirmation, thus resolving the conflict between different estimation results and improving reliability
2Measurement precision
If the system makes inquiries to confirm emotion estimation, then the accuracy of emotion recognition is improved, but the time required for response creation increases
Solution Approach 1:
The system applies partial action by making inquiries only when necessary - specifically when discrepancies occur between different estimation methods. When estimation results are consistent, no inquiry is made, thus avoiding unnecessary time loss while maintaining high accuracy when needed
3Reliability
If the system inquires with the user to resolve discrepancies, then the reliability of emotion estimation is improved, but the complexity of the response creation process increases
Solution Approach 1:
The response creation process is segmented into distinct stages: initial emotion estimation by multiple methods, discrepancy detection, conditional inquiry execution, and final response generation. This segmentation makes the complex process more manageable and systematic, reducing the perceived complexity while maintaining reliability
Data Source
AI summary
A voice dialog device, comprises a voice processing unit configured to obtain a voice pronounced by a user and a result of recognizing the voice; a plurality of estimation units configured to estimate emotion of the user by different methods; and a response unit configured to create a response sentence, based on results of estimating the emotion of the user, and provide the response sentence to the user, wherein when a discrepancy exists between the results of estimating the emotion of the user by the plurality of estimation units, the response unit makes an inquiry to the user, and determines which estimation result is to be adopted, based on content of an obtained response.