Emotion Estimation System Using Adaptive Sensor Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current emotion estimation systems fail to accurately assess user emotions in varying situations due to limitations in integrating external and biological information effectively, leading to inconsistent emotion detection.
Innovation Solution
An emotion estimating system that utilizes a learning model to combine external information from environmental sensors and biological data from biosensors, adjusting weightings based on the user's situation to provide accurate emotion estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fixed weightings are applied to external and biological information, then the system structure is simple, but emotion estimation accuracy deteriorates in varying situations
Solution Approach 1:
The patent applies dynamics by making the weighting coefficients adaptive rather than fixed. The weighting applied to external information and biological information dynamically changes based on the detected situation around the user. This allows the system to optimize emotion estimation accuracy for different situations without requiring completely different systems for each scenario.
Solution Approach 2:
The patent changes the parameter of weighting coefficients based on situation detection. By adjusting the weighting values according to the user's situation (e.g., private vs. public, work vs. leisure), the system adapts its information integration strategy to maintain high accuracy across varying contexts while using a single unified system.
2Measurement precision
If situation-based weighting adjustment is implemented, then emotion estimation accuracy improves, but system complexity increases
Solution Approach 1:
The patent implements preliminary action by pre-defining multiple sets of weighting coefficients corresponding to different situation types. Rather than calculating optimal weights in real-time, the system prepares weighting schemes in advance for various situations (private, public, work, leisure, etc.), allowing quick selection based on detected situation without complex real-time optimization.
Solution Approach 2:
The system uses feedback from situation detection to select appropriate weighting coefficients. The situation detector continuously monitors the user's environment and provides feedback about the current situation type, which then determines which pre-defined weighting scheme to apply, creating a closed-loop adaptive system.
Data Source
AI summary
An emotion estimating system includes a learning model and an estimation unit. The learning model accepts external information and biological information as input, and outputs an emotion of a user. The estimation unit changes a weighting applied to external information about the user detected by a first detector and a weighting applied to biological information about the user detected by a second detector in accordance with a situation around the user, and estimates the emotion output as a result of inputting external information and biological information changed by the respective weightings into the learning model as the emotion of the user.