Emotion Recognition System with Credibility Algorithm
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing emotion recognition systems rely on subjective manual user feedback, which can lead to biased and inaccurate emotion recognition due to user inconsistencies and outliers, limiting the accuracy and reliability of emotion detection and potentially corrupting databases.
Innovation Solution
An emotion recognition system utilizing a Valence-Arousal model with a credibility algorithm to distinguish and discredit outlier feedback, combining actual user input measurements from devices like EEG and ECG with AI to provide objective emotion recognition, and allowing continuous learning and refinement of emotion definitions based on user feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual user feedback is used for emotion recognition, then the system can learn from user experiences, but the accuracy and reliability deteriorate due to user inconsistencies and outliers
Solution Approach 1:
The system implements a feedback loop where user responses to emotion recognition results are collected and used to iteratively improve the AI model. The credibility algorithm processes this feedback to identify reliable patterns while filtering out outliers, allowing the system to adapt and learn from user experiences while maintaining accuracy through continuous refinement of emotion definitions and recognition thresholds.
2Quantity of substance
If all user feedback is accepted for training, then the database grows with more data, but the data quality deteriorates due to inclusion of outliers and incorrect entries
Solution Approach 1:
The credibility algorithm extracts and identifies outlier feedback from the user responses by analyzing patterns and comparing against established emotion definitions. Reliable feedback is separated from unreliable feedback, allowing the system to maintain a growing training database while filtering out incorrect or anomalous entries that would degrade data quality.
Solution Approach 2:
The credibility algorithm acts as an intermediary between raw user feedback and the training database. It processes user responses through credibility assessment, using AI analysis to determine whether feedback should be accepted or rejected, thereby mediating between data quantity accumulation and quality maintenance.
3Ease of operation
If subjective manual emotion descriptions are used, then the system can capture user self-perception, but the measurement precision deteriorates due to qualitative vs quantitative mismatch
Solution Approach 1:
The system transforms subjective qualitative emotion descriptions into objective quantitative measurements by using AI analysis on physiological signals (EEG, ECG, GSR). The credibility algorithm compares user self-reports against these objective measurements, adjusting and refining emotion definitions to bridge the gap between subjective perception and objective data, thereby improving measurement precision while preserving ease of user operation.
Data Source
AI summary
The present invention relates to a system and method of emotion recognition. An emotion recognition system may utilize a Valence-Arousal factor along with training data. The training data may exist as emotions assigned to actual measurements of user inputs. The actual measurements of user inputs may be assigned to a plurality of points on the Valence-Arousal model. A user input acquisition device may be used to collect actual measurements of user inputs. A processor may utilize an algorithm to assign user emotions based on the training data. A user may provide feedback on the assigned user emotions, and the training data may be updated based on the user feedback, depending on whether the user feedback is considered an outlier to the training data.