Real-Time Personality Prediction via AU Intensity Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting user personality fail to reflect changing user characteristics in real-time, as they do not effectively incorporate time-series data from facial expressions and actions.
Innovation Solution
A personality prediction method that acquires personality indicators through psychology questionnaires and correlates them with time-series data from facial expressions and actions, using a trained model to predict personality changes in real-time, specifically by quantifying the contribution of AU intensities to personality indicators and normalizing them for input into a personality prediction model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If personality prediction is performed using traditional methods without time-series data, then the prediction process is simpler, but the prediction accuracy and real-time responsiveness deteriorate
Solution Approach 1:
The system performs preliminary actions by collecting and storing time-series data (facial expressions, actions, voice) and personality indicators in advance through multiple acquisition units. This pre-collected data is then used by the prediction model to achieve accurate real-time personality prediction without complex processing during the actual prediction moment
Solution Approach 2:
The patent introduces a personality prediction model as an intermediary component that processes time-series data and personality indicators. This model acts as a mediator between raw data acquisition and final personality prediction, simplifying the overall system architecture while enabling accurate real-time prediction through learned correlations
2Measurement precision
If direct image analysis is performed for personality prediction, then comprehensive feature extraction is achieved, but calculation time increases
Solution Approach 1:
The system extracts specific key features (AU intensities, facial expressions, actions, voice characteristics) from images and other data sources, rather than performing comprehensive direct image analysis. This selective extraction of relevant features maintains prediction accuracy while significantly reducing calculation time and computational resources required
Solution Approach 2:
The patent segments the personality prediction process into distinct components: acquiring external features (facial expressions, actions, voice), acquiring personality indicators, and training/predicting using a personality prediction model. This segmentation allows parallel processing and optimization of each component, reducing overall calculation time while maintaining comprehensive feature analysis
Data Source
AI summary
There is provided a user personality prediction method using pre-obtained personality indicators and time-series information. According to an embodiment, a personality prediction method may acquire personality indicators representing personalities of a user, may acquiring external features of the user as time-series data, may train a personality prediction model with correlations between the acquired external features and the personality indicators, and may predict personality indicators of the user from the external features of the user by using the trained personality prediction model. Accordingly, a personality of a user is predicted in real time based on external features extracted in real time, and hence, personality prediction may be performed flexibly in response to a subtle change in AU intensities acquired as time-series data.