Mood Score Calculation via Terminal Operation Interval Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating mental health conditions in office workers are burdensome and inefficient, particularly for daily mood assessments, which are essential for early detection and prevention of mental illness.
Innovation Solution
A mood score calculation system that utilizes a processor and memory to analyze operational interval time data from user terminals, calculating statistical features such as fractal dimension and scaling-law index from keyboard and mouse operations to determine a user's mood score without requiring their attention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mood evaluation methods (POMS, BDI-II) are used, then mental health conditions can be assessed, but subjects bear a heavy burden due to dozens of questions required each time
Solution Approach 1:
The system uses terminal operation data that users generate automatically during their normal work activities. The mood evaluation is performed automatically based on these operations without requiring user participation, making the system self-service in nature. This resolves the contradiction by eliminating the burden of answering questions while maintaining assessment capability through objective operational analysis.
Solution Approach 2:
The patent replaces the mechanical questionnaire-based assessment system with an automated system that analyzes terminal operation data. Instead of requiring users to manually answer mood questions, the system automatically calculates mood scores based on keyboard input speed, backspace key frequency, and other operational metrics, substituting the manual evaluation process with automated computational analysis.
2Adaptability or versatility
If fundamental indicators like keyboard input speed and backspace key frequency are used for machine learning, then training data can be acquired, but the mental condition is not determined significantly based on these indicators alone
Solution Approach 1:
The patent extends the evaluation beyond basic keyboard and mouse operations to include a comprehensive set of terminal operations such as application switching, window management, scrolling, and media control. This multi-functional approach captures diverse aspects of user behavior and mental state, improving determination accuracy while maintaining the machine learning framework's adaptability.
Solution Approach 2:
The patent introduces temporal dimensionality by analyzing the timing and sequence of operations, calculating inter-operation time intervals and their statistical features. This adds a time-based dimension to the analysis, transforming static operation counts into dynamic temporal patterns that significantly improve mental condition determination accuracy.
3Ease of operation
If operation logs are analyzed to estimate mood, then non-intrusive measurement is achieved, but significant estimation accuracy based on operational interval time fluctuation is required
Solution Approach 1:
The patent transforms raw operation logs into meaningful mood indicators by calculating statistical parameters of inter-operation time intervals, including mean, standard deviation, skewness, and kurtosis. This parameter transformation converts simple timing data into comprehensive temporal pattern metrics that accurately reflect mental state while requiring no user attention during data collection.
Data Source
AI summary
A mood score calculation system includes a processor and a memory. The memory is configured to hold relationship information on a relationship between a mood score of a user and a statistical feature for indicating fluctuation of operational interval time of a user terminal. The processor is configured to acquire an operation log of a first user terminal. The processor is configured to calculate, from the operation log, a value of a statistical feature for indicating fluctuation of operational interval time of the first user terminal. The processor is configured to determine a mood score of a user of the first user terminal based on the value of the statistical feature and the relationship information and output the mood score.