Sleep State Estimation Using Supervised Learning on Behavior History
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating a user's health state based on their behavior history have limitations in performance and accuracy.
Innovation Solution
A computer program and information processing device that acquire behavior data from users and input it into a supervised learning model to estimate the user's sleep state, including sleep properties, rhythms, times, and categories, and also predict menopause symptom states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods are used to estimate health state based on behavior history, then the system is simple to implement, but the estimation accuracy and performance are insufficient
Solution Approach 1:
The patent transforms the estimation approach by changing the parameter representation from simple behavior categories to detailed behavioral parameters including time, location, and type information. The behavior history is encoded with multiple dimensions (behavior type, timing, frequency, location) that are fed into the learning model, enabling more precise health state estimation while maintaining a systematic processing framework.
Solution Approach 2:
The patent replaces traditional rule-based or statistical estimation methods with a machine learning model (neural network or similar algorithm). This substitution enables the system to automatically learn complex patterns from behavioral data and provide more accurate health state predictions, overcoming the limitations of simpler methods while managing complexity through automated processing.
2Measurement precision
If detailed behavior data is collected to improve estimation accuracy, then the measurement precision improves, but the data processing complexity and computational load increase
Solution Approach 1:
The patent segments the behavior history into distinct behavioral units with specific attributes (type, time, location, frequency). Each behavior is broken down into manageable parameters that can be independently processed and analyzed. This segmentation allows the learning model to efficiently handle detailed data without being overwhelmed by raw unstructured information.
Solution Approach 2:
The patent performs preliminary processing of behavior data by organizing and structuring it before input to the learning model. Behavior histories are pre-processed to extract relevant features, categorize actions, and standardize formats. This preliminary action reduces the computational burden on the main estimation algorithm while preserving the detailed information needed for accurate predictions.
Data Source
AI summary
Provided is a computer program, an information processing device, and a method that are used to estimate a health state of a target user based on a history of behaviors executed by the target user, and have at least partially improved performance.According to one embodiment, a computer program can cause, by being executed at least one processor, the at least one processor to function to: acquire target behavior data for identifying a history of behavior executed by a target user; and output, from an estimation model generated by executing supervised learning, target sleep state data for identifying a sleep state of the target user, the target sleep state data including at least one of target property data for identifying a sleep property of the target user, target rhythm data for identifying a sleep rhythm of the target user, target time data for identifying a sleep time of the target user, and target category data for identifying a sleep category to which the target user belongs, by inputting the target behavior data to the estimation model.