Smartphone Inactivity Clustering for Sleep State Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for evaluating sleep disturbances rely on self-reported smartphone usage, which is often inaccurate, particularly for individuals with problematic usage, and there is a need for objective measures to correlate with mental and physical health symptoms.

Innovation Solution

Utilizing passively collected smartphone data to characterize patterns of usage and inactivity, identifying periods of inactivity correlated with sleep periods, and assessing their relationship with clinical outcomes such as sleep disturbances and mental health symptoms, using machine learning models to predict future states and generate actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If self-reported smartphone usage data is collected, then data collection is simple and easy to implement, but the accuracy and reliability of sleep disturbance evaluation deteriorates

Engineering Contradiction:

Improvedata collection simplicityVSAvoidsleep disturbance evaluation accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary mechanism (smartphone sensor system) that automatically collects objective usage data without requiring user reporting. The system uses sensors to detect smartphone interactions, screen on/off events, and usage patterns, transforming subjective self-reporting into objective automated measurement, thereby resolving the contradiction between ease of data collection and measurement accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual/mechanical system of self-reporting with an automated electronic sensing system. Smartphone sensors (accelerometers, gyroscopes, screen sensors) automatically detect and record usage behavior, substituting human memory and honesty with mechanical detection, thus improving measurement precision while maintaining ease of operation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If objective smartphone usage data is collected through automated sensing, then measurement precision improves, but device complexity and data processing requirements increase

Engineering Contradiction:

Improveusage data accuracyVSAvoiddata processing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential features needed for sleep disturbance evaluation from the complex smartphone data stream. It focuses on key metrics such as total usage time, usage patterns during bedtime hours, and inactivity periods, separating these critical measurements from the vast amount of irrelevant data, thereby reducing processing complexity while maintaining high measurement precision

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the continuous smartphone usage data into discrete, analyzable units such as usage episodes, inactivity periods, and bedtime patterns. By dividing the data stream into meaningful segments and applying specific analysis algorithms to each, the system manages complexity while preserving measurement accuracy

Inventive Principle:

Principle #1Segmentation

3Loss of information

If detailed interaction data is collected and analyzed, then insight quality improves, but loss of time for data processing increases

Engineering Contradiction:

Improvebehavioral pattern insight qualityVSAvoiddata processing time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent performs preliminary processing and filtering of smartphone data as it is collected, organizing data into structured formats and pre-identifying key patterns such as usage episodes and inactivity periods. This preliminary action reduces the complexity of subsequent analysis, enabling comprehensive insight generation with reduced processing time

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12481724B1Systems and methods for determining states using run-length encoders, binarized bins, and k-means cluster models

Publication Date: 2025.11.25 MINDSTRONG INC

AI summary

In some embodiments, a method includes receiving longitudinal interaction data. The longitudinal interaction data is sorted into a plurality of bins. Using a run-length encoder, at least one inactivity period indication is generated, and an inferred period indication is generated based on the at least one inactivity period indication. The method also includes (1) generating, based on the plurality of bins, a plurality of activity metrics and (2) sorting, using a clustering model and based on the plurality of activity metrics, the plurality of bins to produce an inactivity cluster. An expected period indication and a characteristic value are generated based on (1) the inferred period indication and (2) the expected period indication. A series of actions is determined by providing, via the processor, the characteristic value as input to a machine learning model.