Activity Complexity Model for Health Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to accurately and efficiently determine condition-specific health, cognitive, and behavioral anomalies based on daily user activities, lacking effective monitoring and analysis techniques.
Innovation Solution
A method and system that monitor daily activities, determine activity complexity datasets, create user and reference complexity models, calculate distance vectors, and use machine learning models to identify anomalies and conditions, enabling tracking and trend analysis of user conditions over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive monitoring of daily activities is implemented, then detection precision of health, cognitive and behavioral anomalies is improved, but device complexity and computational requirements increase
Solution Approach 1:
The system segments the monitoring process into distinct modules: activity detection module, complexity calculation module, model comparison module, and anomaly detection module. Each module processes specific aspects of the data independently, reducing overall system complexity while maintaining comprehensive monitoring capabilities. The activity complexity datasets are segmented by activity type, allowing targeted analysis of specific behaviors.
Solution Approach 2:
The patent introduces activity complexity datasets as intermediary representations that bridge raw sensor data and final anomaly detection. These datasets serve as a compressed, processed intermediate form that captures essential complexity information without requiring the entire raw data to be processed through all analysis stages, thereby reducing computational complexity while preserving detection precision.
2Reliability
If continuous monitoring over extended periods is implemented, then reliability of condition detection is improved, but loss of time and computational resources increase
Solution Approach 1:
The system performs preliminary processing by pre-computing activity complexity datasets during the monitoring period, and pre-establishing reference models before actual anomaly detection is needed. This allows the heavy computational tasks to be performed in advance or in parallel, reducing the time required for real-time analysis while maintaining continuous monitoring reliability.
Solution Approach 2:
The monitoring system operates continuously to collect activity data, but the heavy computational analysis is performed in batches or during low-computational-demand periods. The continuity of data collection is maintained, while computational resources are allocated efficiently by processing data in manageable intervals rather than continuously, reducing overall computational resource consumption.
3Adaptability or versatility
If multiple activity types are monitored simultaneously, then comprehensiveness of condition assessment is improved, but measurement and processing difficulty increase
Solution Approach 1:
The system processes different activity types separately through dedicated activity complexity datasets, with each dataset tailored to the specific characteristics of that activity type. This segmentation allows specialized processing algorithms to be applied to each activity type, reducing the complexity of processing diverse data compared to a unified approach.
Solution Approach 2:
The patent creates a universal framework for handling multiple activity types through the common use of activity complexity datasets and the same model comparison mechanism. While the processing steps are standardized, the system adapts to different activity types by collecting and processing their specific characteristics through the same overall architecture, reducing processing difficulty through standardization while maintaining comprehensive monitoring capability.
Data Source
AI summary
A method of determining a condition of a user, the method may include: monitoring one or more activities performed by a user during a predetermined monitoring time period; determining one or more activity complexity datasets each for one of the one or more monitored activities; determining a user complexity model based on at least one of the one or more activity complexity datasets; determining a distance vector between the user complexity model and a reference user complexity model; and determining a condition of the user based on the distance vector and a reference distance-condition model.