Personal Risk Assessment via Divergence from Expected State
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional tracking methods for wearable computing devices fail to adequately assess personal risk by not considering factors beyond location, such as medical states like heart rate, and do not account for time-dependent safety of locations.
Innovation Solution
A system and method that collect initial information about a user's expected state, including medical and location data, and compare it to subsequent data to calculate a risk score, performing safety actions based on divergence from the expected state, using modules for collection, determination, reception, calculation, and safety actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional tracking methods are used to monitor user location, then location information can be obtained, but the assessment of personal risk is insufficient because medical state factors are not considered
Solution Approach 1:
The patent combines location tracking data with medical state monitoring data from wearable devices to create a comprehensive risk assessment system. The server integrates GPS location information with physiological parameters (heart rate, respiratory rate, blood pressure) to evaluate personal risk more accurately than location-only methods.
Solution Approach 2:
The wearable computing device performs multiple functions: it tracks location, monitors medical state parameters, and transmits both types of data to the server for integrated analysis. This multi-functional approach enables simultaneous collection of spatial and physiological information for holistic risk assessment.
2Measurement precision
If traditional tracking methods monitor user location, then location data is available, but time-dependent safety variations of locations are not accounted for
Solution Approach 1:
The system dynamically evaluates location safety based on time of day. The server compares current location and time data against stored safety profiles that vary by time period, allowing the same location to have different risk assessments at different times (e.g., a park may be safe during daytime but risky at night).
3Measurement precision
If comprehensive data collection is performed to improve risk assessment accuracy, then more information is available, but system complexity increases
Solution Approach 1:
The server acts as an intermediary that handles the complex tasks of data integration, comparison, and risk calculation. The wearable device itself remains relatively simple, collecting and transmitting data, while the server performs the sophisticated analysis by comparing current state against expected state profiles stored in its database.
Solution Approach 2:
The system divides functionality between the wearable device and the server. The wearable handles data collection and transmission, while the server manages data storage, profile maintenance, comparison logic, and risk score generation. This segmentation distributes complexity across multiple components.
Data Source
AI summary
A disclosed computer-implemented method for assessing levels of personal risk may include (1) collecting, from a computing system, initial information that describes a user at an initial period of time, (2) determining, based on the initial information, an expected state of the user, (3) receiving, from the computing system, additional information that describes the user at a subsequent period of time after the initial period of time, (4) calculating a risk score by comparing the additional information with the expected state to determine a degree of divergence from the expected state, and (5) performing a safety action based on the risk score. The expected state and/or the additional information may each specify a medical state and/or a location. Various other methods, systems, and computer-readable media are also disclosed.