Motion-Sensor Fall Confidence Scoring for Accurate Help-Seeking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fall detection systems in wearable devices inaccurately trigger help-seeking actions due to similarities between common user motions and fall motions, leading to low accuracy and unnecessary assistance requests.
Innovation Solution
Implement a multi-layered detection system using an acceleration sensor and gyro sensor to determine fall confidence, combined with heart rate and sound analysis to confirm falls, and provide options for user-selected contacts for assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If motion parameter matching is used for fall detection, then fall detection capability is provided, but false triggering occurs due to similarity between common actions and fall motions
Solution Approach 1:
The fall detection process is divided into multiple independent stages: initial motion parameter matching (first preset fall parameter), confidence assessment (fall confidence calculation), and secondary verification (preset interference parameter comparison). Each stage acts as a filter to progressively eliminate false positives while maintaining detection capability.
Solution Approach 2:
Fall confidence serves as an intermediary metric between motion parameter matching and final fall determination. It quantifies the likelihood that a detected motion pattern represents a genuine fall, allowing the system to make more accurate decisions by considering probability rather than binary matching alone.
2Loss of time
If automatic help-seeking is triggered on motion parameter match, then timely assistance is provided, but unnecessary help-seeking requests are generated
Solution Approach 1:
The system performs preliminary assessments before triggering help-seeking: first checking if motion parameters match fall patterns, then calculating fall confidence, and finally comparing against interference parameters. Only after all preliminary checks confirm a genuine fall does the system activate help-seeking, preventing premature or false alarms.
Solution Approach 2:
The system incorporates feedback mechanisms where fall confidence results from motion analysis feed into the decision-making process, and the comparison with preset interference parameters provides additional feedback to confirm or refute fall detection. This multi-layer feedback ensures accurate triggering before help-seeking activation.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Embodiments of this application provide a fall detection-based help-seeking method and an electronic device, to improve accuracy of fall detection performed by an electronic device, and reduce a probability of mistakenly triggering automatic help-seeking of the electronic device. A specific solution includes the following: The electronic device includes a motion sensor, and the motion sensor includes an acceleration sensor and a gyro sensor. The electronic device collects a first motion parameter of a user by using the motion sensor. The electronic device obtains a fall confidence of the first motion parameter if the first motion parameter matches a first preset fall parameter, where the fall confidence of the first motion parameter is used to represent a probability that the first motion parameter is a motion parameter collected when the user falls. The electronic device sends help-seeking information if the fall confidence of the first motion parameter is greater than a preset confidence threshold.