Tracking Device Power Management via Machine-Learned Routine Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic tracking devices consume excessive power and generate unnecessary notifications by continuously using GPS and cellular signals, even when the device is following a routine path, especially in areas where these signals are weak or unavailable.
Innovation Solution
A tracking device that scans access point signals and uses machine learning to identify recurring patterns, allowing it to conserve power by reducing transmissions when it recognizes a routine path and avoiding unnecessary alerts to the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the tracking device continuously uses GPS and cellular signals for location tracking, then the location accuracy and real-time monitoring capability are improved, but the power consumption increases significantly
Solution Approach 1:
The system performs preliminary actions by scanning for access point signals and other nearby device signals continuously in the background, building up historical data before actual tracking decisions are needed. This preliminary data collection enables the machine learning model to make accurate predictions about routine paths without requiring continuous high-power GPS usage during normal operations.
Solution Approach 2:
The tracking device uses its own scanned signal data and onboard sensors to independently determine routine patterns and make decisions about when to reduce GPS usage. The device serves itself by using the historical signal information and machine learning models to autonomously decide when it can safely reduce power-intensive transmissions while maintaining tracking reliability.
2Use of energy by moving object
If the tracking device uses machine learning to identify routine paths and reduce transmissions, then power consumption is reduced, but the complexity of the system increases
Solution Approach 1:
The machine learning model acts as an intermediary between the raw signal data and the tracking decisions. It processes the historical signal information and onboard sensor data to produce predictions about routine paths, which then guide the decision to reduce or maintain GPS transmissions. This intermediary layer simplifies the overall system architecture by centralizing the complexity in a dedicated processing component.
3Use of energy by moving object
If the tracking device reduces transmissions when following routine paths, then power consumption and transmission costs are reduced, but the real-time monitoring capability decreases
Solution Approach 1:
The system implements periodic action by maintaining continuous background scanning for access point and nearby device signals, while intermittently using high-power GPS transmissions only when necessary to detect deviations from routine paths. This periodic usage pattern maintains monitoring capability during critical events while significantly reducing overall power consumption during normal routine operations.
Solution Approach 2:
The machine learning model continuously receives feedback from the tracking device's location data and signal information, refining its predictions about routine paths over time. This feedback mechanism ensures that the system adapts to changing patterns and maintains high monitoring capability for actual deviations while continuing to reduce power consumption during normal operations.
Data Source
AI summary
A method comprises accessing historical signal and other information received from a tracking device configured to scan for signals transmitted by local devices and record other data as the tracking device moves within the geographic area during each of a plurality time intervals. A training dataset is generated based on the historical signal and other information and used to train a machine learning model configured to predict tracking device movement patterns. The machine learning model is applied to current signal and other information to detect a variance from one or more predefined routines associated with the tracking device. A notification is sent to a monitoring device associated with the tracking device in response to detecting the variance from the one or more predefined routines associated with the tracking device.