Occupancy Simulation Using Learned Activity Patterns to Deter Burglary
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing security systems lack the ability to realistically simulate human activity in unoccupied properties, making them vulnerable to burglaries as burglars can easily identify and exploit patterns in user-set schedules.
Innovation Solution
A monitoring system generates models of human activity based on collected data, creating occupancy simulations that mimic real-life activities to deter burglars by making the property appear occupied, using smart devices and sensors to execute these simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If user-defined automation schedules are used to simulate occupancy, then the system is easy to operate and set up, but the simulations are easily predictable and fail to realistically mimic human activity patterns
Solution Approach 1:
The system automatically generates occupancy simulations by analyzing historical sensor data and user behavior patterns without requiring manual programming. The monitoring system self-learns and creates realistic activity schedules autonomously, eliminating the need for users to define complex automation rules while producing unpredictable, human-like patterns.
Solution Approach 2:
The system continuously monitors actual occupancy and sensor data, then uses this feedback to refine and adjust the generated simulations. By comparing predicted patterns with actual human behavior over time, the system adapts its simulations to maintain realism and unpredictability, ensuring the patterns remain convincing to potential intruders.
2Device complexity
If simple user-defined schedules are used for occupancy simulation, then the device complexity is low, but the simulations lack creativity and realism
Solution Approach 1:
The monitoring system automatically analyzes historical data from sensors and connected devices to generate creative, realistic occupancy patterns without requiring complex user configuration. The system performs data aggregation, pattern recognition, and simulation generation autonomously, achieving high adaptability and creativity while keeping the user interface simple.
Solution Approach 2:
The simulation patterns are dynamically generated based on learned human behavior patterns rather than being static pre-defined schedules. The system adapts the complexity and variability of simulations based on the property's specific usage patterns, creating unpredictable sequences of events that realistically mimic human activity without requiring complex manual setup.
3Reliability
If occupancy simulations are implemented, then security is enhanced by deterring burglars, but energy consumption increases due to activating multiple devices
Solution Approach 1:
The system implements occupancy simulations selectively based on risk assessment and detected vacancy patterns rather than continuously. Simulations are activated only when the property is determined to be unoccupied and at risk, and the intensity/duration of simulations can be adjusted. This partial action approach maintains security effectiveness while reducing unnecessary energy consumption during periods when simulations provide minimal additional value.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A monitoring system includes one or more sensors, one or more connected electronic, and a monitor control unit that is configured to receive sensor data from the one or more sensors, determine usage data that reflects a level of usage of the one or more connected electronic devices, receive occupancy data that reflects an occupancy level of the property, train a predictive model that is configured to determine a likely occupancy level of the property, receive, at a current time and from the one or more sensors, current sensor data, determine, current usage data that reflects a current level of usage of the one or more connected electronic devices, apply the current usage data and the current sensor data to the predictive model, determine a likely current occupancy level of the property, determine that the likely current occupancy level of the property is unexpected, and perform an action.