Method of smart scene management using big data pattern analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional home automation systems face difficulties in reprogramming automated features when a homeowner's schedule changes, as they require manual modifications by installers or users, limiting flexibility and convenience.
Innovation Solution
A home automation system that uses cloud-based Big Data analysis of sensor data to dynamically modify actuator controls based on user activity patterns, allowing for intelligent modification, addition, or deletion of static scenes, thereby automating the adjustment of environmental settings and enhancing user comfort and convenience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional home automation systems use fixed pre-programmed schedules, then system reliability is improved, but adaptability deteriorates when homeowner schedules change
Solution Approach 1:
The system automatically monitors sensor data and learns user behavior patterns without requiring manual reprogramming. The cloud processor autonomously analyzes sensor activations, identifies patterns, and modifies actuator schedules based on observed user habits, allowing the system to self-adapt when schedules change.
Solution Approach 2:
The system continuously collects feedback from sensors regarding user presence and activity patterns. This feedback is processed by the cloud processor to dynamically adjust automation schedules, creating a closed-loop system that adapts to changing user needs while maintaining operational reliability.
2Device complexity
If manual reprogramming is required when schedules change, then device complexity is reduced, but ease of operation deteriorates
Solution Approach 1:
The system performs automatic pattern recognition and schedule modification without requiring user intervention. Sensors continuously monitor user behavior, the cloud processor analyzes the data to identify patterns, and the system automatically adjusts actuator schedules, eliminating the need for manual reprogramming operations.
Solution Approach 2:
The cloud-based pattern recognition module acts as an intermediary between sensor data and actuator control. This intermediary layer automatically processes sensor inputs, identifies user behavior patterns, and translates them into appropriate schedule adjustments, shielding users from complex reprogramming tasks while maintaining system adaptability.
3Ease of manufacture
If static scenes are used for automation, then ease of manufacture is improved, but adaptability deteriorates when user habits change
Solution Approach 1:
The system transitions from static pre-programmed scenes to dynamic adaptive scheduling. The cloud processor continuously monitors sensor data, identifies changing user behavior patterns, and automatically modifies actuator schedules in real-time, allowing the system to evolve with user habits while maintaining the simplicity of scene-based automation.
Solution Approach 2:
The system automatically learns and adapts to user behavior patterns without requiring manual scene reconfiguration. The pattern recognition module analyzes sensor data to understand user habits and autonomously adjusts automation schedules, enabling the system to self-adapt when user habits change while maintaining ease of initial deployment.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An automation system including sensors that detect threats within a secured area, a plurality of prospective events defined within a memory of the automation system, each event including at least a physical change in an environment of the secured area, a time of execution of the physical change and a corresponding actuator that causes the physical change, a processor of the automation system that periodically activates the corresponding actuator at the time of each of the plurality of events, a processor that monitors each of the plurality of sensors for activation by an authorized human user and that saves a record of each activation to a cloud memory and a cloud processor that monitors the saved activation records of each sensor over a time period, determines a difference between the saved activations and the plurality of events and that modifies the plurality of events based upon the determined differences.