Air anomaly alarming method, device and storage medium
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing air quality monitoring systems rely on fixed threshold values for alarming, leading to false or missed alarms due to normal indoor activities, rather than accurately detecting anomalies indicative of potential hazards like fires.
Innovation Solution
An air anomaly alarming method and device that acquires and compares indoor air composition data with a pre-generated air change pattern, sending alerts only when differences exceed preset thresholds, thereby distinguishing between normal and hazardous conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a single fixed threshold value is used for alarm monitoring, then the alarm system is simple to operate, but false alarms or missed alarms occur easily
Solution Approach 1:
The patent transforms the static fixed threshold into a dynamic adaptive threshold that automatically adjusts based on historical air quality data and learned patterns of normal activities. The system continuously updates the threshold values to reflect changing environmental conditions and user behaviors, thereby maintaining high alarm accuracy without increasing operational complexity.
Solution Approach 2:
The system performs preliminary learning during an initial period to establish baseline air quality patterns and normal activity ranges before entering the alarm monitoring phase. This preliminary action enables the system to distinguish between normal variations and actual anomalies, reducing false alarms while maintaining simplicity for end users.
2Ease of manufacture
If a fixed threshold value is used for alarm monitoring, then the alarm system is easy to implement, but it cannot adapt to different scenarios and causes false alarms
Solution Approach 1:
The system implements a preliminary learning phase where it collects and analyzes historical air quality data to establish scenario-specific baselines and patterns. This preliminary action enables automatic adaptation to different scenarios (e.g., cooking, smoking, fire) without requiring manual configuration or complex implementation, maintaining ease of deployment while achieving high adaptability.
Solution Approach 2:
The alarm system performs self-adjustment by automatically learning normal air quality patterns and adapting threshold values based on observed behaviors. The system serves itself by continuously improving its detection accuracy through automated pattern recognition, eliminating the need for manual calibration or scenario-specific configuration while maintaining implementation simplicity.
3Measurement precision
If air composition information is compared with pre-acquired air change pattern, then alarm accuracy is improved, but system complexity increases
Solution Approach 1:
The system creates simplified digital copies or models of normal air quality patterns through historical data analysis. Instead of implementing complex real-time pattern recognition algorithms, the system uses pre-learned reference patterns that approximate normal behaviors, achieving high detection accuracy while maintaining relatively simple system architecture through template matching approaches.
Data Source
AI summary
An air anomaly alarming method, an air anomaly alarming device and a storage medium are provided. The method includes: air composition information of an indoor environment is acquired; the air composition information of the indoor environment is compared with corresponding air composition information in a pre-acquired air change pattern; and an alarming message is sent to preset target equipment when a difference between the air composition information of the indoor environment and the corresponding air composition information in the air change pattern is greater than a first preset air threshold value.