Household appliance, odor detection method and system for household appliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing odor detection systems in household appliances are not intelligent enough to meet individual user preferences, as they lack personalization and adaptability, leading to ineffective odor removal based on fixed, laboratory-defined detection logic that fails to account for varying user preferences over time.
Innovation Solution
A machine learning model is used to predict odor attributes based on environmental data, iteratively updated with user feedback, allowing for personalized odor detection and removal, with the model training and updating performed locally within the appliance without external support.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If fixed laboratory-defined odor detection logic is used, then device complexity is reduced, but adaptability to individual user preferences deteriorates
Solution Approach 1:
The patent implements dynamic odor detection logic through a machine learning model that continuously learns and adapts to individual user preferences. The system transitions from static, fixed detection rules to dynamic, user-specific detection patterns by training the model on user feedback data, allowing the detection logic to evolve and personalize over time while managing complexity through efficient model architecture and incremental learning approaches
Solution Approach 2:
The system enables self-service by automatically collecting user feedback, training the machine learning model, and updating detection logic without requiring manual configuration or external intervention. The appliance autonomously improves its odor detection capabilities by processing user responses and automatically adjusting its detection parameters, reducing the need for complex manual setup while enhancing adaptability to individual preferences
2Ease of operation
If same detection logic is applied to all users, then ease of operation is improved, but loss of information regarding individual preferences increases
Solution Approach 1:
The patent implements a feedback mechanism where user responses to odor detections are collected and used to retrain the machine learning model. This feedback loop allows the system to retain and learn individual user preferences over time, preventing information loss while maintaining ease of operation. The feedback data is systematically processed to update detection logic, ensuring that individual preferences are captured and applied in future detections
Solution Approach 2:
The system dynamically changes detection parameters based on learned user preferences. The machine learning model adjusts detection thresholds, sensitivity levels, and classification criteria according to individual user patterns, allowing the system to maintain simple operation while preserving and utilizing personalized information. Parameter adaptation occurs automatically through model updates without requiring complex user configuration
3Adaptability or versatility
If machine learning model is iteratively updated with user feedback, then adaptability to user preferences is improved, but device complexity increases
Solution Approach 1:
The patent implements dynamic model updating where the machine learning model is iteratively retrained using newly collected user feedback data. This dynamic approach allows the system to adapt to changing user preferences over time while managing complexity through efficient training strategies such as incremental learning, data sampling, and model compression techniques that enable updates without requiring complete system redesign
Solution Approach 2:
The system performs self-updating by automatically collecting feedback data, processing it through the training pipeline, and deploying updated model versions without external intervention. This self-service capability manages complexity by automating the entire model lifecycle management process, reducing the burden of manual model maintenance while enabling continuous adaptation to user preferences through systematic self-improvement
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A household appliance, and an odor detection method and system for a household appliance are provided. The odor detection method for a household appliance includes: obtaining environmental data in a chamber of the household appliance, where the environmental data includes gas data; and inputting the environmental data into a preset machine learning model and obtaining a classification result, where the preset machine learning model is used to predict a current odor attribute in the chamber based on the environmental data, the preset machine learning model is iteratively updated based on feedback data, and the feedback data is obtained from a user associated with the household appliance and is used to at least represent a predicted satisfaction for the classification result. Through the solution of the present invention, an odor detection logic of the household appliance can be personalized and customized based on a user preference, which is beneficial to improving an intelligence degree of the household appliance.