User Sensitivity Classification for Appliance Wear Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current personal care appliances lack effective methods to accurately assess cutting element wear, leading to inconsistent shaving experiences and potential discomfort due to inadequate wear detection.
Innovation Solution
A computer-implemented method using machine learning models to classify user sensitivity to a treatment head and estimate cutting element wear by analyzing physical parameters such as motor current and power, enabling timely replacement and improved shaving experiences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional wear detection methods (pad print or prolonged shaving periods) are used, then the appliance can detect cutting element wear, but the accuracy of wear detection deteriorates due to inability to accommodate individual user characteristics and usage variations
Solution Approach 1:
The system performs preliminary classification of users into sensitivity categories (sensitive, normal, insensitive) before actual wear detection occurs. This preliminary action allows the system to adapt wear detection thresholds and parameters to individual user characteristics, thereby improving both measurement precision and adaptability simultaneously
Solution Approach 2:
The system changes detection parameters based on user classification. Different sensitivity categories have different threshold values and detection criteria for wear assessment. This parameter adaptation enables accurate wear detection tailored to individual user characteristics and pain tolerance levels
2Duration of action of stationary object
If traditional wear detection methods are used, then the appliance operates for extended periods, but the shaving experience deteriorates due to inconsistent performance and potential discomfort from worn cutting elements
Solution Approach 1:
The system continuously monitors motor power consumption and compares it against classified user sensitivity thresholds. When wear indicators exceed user-specific thresholds, the system provides feedback to recommend replacement. This feedback mechanism maintains reliable shaving experience by preventing use of excessively worn elements while accommodating individual user tolerance levels
Solution Approach 2:
The system establishes user-specific wear thresholds in advance based on sensitivity classification. This preliminary configuration enables the system to provide consistent and reliable shaving experiences by comparing real-time motor data against pre-determined user-appropriate limits, rather than using one-size-fits-all duration-based replacement schedules
3Measurement precision
If machine learning models are implemented to classify user sensitivity and detect wear, then the accuracy of wear assessment improves, but the device complexity increases
Solution Approach 1:
The system replaces complex mechanical wear indicators (pad prints, visual inspection mechanisms) with electronic sensor-based motor power monitoring combined with machine learning classification. This substitution achieves high measurement precision through software-based user sensitivity classification while avoiding the mechanical complexity of traditional wear indication systems
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
The subject-matter of the present disclosure relates to a computer-implemented method of classifying sensitivity of a user to a treatment head of an appliance (10). The computer-implemented method comprises: receiving (S500), from a sensor of the appliance, data representing physical parameters associated with operating the appliance; assigning (S502), using a machine learning model, a user to a classification of sensitivity to a treatment head of the appliance based on the received data; and sending (S504) a signal indicating the assigned classification.