Aerosol Device Pupil Biometric Cartridge Recommendation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aerosol generating devices lack the ability to recommend cartridges based on the emotional states of users, relying solely on user preference without considering emotional needs.
Innovation Solution
An aerosol generating device equipped with a biometric information obtaining unit to capture pupil images, a communication unit to transmit data to a server, and a controller to output recommended cartridges calculated using neural-network-based emotion and cartridge recommendation models, which are updated based on user interactions and replacement cartridges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cartridge selection is based solely on user preference, then the device is simple to operate, but user satisfaction is limited and emotional needs are not addressed
Solution Approach 1:
The patent introduces a server as an intermediary component that hosts the emotion calculation model and cartridge recommendation model. The server receives pupil images from the aerosol generating device, performs the complex neural network calculations, and returns recommendations. This intermediary approach enables sophisticated emotional state analysis without burdening the device itself with complex processing hardware, thus improving measurement precision while controlling device complexity.
Solution Approach 2:
The patent replaces traditional mechanical or manual cartridge selection methods with an intelligent system based on neural networks. Instead of relying on simple user preference inputs or physical cartridge organization, the system uses biometric data (pupil images) processed through emotion calculation models to automatically determine appropriate cartridge recommendations, thereby enhancing the precision of user needs assessment.
2Measurement precision
If the system uses neural-network-based emotion calculation models, then emotional state identification accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The emotion calculation model and cartridge recommendation model are pre-trained and deployed on the server before actual use. The neural networks undergo extensive training with labeled data in advance, so that when pupil images are received during operation, the server can perform rapid inference using the already-optimized models. This preliminary preparation reduces real-time processing time while maintaining high accuracy.
3Adaptability or versatility
If the cartridge recommendation system is updated based on user interactions, then recommendation accuracy is improved, but system complexity and data management requirements increase
Solution Approach 1:
The system implements a feedback mechanism where user interactions with cartridge recommendations are collected and used to update the cartridge recommendation model. When users select or reject recommended cartridges, this feedback data is transmitted to the server, which uses it to refine the model through continued learning. This feedback loop enables the system to adapt to individual user preferences over time, improving customization while centralizing the complexity of model management on the server.
Data Source
AI summary
An aerosol generating device includes: an output unit; a biometric information obtaining unit configured to obtain an image of a pupil of a user; a communication unit configured to transmit the image of the pupil of the user to a server and receive information about a recommended cartridge corresponding to the emotional state calculated by the server using a neural-network-based emotion calculation model and a neural-network-based cartridge recommendation model; and a controller configured to control the output unit to output the recommendation cartridge information.