Electronic Device Personal AI Model for Media Preference Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing portable digital communication devices struggle to accurately identify user preferences and provide personalized content services due to the lack of effective AI recognition technologies.
Innovation Solution
An electronic device equipped with a processor, memory, and communication circuitry uses a main AI model to analyze user media usage patterns, extract features, and train a personalized AI model to determine preferences, enabling functions such as media recommendation and classification based on these preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a personalized AI model is trained using user media usage patterns and features, then the accuracy of user preference identification is improved, but the device complexity and computational resources required increase
Solution Approach 1:
The patent divides the AI model into a pre-trained main AI model and a personalized sub-model. The main AI model handles general media analysis, while the personalized sub-model focuses on individual user preferences. This segmentation allows the system to achieve high preference identification accuracy without requiring a completely complex custom model for each user, thus resolving the contradiction between precision and complexity.
Solution Approach 2:
The system performs preliminary training of the main AI model with general media data before personalization. This pre-trained model serves as a foundation that reduces the computational burden during personalized training. By preparing the base model in advance, the system achieves accurate preference identification without requiring excessive computational resources for each individual user's model training.
2Measurement precision
If AI models continuously learn from user media usage patterns, then the personalization accuracy improves over time, but the energy consumption and processing time increase
Solution Approach 1:
Instead of continuously training the entire AI model from scratch, the system performs partial updates only on the personalized sub-model using recent user behavior data. This partial action approach allows the system to improve personalization accuracy over time without the excessive energy consumption that would result from retraining the complete model, thus resolving the contradiction between improving precision and energy usage.
3Measurement precision
If the system extracts features from all media items using the main AI model, then the quality of preference analysis improves, but the processing time and computational load increase
Solution Approach 1:
The patent applies local quality by extracting features selectively from media items based on user interaction history and importance. Rather than processing all media uniformly, the system prioritizes feature extraction for media that is more likely to be relevant to user preferences, determined by local characteristics such as user engagement patterns. This approach maintains high analysis quality for critical media while reducing overall processing time, resolving the contradiction between precision and time efficiency.
Data Source
AI summary
An electronic device includes a memory storing one or more instructions; a communication circuit; and a processor operatively coupled to the memory and the communication circuit, in which the one or more instructions, when executed by the processor, cause the electronic device to: identify a use pattern of specified media items from a plurality of media items stored in the memory, determine, based on the use pattern, a score of each of the specified media items, extract, using a main AI model stored in the memory, a feature corresponding to a characteristic of each of the specified media items, acquire a first AI model trained based on the score and the feature, based on the first AI model, determine a first preference of each of first media items from the plurality of media items, and based on the first preference, perform a function related to the first media items.