Multi-classifier Recommendation Accuracy via Dynamic Sub-selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data classification methods are inadequate for the big data era, as they assume linearly separable data and fail to meet the increased demands for accuracy in data classification prediction.
Innovation Solution
A multi-classifier-based recommendation method that uses a primary classifier and a target sub-classifier with the highest similarity to the feature data, combining predictions to improve classification accuracy, and updates parameters based on user feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single classifier is used for data classification, then the device complexity is low, but the classification prediction accuracy is insufficient to meet big data requirements
Solution Approach 1:
The patent divides a single classifier into multiple specialized classifiers (primary classifier and sub-classifiers), where each classifier focuses on specific data subsets or patterns. This segmentation allows each classifier to specialize in particular aspects of the data, improving overall classification accuracy while managing complexity through modular design
Solution Approach 2:
The patent dynamically adjusts classifier parameters including selecting different sub-classifiers based on data distribution characteristics, modifying classification thresholds, and adapting model parameters based on feedback. This allows the system to optimize accuracy for different data scenarios without requiring a completely different classifier structure
2Adaptability or versatility
If conventional linear classification methods are used, then the ease of operation is high, but the adaptability to diverse big data patterns is insufficient
Solution Approach 1:
The patent implements dynamic classifier selection where the system automatically chooses appropriate sub-classifiers based on the characteristics of the input data. The classifier configuration adapts dynamically to different data distributions, patterns, and scenarios, enabling high versatility without requiring manual intervention to switch between different classification approaches
Solution Approach 2:
The patent creates a universal classification framework that can handle multiple types of data patterns through a single multi-classifier system. The primary classifier and multiple sub-classifiers work together to provide a unified solution that adapts to various data types, eliminating the need for separate specialized systems for different classification scenarios
Data Source
AI summary
The present specification discloses a multi-classifier-based recommendation method and device, and an electronic device. In the method, a target sub-classifier is obtained from k sub-classifiers in a multi-classifier based on received data, where the target sub-classifier is a sub-classifier whose data distribution has a highest similarity with feature data in the multi-classifier; the first prediction data obtained after the primary classifier performs prediction on the feature data is obtained, the second prediction data obtained after the target sub-classifier performs prediction on the feature data is obtained, and then the third prediction data is obtained by combining the first prediction data and the second prediction data, so that more accurate prediction data is obtained, thereby resolving the technical problem of low accuracy of data classification prediction in the existing technology; and the feature data is recommended based on the third prediction data, so that the accuracy of data recommendation is improved.