User-Personalization Interest Parameter Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing content recommendation systems face challenges in efficiently determining user-personalization interest parameters due to the overwhelming volume of targeted content items and scarce user information, leading to high computational burdens and resource expenses.
Innovation Solution
A method and system that generate a user-personalization interest parameter by analyzing navigational history data, using machine learning algorithms to process URL segments and assign weight values based on frequency and recency, to identify targeted content items that align with user interests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional content recommendation systems process large volumes of targeted content items and user activity history, then recommendation accuracy is improved, but computational burden and energy consumption increase significantly
Solution Approach 1:
The patent extracts only the most relevant features from user activity history and targeted content items, rather than processing complete datasets. By identifying and extracting key characteristics that drive recommendation accuracy, the system reduces computational load while maintaining effective recommendation performance.
Solution Approach 2:
The system applies different processing quality levels to different data elements based on their importance. High-priority features receive detailed processing while lower-priority elements receive simplified processing, optimizing the balance between recommendation accuracy and computational resource consumption.
2Measurement precision
If comprehensive user activity history is collected and processed, then user profiling accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The system extracts only the essential temporal patterns and behavioral characteristics from user activity history that are critical for accurate profiling. By focusing on key temporal features rather than processing complete activity logs, the system achieves accurate user profiling with reduced processing time.
Solution Approach 2:
The system performs preliminary processing and feature extraction on user activity data before main analysis. By pre-identifying and organizing relevant temporal patterns in advance, the system reduces the computational burden during actual recommendation generation while maintaining profiling accuracy.
3Measurement precision
If detailed analysis of all targeted content items is performed, then content matching precision is improved, but system complexity and processing overhead increase
Solution Approach 1:
The system extracts and analyzes only the most discriminative features of targeted content items that are essential for accurate matching. By identifying and processing only the critical content characteristics rather than analyzing all item attributes in detail, the system achieves precise content matching with reduced processing complexity.
Data Source
AI summary
A computer implemented method of generating a user-personalization interest parameter is disclosed. The method comprises receiving, navigational history data associated with a browser application; generating, one or more navigational session transition patterns; for each navigational session transition pattern: truncating, each of the one or more URLs included within the navigational session transition pattern, to obtain a respective URL segment; generating, a respective vector value representative for each of the URL segments; assigning a weight value for each URL segments; determining a navigational profile value for the user, based on at least one vector value and the associated weight value; generating, the user-personalization interest parameter associated with the user based on the navigational profile value.