Interest Contour Computation for Dynamic User Profiling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern user profiling systems are inadequate in delivering relevant content to users as they rely on user-selected interests, which become outdated and require multiple profile/interest lists, leading to dissatisfaction and information overload, especially in enterprise environments where interests need to be dynamically updated based on user activities and social networks.
Innovation Solution
A method and system for computing and managing user interests profiles based on user-generated content, where meta-data such as tags and keywords from authored content are crawled, validated, and added to a user's profile, with the option for users to specify a time period for data relevance and modify their profiles directly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If user profiling systems rely on user-selected interests from lists, then content personalization can be provided, but the profiles become outdated and require multiple profile lists, leading to user dissatisfaction
Solution Approach 1:
The system automatically updates user profiles by crawling and analyzing content that users interact with or generate, eliminating the need for users to manually maintain profile lists. The profile is self-updating based on actual user behavior patterns, ensuring continuous accuracy without user intervention.
Solution Approach 2:
The system continuously monitors user interactions with content and uses this feedback to dynamically update the interest profile. By analyzing actual usage patterns, the system adapts the profile to reflect current user interests, resolving the contradiction between providing personalization and maintaining accurate, up-to-date profiles.
2Reliability
If users manually maintain profile accuracy and complete multiple profile lists, then profile relevancy can be maintained, but user time and effort increase leading to dissatisfaction
Solution Approach 1:
The profile maintenance process is automated through content crawling and analysis. The system independently monitors user interactions, extracts interest information from content, and updates profiles without requiring user time or effort, thus maintaining relevancy while eliminating manual maintenance burden.
Solution Approach 2:
The system performs preliminary analysis of user interactions and content in advance, continuously updating profiles before users need them. This proactive approach ensures profiles remain current without requiring users to actively maintain them, saving user time while ensuring profile accuracy.
3Adaptability or versatility
If cookies are used for content personalization, then content delivery can be customized, but user privacy concerns and mistrust increase
Solution Approach 1:
The system uses content crawling and analysis as an intermediary mechanism between content providers and users, replacing cookies as the personalization tool. Instead of directly tracking users through cookies, the system analyzes content interactions and generates profiles indirectly, maintaining personalization capability while addressing privacy concerns.
Solution Approach 2:
The patent replaces the cookie-based mechanical tracking system with a content-analysis-based system. Instead of using cookies to store and transmit user data, the system uses content crawling, meta-data extraction, and profile generation algorithms to achieve personalization, eliminating the harmful cookie mechanism while preserving the desired personalization function.
Data Source
AI summary
Embodiments of the present invention provide a method, system and computer program product for interest contour computation and management based upon user generated content and associated meta-data. In an embodiment of the invention, an interest contour computation and management method is provided. The method includes crawling content sources disposed about a computer communications network for authored content created by an end user. The method further includes identifying meta data provided for the authored content and adding the meta data to a user interests profile of the end user. The meta-data further can include extracted text from the content. Of note, the method can further include receiving from the end user a specified time period and limiting the addition of the meta data to meta data applied to the authored content during the specified time period.