Knowledge Base for Dynamic User Interest Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately determine and update user interests over time, leading to a lack of personalized digital content recommendations.
Innovation Solution
A knowledge base is utilized to process user activity data, evaluate interacted digital content, and map topics to entities, allowing for inference of user interests and updating them as more information becomes available.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If user activity data is analyzed to determine user interests, then personalized digital content recommendations can be provided, but the system cannot accurately determine and update user interests over time
Solution Approach 1:
The system continuously monitors user interactions with digital content and uses this feedback to update and refine user interest profiles over time. The interest level data is dynamically adjusted based on new user activity, ensuring that recommendations remain accurate and current as user preferences evolve.
Solution Approach 2:
The system pre-establishes a knowledge base containing entities and their relationships before user analysis begins. This pre-structured knowledge base enables efficient mapping of user interactions to relevant topics and interests, improving both the speed and accuracy of interest determination.
2Loss of information
If relationships between topics are analyzed to discover new user interests, then new related interests can be discovered, but the system complexity increases
Solution Approach 1:
The knowledge base serves as an intermediary structure that pre-organizes entities and their relationships. Instead of directly analyzing complex user interaction patterns, the system maps interactions to predefined knowledge base entities, simplifying the discovery process while maintaining comprehensive interest detection.
Solution Approach 2:
The system divides the complex task of interest discovery into separate components: user activity collection, interaction analysis, knowledge base mapping, and interest inference. This segmentation allows each component to be optimized independently, reducing overall system complexity while improving effectiveness.
3Measurement precision
If user interests are updated over time as more information becomes available, then deep understanding of user interests is achieved, but processing time and computational resources increase
Solution Approach 1:
The system updates user interest profiles selectively rather than completely reprocessing all data with each new interaction. It focuses computational resources on analyzing new user activities and updating only the relevant portions of interest profiles, achieving deep understanding while minimizing processing time.
Data Source
AI summary
In one implementation, a computer-implemented method for determining user interests includes receiving user activity data that describes an interaction between a user and digital content. The method further includes generating first interest-level data that quantifies a first level of interest between the user and an entity that is a topic of the digital content, where the entity is of a plurality of entities included within a knowledge base. The knowledge base includes an ontology that indicates relationships between the plurality of entities. The method further includes identifying a candidate entity based on the candidate entity having one of the relationships to the entity within the knowledge base. Additionally, the method includes generating second interest-level data that quantifies a second level of interest between the user and the candidate entity based on an analysis of the one of the relationships of the candidate entity to the entity within the knowledge base.