Method and electronic device for personalizing classification framework
By personalizing a classification framework using user history analysis and a Knowledge Graph, the method effectively organizes and retrieves user content, addressing the challenge of finding relevant information amidst increasing volumes of collected data.
WO2026106037A1PCT designated stage Publication Date: 2026-05-21SAMSUNG ELECTRONICS CO LTD
View PDF 5 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SAMSUNG ELECTRONICS CO LTD
- Filing Date
- 2025-08-13
- Publication Date
- 2026-05-21
AI Technical Summary
Technical Problem
As users collect increasing volumes of content from various sources, it becomes difficult to find specific information due to the accumulation of unnecessary materials of temporary interest, making it challenging to locate needed content efficiently.
Method used
A method and electronic device that personalize a classification framework by analyzing user usage history to update a Knowledge Graph, determining whether to reconfigure the classification system based on user interests, and classifying content accordingly.
Benefits of technology
The solution enables efficient organization and retrieval of user content by dynamically adapting the classification system to reflect changing user interests, improving content accessibility and relevance.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure KR2025012298_21052026_PF_FP_ABST
Abstract
According to one aspect of the present disclosure, provided is a method by which an electronic device personalizes a classification framework for classifying content collected by a user. The method may comprise a step of acquiring a usage history of a user for a user device. The method may comprise a step of updating a knowledge graph (KG) related to a topic of interest of the user on the basis of the usage history of the user. The method may comprise a step of determining whether to reconstruct the classification framework on the basis of the relationship between a node included in the knowledge graph and content collected by the user. The method may comprise a step of, when it is determined to reconstruct the classification framework, reconstructing the classification framework on the basis of the topic of interest of the user identified from the updated knowledge graph.
Need to check novelty before this filing date? Find Prior Art