Knowledge graph-based user portrait generation method and device, and storage medium

By using a knowledge graph-based approach to identify and model causal relationships in user behavior, user profile tags containing causal explanations are generated. This solves the problem of insufficient in-depth explanation in existing user profiles and enhances the application value of user profiles in refined services and personalized decision-making.

CN121563587BActive Publication Date: 2026-06-09SICHUAN PROVINCIAL QUALITY & STANDARDIZATION RESEARCH INSTITUTE (SICHUAN PROVINCIAL QUALITY & TECHNOLOGY REVIEW CENTER SICHUAN PROVINCIAL STANDARD & TECHNOLOGY REVIEW CENTER)
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SICHUAN PROVINCIAL QUALITY & STANDARDIZATION RESEARCH INSTITUTE (SICHUAN PROVINCIAL QUALITY & TECHNOLOGY REVIEW CENTER SICHUAN PROVINCIAL STANDARD & TECHNOLOGY REVIEW CENTER)
Filing Date
2025-11-20
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing user profiling technologies struggle to deeply uncover the intrinsic connections between user behaviors and the driving factors behind those behaviors. As a result, the generated user profile tags are mostly static descriptive information, lacking effective explanations for the formation of user behavior patterns, which limits their application value in refined services and personalized decision-making.

Method used

By using a knowledge graph-based approach, causal associations of user behavior records are identified, generating a set of causal event pairs that include the relationship between behavior triggering conditions and the impact of results. A user behavior knowledge graph with directed edge connections is constructed, and a hierarchical graph neural network is invoked to perform multi-hop relationship propagation calculations. Multi-level neighbor feature information of entities is fused to identify potential causal transmission paths and generate causal association features of user behavior that include path dependencies. Finally, a user profile tag system with multi-dimensional causal explanation information is generated through a behavior pattern clustering algorithm.

Benefits of technology

This enhances the depth and application value of user profiles, enabling the generated user profiles to not only contain descriptive information but also incorporate causal explanatory information, thus better supporting refined services and personalized decision-making.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121563587B_ABST
    Figure CN121563587B_ABST
Patent Text Reader

Abstract

The application provides a knowledge graph-based user portrait generation method and device and a storage medium. The method comprises the following steps: performing event causal correlation identification on a continuously collected user behavior record sequence to generate a user behavior causal event pair set; performing entity relationship extraction on the set to generate a triple set; further generating a user behavior knowledge graph; performing multi-hop relationship propagation calculation on the user behavior knowledge graph; fusing multi-order neighbor feature information of each entity to generate an entity embedding vector set; performing path mining on the entity embedding vector set through a preset causal reasoning model to identify potential causal conduction paths between different behavior entities; calculating influence weight coefficients between behavior patterns and result states based on the potential causal conduction paths; generating user behavior causal correlation features; fusing the user behavior causal correlation features with the entity embedding vector set to generate user behavior pattern classification results; and generating a user portrait label system. The application improves the depth and application value of the user portrait.
Need to check novelty before this filing date? Find Prior Art