A cross-business credit risk assessment method and system based on a graph neural network and a bank joint knowledge graph

By constructing a cross-business credit risk assessment method based on graph neural networks and bank joint knowledge graphs, the problems of insufficient integration of multi-business data and inadequate identification of risk transmission paths are solved, achieving accuracy and interpretability of cross-business risk assessment and generating reliable hierarchical early warning results.

CN122390861APending Publication Date: 2026-07-14NANJING DAYAN DIGITAL TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANJING DAYAN DIGITAL TECHNOLOGY CO LTD
Filing Date
2026-06-16
Publication Date
2026-07-14

AI Technical Summary

Technical Problem

Existing bank credit risk assessment technologies suffer from insufficient integration of multi-business data, inadequate identification of cross-business risk transmission paths, and difficulty in calibrating the timeliness of relationships and the contribution of path risks. As a result, credit risk scoring results are difficult to explain the sources of risk and the transmission chain.

Method used

A cross-business credit risk assessment method based on graph neural networks and bank joint knowledge graphs is constructed. By collecting customer data from multiple businesses, a multi-source heterogeneous original dataset is constructed, time decay weights are configured, cross-business meta-paths such as guarantee chains, equity penetration, and fund transfers are preset, node-level and semantic-level attention coefficients are calculated, path masking is compared, path risk confirmation coefficients are generated, and risk aggregation is performed using graph neural networks to generate graded early warning results.

Benefits of technology

It improves the accuracy, interpretability, and timeliness of credit risk assessment, effectively identifies and calibrates risk transmission paths across businesses, and generates interpretable risk scoring results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122390861A_ABST
    Figure CN122390861A_ABST
Patent Text Reader

Abstract

The application discloses a cross-business credit risk assessment method and system based on a graph neural network and a bank joint knowledge graph, relates to the technical field of financial business data processing and bank credit risk assessment, and comprises the following steps: collecting multi-business customer data, and constructing a multi-source heterogeneous original data set; constructing a cross-business joint knowledge graph based on a customer entity, a business event and a cross-business association relationship, and configuring a time decay weight; extracting a customer fusion embedding vector and a candidate risk transmission path set based on a guarantee chain, equity penetration and a fund flow meta path; generating a path risk confirmation coefficient through path masking comparison, and performing cross-business risk aggregation based on the path risk confirmation coefficient to obtain a customer credit risk score and a grading early warning result. The application improves the accuracy, interpretability, early warning timeliness and the like of cross-business credit risk assessment.
Need to check novelty before this filing date? Find Prior Art