China Mobile Communications Group Jiangxi
Next-generation Telecommunication Fraud Prevention, Deterrence, and Traceability System based on Graph Databases
Preventing and combating telecommunications fraud aligns with the characteristics of graph databases, which facilitate interconnectedness of all things and visually express relationships between data. The efficiency of graph databases in processing relationship data is 2 to 3 orders of magnitude higher than that of relational databases.
Deputy General Manager of the Network Department at Ganzhou Branch of Jiangxi Mobile - Xie Wenfeng
Customer Profile
China Mobile Communications Group Jiangxi Co., Ltd. (referred to as 'Jiangxi Mobile') is a subsidiary of China Mobile Communications Corporation, leading the industry in terms of user base and revenue scale. It has excelled in operating business within China Mobile Group for four consecutive years.
Business Pain Points
China Mobile previously used traditional Oracle relational databases for anti-fraud models, but has hit performance bottlenecks.
Slow associative queries
With a vast internal user data set, query results are slow to retrieve during associative queries, with business query times doubling as user volume increases.
Frequent system crashes
Currently, Jiangxi Mobile adds hundreds of millions of new user call records daily. Existing model queries are limited by hardware conditions, leading to situations where query results cannot be output.
Verbose model statements
Anti-fraud models require frequent iterative upgrades. However, using SQL for model statements results in convoluted queries due to multiple join operations in various relational databases, reducing readability and maintainability.
solution
Jiangxi Mobile has established a pilot team for graph database anti-fraud efforts, building a next-generation anti-fraud system based on the Galaxybase graph database.
Model
Convert existing anti-fraud models to graph database models, simultaneously create advanced graph database anti-fraud models and continuously iterate for optimization.
Exploration
Leveraging the characteristics of graph databases, deeply explore the relationships among fraudulent numbers, trace and combat fraud ringleaders, and tackle fraud at its roots.
Conversion
Transform the massive traditional relational data structures of Jiangxi Mobile into graph data structures, creating an 'Anti-Fraud Graph Database.'
Architecture Diagram
Value of Use
Speed
The timeliness of fraudulent number identification and victim alert deterrence improved from 'hourly' to 'minutes' with the application of graph databases.
Accuracy
By establishing a trusted user database based on the graph relationship characteristics of normal users, the misjudgment rate of the graph data model decreased by 30%, enabling precise identification of fraudsters and building up a knowledge graph for accurate recognition.
Effectiveness
Effortlessly uncovering deep relationships among fraudsters, tracing and combating ringleaders to achieve the ultimate goal of eradicating fraud at its source. Additionally, consolidating a knowledge graph for precise identification of fraudulent individuals.
Create Link is the first domestic commercial graph database supplier with fully independent intellectual property rights, dedicated to providing world-class graph database products and graph intelligence services.
Business Consulting
400-882-6897
Pre-sales Consulting
0571-88013575、0571-88016275
Enterprise Email
partner@chuanglintech.com
Media Cooperation
Marketing@chuanglintech.com
Address
L12, Building E2, Zhi Hui Zhong Chuang Center, No.3 Xiyuan No.8 Road, Xihu District, Hangzhou, China
Contact Us