对多源数据进行同一用户识别的方法、装置、设备及介质
By classifying, cleaning, and performing graph connectivity calculations on multi-source data, the relationship between device and account data is generated, solving the problems of low efficiency and low accuracy in multi-source data identification and improving the marketing efficiency of financial products.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- PING AN TECH (SHENZHEN) CO LTD
- Filing Date
- 2023-06-02
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for identifying the same user from multiple sources are inefficient and have low accuracy. They cannot effectively handle multi-source data with unrelated IDs and fail to distinguish between different types of multi-source data, resulting in low efficiency in financial product marketing.
By classifying the user data to be processed into data sources, cleaning and calculating device data and account data separately, generating relationships between device and account data using graph connectivity calculation and connected subgraph calculation, and replacing internal data relationships to form a set of data relationships for the same user.
It improves the accuracy and efficiency of user identification, reduces the amount of computational data, clarifies the logical relationships between account data, and thus enhances the marketing efficiency of financial products.
Smart Images
Figure CN116680449B_ABST