Method and device for identifying relationship information between transaction parties

Abstract

The embodiment of this specification provides a method and device for identifying relationship information between transaction parties. The method includes: obtaining a knowledge graph constructed based on multiple relationships among multiple users; the knowledge graph includes multiple nodes corresponding to multiple users, and multiple categories of connection edges corresponding to multiple relationships, and multiple Users include natural person users and / or enterprise users; then, use the pre-trained graph embedding model to perform graph embedding processing on the knowledge graph to obtain the node embedding vectors corresponding to each node; the two corresponding to the two users involved in the target transaction The node embedding vector and the edge embedding vector of each category are respectively composed of triplets, which are input into the pre-trained prediction model, and the evaluation scores corresponding to each triplet are predicted by the prediction model. Furthermore, based on the evaluation score, the relationship category information between users is identified to assist in determining whether the transaction is safe.

Description

technical field [0001] One or more embodiments of this specification relate to the field of machine learning, and in particular, to a method and apparatus for identifying relationship information between two parties in a transaction. Background technique [0002] The third-party payment platform improves the convenience of transfers and payments in people's daily production. In order to ensure transaction security, its risk control system will intelligently identify the risks that may exist in transactions, especially those involving large-value transfers. Transactions between enterprise users have always adopted stricter risk control strategies. [0003] Some current risk control schemes mostly evaluate possible risks from the perspectives of user behavior, hardware equipment used for transfer, network environment, etc. Although such schemes can improve transaction security to a certain extent, they ignore other factors that can reflect Some key data or information for tra...

AI Technical Summary

Problems solved by technology

For example, when there is some commonsense information that can indicate that the probability of risk in the transaction is very low, some schemes under the existing technology still adopt relatively strict control strategies because they cannot recognize the commonsense information, so that users Still need to cooperate with the cumbersome verification operation, which affects the user experience

Images