A method, device and equipment for identifying abnormal transaction behavior

Abstract

The embodiment of this specification discloses a method, device, and equipment for identifying abnormal transaction behaviors. The method includes: acquiring an abnormal identification model, wherein the abnormal identification model is based on the user identification of at least one user and the user ID of the at least one user. The identification of the transaction object in the historical transaction data is established. The abnormal recognition model is used to calculate the topic distribution vector in the user transaction. Then, the abnormal recognition model can be used to calculate the topic distribution vector corresponding to the transaction to be recognized. According to the Describe the topic distribution vector corresponding to the transaction to be identified, and identify the abnormality of the transaction to be identified.

Description

technical field

[0001] This specification relates to the field of computer technology, and in particular to a method, device and equipment for identifying abnormal transaction behavior. Background technique

[0002] With the development of network technology and terminal technology, e-commerce plays an important role in people's life, and with the continuous development of e-commerce, people pay more and more attention to transaction security.

[0003] In order to ensure the security of network transactions, the corresponding business systems are usually equipped with detection mechanisms for network transaction behaviors, such as intercepting possible risky transactions in the business system through blacklists or whitelists. With the continuous improvement of network technology, there are more and more network viruses or network Trojan horse programs, and it is difficult for blacklists or whitelists to cover all possible network viruses or network Trojan horse programs in ...

Images