Financial abnormal message identification method and device

Abstract

The invention belongs to the technical field of artificial intelligence, and provides a financial abnormal message identification method and device, and the method comprises the steps: obtaining a to-be-identified message which comprises the message receiving time, the amount, a message initiator, a message appendix and a message initiating mechanism; and identifying the to-be-identified message according to the message receiving time, the amount, the message initiator, the message initiating mechanism and a pre-established random forest abnormal message identification model. According to the invention, automatic identification of abnormal messages is realized by adopting automatic acquisition and learning of historical data; a system is prevented from being impacted by the abnormal messages, the workload of tellers for processing the abnormal messages is reduced, clients are prevented from receiving harassment of advertisement pushing, the availability of a financial institution system can be guaranteed, and manpower of workers can be greatly saved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a method and device for identifying abnormal financial messages. Background technique [0002] In the existing technology, in various financial business scenarios, such as: based on transfer and remittance, query and reply, etc., all are supported by the message interaction system of each commercial bank. But in reality, in addition to normal business transactions, various abnormal messages may also be generated. Such abnormal packets usually occur in the following scenarios: [0003] 1. Institutions use messages to push advertisements; use message postscripts to send advertisements. The beneficiary bank will automatically send a short message to the customer and display the postscript. [0004] 2. Prevent the originator from using the message to attack; the originator uses the name of the payee and the account number to send a large number of attacks...

AI Technical Summary

Problems solved by technology

Occupying the system resources of the receiver, putting pressure on the receiver, or requiring manual landing processing, resulting in redundant workload

[0005] 3. An abnormality occurred in the counterparty’s system, which resulted in the sending of an abnormal message

This situation is not intentional, but it may cause pressure and other effects on the receiver system

[0006] For the recipients of financial institutions, if they cannot identify these abnormal messages, it may cause a decline in reputation, paralysis of information systems, and increased manual operations by business personnel.

However, due to the diversity and constant changes of abnormal messages, it may cause problems such as low recognition accuracy, missed judgments, and misjudgments.

Images