Risk prompting method, device and equipment and computer storage medium

Abstract

The embodiment of the invention provides a risk prompting method and device, equipment and a computer storage medium, and relates to the technical field of artificial intelligence. The method comprises the steps of performing feature extraction on attribute information and financial data in feature information of a target object to obtain a fusion feature vector corresponding to the attribute information and the financial data; performing risk assessment on the fusion feature vector to obtain an assessment tag vector of the target object; according to the evaluation label vector, determining a target crime-related type of the target object and at least one suspicious feature corresponding to the target crime-related type; and sending at least one of the target crime-related type and the suspicious feature as risk prompt information to a client to realize risk prompt of the target object. According to the embodiment of the invention, the method can help the auditor to quickly and accurately locate the possible risk of the customer, greatly improves the trial efficiency and accuracy, and also reduces the requirements for the experience of the auditor.

Description

technical field [0001] The embodiment of the present application relates to the technical field of the Internet, and involves but is not limited to a risk warning method, device, equipment and computer storage medium. Background technique [0002] At present, the anti-money laundering review system of financial institutions generally only provides information such as the basic attributes of customers and transaction summaries, and does not actively prompt customers of risk types, nor does it provide personalized prompts of risk characteristics that match customer risk types. Analysis, review and risk reporting can only be carried out through the experience accumulated by humans. Obviously, this manual trial method has disadvantages such as low trial efficiency, poor accuracy, and high requirements for manual experience. Contents of the invention [0003] Embodiments of the present application provide a risk warning method, device, equipment, and computer storage medium, w...

AI Technical Summary

Problems solved by technology

[0002] At present, the anti-money laundering review system of financial institutions generally only provides information such as the basic attributes of customers and transaction summaries, and does not actively prompt customers of risk types, nor does it provide personalized prompts of risk characteristics that match customer risk types. Analysis and review and risk reporting can only be carried out through the experience accumulated by humans

Obviously, this manual trial method has disadvantages such as low trial efficiency, poor accuracy, and high requirements for manual experience.

Images