Message anomaly detection method and device

Abstract

The embodiment of the invention provides a message anomaly detection method and device. The method comprises the steps of determining an event type of a to-be-detected message by a service system; generating the to-be-detected message by the service system according to a user event reported by a client and an associated user event of the user event; performing word segmentation on the to-be-detected message to obtain each message segmented word of the to-be-detected message; determining each preset keyword corresponding to each message segmented word from a preset keyword set corresponding to the event type of the to-be-detected message; determining the matching degree between each message segmented word and each preset keyword according to a matching degree calculation formula; and determining a detection result of the to-be-detected message according to the matching degree. Compared with the prior art that the message is not detected, the method has the advantages that the message can be automatically generated and detected; the message generation cost is reduced, and the message accuracy and the user experience are improved.

Description

technical field [0001] The present application relates to the computer technology field of financial technology (Fintech), and in particular to a message anomaly detection method and device. Background technique [0002] In recent years, with the development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually transforming into Fintech. Make higher demands. For example, banking-related businesses need to communicate with users in a timely manner, and users can be reminded of relevant business information through reminder messages; the content of the reminder message must be accurate to prevent wrong reminder information from misleading users. For example, for bank loan business, the repayment date in the reminder message is particularly important. If the information such as the repayment date is wrong and misleads the user, it may lead to the customer's overdue repayment and affect the cu...

AI Technical Summary

Problems solved by technology

If the information such as the repayment date is wrong and misleads the user, it may cause the customer to repay overdue and affect the customer's credit investigation, which will have a negative impact on the customer's reputation and the bank's reputation

[0003] In the prior art, the reminder message template is generally manually configured, so that the business system generates a reminder message according to the reminder message template and the corresponding reminder information; however, this method requires manual configuration of the reminder message template, which wastes manpower and material resources, and cannot guarantee the accuracy of the reminder message sex

Images