Event time sequence data processing method, device and system for recognizing user behaviors

Abstract

The invention provides an event time sequence data processing method, device and system for recognizing user behaviors. The method comprises the steps of obtaining event operation data of a user within a preset period of time, and converting the event operation data into user event time sequence data conforming to constructed hidden Markov recognition model input data formats; inputting user event time sequence data into the constructed hidden Markov recognition models of different label types for calculating to obtain probability value data of the user event time sequence data in the hidden Markov recognition models of different label types; selecting label types corresponding to the hidden Markov recognition models with the probability value data conforming to the screening condition as the behavior type to which the recognized user s behavior belongs. By means of the event time sequence data processing method, on the basis of time sequence user s behavior data, recognized user s behaviors of the user are judged, the user operation behavior recognition result accuracy and reliability are improved, and the user s risk operation behavior recognition and control prevention effects are improved.

Description

technical field [0001] The present application belongs to the technical field of information data classification, recognition and processing, and in particular relates to a method, device and system for processing event time series data for recognizing user behavior. Background technique [0002] With the development of Internet information technology, the rise of Internet finance has brought benefits and conveniences that traditional banks cannot match to people's lives. Different from physical cards in traditional banking, Internet finance usually only requires simple registration and real-name authentication to transfer money and spend online and offline. [0003] Although the financial system based on the Internet has greatly facilitated the life of members, the ensuing problem is that it is more difficult to guarantee the safety of members' funds and prevent and control financial risks. The particularity of the financial industry puts forward higher requirements for th...

AI Technical Summary

Problems solved by technology

If only from the environmental information of the transaction event of the sale of stolen goods, there is no difference with the normal transaction operation of the user's history, and the model constructed based on the single-point operation event will be judged as a normal operation, resulting in the success of the stolen goods.

[0005] Therefore, the recognition accuracy and reliability of user operation behaviors based on single-point operation events in the prior art are low, and it is difficult to effectively guarantee the accurate identification of user risk operation behaviors and reduce the identification and prevention of user risk operation behaviors. Effect

Images