Abnormal behavior risk assessment model establishment method and abnormal behavior risk assessment method

Abstract

The invention relates to an abnormal behavior risk assessment model building method and an abnormal behavior risk assessment method.The abnormal behavior risk assessment model building method provided by the embodiment of the invention comprises the steps that target data are collected, and the target data are used for assessing abnormal behaviors; preprocessing the target data to obtain a target vector, and constructing a data set according to the target vector; a neural network model is constructed, the neural network model comprises multiple layers of full-connection networks, and each full-connection layer comprises batch standardization; the neural network model is trained through the data set, an abnormal behavior risk assessment model is obtained, the abnormal behavior risk assessment model is used for monitoring abnormal behaviors, abnormal behavior risk assessment can be achieved directly through automatic data collection, the mode of manual interview and return visit is not needed any more, and manpower resources are saved.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for establishing an abnormal behavior risk assessment model and an abnormal behavior risk assessment method. Background technique [0002] In related technologies, the behavior of the concerned person is monitored to assess whether there is abnormal behavior of the concerned person. The behavior monitoring of the concerned person includes: talking, visiting, etc., and evaluating its behavior in combination with business rules and expert experience to judge Watch out for unusual behavior from personnel. [0003] There are some defects in the above method. First, the traditional evaluation method is complicated, time-consuming and labor-intensive, and requires a lot of manual participation. The second point is that artificial experience is often only satisfied with a certain type of human behavior of concern. The third point is that real-time response is difficult. The fourth p...

AI Technical Summary

Problems solved by technology

[0003] There are some shortcomings in the above method. First, the traditional evaluation method is complicated, time-consuming and labor-intensive, and requires a lot of manual participation.

The second point is that artificial experience is often only satisfied with a certain type of behavior of people of concern

The third point is that real-time response is difficult

The fourth point, when the number of followers increases, it will cost more labor

The fifth point is that it is difficult to pay attention to multiple behaviors at the same time. That is to say, the traditional method first requires too much manpower. Usually, paying attention to one concerned person will consume multiple manpower. Secondly, the above-mentioned evaluation methods are difficult to adapt to the constantly upgrading various Noteworthy Behavior

Images