Risk grade evaluation method based on prison prisoner effective influence factors and implementation system thereof

Abstract

The invention relates to a risk grade evaluation method based on prison prisoner effective influence factors and an implementation system thereof. The method comprises the following steps: (1) acquiring prisoner feature information and performing data mining; (2) training an RF classification model; (3) querying: generating an evaluation level, namely a criminal danger level label, of each prisoner, and storing the evaluation levels into a database; and (5) performing extremely high risk early warning: displaying the feature information and the risk grade score corresponding to the sentences with the highest risk grade score of the first 5%, and sending out an early warning for police officers to check the states of the dangerous persons and take corresponding control measures for the dangerous situations. The risk levels of the prisoners are evaluated, evaluation feedback of police officers is received in real time, the RF classification model is continuously updated and optimized, and the evaluation precision and effectiveness are improved.

Description

technical field [0001] The invention relates to a risk level evaluation method based on effective influencing factors of prison inmates and an implementation system thereof, belonging to the technical field of prison administration, and in particular to a research method for prison risk level evaluation. Background technique [0002] With the increasingly close connection between information technology and prison management, and the deepening of paperless, the basic file information, psychological assessment status and reform assessment status of prisoners have also become digital information that is easily obtained. Judging by the basic information of prisoners Its potential dangers and the degree of attention it should give have also become part of prison informatization. In the past prison management process, many prisons lacked an effective danger warning system or the existing danger warning system relied heavily on the subjective judgment of the police officers on the ...

AI Technical Summary

Problems solved by technology

[0003] The deficiencies of the existing methods are specifically manifested in: (1) The judgment of the danger of prisoners based on the personal experience of the police officers is accurate within a certain range, that is, among the prisoners under the jurisdiction of the police officers, but it is impossible to compare the differences between different police officers and groups under different jurisdictions. (2) The degree of danger of inmates judged through big data combined with policemen’s experience weights of various types of crimes is slightly insufficient in accuracy and has a serious lag

In the process of effectively quantifying the degree of danger of prisoners, the existing method is to consider all prisoner information as a potential danger level, which not only brings a lot of data redundancy, but also defaults to the potential danger of all kinds of information to prisoners. The degree of influence is the same, a large amount of important information is ignored, and the wrong degree of risk and attention will bring a huge burden to prison management; (3) The collection of basic information of prisoners and the acquisition of risk labels are heavily dependent on manual work, and Labels have a certain timeliness

Images