Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Prisoner dangerous behavior prediction method and system based on effective influence factors

A technology of serving prisoners and influencing factors, applied in the research field of risk behavior prediction in prisons, can solve the problems of model correction and optimization lag, and achieve the effect of reducing complexity, improving efficiency and accuracy

Pending Publication Date: 2020-12-25
SHANDONG UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a method and system for predicting risky behaviors of inmates based on effective influencing factors, which integrates an effective influencing factor extraction method, risky behavior evaluation based on weight scores and correction based on online learning algorithm Optimize the model, improve the accuracy of the prediction model, solve the problem of model revision and optimization lag, and improve the timeliness of the prediction of dangerous behaviors of prisoners;

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Prisoner dangerous behavior prediction method and system based on effective influence factors
  • Prisoner dangerous behavior prediction method and system based on effective influence factors
  • Prisoner dangerous behavior prediction method and system based on effective influence factors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A method for predicting risky behaviors of prisoners based on effective impact factors, such as figure 2 shown, including the following steps:

[0061] (1) Structured processing:

[0062] 1) Data cleaning: Supplement, modify, and delete the default items, irregular items, and erroneous items in the characteristic information of inmates, so as to ensure the validity of the data set.

[0063] The characteristic information of inmates includes criminal basic information, crime information, psychological condition and daily behavior;

[0064] The basic information, criminal information, psychological status and daily behavior of criminals include the specific information shown in Table 1:

[0065] Table 1

[0066]

[0067] 2) extract effective impact factor: the present invention proposes a kind of hierarchical feature extraction method based on Pearson correlation coefficient method (PCC) and information gain (IG), from two aspects of correlation and information amo...

Embodiment 2

[0093] According to a method for predicting dangerous behaviors of prisoners based on effective impact factors described in Example 1, the difference is that:

[0094] Use r to represent the PCC coefficient, and its calculation formula is shown in formula (I):

[0095]

[0096] In formula (I), X i and Indicates the value of the data of each prisoner and the mean value of the data of all prisoners in the feature field in the data set after data cleaning, Y i and Represents the value of the label of each sample and the overall mean, i represents a sample under the feature, and n represents the total number of samples.

Embodiment 3

[0098] According to a method for predicting dangerous behaviors of prisoners based on effective impact factors described in Example 1, the difference is that:

[0099] Use IG(Y|X) to represent the information entropy of a feature, and its calculation formula is shown in formula (II), formula (III) and formula (IV):

[0100]

[0101]

[0102] IG(Y|X)=H(Y)-H(Y|X) (IV)

[0103] In formula (II), formula (III) and formula (IV), H(X) refers to the information entropy of feature field X, p(x i ) means that the value of this feature is x i probability of x i Indicates the value under this feature, b is the base of the logarithm, taking 2; H(Y|X) refers to the conditional entropy; H(Y) refers to the amount of information of the category label.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a prisoner dangerous behavior prediction method and system based on effective influence factors. The method comprises the following steps: (1) structured processing: 1) data cleaning, and 2) extracting of effective influence factors; (2) dangerous behavior prediction based on weight scores: firstly, classifying all to-be-assessed personnel, and secondly, in combination with prison administration business, managers often pay attention to a small part of groups with extremely high dangerous behaviors and dangerous behavior prediction and early warning based on weight scores; and (3) carrying out online optimization on the Random Forest model. According to the method, analysis and screening are carried out from two aspects of data correlation of evaluation personnel and information entropy provided by fields, and important factors for dangerous behaviors of the prisoners are mined. The method and the system can reduce the calculation complexity and model complexity, and improves the evaluation and prediction accuracy and effectiveness.

Description

technical field [0001] The invention relates to a method and system for predicting dangerous behaviors of inmates based on effective influencing factors, belonging to the technical field of prison administration, and in particular to a research method for predicting dangerous behaviors in prisons. Background technique [0002] Prison management in prisons plays an important role in prison work. Under the current social situation, in addition to doing a good job in the reform of inmates, it is also very important to monitor the daily behavior and risk assessment of inmates in prison. This is a guarantee It is a fundamental part of the safety of the prison environment and the promotion of good reform of personnel. Routine risk prediction and assessment work mainly includes: suicide risk, escape risk, violence risk, etc. At present, this work in the prison administration mainly relies on the observation and evaluation of the police officers in the prison area, and the paper qu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06F16/215G06F16/245G06Q10/06G06Q50/26
CPCG06F16/215G06F16/245G06Q10/0639G06Q50/26G06F18/24323
Inventor 李玉军邓媛洁刘治贲晛烨
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com