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

Method for realizing tobacco sales abnormal behavior detection based on isolated forest model

A forest model and anomaly detection technology, which is applied in the field of tobacco and sales behavior anomaly detection, can solve problems such as difficulty in collecting data volume and data labels, seldom consider the characteristics of the prediction object itself, and the difference in prediction results, etc., to achieve the maximum utilization of information The effects of modernization, effective decision support, and high recall rate

Pending Publication Date: 2020-05-01
THE THIRD RES INST OF MIN OF PUBLIC SECURITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the current research on market forecasting, most scholars use quantitative historical data to construct forecasting models, and seldom take into account the characteristics of the forecasting object itself, and the difference in the forecasting object will lead to the difference in the forecasting results.
In addition, it is difficult to collect sufficient data volume and data labels

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
  • Method for realizing tobacco sales abnormal behavior detection based on isolated forest model
  • Method for realizing tobacco sales abnormal behavior detection based on isolated forest model
  • Method for realizing tobacco sales abnormal behavior detection based on isolated forest model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to describe the technical content of the present invention more clearly, further description will be given below in conjunction with specific embodiments.

[0028] The method for detecting abnormal behavior of tobacco sales based on the isolated forest model of the present invention comprises the following steps:

[0029] (1) Preprocessing the data set;

[0030] (2) Perform feature extraction on the data set;

[0031] (3) Build an isolated forest model;

[0032] (3.1) Randomly extract ψ sample points from the data sample population to form a subset, and put them into the root node of the isolated tree;

[0033] (3.2) Randomly specify a feature q from all features, and randomly generate a cutting point p in the feature value of the current data feature q;

[0034] (3.3) Cut the sample space and divide the current data space into two subspaces;

[0035] (3.4) Judging whether all nodes have only one sample point or the isolated tree reaches the specified heigh...

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 method for realizing tobacco sales abnormal behavior detection based on an isolated forest model. The method comprises the following steps: preprocessing a data set, performing feature extraction on the data set, constructing the isolated forest model, and performing abnormal detection on prediction data through the isolated forest model. By adopting the method for realizing tobacco sales abnormal behavior detection based on the isolated forest model, behavior characteristics and attribute characteristics of fake cigarettes sold by cigarette retailers are analyzed, traditional sales indexes are refined, and attribute characteristics for depicting inherent attributes of retailers, a control time effect and periodic month indexes are added. In combination with thecharacteristics of small data volume and few labels in an actual scene, anomaly detection is made by adopting an unsupervised isolated forest algorithm. Therefore, the algorithm can still obtain a high recall ratio under the condition of small data volume, decision support is provided for law enforcement departments more effectively, and information utilization is maximized.

Description

technical field [0001] The invention relates to the field of tobacco, in particular to the field of abnormal sales behavior detection, and specifically refers to a method for detecting abnormal tobacco sales behavior based on an isolated forest model. Background technique [0002] The state implements a tobacco monopoly management system, which makes the tobacco industry a special industry. It is not only closely related to government fiscal revenue, but also affects the health of consumers. In 2018, the tobacco industry achieved industrial and commercial tax profits of 1,155.6 billion yuan, but at the same time, a small number of cigarette retailers will pursue the maximization of their own interests by selling counterfeit cigarettes. In 2018, 9,100 cases worth more than 50,000 yuan were investigated and dealt with nationwide, and 553,000 counterfeit and non-cigarettes were seized. This kind of behavior has seriously damaged the healthy development of the tobacco industry...

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
IPC IPC(8): G06Q30/02G06Q40/00G06Q50/26G06K9/62
CPCG06Q30/0201G06Q40/10G06Q50/26G06F18/2433
Inventor 王贞陶春和黄丽刘甡泰撖朝润吴志鹏甘小莺
Owner THE THIRD RES INST OF MIN OF PUBLIC SECURITY
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