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

A method for predicting poverty degree of students based on machine learning

A technology of machine learning and forecasting methods, applied in forecasting, instrumentation, unstructured text data retrieval, etc., can solve problems such as egalitarianism defects

Active Publication Date: 2019-01-04
北京桃花岛信息技术有限公司
View PDF9 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the defect of egalitarianism when poor students are subsidized, and propose a method for predicting the poverty degree of students based on machine learning

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
  • A method for predicting poverty degree of students based on machine learning
  • A method for predicting poverty degree of students based on machine learning
  • A method for predicting poverty degree of students based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] A method for predicting the degree of poverty of students based on machine learning, characterized in that: comprising the following steps;

[0055] Step A1, data acquisition: the data includes poverty alleviation data, civil affairs department data, student aid system data, student engineering system data, school educational administration system data, campus card consumption data, online behavior data, attendance system data, school forum data, books Museum data, school hospital system data, and establish a database for storage;

[0056] The acquisition of data includes extracting basic student information data, including name, place of origin, ethnicity, nationality, health status, political status, whether to enroll through the green channel, whether to apply for a student source loan, whether to apply for a campus loan, whether to enjoy a supplement, What kind of rewards or funding received during the university, enrollment method, school name, student number, coll...

Embodiment 2

[0095] Embodiment 2, a method for extracting the causes of impoverished students, comprising the following steps:

[0096] Step B1, data acquisition: the data includes poverty alleviation data, civil affairs department data, student aid system data, student engineering system data, school educational administration system data, campus card consumption data, online behavior data, attendance system data, school forum data, books Museum data, school hospital system data, and establish a database for storage;

[0097] Step B2, data analysis, divide the data into unstructured text data and structured data, use NLP natural language processing technology for text data, call the snownlp library in python to realize text segmentation, named entity recognition, and syntax analysis functions, and extract text Describe the object and object characteristics in it, and make a table output.

Embodiment 3

[0098] Embodiment 3, a method for rapid monitoring and filtering of data of abnormally poor students, comprising the following steps:

[0099] Step C1, data acquisition: the data includes poverty alleviation data, civil affairs department data, student aid system data, student engineering system data, school educational administration system data, campus card consumption data, online behavior data, attendance system data, school forum data, books Museum data, school hospital system data, and establish a database for storage;

[0100] Step C2, data analysis, divide the data into unstructured text data and structured data, and store the structured data directly in the database;

[0101] Step C3, discover and fill in the missing data, use different filling strategies according to different missing situations, including mean value filling, interpolation, and fitting, and complete the initialization of missing data;

[0102] Step C4, performing linear transformation on the origina...

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 predicting poverty degree of students based on machine learning. Through obtaining the data of students' relevant channels, we analyze the data and calculate thevarious eigenvalues of students' poverty, fill the missing values, standardize the data and map them to fixed intervals. Then, according to the fast clustering algorithm, we use Euclidean distance toaggregate the data into multiple categories, and calculate the importance of each category to evaluate the degree of poverty. A matrix compose of each group of data after classification is divided into blocks according to that correlation, and finally the poverty comprehensive score is calculated accord to the matrix after the blocks, and the comprehensive score can be used for reference in the aid amount decision of the aid for the poor students, wherein the higher the score is, the poorer the aid is, and the more the aid is needed. The invention also provides several schemes for quickly discovering abnormal poor students and screening the causes of poverty from the data.

Description

technical field [0001] The invention belongs to the field of big data application technology, and in particular relates to a machine learning-based method for predicting students' poverty levels. Background technique [0002] At present, student aid basically adopts a one-size-fits-all approach. The school allocates funds to students with poorer families in the class according to a fixed ratio. At present, most colleges and universities mainly rely on the student’s family economic situation questionnaire and comprehensively reflect the situation reported by relevant teachers and classmates. Preliminary determination of family economic situation in the class. The degree of poverty of sponsored students cannot be quantified, and funding will inevitably fall into egalitarianism. [0003] With the development of technology in the era of big data, the global backbone communication network transmits tens of terabytes of data every day. Everyone's behavior is recorded by various f...

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): G06F16/35G06Q10/04G06Q50/20
CPCG06Q10/04G06Q50/205
Inventor 陈岩俞跃舒
Owner 北京桃花岛信息技术有限公司
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