Unlock instant, AI-driven research and patent intelligence for your innovation.

Academic score prediction method based on C-LSTM

A prediction method and performance technology, applied in the field of academic performance prediction based on C-LSTM, can solve the problems of small samples, untrue feedback, analysis errors, etc., and achieve high accuracy

Pending Publication Date: 2020-09-25
BEIJING UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method mainly faces problems such as small samples and untrue feedback, which will lead to certain analysis errors.

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
  • Academic score prediction method based on C-LSTM
  • Academic score prediction method based on C-LSTM
  • Academic score prediction method based on C-LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] 1. Campus big data analysis platform

[0015] The platform is a supporting framework for academic performance prediction, mainly used for the collection, analysis and management of multi-source heterogeneous data, and can be divided into five layers from bottom to top, namely data source layer, data collection layer, data storage and analysis layer, Data management layer, data analysis and visualization layer. The overall framework is as figure 1 .

[0016] (1) Data source layer. This layer is mainly used to connect the data of various business systems. The data can be divided into three types: structured data, semi-structured data and unstructured data. For example, artificial statistical information and student status information of students are structured data, which can be Directly use relational database storage; students’ online log data is semi-structured data, which is generally stored in the form of files, which can be converted into structured data through ...

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 provides a score classification prediction method based on a deep learning technology. The score classification prediction method is integrally divided into three stages of data collection, data preprocessing and data modeling. The data collection stage is responsible for collecting multi-source heterogeneous data of students, including basic information, all-purpose card consumptiondata, record data of entering a library and internet log data; in the data preprocessing stage, standardization, deduplication or merging operation is mainly carried out on data. In the data modelingstage, firstly, features are extracted from different behavior data, and then classification prediction is conducted by combining all the behavior features and the basic information features. According to the invention, the multi-source behavior data of students is collected, after data preprocessing, the deep learning model is directly utilized to autonomously learn features and perform score classification prediction, manual feature extraction is not needed, and the prediction analysis result has high accuracy.

Description

technical field [0001] The invention relates to a method for classifying and predicting academic performance based on deep learning technology and using basic information of students and campus behavior data. The technology can be widely applied to the scene of classifying and predicting using basic prior knowledge and multi-source sequence data. The present invention relates to the classifying of student achievement in the field of education. Background technique [0002] The Ministry of Education issued the "Education Informatization 2.0 Action Plan" in 2018, which requires deepening the application of educational big data and comprehensively improving the ability of education management informatization to support business management, government services, and teaching management; vigorously promote smart education, and carry out Learner-centered intelligent teaching supports the construction of an environment, promotes the full-process application of artificial intelligenc...

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): G06Q10/04G06Q50/20G06N3/04G06N3/08
CPCG06Q10/04G06Q50/205G06N3/049G06N3/08G06N3/045
Inventor 李小勇张勇尹宝才周菲菲
Owner BEIJING UNIV OF TECH