College poor student accurate subsidy model based on LSTM neural network

Abstract

The invention discloses a college poor student precise subsidy model based on a long short-term memory (LSTM) neural network, which constructs the college poverty student precise subsidy model based on the LSTM neural network, analyzes the number of hidden layer neural units of the LSTM neural network through a data experiment, trains a relationship between an optimization algorithm and a povertystudent subsidy level recognition rate, and structure and parameter optimization is carried out on the college poor student accurate subsidy model based on the LSTM. The accurate subsidy model can identify the national college subsidy level according to the college poverty student consumption data, provides an intelligent quantification tool for accurate identification and classification of college poverty student subsidy, can reduce human interference factors, and has innovative significance for college student subsidy and learning assistance work.

Description

technical field [0001] The invention relates to an accurate subsidy model for impoverished college students based on LSTM neural network. Background technique [0002] The funding system for impoverished students in colleges and universities is an important part of national education poverty alleviation. With the rapid development of social economy, the funding system for impoverished students in colleges and universities is also facing some basic and common problems, and the identity identification of poor students has always been the foundation and difficulty of funding work At this stage, there are mainly problems such as simple identification basis, interference from human factors, one-sided reference standards, and difficulty in verifying the authenticity of quantitative indicators. At this stage, the research on precision funding for education mainly focuses on the precise identification of funding targets. The current research results are mainly divided into the foll...

AI Technical Summary

Problems solved by technology

[0004] The second is to carry out research on the implementation plan of the precise identification technology of funding objects from the technical path level, and this aspect of research is seldom reported.

[0005] The above research still needs to be further studied: first, the existing technology implementation scheme is not perfect in accurately identifying funding objects, and more is to verify the operation of the funding system and find "suspicious" objects; second, how to use big data Thinking digs out the interrelationships and potential laws from the massive data, so as to accurately identify the objects to be funded needs in-depth research. The traditional mathematical models and methods in the context of big data research have been "incapable"

However, since the BP neural network weight adjustment adopts the negative gradient descent method, if the initial state parameters are not properly selected, it is easy to make the convergence speed of the BP network very slow or even stop, so that the BP neural network falls into a local minimum and the recognition fails; and the test The number of samples is small, and more data needs to be provided for testing in the verification of model identification accuracy, and there is a lack of theoretical guidance in the selection of identification features for poor students;

Images