Back propagation (BP) neural network-based appropriation budgeting method for scientific research project

Abstract

The invention discloses a neural-network-based appropriation budgeting method for a scientific research project, and aims to the problem that scientific research appropriation budgeting accuracy and practicability cannot be combined. The method comprises the following steps of: analyzing components of appropriation of the scientific research project and key factors influencing budgeting, wherein the key factors comprise a research cycle, the number of researchers, a key technical coefficient, a project result coefficient and the innovativeness and complexity of the project; and establishing a quantified expression of the influencing factors, and establishing a nonlinear expression between a quantification result and an appropriation budgeting result of the project through a neural network by taking the quantification result as input and taking the appropriation budgeting result of the project as output. An application result shows that the method is reliable and high in evaluation accuracy.

Description

technical field [0001] The invention relates to a BP neural network-based budgeting method for scientific research project funds, which can realize new scientific research project fund budgets based on historical project fund data. Background technique [0002] At present, the commonly used budgeting methods for scientific research projects include parameter estimation method, engineering estimation method, empirical estimation method and analogous cost estimation method, etc. [0003] According to the historical data of model development, the parameter estimation method takes the characteristic parameters related to the development process as variables, uses mathematical statistics methods, and estimates the cost of new models by establishing a cost estimation relationship (CER). The parameter estimation method can quickly and objectively estimate funds. In the case of accurate and complete historical data, the prediction accuracy is high, but it has high requirements in te...

AI Technical Summary

Problems solved by technology

The present invention utilizes the unique excellent performances of BP neural network parallel distributed processing, self-organization, self-adaptation, self-learning and its fault tolerance, overcomes the shortcomings of the above several estimation methods, and better solves the problem of scientific research project budget factors, nonlinear problems

Images