Prediction device and equipment based on BP (Back Propagation) nerve network

Abstract

The invention discloses a prediction device based on a BP (Back Propagation) nerve network. The prediction device comprises a data receiving unit, a data preprocessing unit, an initializing unit, a learning unit, an iteration prediction unit and a data recovery unit. The used improved algorithm can automatically judge the original training data mode, and perform sample establishment and normalization on the original training data mode. The prediction device can be suitable for various complicated situations, has high flexibility and can finish prediction without auxiliary data and recover prediction results to be in a numerical range corresponding to the original training data.

Description

technical field

[0001] The present invention mainly relates to the technical field of data mining. Background technique

[0002] 1. Data mining technology:

[0003] With the development of storage devices and database technology, data storage is no longer a problem. On the contrary, people have begun to feel overwhelmed by a large amount of data. Therefore, there is an urgent need for a scientific method to convert massive data into practically meaningful knowledge for people. And law, data mining is the technology produced under this background.

[0004] In the late 1980s, data mining quietly emerged as a new research field. The purpose of data mining research is to discover those hidden information with specific rules that people are interested in in large data sets. With the development of data mining, this technology is applied in many fields such as business management, government office, scientific research and engineering development.

[0005] In general, the basi...

Images