Effectively classified information processing system

Abstract

The invention discloses an effectively classified information processing system. The system includes a fitting module used for conducting linear regression fitting on data to generate a fitting function, an empirical module used for obtaining empirical risks according to the fitting function and the data, a regularization module used for setting regularization items, a structure module used for calculating the sum of the regularization items and the empirical risks to obtain a structural risk, and an amendment module used for amending the fitting function according to the structural risk. Theregularization items adopt a multi-dimensional function. The fitting function adopts a high-order polynomial. The term number of the high-order polynomial is at least five. The amendment module worksout an L1 norm of the structural risk and conducts amendment on the fitting function according to the L1 norm. According to the effectively classified information processing system, by introducing theregularization items and avoiding items with small influence factors, inhomogeneous similar items cannot be classified into one class, and therefore the precision of an analysis result is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an information processing system for effective classification. Background technique [0002] Data analysis refers to the process of analyzing a large amount of collected data with appropriate statistical analysis methods, extracting useful information and forming conclusions to study and summarize the data in detail. This process is also a supporting process of the quality management system. In practical terms, data analysis can help people to make judgments so that appropriate actions can be taken. The mathematical foundation of data analysis was established in the early 20th century, but it was not until the advent of computers that the practical operation became possible and data analysis was popularized. Data analysis is the product of the combination of mathematics and computer science. [0003] However, in the existing data information analysis methods, because it is i...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that in the existing data information analysis method, since all the items in the data cannot be accurately confirmed, in the analysis results obtained, it is very easy to overfit, that is, similar items of different types Classified into one category, affecting the results of data analysis, the purpose is to provide an effective classification information processing system to solve the above problems

Images