Method and device for calculating character string similarity and material classification method and device

Abstract

The invention discloses a character string similarity calculation method and device as well as a material classification method and device. The similarity calculation method includes: calculating the initial similarity between the character string X and the character string di; obtaining the character string X and the character string di; The longest common prefix and the longest common suffix between di; determine the weight of the longest common prefix and the weight of the longest common suffix; and calculate the similarity between the string X and the string di. Through the above technical scheme, aiming at the characteristics of Chinese material names, the present invention provides a method for calculating the similarity of Chinese character strings oriented to material classification (that is, the dynamic weight method (DynamicWeight)), which can dynamically estimate the material name characters The weight of the prefix and suffix of the string makes the material names of the same category have a higher similarity, which improves the accuracy of automatic material classification.

Description

technical field [0001] The present invention relates to the fields of similarity calculation and material classification, in particular to a string similarity calculation method and device based on string prefix and suffix dynamic weights, and a material classification method and device. Background technique [0002] At present, relatively mature text automatic classification technologies include neural network (Neural Net, NNet), support vector machine (Support Vector Machine, SVM), simple Bayesian (Naive Bayes, NB), k nearest neighbor (k nearest neighbor, k-NN ) and linear least squares fitting (Linear Least Squares Fit, LLSF), etc. To apply these methods to material classification, it is necessary to solve the problem of calculating the similarity between materials. Different from the application environment of traditional automatic text classification, the names and descriptions of materials in enterprises are often relatively short, and the text similarity calculation ...

AI Technical Summary

Problems solved by technology

[0004] Although there have been many achievements in the research of text classification and string similarity, there is no research specifically on the classification of enterprise materials in the Chinese environment.

Images