Chinese interword weighing positive and negative mode excavation method and system based on relevant coefficients

Abstract

The invention discloses a Chinese interword weighing positive and negative mode excavation method and a Chinese interword weighing positive and negative mode excavatiom system based on relevant coefficients. The method comprises the steps of preprocessing a Chinese text through a Chinese text information preprocessing module; generating a feature word candidate 1-item set through a Chinese feature word candidate item set generation module, generating a candidate i-item set according to a candidate (i-1)-item set from an i item set (i is greater than or equal to 2), calculating the supporting degree of the candidate i-item set, obtaining a frequency item set and a negative item set, and performing item set cutting according to the association of the item sets to obtain an interesting feature word frequent item set and a negative item set; calculating an association rule interesting degree and a confidence coefficient through a Chinese feature word positive and negative association rule generation and result display module, and displaying an interesting feature word positive and negative association rule mode excavated from the frequent item set and the negative item set to a user. According to the method and the system, appearance of ineffective and uninteresting Chinese feature word association modes can be avoided, and the excavation efficiency is greatly improved; the association rule mode is applied to the field of Chinese text information retrieval, so that inquiry expansion is realized; the information retrieval and inquiry performance is improved.

Description

technical field [0001] The invention belongs to the field of text mining, and specifically relates to a correlation coefficient-based Chinese inter-word weighted positive and negative pattern mining method and its mining system, which is applicable to the discovery of feature word association patterns in Chinese text mining and Chinese text information retrieval query expansion, cross-language information retrieval etc. The positive and negative association mode of the feature words of the present invention is applied to web search engines such as Baidu and Google to realize query expansion, which helps to improve their query performance and meet the needs of users for querying information. Background technique [0002] In the past 20 years, remarkable achievements have been made in association pattern mining research, which can be summarized as unweighted positive and negative association pattern mining technology, weighted positive and negative association pattern mining t...

AI Technical Summary

Problems solved by technology

The disadvantage of unweighted positive and negative association pattern mining is that it does not consider the different importance of items and the different weights of items in the transaction database, resulting in a large number of invalid, redundant and uninteresting association patterns.

The defect of item weighted positive and negative association mode mining is that it ignores the case that item weights have different weights in the transaction database

These methods effectively mine matrix-weighted association rules, but cannot mine matrix-weighted negative association patterns

Images