Method and system for excavating approximate dictionary rule of database, and database terminal

Abstract

The invention is applicable to the field of approximate dictionary rule excavation, and provides a method and a system for excavating an approximate dictionary rule of a database, and a database terminal. The method for excavating the approximate dictionary rule comprises the following steps: scanning and analyzing a database r, getting rid of single value columns, and columns in which all values are unique, and marking a remaining candidate column set as R; counting the support degree of each item in each column in the candidate column set R, and ending an item of which the support degree is greater than a given minimum support degree with an integer; numbering events in each row in the database r sequentially, recording the row event number of each item with a list, and caching; excavating the approximate dictionary rule of the database r by an LCfd (large Chinese face database) method; outputting the approximate dictionary rule. By applying the approximate dictionary rule excavating method of the LCfd to the database and through a reversely increasing search strategy, a search tree is pruned by a pruning method and a rule which has been found is cached, so that the computing amount of the whole excavating method can be reduced and the approximate dictionary rule in the database can be automatically and efficiently found out.

Description

technical field

[0001] The invention relates to the field of mining approximate dictionary rules, in particular to a method, system and database terminal for mining approximate dictionary rules in a database. Background technique

[0002] With the rapid development of the Internet and the improvement of informatization in various fields of society, the amount of data is blowing out at an unprecedented rate, and human beings are entering the era of big data. The era of big data is characterized by a larger amount of data, more complex data sources, faster data updates, and uneven data quality. It is almost impossible to manage data quality only by manual means. The field of data management is undergoing major changes and breakthroughs. The technologies that have been commercialized basically stay in the second-generation data quality management stage that is manual and based on experience. didn't show up. An important part of the automated management system is the automated...

Examples

Embodiment Construction

[0111] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0112] Related concepts

[0113] Consider the database r, define the set of all columns in r as R, and the different values ​​in each column are called items (item), and the set of all items is defined as item set I; each row of r is called transaction t (transaction),

[0114] (1) Support: For a given itemset Define its support degree supp(X) as the number of transactions containing item set X in r, which satisfies number of transactions.

[0115] (2) Superset, subset: For two itemsets X, Y, if satisfy Then it is said that Y is a superset of X, X is a subset of Y, and there is supp(Y)<=su...

technical field

[0001] The invention relates to the field of mining approximate dictionary rules, in particular to a method, system and database terminal for mining approximate dictionary rules in a database. Background technique

[0002] With the rapid development of the Internet and the improvement of informatization in various fields of society, the amount of data is blowing out at an unprecedented rate, and human beings are entering the era of big data. The era of big data is characterized by a larger amount of data, more complex data sources, faster data updates, and uneven data quality. It is almost impossible to manage data quality only by manual means. The field of data management is undergoing major changes and breakthroughs. The technologies that have been commercialized basically stay in the second-generation data quality management stage that is manual and based on experience. didn't show up. An important part of the automated management system is the automated...

Examples

Embodiment Construction

[0111] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0112] Related concepts

[0113] Consider the database r, define the set of all columns in r as R, and the different values ​​in each column are called items (item), and the set of all items is defined as item set I; each row of r is called transaction t (transaction),

[0114] (1) Support: For a given itemset Define its support degree supp(X) as the number of transactions containing item set X in r, which satisfies number of transactions.

[0115] (2) Superset, subset: For two itemsets X, Y, if satisfy Then it is said that Y is a superset of X, X is a subset of Y, and there is supp(Y)<=su...

Images