Database table intelligent classification method and device, electronic equipment and storage medium

Abstract

The invention relates to the field of intelligent decision, and discloses a database table intelligent classification method, which comprises the following steps of: acquiring historical data of a data table, and performing entry division on the historical data according to a preset custom dictionary to obtain entry data; converting the entry data into a spatial vector, performing dimension reduction processing on the spatial vector to obtain a dimension-reduced vector, and calculating a weight value of the dimension-reduced vector; training a pre-constructed data table classification model by using the dimension reduction vector and the weight value to obtain a trained data table classification model; and classifying the to-be-classified data tables by using the trained data table classification model to obtain a classification result. The classification accuracy of the data tables can be improved.

Description

technical field [0001] The invention relates to the field of intelligent decision-making, in particular to a method, device, electronic device and storage medium for intelligent classification of database tables. Background technique [0002] With the rapid development of the Internet in recent years, the amount of data has grown exponentially. At the same time, more and more enterprises have gradually understood the value contained in data, and have paid more and more attention to data. At this time, data governance came into being. Only by doing a good job in data governance and improving data quality can we do a good job in data analysis and effectively mine data value. Among them, in data value mining, the classification of data tables for storing data is an indispensable link. Classification is the process of classifying multiple data tables into different types. [0003] At present, the classification of data tables is mainly realized by word frequency classification ...

AI Technical Summary

Problems solved by technology

[0003] At present, data table classification is mainly realized through the word frequency classification algorithm, that is, word frequency statistics are made after word segmentation of all metadata in the data table, and according to the results of word frequency statistics, the top-ranked metadata categories are selected as the classification of the data table category, but because in actual business scenarios, many metadata will contain different data categories, so there will be multiple metadata categories in the process of word frequency statistics, which will easily affect the category accuracy of subsequent word frequency statistics, which in turn will affect the data The classification accuracy of the table

Images