Method and system for processing data table and automatically training machine learning model

Abstract

The invention provides a method and a system for processing a data table and automatically training a machine learning model. The method for processing the data tables comprises the steps that table relation configuration information about a plurality of data tables is obtained, and the table relation configuration information comprises the incidence relation between every two data tables; based on the table relationship configuration information, splicing the plurality of data tables into a basic sample table; and generating derivative features about the fields based on the fields in the basic sample table, and merging the generated derivative features into the basic sample table to form a sample table comprising a plurality of machine learning samples.

Description

technical field [0001] The present disclosure generally relates to the field of data processing, and more specifically, relates to a method and system for processing data tables, and a method and system for automatically training machine learning models. Background technique [0002] In real business environments such as online advertising, recommendation systems, financial market analysis, and medical care, data comes from a wide range of sources and is often stored in different data tables. At the same time, data such as user behavior or product transaction volume will change over time, so there is a large amount of time-series relational data. [0003] In machine learning applications, scientists with rich modeling experience need to go through continuous trial and error to construct valuable features based on multiple related data tables to improve the effect of machine learning models. Contents of the invention [0004] Exemplary embodiments of the present disclosure...

AI Technical Summary

Problems solved by technology

[0004] Exemplary embodiments of the present disclosure provide a method and system for processing data tables to solve the problem in the prior art that multiple data tables cannot be conveniently and effectively processed to obtain machine learning samples

In addition, the exemplary embodiments of the present disclosure also provide a method and system for automatically training a machine learning model, so as to solve the problem existing in the prior art that machine learning cannot be effectively performed automatically starting from data splicing

Images