Methods and systems for visualizing feature generation process in machine learning process

Abstract

A method and system for visualizing a feature generation process in a machine learning process is provided. The method comprises the following steps: determining a feature for visualizing a generationprocess; analyzing at least one data processing step for generating the feature in the machine learning process to obtain generation process information of the feature, the generation process information comprising data information and / or processing information of the at least one data processing step; generating a process display view for depicting a generation process of the feature based on the generation process information; and graphically displaying the process display view.

Description

technical field [0001] The present invention relates to the field of machine learning, more specifically, to a method and system for visualizing the feature generation process in the machine learning process. Background technique [0002] With the advent of the big data era, many industries generate massive amounts of data, and the data types, data scale, and data dimensions are constantly expanding. In order to discover knowledge and value from massive data, the application of machine learning technology is becoming more and more extensive. [0003] Here, data, as the raw material of the machine learning process, is of great significance to the effect of the machine learning model. In order to apply data to machine learning, it is often necessary to perform corresponding processing on the data, such as data cleaning, data filling, and data splicing. or feature extraction etc. [0004] In practice, the data processing process can be realized by running the code written by ...

AI Technical Summary

Problems solved by technology

[0004] In practice, the data processing process can be realized by running the code written by the programmer, or it can be realized by the machine learning platform according to the script, configuration and / or interactive operation input by the user. The entire data processing process often involves a huge amount of data or complex processing operations

The interaction between existing machine learning platforms and users is poor, and general users cannot intuitively understand the logical thinking and working details of the data processing process, that is, it is difficult to understand the generation process of a specific feature

Even if users understand each step in the entire machine learning process, it is difficult to quickly discern which data processing steps a specific feature is associated with

As a result, for example, when anomalies or errors occur in the machine learning process, it is difficult for users to quickly trace the source of the anomalies or errors, or when they are interested in certain features in the machine learning process, it is difficult for users to quickly understand the details about features

On the existing machine learning platform, users can only rely on the user to gradually decompose and analyze the entire machine learning process, and then the user can extract the meaning of specific features and its generation process. However, this will increase the burden on users and seriously affect Promotion and application of machine learning technology

Images