Process visualization modeling method, server, computer system and medium

Abstract

The invention discloses a flow visualization modeling method, a server, a computer system and a medium. In a specific implementation mode, the modeling method comprises the steps that a directed acyclic graph is constructed in response to a first operation of a user on a graphical component on an interactive interface, and the directed acyclic graph comprises a plurality of intermediate components generated by the graphical component and connecting lines representing the data flow direction between the intermediate components; in response to a second operation of the user on any intermediate component in the directed acyclic graph, executing model training on any intermediate component; in response to a third operation of the user on the intermediate component after the model training is executed, visually displaying a training result; and in response to a fourth operation of the user on the intermediate component after the model training is executed, instantiating the intermediate component so as to generate the model.

Description

technical field [0001] The present invention relates to the field of computer modeling. More specifically, it relates to a process visualization modeling method, server, computer system and medium. Background technique [0002] The existing model creation process is very cumbersome. Taking the creation of a machine learning model as an example, the creation process usually includes: feature analysis, model training, model validation, model tuning, model export, and model loading. Among them, each stage needs to be coded independently, especially the creation and analysis process is very cumbersome and time-consuming, requiring a lot of time for data analysts and engineers. [0003] In addition, a large number of tools in the field of machine learning are currently programming machine learning libraries, such as R, Python, and the deep learning library Caffe. These machine learning tools have certain thresholds and have a relatively high learning curve. data analyst. There...

AI Technical Summary

Problems solved by technology

[0005] However, this solution only discloses a solution for verifying the entire model, although it mentions that intermediate results can be displayed, but "displaying intermediate results" in the specification specifically refers to displaying the status and calculation progress of each intermediate stage, etc.

In this case, if the calculation logic of a certain step in the middle is wrong, the model needs to be reconstructed again. Therefore, the visual modeling method in the related art cannot guarantee the modeling accuracy of the entire modeling process

Images