A code-generated machine learning model full-process automatic deployment method and system

Abstract

The present application discloses a method and system for automatically deploying the whole process of a code-generated machine learning model. The method includes: obtaining the step information of the whole process of the first machine learning model; Online software, obtaining the first online software environment; further generating the first character string template; inputting the first character string template for rendering by extracting the trained parameters in the data processing operator, and generating a single-step code text; generating a first deployment structure; constructing a first general prediction template; and obtaining a first deployment result based on the single-step code text. It solves the technical problem in the existing technology that the automatic deployment of the whole process of the machine learning model cannot be realized based on the code generation technology, so that the real-time prediction performance of the machine learning model cannot be further improved. It has achieved the technical effect of using the code generation technology in the compilation principle to realize the automatic deployment of the whole process of the machine learning model.

Description

technical field [0001] The present application relates to the field of computers, and in particular to a method and system for automatically deploying a machine learning model for code generation throughout the entire process. Background technique [0002] Algorithm engineers often need to train models in production, and deploy the trained models to online software systems, that is, convert the calculation results of some third-party open source frameworks or enterprise internal frameworks on data into an online service, which can Get the same effect as the offline model. However, machine learning models running in production are complex software systems. Unlike ordinary software development and deployment, machine learning engineers face some new challenges. For example, complex model pipelines are composed of different data processing operations and usually contain many parameters; even multiple model pipelines will be integrated, which seriously exacerbates the difficul...

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to provide a code-generated machine learning model full-process automatic deployment method and system to solve the problem in the prior art that the automatic deployment of the whole process of the machine learning model cannot be realized based on the code generation technology, so that the machine learning model cannot be further improved. Technical Issues of Learning Models for Real-time Predictive Performance

Images