Method, device and readable storage medium for running pluggable machine learning algorithm

Abstract

The invention relates to a method, device and readable storage medium for running a pluggable machine learning algorithm, wherein the method comprises the following steps of: defining a preset algorithm; carrying out uniform encapsulation on the preset algorithm; establishing a machine learning operation framework, and building the uniformly encapsulated preset algorithm in the machine learning operation framework; when an orientation requirement of a user is received, calling the built-in preset algorithm according to the policy mode of the machine learning operation framework. The device hasthe advantages that the uniform encapsulation of the programming interfaces of common statistical analysis, algorithm and optimization parameters is achieved through the machine learning framework, for the machine learning requirements in different scenes, the algorithm design can be completed only by assembling and deploying on the upper layer of the frame, the problem that a prior algorithm canonly solve a single fault is solved, the fast algorithm design through the encapsulation of the preset algorithm and pluggable algorithm replacement of can be achieved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of machine learning, and in particular to a pluggable machine learning algorithm running method, device and readable storage medium. Background technique [0002] Nowadays, artificial intelligence and machine learning are gradually penetrating into various fields. In the direction of IT operation and maintenance, more and more people are paying attention to how machine learning can provide real-time event management capabilities, so as to help large-scale enterprises improve service quality. The key point is to detect anomalies early before users discover problems, thereby reducing the negative impact of production accidents and interruptions. [0003] The current common way in the field of machine learning in the direction of intelligent operation and maintenance is to develop oriented to a specific requirement. For example, in the context of IT operation and maintenance, machine l...

AI Technical Summary

Problems solved by technology

[0004] The current common use method in the field of machine learning is directional development for a specific need. Its data preprocessing, feature engineering, model fitting and evaluation all need to start from scratch each time according to different goals, and there are still primary selection models that are completely inappropriate. possible rework, wasting manpower and time

Images