Machine-learning model to predict probability of success of an operator in a PaaS cloud environment

Patent metadata

Field	Value
Publication number	US-12124924-B2
Application number	US-202016950228-A
Country	US
Kind code	B2
Filing date	Nov 17, 2020
Priority date	Nov 17, 2020
Publication date	Oct 22, 2024
Grant date	Oct 22, 2024

Abstract

Systems and methods are provided that integrate a machine-learning model, and more specifically, utilizing a platform as a service (PaaS) cloud to predict probability of success for an operator in an environment. An embodiment comprises a system having: a processor that executes computer executable components stored in memory, trained machine-learning model that predicts probability of success for deployment of an operator in an environment with a namespace of a platform as a service (PaaS) cloud, and a deployment component that receives a first operator and a first namespace and employs the trained machine-learning model to predict success of deployment of the first operator in a first environment.

First claim

What is claimed is:

1. A system, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise;
a training component that trains, using training data comprising historical operators, historical environments, historical namespaces associated with historical environments, historical configurations associated with the historical namespaces, historical outcomes indicative of whether respective combinations of historical operators and features of the historical configurations were successful, a machine-learning model to:
convert respective descriptions of the historical operators into historical description vectors,
convert respective program code of the historical operators into historical code vectors,
convert the features of the historical configurations into historical feature vectors,
generate combination vectors based on the historical description vectors, the historical code vectors, the historical feature vectors, and the historical outcomes, and
predict, based on the combination vectors, probabilities of success for deployments of operators that perform automated functions related to system management in environments with namespaces in platforms as a service cloud, wherein the namespaces have respective configurations associated with isolated entities in the environments; and

a deployment component that:
receives a first operator and a first namespace of a first environment of a first platform as a service cloud, and
employs the machine-learning model to predict a probability of success of deployment of the first operator in the first namespace of the first environment.

2. The system of claim 1 , wherein the first namespace has a first configuration that applies to the first namespace.

3. The system of claim 1 , wherein the deployment component, in response to the probability of success exceeding a defined threshold, deploys the first operator in the first namespace of the first environment.

4. The system of claim 1 , wherein the deployment component, in response to the probability of success not exceeding a defined threshold, generates a notification regarding a predicted failure of the first operator in the first namespace of the first environment.

5. The system of claim 1 , wherein the machine-learning model employs similarity learning to predict the probability of success of deployment of the first operator in the first namespace of the first environment.

6. The system of claim 5 , wherein the similarity learning is utilized to provide instructions regarding troubleshooting deployment of the first operator deployment in the first namespace of the first environment.

7. The system of claim 5 , wherein the similarity learning is used to generate a flag regarding security issues associated with deployment of the first operator deployment in the first namespace of the first environment.

8. A computer-implemented method, comprising:
training, by a system operatively coupled to a processor, using training data comprising historical operators, historical environments, historical namespaces associated with historical environments, historical configurations associated with the historical namespaces, historical outcomes indicative of whether respective combinations of historical operators and features of the historical configurations were successful, a machine-learning model to;
convert respective descriptions of the historical operators into historical description vectors,
convert respective program code of the historical operators into historical code vectors,
convert the features of the historical configurations into historical feature vectors,
generate combination vectors based on the historical description vectors, the historical code vectors, the historical feature vectors, and the historical outcomes, and
predict probabilities of success for deployments of operators that perform automated functions related to system management in environments with namespaces in platforms as a service cloud, wherein the namespaces have respective configurations associated with isolated entities in the environments;

receiving, by the system, a first operator and a first namespace of a first environment of a first platform as a service cloud; and
predicting, by the system, using the machine-learning model, a probability of success of deployment of the first operator in the first namespace of the first environment.

9. The computer-implemented method of claim 8 , wherein the first namespace has a first configuration that applies to the first namespace.

10. The computer-implemented method of claim 8 , further comprising, in response to the probability of success exceeding a defined threshold, deploying, by the system, the first operator in the first namespace of the first environment.

11. The computer-implemented method of claim 8 , further comprising, in response to the probability of success not exceeding a defined threshold, generating, by the system, a notification regarding a predicted failure of the first operator in the first namespace of the first environment.

12. The computer-implemented method of claim 8 , further comprising employing, by the system, similarity learning to predict the probability of success of deployment of the first operator in the first namespace of the first environment.

13. The computer-implemented method of claim 12 , further comprising utilizing the similarity learning to provide instructions regarding troubleshooting deployment of the first operator deployment in the first namespace of the first environment.

14. The computer-implemented method of claim 12 , further comprising utilizing the similarity learning to generate a flag regarding security issues associated with deployment of the first operator deployment in the first namespace of the first environment.

15. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
train, using training data comprising historical operators, historical environments, historical namespaces associated with historical environments, historical configurations associated with the historical namespaces, historical outcomes indicative of whether respective combinations of historical operators and features of the historical configurations were successful, a machine-learning model to:
convert respective descriptions of the historical operators into historical description vectors,
convert respective program code of the historical operators into historical code vectors,
convert the features of the historical configurations into historical feature vectors,
generate combination vectors based on the historical description vectors, the historical code vectors, the historical feature vectors, and the historical outcomes, and
predict probabilities of success for deployments of operators that perform automated functions related to system management in environments with namespaces in platforms as a service cloud, wherein the namespaces have respective configurations associated with isolated entities in the environments;

receive a first operator and a first namespace of a first environment of a first platform as a service cloud;
predict, using the machine-learning model, a probability of success of deployment of the first operator in the first namespace of the first environment.

16. The computer program product of claim 15 , wherein the first namespace has a

Assignees

• IBM

Inventors

• Kanso Ali
• Hwang Jinho
• Bulut Muhammed Fatih
• Nadgowda Shripad
• Lin Chen

Classifications

• G06F8/61

  Installation · CPC title

• H04L41/50

  Network service management, e.g. ensuring proper service fulfilment according to agreements · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F8/60 Primary

  Software deployment · CPC title

• G06N3/02

  Neural networks · CPC title