DEPLOYMENT SCHEDULING USING FAILURE RATE PREDICTION

Patent №

US 11,093,229

Granted

2021-08-17

Filed 2020

Owner

INTERNATIONAL BUSINESS MACHINES CORPORATION

AI components

3

ml · planning · evo

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16749465

A failure rate model modeling a failure rate of a training functionality deployment in a training set of functionality deployments is constructed. The failure rate model is configured to receive functionality deployment data and output a corresponding failure rate prediction. Using the failure rate model, a set of functionality deployment failure rates is predicted, a functionality deployment failure rate in the set of functionality deployment failure rates corresponding to an upcoming functionality deployment. Using the set of functionality deployment failure rates, a deployment sequence of the set of upcoming functionality deployments is constructed to minimize a predicted overall failure rate of the set of upcoming functionality deployments. The deployment of each functionality deployment in the set of upcoming functionality deployments is caused, the deployment comprising activating the upcoming functionality program code according to the deployment sequence.

AI classification

Machine learning1.00
Evolutionary computation0.99
Planning0.97
Knowledge representation0.15
AI hardware0.10
Natural language0.03
Vision0.00
Speech0.00

Ownership

INTERNATIONAL BUSINESS MACHINES CORPORATION

assignment · 515860515

Assignors

TIWARI, PRANSHU, BHARTI, HARISH, NARAYANASWAMY, NAVEEN, MUNAGALA, RAM PRASAD REDDY

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC