OPEN TEXT HOLDINGS, INC. (20240330764). SYSTEMS AND METHODS FOR FORMAT-AGNOSTIC PUBLICATION OF MACHINE LEARNING MODEL simplified abstract
Contents
SYSTEMS AND METHODS FOR FORMAT-AGNOSTIC PUBLICATION OF MACHINE LEARNING MODEL
Organization Name
Inventor(s)
Abhishek Pattanaik of Hyderabad (IN)
Thirumalesh Yenagandula of Hyderabad (IN)
Mahima Khatri of Puppalaguda (IN)
SYSTEMS AND METHODS FOR FORMAT-AGNOSTIC PUBLICATION OF MACHINE LEARNING MODEL - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240330764 titled 'SYSTEMS AND METHODS FOR FORMAT-AGNOSTIC PUBLICATION OF MACHINE LEARNING MODEL
The abstract describes a system for format-agnostic publication of machine learning models through an API, allowing models from different computing environments to be validated, normalized, and deployed to managed clusters.
- Machine learning models can be submitted through an API for validation and normalization.
- Docker images are generated for each validated model and published to a docker registry.
- The docker images can be deployed to managed clusters in enterprise or cloud computing environments.
- This approach enables deployment of analytics models developed in any environment to any managed cluster.
Potential Applications: - Deployment of machine learning models across different computing environments. - Streamlining the process of validating and deploying models to managed clusters.
Problems Solved: - Simplifies the deployment of machine learning models developed in disparate environments. - Ensures consistency and compatibility of models across different computing environments.
Benefits: - Increased flexibility in deploying machine learning models. - Streamlined process for model validation and deployment. - Enhanced compatibility and consistency of models across different environments.
Commercial Applications: - This technology can be used by companies to efficiently deploy machine learning models across various computing environments, improving operational efficiency and scalability.
Questions about the technology: 1. How does this system ensure the compatibility of machine learning models across different computing environments? 2. What are the key advantages of using docker images for deploying machine learning models?
Original Abstract Submitted
a system for format-agnostic publication of a machine learning model may receive, through an application programming interface (api), machine learning models that have been built, developed, and trained in disparate computing environments, validate and normalize these machine learning models, generate a docker image for each validated and standardized machine learning model, and publish the docker images to a docker registry. the docker images can then be deployed to a managed cluster such as an on-prem managed cluster operating in an enterprise computing environment and/or a managed hyperscale cluster operating in a cloud computing environment. this api-based machine learning model publication approach allows any analytics model developed and trained in any modeling environment be deployed to any managed cluster.
