International business machines corporation (20240256852). ENTITY STANDARDIZATION FOR APPLICATION MODERNIZATION simplified abstract

ENTITY STANDARDIZATION FOR APPLICATION MODERNIZATION

Organization Name

international business machines corporation

Inventor(s)

Jiaqing Yuan of Raleigh NC (US)

Michele Merler of New York NY (US)

Mihir Choudhury of Jersey City NJ (US)

Venkata Nagaraju Pavuluri of New Rochelle NY (US)

Maja Vukovic of New York NY (US)

ENTITY STANDARDIZATION FOR APPLICATION MODERNIZATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240256852 titled 'ENTITY STANDARDIZATION FOR APPLICATION MODERNIZATION

The abstract of the patent application describes a method for standardizing a mention of an application component in a free-form text by encoding the mention with an embedding space encoder, creating an encoded representation in a multi-dimensional space, and mapping it to an entity in a knowledge base.

• The method involves extracting and encoding mentions of application components in a technology stack text.
• The encoding is done using a machine learning model trained with contrastive learning.
• The encoded representation of the mention is mapped to an entity in a multi-dimensional embedding space from a knowledge base of computer components.
• The output is the entity whose encoded representation maps to the mention's encoded representation.

1. 1. 1. Potential Applications:

This technology can be used in natural language processing applications, information retrieval systems, and knowledge base management tools.

1. 1. 1. Problems Solved:

This technology addresses the challenge of standardizing mentions of application components in unstructured text, improving search accuracy and information retrieval.

1. 1. 1. Benefits:

The method improves the efficiency of extracting and encoding application component mentions, enhancing the accuracy of mapping to entities in a knowledge base.

1. 1. 1. Commercial Applications:

This technology can be applied in software development tools, search engines, and data management systems to streamline information processing and enhance search capabilities.

1. 1. 1. Questions about the Technology:

1. How does the contrastive learning approach improve the encoding of mentions in the embedding space? 2. What are the potential limitations of mapping mentions to entities in a knowledge base using this method?

1. 1. 1. Frequently Updated Research:

Stay updated on advancements in machine learning models for text encoding and entity mapping to enhance the efficiency and accuracy of this technology.

Original Abstract Submitted

standardizing a mention of an application component in a free-form text describing the technology stack of the application includes extracting the mention and encoding the mention with an embedding space encoder. the encoding creates an encoded representation of the mention in a multi-dimensional embedding space. the embedding space encoder implements a machine learning model trained using contrastive learning. the encoded representation of the mention is mapped to an encoded representation of an entity in the multi-dimensional embedding space, the entity extracted from a knowledge base of computer components. the entity whose encoded representation maps to the encoded representation of the mention can be output responsive to the mapping.