18071911. ADAPTABLE AND EXPLAINABLE APPLICATION MODERNIZATION DISPOSITION simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

ADAPTABLE AND EXPLAINABLE APPLICATION MODERNIZATION DISPOSITION

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Anup Kalia of White Plains NY (US)

Mihir Choudhury of Jersey City NJ (US)

Jin Xiao of White Plains NY (US)

Divya Sankar of West Nyack NY (US)

John Rofrano of Mahopac NY (US)

Venkata Nagaraju Pavuluri of New Rochelle NY (US)

Lambert Pouguem Wassi of Yonkers NY (US)

Maja Vukovic of New York NY (US)

Michele Merler of New York City NY (US)

ADAPTABLE AND EXPLAINABLE APPLICATION MODERNIZATION DISPOSITION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18071911 titled 'ADAPTABLE AND EXPLAINABLE APPLICATION MODERNIZATION DISPOSITION

Simplified Explanation

The method described in the abstract involves extracting structured information from a natural language problem statement related to application modernization needs using a neural word segmentation method. This information is then used to generate standardized technical entities, business entities, and dispositions through machine learning models. Based on this standardized information, recommended dispositions are generated for technical entities based on business constraints mentioned in the problem statement.

• Extraction of structured information from natural language problem statements
• Generation of standardized technical entities, business entities, and dispositions using machine learning models
• Recommendation of dispositions for technical entities based on business constraints

Potential Applications

This technology can be applied in various industries for automating the process of understanding and solving complex application modernization needs.

Problems Solved

This technology helps in efficiently analyzing and addressing application modernization requirements by automating the extraction and processing of information from natural language problem statements.

Benefits

The benefits of this technology include improved accuracy and speed in generating recommendations for application modernization, leading to more efficient decision-making processes.

Potential Commercial Applications

Automating the analysis and recommendation process for application modernization can be valuable for software development companies, IT consulting firms, and organizations looking to streamline their modernization efforts.

Possible Prior Art

One possible prior art could be the use of natural language processing techniques in software development to automate tasks related to requirements analysis and solution generation.

How does this technology handle complex and ambiguous natural language problem statements?

The method described in the abstract uses a neural word segmentation method to extract structured information from natural language problem statements. This approach helps in breaking down complex statements into manageable components for further processing and analysis.

What are the limitations of using machine learning models for generating standardized entities and dispositions?

While machine learning models can provide valuable insights and recommendations based on input data, they may be limited by the quality and quantity of training data available. Additionally, the accuracy of the recommendations may vary depending on the complexity of the problem statement and the capabilities of the models used.

Original Abstract Submitted

A method includes receiving a natural language problem statement corresponding to application modernization needs of a user, the natural language problem statement including at least one technical entity, business constraint and disposition information; providing structured information by extracting information from the natural language problem statement using a neural word segmentation method; generating standardized technical entities, standardized business entities, and standardized dispositions by inputting the structured information to at least one machine learning model; and generating at least one recommended disposition of at least one technical entity to a second technical entity based at least on a business constraint corresponding to the natural language problem statement using the standardized technical entities, business entities, and dispositions. Optionally, the at least one recommended disposition corresponds to one or more possible target environments along with explanation generated based on the business constraints and mentions of technical entities present in the natural language problem statement.