Procedure extraction and enrichment from unstructured text using natural language processing (NLP) techniques

A computer system for extraction and enrichment of a procedure from an unstructured text document, comprising:

• one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
• identifying a potential location of a procedure in the unstructured text document;
• detecting a beginning boundary and an end boundary associated with the identified potential location of the procedure;
• validating a text associated with the identified potential location of the procedure in the unstructured text document;
• determining an intent from the identified potential location of the procedure based on at least one of the beginning boundary, the end boundary, a surrounding text associated with the identified potential location of the procedure, a context associated with the unstructured text document, and a title of the unstructured text document;
• and enriching the procedure based on the determined intent;
• identifying a plurality of paths in the unstructured text document that lead to a same step in the procedure, wherein the identified plurality of paths are located outside the identified beginning boundary and the identified end boundary;
• and annotating the identified plurality of paths, wherein annotating the identified plurality of paths comprises determining an input/output relation of the identified plurality of paths and storing the determined input/output relation inside the unstructured text document and in a database.

A computer program product for extraction and enrichment of a procedure from an unstructured text document, comprising:

• one or more computer-readable storage devices and program instructions stored on at least one of the one or more tangible storage devices, the program instructions executable by a processor, the program instructions comprising:
• program instructions to identify a potential location of a procedure in the unstructured text document;
• program instructions to detect a beginning boundary and an end boundary associated with the identified potential location of the procedure;
• program instructions to validate a text associated with the identified potential location of the procedure in the unstructured text document;
• program instructions to determine an intent from the identified potential location of the procedure based on at least one of the beginning boundary, the end boundary, a surrounding text associated with the identified potential location of the procedure, a context associated with the unstructured text document, and a title of the unstructured text document;
• and program instructions to enrich the procedure based on the determined intent;
• program instructions to identify a plurality of paths in the unstructured text document that lead to a same step in the procedure, wherein the identified plurality of paths are located outside the identified beginning boundary and the identified end boundary;
• and program instructions to annotate the identified plurality of paths, wherein annotating the identified plurality of paths comprises determining an input/output relation of the identified plurality of paths and storing the determined input/output relation inside the unstructured text document and in a database.