Automated analysis of unstructured computer text for generation of an enforcement action database using machine learning

A computer system in which unstructured computer text is analyzed for generation of an enforcement action database using machine learning, the system comprising a computing device having a memory for storing computer-executable instructions and a processor that executes the computer-executable instructions to:

• receive a digital document comprising a corpus of unstructured text;
• convert each sentence in the corpus of unstructured text into a set of tokens;
• identify one or more entities in each set of tokens and transform the identified entities into a normalized form;
• classify each sentence in the corpus of unstructured text as relevant to an enforcement action or not relevant to an enforcement action;
• for each sentence classified as relevant to an enforcement action:
• generate a record in a first data structure, the record in the first data structure comprising a name of an entity in the sentence, a type of the entity in the sentence, and a first enforcement attribute;
• generate a record in a second data structure, the record in the second data structure comprising the first enforcement attribute and a second enforcement attribute;
• map the records in the first data structure to the records in the second data structure based upon the enforcement attribute in each data structure to generate a third data structure, each record in the third data structure comprising the name of the entity in the sentence, the type of the entity in the sentence, the first enforcement attribute, and the second enforcement attribute;
• and
• aggregate the records in the third data structure based upon the name of the entity in the sentence and the type of the entity in the sentence to determine an aggregated first enforcement attribute for each entity in the third data structure.