Dynamic question formulation to query data sources

A computer program product comprising:

• a non-transitory computer readable storage medium readable by one or more processor and storing instructions for execution by the one or more processor for performing a method comprising:
• obtaining, by one or more processor, a natural language query, wherein the natural language query is comprised of a first group of terms;
• converting, by the one or more processor, the natural language query to a machine language query and executing the machine language query on at least one computer resource;
• obtaining, by the one or more processor, search results responsive to the machine language query, wherein the search results comprise related terms derived from terms in the first group of terms, wherein one or more processor derived the related terms utilizing concept expansion;
• parsing, by the one or more processor, the search results by applying a statistical information extraction to the terms in the first group of terms and to the related terms to identify as entities at least one of:
• a portion of the terms, or a portion of the related terms, wherein the parsing comprises:
• utilizing, by the one or more processor, the natural language query to perform an automated search to ingest entries from a structured data source;
• generating, by the one or more processor, a sentiment measure for each ingested entry;
• and extracting, by the one or more processor, trending terms to identify the entities;
• and generating, by the one or more processor, at least one additional natural language query by incorporating a portion of the identified entities into the at least one additional natural language query, wherein the identified entities in the at least one additional natural language query comprise a second group of terms, and wherein at least one term in the second group of terms is not in the first group terms, wherein the generating further comprises generating some of the at least one additional natural language query based on the trending terms and the sentiment measures.

A system comprising:

• a memory;
• one or more processor in communication with the memory;
• and program instructions executable by the one or more processor via the memory to perform a method, the method comprising:
• obtaining, by one or more processor, a natural language query, wherein the natural language query is comprised of a first group of terms;
• converting, by the one or more processor, the natural language query to a machine language query and executing the machine language query on at least one computer resource;
• obtaining, by the one or more processor, search results responsive to the machine language query, wherein the search results comprise related terms derived from terms in the first group of terms, wherein one or more processor derived the related terms utilizing concept expansion;
• parsing, by the one or more processor, the search results by applying a statistical information extraction to the terms in the first group of terms and to the related terms to identify as entities at least one of:
• a portion of the terms, or a portion of the related terms, wherein the parsing comprises:
• utilizing, by the one or more processor, the natural language query to perform an automated search to ingest entries from a structured data source;
• generating, by the one or more processor, a sentiment measure for each ingested entry;
• and extracting, by the one or more processor, trending terms to identify the entities;
• and generating, by the one or more processor, at least one additional natural language query by incorporating a portion of the identified entities into the at least one additional natural language query, wherein the identified entities in the at least one additional natural language query comprise a second group of terms, and wherein at least one term in the second group of terms is not in the first group of terms, wherein the generating further comprises generating some of the at least one additional natural language query based on the trending terms and the sentiment measures.