Determination of a response to a query

A system for determining a response to a query, the system comprising:

• a receiver to receive a query along with a plurality of potential responses to the query;
• an extractor in communication with the receiver to extract information from the query and the plurality of potential responses based on text and structure of the query and the plurality of potential responses;
• a detector in communication with the extractor to detect a topic and a type of the query, based on the extracted information, wherein the query is one of a factoid query, a computational query, or a combination thereof;
• a selector in communication with the detector to select at least one of a plurality of techniques for processing the query and the plurality of potential responses, based on the topic and the type of the query, wherein the plurality of techniques includes an information retrieval technique, an n-gram association technique, a deep learning technique, an inferencing technique, a generalized template framework technique, and a topic-specific technique;
• an obtainer in communication with the selector to obtain an answer by execution of each of the selected techniques for processing the query and the plurality of potential responses, wherein the answer is from among the plurality of potential responses;
• a generator in communication with the selector and the obtainer to generate a confidence score for each answer obtained by execution of each of the selected techniques, wherein the confidence score is indicative of an accuracy of the answer obtained by execution of a respective technique;
• and
• a determinator in communication with the extractor, the detector, and the obtainer to determine one of obtained answers as a correct response to the query, based on a comparison between confidence scores associated with the answers.

A computer-implemented method, for determining a response to a query, executed by at least one processor, the method comprising:

• receiving, by the at least one processor, a query along with a plurality of potential responses to the query;
• detecting, by the at least one processor, a topic and a type of the query, based on information extracted from text and structure of the query and the plurality of potential responses, wherein the query is one of a factoid query, a computational query, or a combination thereof;
• selecting, by the at least one processor, at least one of a plurality of techniques for processing the query and the plurality of potential responses, based on the topic and the type of the query, wherein the plurality of techniques includes an information retrieval technique, an n-gram association technique, a deep learning technique, an inferencing technique, a generalized template framework technique, and a topic-specific technique;
• obtaining, by the at least one processor, an answer by execution of each of the selected techniques for processing the query and the plurality of potential responses along with an associated confidence score, wherein the answer is from among the plurality of responses and the confidence score is indicative of an accuracy of the answer obtained by execution of a respective technique;
• and
• determining, by the at least one processor, one of obtained answers as a correct response to the query, based on a comparison between confidence scores associated with the answers.