Predicting user question in question and answer system

A computer program product for predicting and presenting a future question in an automated question answering system, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions readable by a device to cause the device to perform a method comprising:

• receiving an input question in an automated question answering system;
• searching a question database storing questions and a conditional probability of one question to be asked given that a previous question was asked, the conditional probability determined based on a supervised machine learning algorithm and natural language processing that determines distance metric between the questions;
• predicting the future question based on the conditional probability stored in the question database given the input question as the previous question;
• suggesting the future question;
• and
• responsive to receiving an acceptance of the future question, updating the question database to strengthen the conditional probability associated with the future question occurring given the input question,
• wherein at least the natural language processing determined distance metric between the questions extends a training data set with which the supervised machine learning algorithm was trained, and wherein the supervised learning algorithm is automatically retrained based on the extended training data set.

A system of predicting and presenting a future question in an automated question answering system, comprising:

• at least one hardware processor coupled to a communication network;
• a storage device coupled to the at least one hardware processor;
• the at least one hardware processor configured to at least:
• receive an input question in an automated question answering system;
• search a question database storing questions and a conditional probability of one question to be asked given that a previous question was asked, the conditional probability determined based on a supervised machine learning algorithm and natural language processing that determines distance metric between the questions;
• predict the future question based on the conditional probability stored in the question database given the input question as the previous question;
• suggest the future question;
• and
• responsive to receiving an acceptance of the future question, update the question database to strengthen the conditional probability associated with the future question occurring given the input question,
• wherein at least the natural language processing determined distance metric between the questions extends a training data set with which the supervised machine learning algorithm was trained, and wherein the supervised learning algorithm is automatically retrained based on the extended training data set.