Virtual agent conducting interactive testing

A system for generating an arrangement of test questions to ask a user during a conversation with a virtual agent, comprising:

• one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to:
• receive an input document;
• preprocess the input document to extract text, parse the extracted text, and detect sections formed within the extracted text;
• process the detected sections through at least one content selection machine learning model to select content from the detected sections;
• process the selected content through at least one test question generating machine learning model to generate a set of test questions;
• process the selected content through at least one distractor generating machine learning model to generate at least one set of distractors corresponding to at least one test question of the plurality of test questions;
• select a plurality of test questions from the set of test questions;
• determine an order in which the selected questions are to be presented to the user, wherein the order is based on the user's previous history of answering test questions from the set of test questions;
• and
• arrange the selected test questions in the determined order to generate the arrangement of test questions.

A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to generate an arrangement of test questions to ask a user during a conversation with a virtual agent by:

• receiving an input document;
• preprocessing the input document to extract text, parse the extracted text, and detect sections formed within the extracted text;
• processing the detected sections through at least one content selection machine learning model to select content from the detected sections;
• processing the selected content through at least one test question generating machine learning model to generate a set of test questions;
• processing the selected content through at least one distractor generating machine learning model to generate at least one set of distractors corresponding to at least one test question of the plurality of test questions;
• selecting a plurality of test questions from the set of test questions;
• determining an order in which the selected questions are to be presented to the user, wherein the order is based on the user's previous history of answering test questions from the set of test questions;
• and
• arranging the selected test questions in the determined order to generate the arrangement of test questions.