System that conducts and evaluates oral question-and-answer sessions using artificial intelligence
An artificial intelligence system that conducts an oral question-and-answer session with a single respondent to achieve an educational outcome, such as reviewing material to reinforce ideas or to prepare the respondent for future tests or events, or evaluating the respondent's knowledge or communication skills. The system may use an artificial intelligence engine that can understand and generate natural language, such as a large-language model like ChatGPT™. Text-to-speech and speech-to-text converters may be coupled to the AI engine to enable the system to communicate directly with the respondent using spoken language. The system may provide an interface for entry of session information such as background information on topics and the type of questioning that should be used during the session. The respondent may be given multiple attempts to answer a question and to select the best response, and the system may provide an evaluation and feedback after each response.
1. A system that conducts and evaluates oral question-and-answer sessions using artificial intelligence, comprising:
an artificial intelligence engine comprising
a processor; and
a large language model;
a text-to-speech converter coupled to said artificial intelligence engine;
a speech-to-text converter coupled to said artificial intelligence engine; and,
a data collection user interface configured to:
accept session information describing a question-and-answer session to be held between said artificial intelligence engine and a respondent, wherein said session information comprises:
a dialog context;
one or more questioning types; and,
transmit said session information to said artificial intelligence engine;
wherein
said artificial intelligence engine is configured to
receive said session information;
generate text questions for said respondent based on said session information and based on previous responses of said respondent,
wherein said session information is received and entered into said data collection user interface prior to said question-and-answer session,
wherein said session information comprises information that is configured to be received from one or more of
a user other than said respondent,
other data sources other than said respondent; and
transmit said text questions to said text-to-speech converter;
said text-to-speech converter is configured to
transform said text questions to audio questions; and
output said audio questions to said respondent; and,
said speech-to-text converter is configured to
receive audio responses from said respondent;
transform said audio responses to text responses; and
transmit said text responses to said artificial intelligence engine; and,
said artificial intelligence engine is further configured to
generate one or more evaluations based on said text responses and on said session information; and,
transmit said one or more evaluations to said respondent.
2. The system that conducts and evaluates oral question-and-answer sessions using artificial intelligence of claim 1 , wherein one or more questioning types comprise one or more of:
adaptive questioning;
additive questioning; and,
hypothetical questioning.
3. The system that conducts and evaluates oral question-and-answer sessions using artificial intelligence of claim 1 , wherein:
said session information further comprises a session introduction; and,
said artificial intelligence engine is further configured to transmit said session introduction to said respondent at a beginning of said question-and-answer session.
4. The system that conducts and evaluates oral question-and-answer sessions using artificial intelligence of claim 1 , wherein said dialog context comprises one or more of:
written output generated by said respondent;
a course rubric;
assignment instructions;
class notes;
class lectures;
anticipated learning outcomes;
background information on a topic.
5. The system that conducts and evaluates oral question-and-answer sessions using artificial intelligence of claim 1 , wherein
said text-to-speech converter is further configured to
translate said text questions into a preferred language of said respondent; and,
said speech-to-text converter is further configured to
translate said text responses from said preferred language of said respondent.
6. The system that conducts and evaluates oral question-and-answer sessions using artificial intelligence of claim 1 , further comprising an image interpreter configured to obtain an image,
wherein said image interpreter is coupled with or is within said artificial intelligence engine; and,
wherein said artificial intelligence engine is configured to update said dialog context based on said image.
7. The system that conducts and evaluates oral question-and-answer sessions using artificial intelligence of claim 1 , further comprising a database;
wherein said artificial intelligence engine is further configured to store said text questions, said text responses, and said one or more evaluations in said database.
8. The system that conducts and evaluates oral question-and-answer sessions using artificial intelligence of claim 1 , wherein said artificial intelligence engine is further configured to:
when said artificial intelligence engine receives a text response corresponding to a text question of said text questions, ask said respondent if said respondent wants to make another attempt to answer said text question; and,
when said respondent generates multiple responses to said text question,
ask said respondent to select a best response of said multiple responses to said text question, and,
generate an evaluation of said best response.