Recommendation technique using automatic conversation

A recommendation system comprising:

• a receiver configured to receive a query from a user;
• a conversation processor configured to apply an intent-entity model, and to determine a first output based on the query;
• a question-answering processor configured to determine a second output based on the query;
• an analyzer configured to calculate a value of degree of ambiguity of the first output to the query, and to calculate a value of extent of satisfaction to which the second output satisfies the query;
• an evaluator configured to calculate a reliability score based on the value of the degree of ambiguity of the first output and the value of extent of satisfaction to which the second output satisfies the query;
• a determinator configured to determine one or more recommendations by comparing the reliability score to a first threshold and to a second threshold, wherein an intersection of the first output and the second output is selected as the one or more recommendations, responsive to a determination that the reliability score is between the first threshold and the second threshold;
• and
• an outputter configured to output the one or more recommendations to the user.

A computer program product for providing a recommendation, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

• receive, by a conversation system, a query from a user;
• input the query into an intent-entity model to obtain a first output;
• input the query into a question-answering system to obtain a second output;
• analyze the first output from the intent-entity model to calculate a value of degree of ambiguity of the first output to the query;
• analyze the query and the second output from the question-answering system to calculate a value of extent of satisfaction to which the second output satisfies the query;
• calculate a reliability score based on the value of the degree of ambiguity of the first output and the value of extent of satisfaction to which the second output satisfies the query;
• determine one or more recommendations by comparing the reliability score to a first threshold and to a second threshold, wherein an intersection the first output and the second output is selected as the one or more recommendations, responsive to a determination that the reliability score is greater than the threshold;
• and
• output the one or more recommendations to the user.