Incomplete problem description determination for virtual assistant user input handling

A computer system comprising:

• a memory;
• and
• a processor in communication with the memory, wherein the computer system is configured to perform a method comprising:
• building and training a cognitive model, the building and training comprising:
• obtaining a corpus of training data comprising complete training problem descriptions;
• deconstructing the complete training problem descriptions to form blocks of statements, at least some of the formed blocks of statements providing incomplete training problem descriptions from the complete training problem descriptions;
• applying a constructor to summarize the formed blocks of statements and identify probabilities that the blocs of statements provide incomplete training problem descriptions;
• and
• training the cognitive model, using the blocks of statements, to identify whether an input statement provides a complete problem description;
• receiving a sequence of natural language statements provided by a user to a virtual assistant;
• applying the cognitive model to the sequence of statements and determining whether the sequence of statements provides a first complete problem description, by the user, to which the virtual assistant is to respond in assisting the user address a problem that the user experiences;
• prompting the user to provide an additional one or more statements to complete the first problem description;
• based on completing the first problem description, formulating and providing a response to the user based on a determined intent of the complete first problem description;
• and
• monitoring input by the user based on providing the response, the input informing feedback for further training of the cognitive model to identify whether statement sequences provide complete or incomplete problem descriptions.

A computer program product comprising:

• a computer readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising:
• building and training a cognitive model, the building and training comprising:
• obtaining a corpus of training data comprising complete training problem descriptions;
• deconstructing the complete training problem descriptions to form blocks of statements, at least some of the formed blocks of statements providing incomplete training problem descriptions from the complete training problem descriptions;
• applying a constructor to summarize the formed blocks of statements and identify probabilities that the blocks of statements provide incomplete training problem descriptions;
• and
• training the cognitive model, using the blocks of statements, to identify whether an input statement provides a complete problem description;
• receiving a sequence of natural language statements provided by a user to a virtual assistant;
• applying the cognitive model to the sequence of statements and determining whether the sequence of statements provides a first complete problem description, by the user, to which the virtual assistant is to respond in assisting the user address a problem that the user experiences;
• prompting the user to provide an additional one or more statements to complete the first problem description;
• based on completing the first problem description, formulating and providing a response to the user based on a determined intent of the complete first problem description;
• and
• monitoring input by the user based on providing the response, the input informing feedback for further training of the cognitive model to identify whether statement sequences provide complete or incomplete problem descriptions.