Integrating multiple domain problem solving in a dialog system for a user

A system, for integrating multiple domain problem solving in a dialog system for a user in a computing environment, comprising:

• one or more processors with executable instructions that when executed cause the system to:
• receive, by the dialog system from the user, user input of dialog form;
• execute machine learning logic to generate, from the user input, a dialog model that defines one or more problem instances for multiple domains according to a problem instance template, an identified user intent, and links to one or more problem solvers associated with the multiple domains;
• execute the machine learning logic to determine a dialog plan to further define the one or more problem instances in response to the user input according to the dialog model, wherein determining the dialog plan includes utilizing the dialog model to minimize a cognitive load placed on the dialog system by formulating queries in the dialog plan in a semantic form that elicits a short-form response from the user;
• and
• generate a solution to the user for the one or more problem instances based on the user input associated with the dialog plan.

A computer program product for, by one or more processors, integrating multiple domain problem solving in a dialog system for a user in a computing environment, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

• an executable portion that receives, by the dialog system from the user, user input of dialog form;
• an executable portion that executes machine learning logic to generate, from the user input, a dialog model that defines one or more problem instances for multiple domains according to a problem instance template, an identified user intent, and links to one or more problem solvers associated with the multiple domains;
• an executable portion that executes the machine learning logic to determine a dialog plan to further define the one or more problem instances in response to the user input according to the dialog model, wherein determining the dialog plan includes utilizing the dialog model to minimize a cognitive load placed on the dialog system by formulating queries in the dialog plan in a semantic form that elicits a short-form response from the user;
• and
• an executable portion that generates a solution to the user for the one or more problem instances based on the user input associated with the dialog plan.