Conversational computing via conversational virtual machine
View Patent ↗A method for conversational computing includes executing code embodying a conversational virtual machine, registering a plurality of input/output resources with a conversational kernel, providing an interface between a plurality of active applications and the conversational kernel processing input/output data, receiving input queries and input events of a multi-modal dialog across a plurality of user interface modalities of the plurality of active applications, generating output messages and output events of the multi-modal dialog in connection with the plurality of active applications, managing, by the conversational kernel, a context stack associated with the plurality of active applications and the multi-modal dialog to transform the input queries into application calls for the plurality of active applications and convert the output messages into speech, wherein the context stack accumulates a context of each of the plurality of active applications.
1. A method for conversational computing comprising:
executing code embodying a conversational virtual machine;
registering a plurality of input/output resources with a conversational kernel;
providing an interface between a plurality of active applications and the conversational kernel processing input/output data;
receiving input queries and input events of a multi-modal dialog across a plurality of user interface modalities of the plurality of active applications;
generating output messages and output events of the multi-modal dialog in connection with the plurality of active applications;
managing, by the conversational kernel, a context stack associated with the plurality of active applications and the multi-modal dialog to transform the input queries into application calls for the plurality of active applications and convert the output messages into speech, wherein the context stack accumulates a context of each of the plurality of active applications.
2. The method of claim 1 , further comprising controlling and accessing a conversational engine through a conversational engine application program interface to process the input queries and input events and to generate the multi-modal dialog and the output events.
3. The method of claim 1 , further comprising providing conversational services and behaviors accessible by the plurality of active applications through a conversational engine application program interface.
4. The method of claim 1 , further comprising:
managing the multi-modal dialog across the plurality of active applications and selecting an active dialog and a resource of an application of the plurality of active applications based on the input queries;
managing and allocating conversational engines during execution of conversational tasks;
coordinating and dispatching the conversational tasks; and
accumulating the contexts of the plurality of active applications implementing an active discourse of a conversational task.
5. The method of claim 1 , wherein the context stack comprises a variable, a state, the input/output data of the multi-modal dialog across the different user interface modalities of the plurality of active applications.
6. A computer program product for conversational computing, the computer program product comprising:
a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to execute code embodying a conversational virtual machine, register a plurality of input/output resources with a conversational kernel, provide an interface between a plurality of active applications and the conversational kernel processing input/output data, receive input queries and input events of a multi-modal dialog across a plurality of user interface modalities of the plurality of active applications, generate output messages and output events of the multi-modal dialog in connection with the plurality of active applications, manage, by the conversational kernel, a context stack associated with the plurality of active applications and the multi-modal dialog to transform the input queries into application calls for the plurality of active applications and convert the output messages into speech, wherein the context stack accumulates a context of each of the plurality of active applications.
7. The computer program product of claim 6 , further comprising controlling and accessing a conversational engine through a conversational engine application program interface to process the input queries and input events and to generate the multi-modal dialog and the output events.
8. The computer program product of claim 6 , further comprising providing conversational services and behaviors accessible by the plurality of active applications through a conversational engine application program interface.
9. The computer program product of claim 6 , further comprising:
managing the multi-modal dialog across the plurality of active applications and selecting an active dialog and a resource of an application of the plurality of active applications based on the input queries;
managing and allocating conversational engines during execution of conversational tasks;
coordinating and dispatching the conversational tasks; and
accumulating the contexts of the plurality of active applications implementing a conversational task.
10. The computer program product of claim 6 , wherein the context stack comprises a variable, a state, the input/output data of the multi-modal dialog across the different user interface modalities of the plurality of active applications.