Abstract: An embodiment according to the present invention addresses reusability and alignment of content across channels in a multi-channel virtual assistant, by allowing users to define content on one channel and then have the content fully or partially translated for the other channels using a mix of pre-defined static rules, dynamic rules or machine learning. Content translation is provided based on communications channels, and content translation is performed from one to many formats, optionally in real time. Performing content translation using machine learning provides an advantage that as users work, content translation becomes more precise and covers more elements.

Abstract: An embodiment according to the present invention addresses reusability and alignment of content across channels in a multi-channel virtual assistant, by allowing users to define content on one channel and then have the content fully or partially translated for the other channels using a mix of pre-defined static rules, dynamic rules or machine learning. Content translation is provided based on communications channels, and content translation is performed from one to many formats, optionally in real time. Performing content translation using machine learning provides an advantage that as users work, content translation becomes more precise and covers more elements.

Abstract: An embodiment of the present invention includes a method for creating a dialog system that provides a framework for creating a multi-modal dialog application and includes a runtime application package (RAP) enabling runtime media grammars, prompts, classifiers, and so forth, to be separate from a multi-modal dialog application that utilizes the RAP. Embodiments disclosed herein enable newly trained runtime media supporting the multi-modal dialog application to be deployed with ease, and to do so while a dialog service is in operation. Embodiments disclosed herein enable the multi-modal dialog application to be created, deployed, and maintained in an easy and flexible manner, saving an end-user that may be providing the multi-modal dialog application to customers both time and cost.

Abstract: An embodiment according to the present invention addresses reusability and alignment of content across channels in a multi-channel virtual assistant, by allowing users to define content on one channel and then have the content fully or partially translated for the other channels using a mix of pre-defined static rules, dynamic rules or machine learning. Content translation is provided based on communications channels, and content translation is performed from one to many formats, optionally in real time. Performing content translation using machine learning provides an advantage that as users work, content translation becomes more precise and covers more elements.

Abstract: An embodiment of the present invention includes a method for creating a dialog system that provides a framework for creating a multi-modal dialog application and includes a runtime application package (RAP) enabling runtime media grammars, prompts, classifiers, and so forth, to be separate from a multi-modal dialog application that utilizes the RAP. Embodiments disclosed herein enable newly trained runtime media supporting the multi-modal dialog application to be deployed with ease, and to do so while a dialog service is in operation. Embodiments disclosed herein enable the multi-modal dialog application to be created, deployed, and maintained in an easy and flexible manner, saving an end-user that may be providing the multi-modal dialog application to customers both time and cost.