Methods for conducting a conversation in an application enabled by a virtual assistant server and devices thereof
A virtual assistant server determines at least one user intent based on an analysis of a received conversational user input. One or more of a plurality of views is identified based on the at least one user intent. Further, the virtual assistant server retrieves content based on the at least one user intent or the identified one or more views. The virtual assistant server determines one of a plurality of graphical user interface layers to display for each of one or more parts of the content and the identified one or more views based at least on one or more factors related to the content. Subsequently, the virtual assistant server outputs instructions based on the determined one of the graphical user interface layers in response to the received conversational user input.
1. A method for generating response by a virtual assistant server comprising:
determining, by the virtual assistant server, at least: one or more user intents based on an executed analysis of a received conversational user input; and one of a plurality of types of sentences for the received conversational user input, wherein the plurality of types of sentences at least comprise an imperative sentence and an interrogative sentence;
identifying, by the virtual assistant server, one or more of a plurality of views based on the one or more user intents;
retrieving content, by the virtual assistant server, based on the one or more user intents;
dividing, by the virtual assistant server, the retrieved content into a plurality of parts;
determining, by the virtual assistant server, for the identified one or more of the plurality of views and at least two of the plurality of parts a different one of a plurality of graphical user interface layers based at least on one or more factors related to the retrieved content;
determining, by the virtual assistant server, an arrangement of at least two of the plurality of parts within at least one of the different ones of the plurality of graphical user interface layers based on the determined one of the plurality of types of sentences for the received conversational user input; and
outputting, by the virtual assistant server, instructions configured to render a display based on the determined ones of the plurality of graphical user interface layers and the determined arrangement in response to the received conversational user input, wherein the method further comprises associating, by the virtual assistant server, the plurality of parts with the identified one or more of the plurality of views by specifying in the output instructions the plurality of parts and one of a plurality of template properties of the identified one or more of the plurality of views in a JavaScript Object Notation (JSON) object.
2. The method of claim 1 , wherein the dividing is based on a number of the one or more user intents determined in the conversational user input.
3. The method of claim 1 , wherein the dividing is based on a plurality of data types in the retrieved content.
4. The method of claim 1 , wherein the determining the one of the plurality of graphical user interface layers is performed at runtime based on a match of the received conversational user input with one of a plurality of template properties.
5. The method of claim 1 , wherein the determining the one of the plurality of graphical user interface layers is based on a layer association property automatically determined based on the one or more of the plurality of views.
6. The method of claim 1 , wherein the one or more factors related to the retrieved content comprise: a size of the retrieved content or a data type of the retrieved content.
7. The method of claim 1 , wherein the plurality of parts comprise at least: one or more bot actions and one or more frequently asked questions.
8. A virtual assistant server comprising:
a processor; and
a memory coupled to the processor which is configured to be capable of executing programmed instructions stored in the memory to:
determine, at least: one or more user intents based on an executed analysis of a received conversational user input; and one of a plurality of types of sentences for the received conversational user input, wherein the plurality of types of sentences at least comprise an imperative sentence and an interrogative sentence;
identify one or more of a plurality of views based on the one or more user intents;
retrieve content based on the one or more user intents;
divide the retrieved content into a plurality of parts;
determine for the identified one or more of the plurality of views and at least two of the plurality of parts a different one of a plurality of graphical user interface layers based at least on one or more factors related to the retrieved content;
determine an arrangement of at least two of the plurality of parts within at least one of the different ones of the plurality of graphical user interface layers based on the determined one of the plurality of types of sentences for the received conversational user input; and
output instructions configured to render a display based on the determined ones of the plurality of graphical user interface layers and the determined arrangement in response to the received conversational user input, wherein the processor is further configured to be capable of executing the stored programmed instructions to associate the plurality of parts with the identified one or more of the plurality of views by specifying in the output instructions the plurality of parts and one of a plurality of template properties of the identified one or more of the plurality of views in a JavaScript Object Notation (JSON) object.
9. The virtual assistant server of claim 8 , wherein the divide retrieved content is based on a number of the one or more user intents determined in the conversational user input.
10. The virtual assistant server of claim 8 , wherein the divide retrieved content is based on a plurality of data types in the retrieved content.
11. The virtual assistant server of claim 8 , wherein the determine the one of the plurality of graphical user interface layers is performed at runtime based on a match of the received conversational user input with one of a plurality of template properties.
12. The virtual assistant server of claim 8 , wherein the determine the one of the plurality of graphical user interface layers is based on a layer association property automatically determined based on the one or more of the plurality of views.
13. The virtual assistant server of claim 8 , wherein the one or more factors related to the retrieved content comprise: a size of the retrieved content or a data type of the retrieved content.
14. The virtual assistant server of claim 8 , wherein the plurality of parts comprise at least: one or more bot actions and one or more frequently asked questions.
15. A non-transitory computer-readable medium having stored thereon instructions for generating a response which when executed by a processor, causes the processor to:
determine, at least: one or more user intents based on an executed analysis of a received conversational user input; and one of a plurality of types of sentences for the received conversational user input, wherein the plurality of types of sentences at least comprise an imperative sentence and an interrogative sentence;
identify one or more of a plurality of views based on the one or more user intents;
retrieve content based on the one or more user intents;
divide the retrieved content into a plurality of parts;
determine for the identified one or more of the plurality of views and at least two of the plurality of parts a different one of a plurality of graphical user interface layers based at least on one or more factors related to the retrieved content;
determine an arrangement of at least two of the plurality of parts within at least one of the different ones of the plurality of graphical user interface layers based on the determined one of the plurality of types of sentences for the received conversational user input; and
output instructions configured to render a display based on the determined ones of the plurality of graphical user interface layers and the determined arrangement in response to the received conversational user input, wherein the instructions when executed by the processor further causes the one or more processors to associate the plurality of parts with the identified one or more of the plurality of views by specifying in the output instructions the plurality of parts and one of a plurality of template properties of the identified one or more of the plurality of views in a JavaScript Object Notation (JSON) object.
16. The non-transitory computer-readable medium of claim 15 , wherein the divide the retrieved content is based on a number of the one or more user intents determined in the conversational user input.
17. The non-transitory computer-readable medium of claim 15 , wherein the divide the retrieved content is based on a plurality of data types in the retrieved content.
18. The non-transitory computer-readable medium of claim 15 , wherein the determine the one of the plurality of graphical user interface layers is performed at runtime based on a match of the received conversational user input with one of a plurality of template properties.
19. The non-transitory computer-readable medium of claim 15 , wherein the determine the one of the plurality of graphical user interface layers is based on a layer association property automatically determined based on the one or more of the plurality of views.
20. The non-transitory computer-readable medium of claim 15 , wherein the one or more factors related to the retrieved content comprise: a size of the retrieved content or a data type of the retrieved content.
21. The non-transitory computer-readable medium of claim 15 , wherein the plurality of parts comprise at least: one or more bot actions and one or more frequently asked questions.