Configuring a chatbot with remote language processing

1. A computer implemented method of configuring a chatbot application, the method comprising:

generating a designer user interface comprising:

a visual authoring canvas that includes:

visual elements identifying a logical flow of processing in a chatbot application, and

linguistic elements output by the chatbot application during operation and linguistic elements expected by the chatbot application, from a bot end user, during operation; and

a system selection user input mechanism;

detecting a user input through the system selection user input mechanism on the designer user interface;

selecting a language processing system based on the user input, the language processing system being external to the chatbot application; and

configuring the chatbot application to access the language processing system during operation.

2. The computer implemented method of claim 1 , wherein selecting a language processing system comprises:

selecting a particular natural language understanding system the chatbot application is to use during operation of the chatbot application.

3. The computer implemented method of claim 2 , and further comprising:

configuring the chatbot application to run a dialog;

selecting a visual element on the visual authoring canvas identifying an action corresponding to performance of natural language understanding;

displaying a natural language understanding system selection mechanism on a property configuration pane on the designer user interface, the property configuration pane corresponding to the selected visual element;

detecting author actuation of the natural language understanding system selection mechanism that selects the particular natural language understanding system.

4. The computer implemented method of claim 1 , and further comprising:

detecting an author input that identities a regular expression recognition system the chatbot application is to use during operation of the chatbot application.

5. The computer implemented method of claim 1 , wherein generating the designer user interface comprises:

displaying an undo actuator and a redo actuator on the designer user interface.

6. The computer implemented method of claim 5 , and further comprising:

detecting an authoring input that changes a state of the chatbot application from a previous state to state N; and

storing a first representation of the chatbot application in state N.

7. The computer implemented method of claim 6 , and further comprising:

detecting an authoring input that changes the state of the chatbot application from state N to state N+1;

detecting author actuation of the undo actuator; and

storing a second representation of the chatbot application in state N+1.

8. The computer implemented method of claim 7 , and further comprising:

retrieving the first representation of the chatbot application in state N; and

populating the visual authoring canvas on the designer user interface with state N of the chatbot application based on the first representation.

9. The computer implemented method of claim 8 , and further comprising:

detecting author actuation of the redo actuator; and

storing the first representation of the chatbot application in state N.

10. The computer implemented method of claim 9 , and further comprising:

retrieving the second representation of the chatbot application in state N+1; and

populating the visual authoring canvas on the designer user interface with state N+1 of the chatbot application based on the retrieved second representation.

11. The computer implemented method of claim 8 , and further comprising:

displaying a property pane and a serialization pane on the designer user interface,

wherein

the property pane includes an author actuatable input mechanism that is actuatable to configure an action corresponding to a visual element selected on the visual authoring canvas, and

the serialization pane includes a serialized representation of the visual element selected on the visual authoring canvas;

populating the property pane and the serialization pane on the designer user interface with state N of the chatbot application.

12. The computer implemented method of claim 10 , and further comprising:

displaying a property pane and a serialization pane on the designer user interface,

wherein

the property pane includes an author actuatable input mechanism that is actuatable to configure an action corresponding to a visual element selected on the visual authoring canvas, and

the serialization pane includes a serialized representation of the visual element selected on the visual authoring canvas; and

populating the property pane and the serialization pane on the designer user interface with state N+1 of the chatbot application.

13. A computer system comprising:

one or more processors; and

memory storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the computer system to:

generate a designer user interface comprising:

a visual authoring canvas that includes:

visual elements identifying a logical flow of processing in a chatbot application, and

linguistic elements output by the chatbot application during operation and linguistic elements expected by the chatbot application, from a hot end user, during operation; and

a system selection user input mechanism;

detect a user input through the system selection user input mechanism on the designer user interface;

select a language processing system based on the user input, the language processing system being external to the chatbot application; and

configure the chatbot application to access the language processing system during operation.

14. The computer system of claim 13 , wherein the instructions, when executed, cause the computer system to

configure the chatbot application to run a dialog;

select a visual element on the visual authoring canvas that identities an action for which natural language processing is performed;

display a natural language processing system selection mechanism on a property configuration pane corresponding to the selected visual element; and

detect author actuation of the natural language processing system selection mechanism identifying a selected natural language understanding system.

15. The computer system of claim 14 , wherein the instructions, when executed, cause the computer system to:

detect the author input that identities a regular expression recognition system the chatbot application is to use during operation of the chatbot application.

16. A computer system comprising:

one or more processors; and

memory storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the computer system to:

generate a designer user interface that represents a chatbot application and comprises:

a visual authoring canvas that includes visual elements identifying a logical flow of processing in the chatbot application, and

a property pane having an author actuatable input mechanism actuatable to configure an action corresponding to a visual element selected on the visual authoring canvas, the designer user interface including an undo actuator and a redo actuator;

detect an authoring input on the designer user interface that changes a state of the chatbot application from a previous state to state N;

store a first representation of the chatbot application in state N;

detect an authoring input on the designer user interface that changes the state of the chatbot application from state N to state N+1;

detect author actuation of the undo actuator;

store a second representation of the chatbot application in state N+1 on the redo stack;

retrieve the first representation of the chatbot application in state N; and

populate the visual authoring canvas and the property pane on the designer user interface with state N of the chatbot application.

17. The computer system of claim 16 , wherein the instructions, when executed, cause the computer system to:

detect actuation of the redo actuator;

store the first representation of the chatbot application in state N;

retrieve the second representation of the chatbot application in state N+1; and

populate the visual authoring canvas and the property pane on the designer user interface with state N+1 of the chatbot application based on the retrieved second representation.

18. The computer system of claim 16 , wherein the instructions, when executed, cause the computer system to:

generate the designer user interface with a serialization pane that represents a serialized representation of the visual element selected on the visual authoring canvas; and

populate the serialization pane on the designer user interface with state N of the chatbot application.

19. The computer system of claim 17 , wherein the instructions, when executed, cause the computer system to:

generate the designer user interface with a serialization pane that represents a serialized representation of the visual element selected on the visual authoring canvas; and

populate the serialization pane on the designer user interface with state N+1 of the chatbot application.

20. The computer system of claim 16 wherein the instructions, when executed, cause the computer system to:

generate the designer user interface with linguistic elements output by the chatbot application during operation or expected by the chatbot application, from a bot end user, during operation;

detect an author input, on the designer user interface, identifying a language processing system that is external to the chatbot application and that is to be accessed by the chatbot application during operation; and

configure the chatbot application to access the language processing system during operation.