Combined menu-based and natural-language-based communication with chatbots

Patent metadata

Field	Value
Publication number	US-10013980-B2
Application number	US-201615285157-A
Country	US
Kind code	B2
Filing date	Oct 4, 2016
Priority date	Oct 4, 2016
Publication date	Jul 3, 2018
Grant date	Jul 3, 2018

Abstract

A user is allowed to communicate with a chatbot. A menu is provided to the user that includes a list of actions that can be performed by the user. Whenever natural language input asking a question is received from the user, this input is forwarded to the chatbot, a response to this input is received from the chatbot, this response is provided to the user, and the menu is again provided to the user. Whenever natural language input is received from the user requesting an action that is not one of the actions in the menu, this input is forwarded to the chatbot, a response to this input is received from the chatbot, where this response includes another menu that includes a list of subsequent actions that are related to the requested action and can be performed by the user, and this other menu is provided to the user.

First claim

Wherefore, what is claimed is:

1. A system for allowing a user to communicate with a chatbot, comprising:
a chatbot communicator comprising one or more computing devices, said computing devices being in communication with each other via a computer network whenever there is a plurality of computing devices, and a computer program having a plurality of sub-programs executable by said computing devices, wherein the sub-programs configure said computing devices to,
provide a menu to the user, the menu comprising a list of actions that can be selected by the user, one or more of said menu-based list of actions being specific tasks that the chatbot can perform for the user, and
whenever the user selects one of the actions from the list,
forward the selected action to the chatbot for performance by the chatbot,
receive a response from the chatbot comprising a subsequent menu listing one or more subsequent actions that are related to the selected action, which can be selected by the user, and wherein one or more of the subsequent actions is a specific task that the chatbot can perform for the user, and
provide the subsequent menu to the user, and

whenever natural language input is received from the user that asks a question,
forward said question input to the chatbot,
receive a response to said question input from the chatbot,
provide the response to said question input to the user, and
again provide the menu to the user.

2. The system of claim 1 , wherein the natural language input comprises a text string that is manually entered by the user.

3. The system of claim 1 , wherein the natural language input comprises one of:
a word that is spoken by the user; or
a phrase that is spoken by the user; or
one or more sentences that are spoken by the user.

4. The system of claim 1 , wherein the sub-programs further configure said computing devices to:
prior to providing the menu to the user,
receive a query submitted by the user,
forward the query to the chatbot,
receive a response to the query from the chatbot, said query response comprising the menu and a welcome message that encourages the user to communicate with the chatbot using natural language and describes the capabilities of the chatbot, and
provide the welcome message to the user.

5. The system of claim 1 , wherein the sub-programs further configure said computing devices to:
whenever natural language input is received from the user that requests an action that is not one of the actions in the menu,
forward said action request input to the chatbot,
receive a response to said action request input from the chatbot, said action request input response comprising another menu comprising a list of subsequent actions that are related to the requested action and can be selected by the user, and
provide said other menu to the user.

6. The system of claim 1 , wherein the sub-programs further configure said computing devices to:
whenever the user selects one of the actions in the menu,
assign the selected action to be a current action; and

whenever natural language input is received from the user that requests an action that is not one of the subsequent actions in the subsequent menu,
abort the current action,
forward said action request input to the chatbot,
receive a response to said action request input from the chatbot, said action request input response comprising another menu comprising a list of subsequent actions that are related to the requested action and can be performed by the user, and
provide said other menu to the user.

7. The system of claim 6 , wherein the sub-program for aborting the current action comprises a sub-program for saving a current state of the current action.

8. The system of claim 6 , wherein the sub-programs further configure said computing devices to:
whenever natural language input is received from the user that requests to abort the current action altogether,
forward said abort request input to the chatbot, and
again provide the menu to the user.

9. The system of claim 8 , wherein the sub-program for forwarding said abort request input to the chatbot comprises a sub-program for saving a current state of the current action.

10. The system of claim 6 , wherein one of the subsequent actions is an abort action and the sub-programs further configure said computing devices to:
whenever the user selects the abort action,
forward said abort action selection to the chatbot, and
again provide the menu to the user.

11. The system of claim 10 , wherein the sub-program for forwarding said abort action selection to the chatbot comprises a sub-program for saving a current state of the current action.

12. The system of claim 6 , wherein the sub-programs further configure said computing devices to:
whenever the user selects one of the subsequent actions in the subsequent menu, forward the selected subsequent action to the chatbot; and
whenever natural language input is received from the user that requests to cancel the selected subsequent action,
forward said cancellation request input to the chatbot, and
again provide the subsequent menu to the user.

13. The system of claim 1 , wherein the sub-programs further configure said computing devices to:
whenever the user selects one of the actions in the menu that was previously aborted and has a state which was saved when it was aborted,
ask the user if they want to resume the selected action from said saved state, and
upon receiving input from the user indicating that they want to resume the selected action from said saved state,
restore said saved state, and
inform the chatbot of said saved state restoration.

14. The system of claim 1 , wherein the sub-programs further configure said computing devices to:
whenever natural language input is received from the user that requests an action that is not one of the actions in the menu, wherein the requested action was previously aborted and has a state which was saved when it was aborted,
ask the user if they want to resume the requested action from said saved state, and
upon receiving input from the user indicating that they want to resume the requested action from said saved state,
restore said saved state, and
inform the chatbot of said saved state restoration.

15. The system of claim 1 , wherein the sub-programs further configure said computing devices to:
whenever the user concludes their communication with the chatbot or resumes a previous conversation they had with the chatbot, and there exists a pending action that was previously aborted, and a current state of said pending action was saved when it was aborted,
ask the user if they want to complete said pending action,
upon receiving input from the user indicating that they want to complete said pending action, ask the user if they want to resume said pending action from the current state thereof, and
upon receiving input from the user indicating that they want to resume said pending action from the current state thereof,
restore the current state of said pending action, and
inform the chatbot of said current state restoration.

16. The system of claim 1 , wherein the menu is one of:
a top-level menu of a user-navigable, hierarchically-organized chain of nested sub-menus; or
a one of said sub-menus.

17. A system for allowing a user to communicate with a chatbot, comprising:
a chatbot communicator comprising one or more computing devices, said computing devices being in communication with each other via a computer network whenever there is a plurality of computing de

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Borsutsky Yuval Pinchas
• Damari Keren
• Ramsey William D
• Schlesinger Benny
• Cohen Eldar

Classifications

• G10L15/222 Primary

  Barge in, i.e. overridable guidance for interrupting prompts · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title