METHOD AND SYSTEM FOR DEVELOPING, TRAINING, AND DEPLOYING EFFECTIVE INTELLIGENT VIRTUAL AGENT

• US 20180052664A1
• Filed: 05/19/2017
• Published: 02/22/2018
• Est. Priority Date: 08/16/2016
• Status: Abandoned Application

• Current Assignee: Rulai, Inc.
• Original Assignee: Rulai, Inc.
• Inventors: Zhang, Yi, Jin, Roger, Chen, Yunfei, Yi, Xing, Sun, Yueming
• Application Number:
  US15/600,251
• Publication Number:
  US 20180052664A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 8/34 Graphical or visual programming
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: H04M 2203/2038 Call context notifications
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements

Abstract

The present teaching relates to developing a virtual agent. In one example, a plurality of graphical objects is presented to a user via a bot design programming interface. Each of the plurality of graphical objects represents a module corresponding to an action to be performed by the virtual agent. One or more inputs from the user are received, via the bot design programming interface, for selecting a set of graphical objects from the plurality of graphical objects. The one or more inputs provide information of a first order of the set of graphical objects. A plurality of modules represented by the set of graphical objects is identified. Based on the one or more inputs, a second order of the plurality of modules is determined based on the first order. The plurality of modules is integrated in the second order to generate a customized virtual agent for executing an associated task according to the second order.

Claims

1. A method implemented on a computer having at least one processor, a storage, and a communication platform for developing a virtual agent, comprising:

presenting, via a bot design programming interface, a plurality of graphical objects to a developer user, wherein each of the plurality of graphical objects represents a module which, once executed, performs an action;

receiving, via the bot design programming interface, one or more inputs from the developer user that selects a set of graphical objects from the plurality of graphical objects and provides information about an order in which the set of graphical objects is organized;

identifying a set of modules represented by the set of graphical objects;

integrating the set of modules in the order to generate the virtual agent which, when deployed, performs actions corresponding to the set of modules in the order.

2. The method of claim 1, further comprising receiving information from the developer user requesting customization of at least one of the set of modules, wherein

for each of the at least one of the plurality of modules,

determining at least one parameter which can be customized,

obtaining at least one input from the developer user directed to each of the at least one parameter, and

automatically modifying the module based on the at least one input directed to each of the at least one parameter and/or additional input obtained based on a machine learning model to generate a modified module, wherein

the step of integrating includes integrating one or more modified modules in place of their corresponding unmodified modules.

3. The method of claim 2, wherein the at least one input from the developer user comprises at least one of:

a selection of the at least one parameter; and

information provided by the developer user associated with a specific state related to any one of the at least one parameter.

4. The method of claim 2, wherein the at least one parameter includes a condition upon which an action corresponding to the module is to be performed.

5. The method of claim 1, further comprising:

receiving, via the bot design programming interface, one or more forms of representing an utterance as a triggering condition to initiate a dialog between a chat user and the virtual agent.

6. The method of claim 1, further comprising presenting, via the bot design programming interface:

a first means through which the developer user is able to initiate a dialog with the virtual agent for testing;

a second means through which the developer user is able to further customize any of the set of modules to generate an updated virtual agent; and

a third means through which the developer user is able to deploy the virtual agent.

7. The method of claim 1, wherein at least some of the plurality of graphical objects represent modules for:

collecting information from a chat user during a dialog with the virtual agent;

sending one or more utterances to the chat user;

executing an application associated with the module wherein the application is related to the task to be performed by the module represented by a graphical object;

inserting an existing task previously developed;

escalating the chat user to one of a human agent and a different virtual agent;

providing multiple options associated with a parameter related to a module; and

executing a sub-task upon the chat user'"'"'s selection of one of the multiple options.

8. The method of claim 1, wherein

the virtual agent is generated for a specific task;

and

each of the set of modules integrated to form the virtual agent performs a sub-task associated with the specific task.

9. The method of claim 8, further comprising:

storing the virtual agent as a template; and

presenting to a different developer user as the basis for developing a different virtual agent intended for a task similar to the specific task.

17. The medium of claim 1, wherein

the virtual agent is generated for a specific task;

and

each of the set of modules integrated to form the virtual agent performs a sub-task associated with the specific task.

18. The medium of claim 17, wherein the information, when the information is read by the machine, further causes the machine

storing the virtual agent as a template;

and

presenting to a different developer user as the basis for developing a different virtual agent intended for a task similar to the specific task.

10. Machine readable and non-transitory medium having information recorded thereon for developing a virtual agent, wherein the information, when read by the machine, causes the machine to perform the following:

presenting, via a bot design programming interface, a plurality of graphical objects to a developer user, wherein each of the plurality of graphical objects represents a module which, once executed, performs an action;

receiving, via the bot design programming interface, one or more inputs from the developer user that selects a set of graphical objects from the plurality of graphical objects and provides information about an order in which the set of graphical objects is organized;

identifying a set of modules represented by the set of graphical objects;

integrating the set of modules in the order to generate the virtual agent which, when deployed, performs actions corresponding to the set of modules in the order.

11. The medium of claim 10, wherein the information, when the information is read by the machine, further causes the machine receiving information from the developer user requesting customization of at least one of the set of modules, wherein

for each of the at least one of the plurality of modules,

determining at least one parameter which can be customized,

obtaining at least one input from the developer user directed to each of the at least one parameter, and

automatically modifying the module based on the at least one input directed to each of the at least one parameter and/or additional input obtained based on a machine learning model to generate a modified module, wherein

the step of integrating includes integrating one or more modified modules in place of their corresponding unmodified modules.

12. The medium of claim 11, wherein the at least one input from the developer user comprises at least one of:

a selection of the at least one parameter; and

information provided by the developer user associated with a specific state related to any one of the at least one parameter.

13. The medium of claim 11, wherein the at least one parameter includes a condition upon which an action corresponding to the module is to be performed.

14. The medium of claim 10, wherein the information, when the information is read by the machine, further causes the machine receiving, via the bot design programming interface, one or more forms of representing an utterance as a triggering condition to initiate a dialog between a chat user and the virtual agent.

15. The medium of claim 10, wherein the information, when the information is read by the machine, further causes the machine presenting, via the bot design programming interface:

a first means through which the developer user is able to initiate a dialog with the virtual agent for testing;

a second means through which the developer user is able to further customize any of the set of modules to generate an updated virtual agent; and

a third means through which the developer user is able to deploy the virtual agent.

16. The medium of claim 10, wherein at least some of the plurality of graphical objects represent modules for:

collecting information from a chat user during a dialog with the virtual agent;

sending one or more utterances to the chat user;

executing an application associated with the module wherein the application is related to the task to be performed by the module represented by a graphical object;

inserting an existing task previously developed;

escalating the chat user to one of a human agent and a different virtual agent;

providing multiple options associated with a parameter related to a module; and

executing a sub-task upon the chat user'"'"'s selection of one of the multiple options.

19. A system for developing a virtual agent, comprising:

a bot design programming interface manager configured for

presenting, via a bot design programming interface, a plurality of graphical objects to a developer user, wherein each of the plurality of graphical objects represents a module which, once executed, performs an action, and

receiving, via the bot design programming interface, one or more inputs from the developer user that selects a set of graphical objects from the plurality of graphical objects and provides information about an order in which the set of graphical objects is organized;

a virtual agent module determiner configured for identifying a set of modules represented by the set of graphical objects; and

a visual input based program integrator configured for integrating the set of modules in the order to generate the virtual agent which, when deployed, performs actions corresponding to the set of modules in the order.

20. The system of claim 19, wherein

the virtual agent module determiner is further configured for receiving information from the developer user requesting customization of at least one of the set of modules, wherein

for each of the at least one of the plurality of modules, the virtual agent module determiner is configured for

determining at least one parameter which can be customized, and

obtaining at least one input from the developer user directed to each of the at least one parameter;

and

the visual input based program integrator is further configured for;

automatically modifying the module based on the at least one input directed to each of the at least one parameter and/or additional input obtained based on a machine learning model to generate a modified module, wherein

the visual input based program integrator integrates one or more modified modules in place of their corresponding unmodified modules.

21. The system of claim 20, wherein the at least one input of the developer user comprises at least one of:

a selection of the at least one parameter; and

information provided by the developer user associated with a specific state related to any one of the at least one parameter.

22. The system of claim 20, wherein the at least one parameter includes a condition upon which an action corresponding to the module is to be performed.

23. The system of claim 19, further comprising a developer input processor configured for receiving, via the bot design programming interface, one or more forms of representing an utterance as a triggering condition to initiate a dialog between a chat user and the virtual agent.

24. The system of claim 19, wherein the bot design programming interface manager is further configured for presenting

a first means through which the developer user is able to initiate a dialog with the virtual agent for testing;

a second means through which the developer user is able to further customize any of the set of modules to generate an updated virtual agent; and

a third means through which the developer user is able to deploy the virtual agent.

25. The system of claim 19, at least some of the plurality of graphical objects represent modules for:

collecting information from a chat user during a dialog with the virtual agent;

sending one or more utterances to the chat user;

executing an application associated with the module wherein the application is related to the task to be performed by the module represented by a graphical object;

inserting an existing task previously developed;

escalating the chat user to one of a human agent and a different virtual agent;

providing multiple options associated with a parameter related to a module; and

executing a sub-task upon the chat user'"'"'s selection of one of the multiple options.

26. The system of claim 19, wherein:

the virtual agent is generated for a specific task; and

each of the set of modules integrated to form the virtual agent performs a sub-task associated with the specific task.

27. The system of claim 26, wherein

the visual input based program integrator is further configured for storing the virtual agent as a template;

and

the bot design programming interface manager is further configured for presenting to a different developer user as the basis for developing a different virtual agent intended for a task similar to the specific task.