Transactional conversation-based computing system

• US 10,466,885 B2
• Filed: 12/27/2017
• Issued: 11/05/2019
• Est. Priority Date: 05/23/2017
• Status: Active Grant

• Current Assignee: ServiceNow Incorporated
• Original Assignee: ServiceNow Incorporated
• Inventors: Yaseen, Rahim, Zhang, Xiaomei, Rizvi, Hasan, Frogner, Sean, Chinnananchi, Muruganantham, Fortson, Michael
• Primary Examiner(s): Pham, Linh K
• Application Number:
  US15/855,197
• Publication Number:
  US 20180341396A1
• Time in Patent Office: 678 Days
• CPC Class Codes: G06F 16/252 between a Database Management System and a front-end application
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04847 Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/01 Customer relationship services
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

A conversation-based computing system may include a back-end computing module, a design module, and an execution module. The design module may be configured to provide a graphical user interface through which different conversation models are defined in metadata. Each model may include a topic containing respective goals, where the goals are associated with respective conversation flows that define respective dialogs that directs conversations toward the associated goals. Each model may also define references to topic-specific content stored in the back-end module. The execution module may be configured to execute a particular model between the system and a front-end computing device and set up integration of a live agent into the model. Execution of the model may involve, in part, carrying out, in an at least partially-automated fashion, the flow for the model according to the dialog, the topic-specific content corresponding to the model, and communicating using a specific communication protocol.

Claims

1. A computing system comprising:

a automated conversation execution module configured to execute a conversation model between the computing system and a front-end computing device, and establish integration of a live agent into the conversation model, wherein the conversation model includes a topic, the topic being associated with one or more goals, wherein respective goals of the one or more goals are associated with respective conversation flows that define respective rules-based dialogs that direct conversations toward the one or more goals, wherein the conversation model defines one or more points during execution of the conversation model at which to invoke the integration of the live agent, wherein the integration of the live agent comprises communication between the live agent and the front-end computing device to address at least one of the one or more goals, and wherein the conversation model is designed based on one or more inputs received via a graphical user interface provided by the computing system to define the topic, the one or more goals, the respective conversation flows, and the one or more points; and

memory storing conversation data that represents a conversation flow of the conversation model between the computing system and the front-end computing device,

wherein execution of the conversation model between the computing system and the front-end computing device comprises;

receive one or more user inputs indicative of a subject from the front-end computing device;

carrying out the conversation flow between the front-end computing device and the automated conversation execution module based on the one or more user inputs to produce the conversation data;

determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model;

in response to determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model, integrating the live agent into the conversation model; and

providing for display, on a computing device of the live agent, the conversation data.

2. The computing system of claim 1, wherein the conversation model defines which of the one or more goals support the one or more points during execution of the conversation model at which to invoke the integration of the live agent.

3. The computing system of claim 1, wherein carrying out the conversation flow between the front-end computing device and the automated conversation execution module comprises sending, to the front-end computing device, automated messages as part of the conversation flow, and wherein execution of the conversation model between the computing system and the front-end computing device further comprises discontinuing the sending of the automated messages as part of the conversation flow while the live agent is integrated into the conversation model.

4. The computing system of claim 1, wherein integrating the live agent into the conversation model comprises establishing a live video call between the computing device of the live agent and the front-end computing device.

5. The computing system of claim 1, wherein integrating the live agent into the conversation model comprises establishing a live audio call between the computing device of the live agent and the front-end computing device.

6. The computing system of claim 1, wherein execution of the conversation model between the computing system and the front-end computing device further comprises:

receiving, from the computing device of the live agent, response data provided by the live agent for integration into the conversation flow; and

integrating the response data into the conversation flow.

7. The computing system of claim 6, wherein the response data includes one or more of:

audio data, video data, or text data.

8. The computing system of claim 1, wherein the one or more points defined by the conversation model include at least one point during execution of the conversation model at which to provide the front-end computing device with a selectable option for invoking the integration of the live agent, and wherein determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model comprises receiving input representing selection of the selectable option for invoking the integration of the live agent.

9. The computing system of claim 1, wherein the one or more points defined by the conversation model include at least one point during execution of the conversation model at which to automatically trigger integration of the live agent.

10. The computing system of claim 1, further comprising:

a conversation design module configured to provide the graphical user interface through which the conversation model is defined and further configured to receive, via the graphical user interface, input representing whether at least one goal of the one or more goals will integrate the live agent into the conversation model.

11. The computing system of claim 1, wherein at least one of the one or more points defined by the conversation model includes a point after the one or more goals have been addressed.

12. A method comprising:

receive one or more user inputs indicative of a subject from a front-end computing device;

carrying out, between the front-end computing device and an automated conversation execution module of a computing system, a conversation flow of a conversation model based on the one or more user inputs, wherein the conversation model includes a topic, the topic being associated with one or more goals, wherein respective goals of the one or more goals are associated with respective conversation flows that define respective rules-based dialogs that direct conversations toward the one or more goals, wherein the conversation model defines one or more points during execution of the conversation model at which to invoke integration of a live agent into the conversation model, wherein the integration of the live agent comprises communication between the live agent and the front-end computing device to address at least one of the one or more goals, wherein carrying out the conversation flow produces conversation data that represents the conversation flow of the conversation model between the computing system and the front-end computing device, and wherein the conversation model is designed based on one or more inputs received via a graphical user interface provided by the computing system to define the topic, the one or more goals, the respective conversation flows, and the one or more points;

determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model;

in response to determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model, integrating the live agent into the conversation model; and

providing for display, on a computing device of the live agent, the conversation data.

13. The method of claim 12, wherein the conversation model defines which of the one or more goals support the one or more points during execution of the conversation model at which to invoke the integration of the live agent.

14. The method of claim 12, wherein carrying out the conversation flow between the front-end computing device and the automated conversation execution module comprises sending, to the front-end computing device, automated messages as part of the conversation flow, the method further comprising:

discontinuing the sending of the automated messages as part of the conversation flow while the live agent is integrated into the conversation model.

15. The method of claim 12, further comprising:

receiving, from the computing device of the live agent, response data provided by the live agent for integration into the conversation flow; and

integrating the response data into the conversation flow.

16. The method of claim 12, wherein the one or more points defined by the conversation model include at least one point during execution of the conversation model at which to provide the front-end computing device with a selectable option for invoking the integration of the live agent, and wherein determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model comprises receiving input representing selection of the selectable option for invoking the integration of the live agent.

17. The method of claim 12, wherein the one or more points defined by the conversation model include at least one point during execution of the conversation model at which to automatically trigger integration of the live agent.

18. An article of manufacture including a non-transitory computer-readable medium, having stored thereon program instructions that, upon execution by a computing system, cause the computing system to perform operations comprising:

receive one or more user inputs indicative of a subject from a front-end computing device;

carrying out, between the front-end computing device and an automated conversation execution module of the computing system, a conversation flow of a conversation model, wherein the conversation model includes a topic, the topic being associated with one or more goals, wherein respective goals of the one or more goals are associated with respective conversation flows that define respective rules-based dialogs that direct conversations toward the one or more goals, wherein the conversation model defines one or more points during execution of the conversation model at which to invoke integration of a live agent into the conversation model, and wherein the integration of the live agent comprises communication between the live agent and the front-end computing device to address at least one of the one or more goals, wherein carrying out the conversation flow produces conversation data that represents the conversation flow of the conversation model between the computing system and the front-end computing device, and wherein the conversation model is designed based on one or more inputs received via a graphical user interface provided by the computing system to define the topic, the one or more goals, the respective conversation flows, and the one or more points;

determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model;

in response to determining that the integration of the live agent has been invoked at one of the one or more points defined by the conversation model, integrating the live agent into the conversation model; and

providing for display, on a computing device of the live agent, the conversation data.

19. The article of manufacture of claim 18, wherein the conversation model defines which of the one or more goals support the one or more points during execution of the conversation model at which to invoke the integration of the live agent.

20. The article of manufacture of claim 18, wherein carrying out the conversation flow between the front-end computing device and the automated conversation execution module comprises sending, to the front-end computing device, automated messages as part of the conversation flow, the operations further comprising:

discontinuing the sending of the automated messages as part of the conversation flow while the live agent is integrated into the conversation model.