Transactional conversation-based computing system

• US 10,452,251 B2
• Filed: 09/27/2017
• Issued: 10/22/2019
• 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:
  US15/717,787
• Publication Number:
  US 20180341395A1
• Time in Patent Office: 755 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 for automating transactional conversations between the computing system and at least one front-end computing device, the computing system comprising:

a conversation design module configured to;

provide a graphical user interface through which a plurality of conversation models are designed, wherein each conversation model comprises;

a topic;

one or more goals; and

a conversation flow that defines a dialog to direct conversations toward the one or more goals;

wherein the topic, the one or more goals, and the conversation flow are defined by one or more inputs via the graphical user interface, and each conversation model of the plurality of conversation models references topic-specific content stored on a back-end computing module;

receive, via the graphical user interface, inputs representing the topic of a new conversation model, the one or more goals for the topic, and a plurality of conversation snippets, wherein each conversation snippet is representative of a single prompt provided by the computing system to the at least one front-end computing device, and wherein at least one conversation snippet of the plurality of conversation snippets is associated with a potential response to a preceding conversation snippet received by the computing system from the at least one front-end computing device; and

automatically generate the new conversation model based on the received inputs; and

a conversation execution module, comprising;

a conversation manager configured to;

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

select a particular conversation model of the plurality of conversation models based on the one or more user inputs received from the at least one front-end computing device; and

carry out, in an automated fashion, the conversation flow for the particular conversation model according to the dialog and the topic-specific content corresponding to the particular conversation model.

2. The computing system of claim 1, wherein the topic of the new conversation model comprises one or more fields that define information that the computing system is to request from the at least one front-end computing device during the conversation flow for the new conversation model, and

wherein the conversation design module is configured to:

receive, via the graphical user interface, additional inputs representing the one or more fields; and

generate the particular conversation model further based on the received additional inputs.

3. The computing system of claim 1, wherein the topic comprises one or more keywords that define terms or phrases that the computing system predicts are likely be received from the at least one front-end computing device during an initial stage of the conversation flow for the new conversation model, and

wherein the conversation design module is configured to:

receive, via the graphical user interface, additional inputs representing the one or more keywords; and

update the new conversation model based on the received additional inputs.

4. The computing system of claim 1, wherein carrying out the conversation flow for the particular conversation model in the automated fashion comprises carrying out the conversation flow for the particular conversation model without involvement of a remote live agent.

5. The computing system of claim 1, wherein the computing system is managed by an enterprise, wherein the topic-specific content stored on the back-end computing module corresponds to, and is tailored to, a distinct third-party client of the enterprise, and wherein the plurality of conversation models includes, for each third-party client, at least one conversation model that defines references to the topic-specific content corresponding to the third-party client.

6. The computing system of claim 1, wherein the conversation execution module comprises:

a protocol adapter configured to connect the conversation execution module with the at least one front-end computing device based on characteristics of the at least one front-end computing device, and to carry out respective conversation flows with the at least one front-end computing device according to a specific communication protocols for the at least one front-end computing device, wherein the protocol adapter is configured for carrying out conversation flows with the at least one front-end computing device via a third-party application installed on the at least one front-end computing device.

7. A computing system comprising:

a processor and a memory;

a conversation design module configured to;

provide a graphical user interface through which a conversation model is designed, wherein the conversation model comprises;

a topic;

one or more goals; and

a conversation flow that defines a dialog to direct conversations toward the one or more goals;

wherein the topic, the one or more goals, and the conversation flow are defined by one or more inputs via the graphical user interface, and the conversation model also references topic-specific content stored on a back-end computing module;

receive, via the graphical user interface, inputs representing the topic of a new conversation model, the one or more goals for the topic, and a plurality of conversation snippets, wherein each conversation snippet is representative of a single prompt provided by the computing system to a front-end computing device, and wherein at least one conversation snippet of the plurality of conversation snippets is associated with a potential response to a preceding conversation snippet received by the computing system from the front-end computing device; and

automatically generate the new conversation model based on the received inputs; and

a conversation execution module, comprising a conversation manager configured to;

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

carry out, in an automated fashion, the conversation flow for the conversation model based on the one or more user inputs and according to the dialog and the topic-specific content.

8. The computing system of claim 7, wherein the conversation execution module comprises a protocol adapter configured to connect the conversation execution module with the front-end computing device and carrying out the conversation flow with the front-end computing device according to a specific communication protocol, wherein the specific communication protocol is based on one or more characteristics of the front end computing device.

9. The computing system of claim 7, wherein the conversation execution module includes an application programming interface connector configured to connect the conversation execution module with the topic-specific content.

10. A method comprising:

receiving, by a computing system, via a graphical user interface through which a new conversation model is designed, one or more inputs defining;

a topic of the new conversation model;

one or more goals associated with the topic;

a conversation flow comprising one or more conversation prompts, wherein the conversation flow defines a dialog to direct conversations toward the one or more goals, and wherein the new conversation model references topic-specific content stored in a back-end computing module of the computing system; and

a plurality of conversation snippets, wherein each conversation snippet is representative of the one or more conversation prompts provided by the computing system to a front-end computing device, and wherein at least one conversation snippet of the plurality of conversation snippets is associated with a potential response to a preceding conversation snippet received by the computing system from the front-end computing device;

based on the one or more received inputs, automatically generating, by the computing system, the new conversation model; and

executing, by the computing system, the new conversation model between the computing system and the front-end computing device, wherein executing the new conversation model comprises;

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

carrying out, in an automated fashion, the conversation flow for the new conversation model based on the one or more user inputs and according to the dialog and the topic-specific content.

11. The method of claim 10, comprising:

receiving, via the graphical user interface, additional inputs representing a plurality of additional conversation snippets associated with the one or more goals, wherein each additional conversation snippet is representative of one or more additional conversation prompts provided by the computing system to the front-end computing device, and wherein at least one additional conversation snippet is associated with a potential response to a preceding conversation snippet received by the computing system from the front-end computing device,

updating the new conversation model based on the received additional inputs.

12. The method of claim 10, wherein the topic comprises one or more fields that define information that the computing system is to request from the front-end computing device during the conversation flow for the new conversation model, the method comprising:

receiving, via the graphical user interface, additional inputs representing the one or more fields; and

updating the new conversation model based on the received additional inputs.

13. The method of claim 10, wherein each topic comprises one or more keywords that define terms or phrases that the computing system predicts to be received from the front-end computing device during an initial stage of the conversation flow for the new conversation model, the method comprising:

receiving, via the graphical user interface, additional inputs representing the one or more keywords; and

updating the new conversation model based on the received additional inputs.

14. The method of claim 10, wherein carrying out the conversation flow for the new conversation model comprises carrying out the conversation flow for the new conversation model without involvement of a remote live agent.

15. The method of claim 10, wherein the computing system is managed by an enterprise, and wherein the new conversation model corresponds to a service provided by the enterprise to consumers of the enterprise, a service provided by a third-party client of the enterprise to consumers of the third-party client, or a combination thereof.