Automating natural language task/dialog authoring by leveraging existing content

• US 10,217,462 B2
• Filed: 08/31/2016
• Issued: 02/26/2019
• Est. Priority Date: 08/31/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Sarikaya, Ruhi, Radostev, Vasiliy
• Primary Examiner(s): Hang, Vu B
• Application Number:
  US15/253,592
• Publication Number:
  US 20180061401A1
• Time in Patent Office: 909 Days
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/143 Markup, e.g. Standard Generalized Markup Language [SGML] or Document Type Definition [DTD]
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G06Q 10/30 Administration of product recycling or disposal
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: Y02W 90/00 Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation

Abstract

Systems and methods for augmenting existing CU system to be used with content, such as a website. The content may be parsed to determine on or more actions that may be performed by a user who uses the content. These actions may then be compared to tasks of CU systems to identify potential matches. When a match is found, the CU system may be updated to include information.

Claims

1. A computer method, the method comprising:

parsing a webpage to identify an element;

determining a domain of the webpage;

determining a suggested task, wherein determining the suggested task comprises;

identifying one or more existing conversational understanding systems that are associated with the determined domain;

based on the parsed webpage, determining an action associated with the element; and

comparing the action to one or more existing tasks for the identified one or more existing conversational understanding systems to identify the suggested task;

providing, via a user interface, the suggested task to an authoring platform; and

receiving, via the user interface, confirmation to use the suggested task to enable a user to vocally interact with the webpage.

2. The method of claim 1, further comprising:

parsing the webpage to identify at least one parameter; and

mapping the at least one parameter to a task parameter associated with the suggested task.

3. The method of claim 2, further comprising:

determining that the parameter is associated with a placeholder entity of the suggested task; and

augmenting the conversational understanding system with the at least one parameter such that the parameter replaces the placeholder entity in the suggested task.

4. The method of claim 3, wherein augmenting the conversational understanding system comprises replacing, in a dialog, a placeholder entity with the at least one parameter.

5. The method of claim 4, further comprising providing the dialog to a client device.

6. The method of claim 1, further comprising:

executing an action of the webpage, wherein the execution results in navigating to a new webpage and presenting a message to a user, and further wherein the new webpage has a URL and the message includes text;

capturing the URL; and

storing the message text.

7. The method of claim 6, wherein executing the action of the webpage occurs by filling in sample information into a field of the webpage.

8. A system comprising:

at least one processor; and

memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform a method comprising;

determining a domain associated with a webpage, wherein the webpage comprises at least one actionable element;

determining a suggested task, wherein determining the suggested task comprises;

identifying one or more existing conversational understanding systems that are associated with the domain;

comparing the actionable element to one or more existing tasks for the identified one or more existing conversational understanding systems to identify the suggested task; and

providing, via a user interface, the suggested task to an authoring platform to confirm use of the suggested task, wherein use of the suggested task enables a user to vocally interact with the webpage.

9. The system of claim 8, further comprising:

determining that the parameter is associated with a placeholder entity of the suggested task; and

augmenting the conversational understanding system with the at least one parameter such that the parameter replaces the placeholder entity in the suggested task.

10. The system of claim 9, further comprising augmenting the conversational understanding system with the at least one parameter.

11. The system of claim 10, wherein augmenting the conversational understanding system comprises replacing, in a dialog, a placeholder entity with the at least on parameter.

12. The system of claim 11, further comprising providing the dialog to a client device.

13. The system of claim 8, further comprising:

executing an action of the webpage, wherein the execution results in navigating to a new webpage and presenting a message to a user, wherein the new webpage has a URL and the message includes text;

capturing the URL; and

storing the message text.

14. The system of claim 13, wherein executing the action of the webpage occurs by filling in sample information into a field of the webpage.

15. A computer-readable storage device storing instructions that, when executed, are capable of performing a method, the method comprising:

parsing a webpage to identify an element on the webpage;

determining a domain associated with the webpage;

determining a suggested task, wherein determining the suggested task comprises;

identifying one or more existing conversational understanding systems that are associated with the determined domain;

based on the parsed webpage, determining an action associated with the element by navigating the webpage; and

comparing the action to one or more existing tasks for the identified one or more existing conversational understanding systems to identify the suggested task; and

providing, via a user interface, the suggested task to an authoring platform to confirm use of the suggested task, wherein use of the suggested task enables a user to vocally interact with the webpage.

16. The computer-readable storage device of claim 15, further comprising:

determining that the parameter is associated with a placeholder entity of the suggested task; and

augmenting the conversational understanding system with the at least one parameter such that the parameter replaces the placeholder entity in the suggested task.

17. The computer-readable storage device of claim 16, further comprising:

augmenting the conversational understanding system with the at least one parameter.

18. The computer-readable storage device of claim 17, wherein augmenting the conversational understanding system comprises replacing, in a dialog, a placeholder entity with the at least on parameter.