Systems and methods for building conversational understanding systems

• US 10,474,439 B2
• Filed: 06/16/2016
• Issued: 11/12/2019
• Est. Priority Date: 06/16/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Khan, Omar Zia, Crook, Paul Anthony, Marin, Marius Alexandru, Sarikaya, Ruhi
• Primary Examiner(s): Aponte, Francisco J
• Assistant Examiner(s): Gooray, Mark A
• Application Number:
  US15/184,007
• Publication Number:
  US 20170364336A1
• Time in Patent Office: 1,244 Days
• Field of Search: None
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 8/20 Software design
• CPC Class Codes: G06F 8/30 Creation or generation of source code
• CPC Class Codes: G06F 8/33 Intelligent editors
• CPC Class Codes: G06F 8/34 Graphical or visual programming
• CPC Class Codes: G06F 8/36 Software reuse
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Systems and methods for building conversational understanding systems are provided. More specifically, the systems and methods utilize prebuilt conversational items that can form a CU system upon selection by a builder without requiring any further input from the builder. Accordingly, the systems and methods for building a conversational understanding system reduce the expertise, time, and resources necessary to build a conversational understanding system for an application when compared to systems and methods that utilize conversational items that require further input from the builder.

Claims

1. A system for building a conversational understanding system, the system comprising:

at least one processor; and

a memory for storing and encoding computer executable instructions that, when executed by the at least one processor is operative to;

provide a library of prebuilt conversational items, wherein the library of the prebuilt conversational items includes a plurality of task specific templates, wherein at least one of the plurality of task specific templates includes a task-independent subtask module, and wherein the prebuilt conversational items include preconfigured parameters and a preconfigured structure;

provide a user interface for selecting one or more prebuilt conversational items from the library;

receive a selection of a first prebuilt conversational item and a second prebuilt conversational item;

automatically generate a conversational component, based at least upon the selection, by integrating the first prebuilt conversational item and the second prebuilt conversational item based on a first preconfigured inheritance of the first prebuilt conversational item and a second preconfigured inheritance of the second prebuilt conversational item; and

provide a conversational understanding system based on the conversational component.

2. The system of claim 1, wherein the at least one processor is further operative to:

provide an option to customize the first prebuilt conversational item and the second prebuilt conversational item; and

receive customizations for the first prebuilt conversational item and the second prebuilt conversational item.

3. The system of claim 2, wherein the option to customize includes at least one of:

select a preconfigured parameter;

select a preconfigured constraint;

remove a preconfigured parameter;

remove a preconfigured constraint;

build and add a non-preconfigured parameter;

build and add a non-preconfigured constraint;

order parameters; and

order the selected item set.

4. The system of claim 1, wherein:

automatically integrating the first prebuilt conversational item and the second prebuilt conversational item is further based on a first preconfigured structure of the first prebuilt conversational item and a second preconfigured structure of the second prebuilt conversational item.

5. The system of claim 1, wherein the first prebuilt conversational item comprises a first task specific template and the second prebuilt conversational item comprises a second task specific template, and

wherein automatically generating the conversational component includes:

automatically combining the first task specific template with the second task specific template by;

integrating the first preconfigured inheritance and the second preconfigured inheritance;

determining common required information between the first task specific template and the second task specific template; and

linking the common required information for synchronized data population.

6. The system of claim 5, wherein the automatic combination of the first task specific template with the second task specific template is further performed by:

determining common task-independent subtask modules between the first task specific template and the second task specific template; and

removing one of the common task-independent subtask modules.

7. The system of claim 1, wherein the at least one processor is further operative to:

create the library of prebuilt conversational items.

8. The system of claim 1, wherein the first prebuilt conversational item comprises a first task-independent subtask module and the second prebuilt conversational item comprises a second task-independent subtask module, and

wherein generate the conversational component comprises:

automatically combine the first task-independent subtask module and the second task-independent subtask module by;

integrating the first preconfigured inheritance and the second preconfigured inheritance;

determining common required information between the first task-independent subtask module and the second task-independent subtask module; and

linking the common required information for synchronized data population.

9. The system of claim 1, wherein the first prebuilt conversational item includes a first task specific template and the second prebuilt conversational item includes a first task-independent task module, and

wherein generate the conversational component comprises:

automatically combine the first task specific template and the first task-independent subtask module by;

integrating the first preconfigured inheritance and the second preconfigured inheritance;

determining common required information between the first task specific template and the first subtask module; and

linking the common required information for synchronized data population.

10. The system of claim 1, wherein the first prebuilt conversational item includes a first task specific template and a first task-independent subtask module, wherein the second prebuilt conversational item includes a second task specific template and a second task-independent subtask module, and

wherein automatically generating the conversational component comprises:

automatically combining the first task specific template, the second task specific template, the first subtask module, and the second subtask module by;

integrating preconfigured inheritances and preconfigured structures among the first task specific template, the second task specific template, the first subtask module, and the second subtask module;

determining common required information the first task specific template, the second task specific template, the first subtask module, and the second subtask module, based on the integrated preconfigured inheritances and preconfigured structures; and

linking the common required information for synchronized data population.

11. The system of claim 10, further comprising:

wherein automatically combine the first task specific template, the second task specific template, the first subtask module, and the second subtask module is further performed by;

determining common task-independent subtask modules between the first task specific template and the second task specific template; and

linking the common task-independent subtask modules for synchronized data population.

12. The system of claim 1, wherein the at least one processor is further operative to:

receive an implementation request; and

responsive to the received implementation request, provide the conversational understanding system.

13. The system of claim 1, wherein the at least one processor is further operative to:

provide a search interface for the first prebuilt conversational items, wherein the search interface is part of the user interface;

receive a query for the search interface;

retrieve one or more prebuilt conversational items from the library based on the query; and

present the retrieved one or more prebuilt conversational items for selection.

14. The system of claim 1, wherein the conversational understanding system is built for a specific application, the specific application is at least one of:

a digital assistant application;

a voice recognition application;

an email application;

a social networking application;

a collaboration application;

an enterprise management application;

a messaging application;

a word processing application;

a spreadsheet application;

a database application;

a presentation application;

a contacts application;

a gaming application;

an e-commerce application;

an e-business application;

a transactional application;

a device control application;

a web interface application;

an exchange application;

or

a calendaring application.

15. The system of claim 1, wherein the system is a server or a network of servers.

16. A method for building a conversational understanding system, the method comprising:

providing a library of prebuilt conversational items, wherein the library of the prebuilt conversational items includes a plurality of task specific templates, wherein one or more of the plurality of task specific templates comprise a task-independent subtask module, and wherein the prebuilt conversational items include preconfigured parameters and a preconfigured structure;

providing a user interface for selecting one or more prebuilt conversational items from the library;

receiving a selection of a first prebuilt conversational item and a second prebuilt conversational item;

automatically generating a conversational component based at least upon the selection, wherein generating the conversational component comprises;

combining the received first prebuilt conversational item and the second prebuilt conversational item by integrating a first preconfigured inheritance of the first prebuilt conversational item and a second preconfigured inheritance of the second prebuilt conversational item; and

providing a conversational understanding system based on the conversational component.

17. The method of claim 16, further comprising:

providing an option to customize the first prebuilt conversational item and the second prebuilt conversational item; and

receiving customizations for the first prebuilt conversational item and the second prebuilt conversational item,

wherein the option to customize includes at least one of;

removing a preconfigured parameter; and

removing a preconfigured constraint.

18. The method of claim 16, wherein generating the conversational component further comprises:

automatically integrating a first preconfigured structure of the first prebuilt conversational item and the first preconfigured inheritance with a second preconfigured structure of the second prebuilt conversational item and the second preconfigured inheritance of the second prebuilt conversational item.

19. The method of claim 16, wherein the library comprises a task specific template repository and a task-independent subtask module repository.

20. A computer readable storage medium storing computer executable instructions which, when executed by a computing device, cause the computing device to perform a method comprising:

accessing a library of prebuilt conversational items, wherein the prebuilt conversational items comprise;

a task specific template and a subtask module, and wherein the prebuilt conversational items include preconfigured parameters and a preconfigured structure;

providing a user interface for selecting one or more prebuilt conversational items from the library;

receiving a selection of at least two prebuilt conversational items through the user interface;

based at least upon the selection, automatically combining the at least two prebuilt conversational items based on a first structure and a first inheritance of a first selected prebuilt conversational item and a second structure and a second inheritance of a second selected prebuilt conversational item;

receiving a provisioning request; and

in response to the provisioning request, providing a conversational understanding system based on a conversational component.