Augmented conversational understanding architecture

• US 10,642,934 B2
• Filed: 03/31/2011
• Issued: 05/05/2020
• Est. Priority Date: 03/31/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Heck, Larry Paul, Chinthakunta, Madhusudan, Mitby, David, Stifelman, Lisa
• Primary Examiner(s): Nguyen, Thu N
• Application Number:
  US13/077,431
• Publication Number:
  US 20120254227A1
• Time in Patent Office: 3,323 Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

An augmented conversational understanding architecture may be provided. Upon receiving a natural language phrase from a user, the phrase may be translated into a search phrase and a search action may be performed on the search phrase.

Claims

1. A method for providing an augmented conversational understanding architecture, the method comprising:

receiving, from a user, a natural language phrase comprising an action request, wherein the natural language phrase represents a current dialogue turn of the user;

determining a context of the action request using a prior dialogue turn of the user and a data type associated with the action request;

determining a context state associated with the user, wherein the context state comprises at least one of a current location of the user and a role associated with the user;

determining one or more objectives based on the context of the action request and the context state;

deriving a plurality of selectable suggested actions based on the one or more objectives, the plurality of selectable suggested actions comprising a plurality of user activities enabling the fulfillment of the action request; and

displaying the plurality of selectable suggested actions to the user.

2. The method of claim 1, further comprising:

translating the natural language phrase into a search phrase; and

performing a search action based on the search phrase, wherein performing the search action comprises mapping the natural language phrase to at least one node of an ontology, the ontology comprising data associated with a plurality of search engine results.

3. The method of claim 1, wherein the natural language phrase is received as an audio stream.

4. The method of claim 2, wherein the search phrase comprises at least one semantic concept.

5. The method of claim 4, wherein the at least one semantic concept comprises a word not contained in the natural language phrase.

6. The method of claim 2, further comprising:

receiving a plurality of search results according to the search action; and

providing the plurality of search results to the user.

7. The method of claim 1, wherein the natural language phrase is derived from a conversation among a plurality of users.

8. The method of claim 1, further comprising:

analyzing a plurality of application programming interfaces (APIs); and

identifying at least one required parameter for each of the plurality of APIs.

9. The method of claim 8, wherein each of the plurality of APIs is associated with a website search function.

10. The method of claim 8, further comprising:

determining whether at least one of the plurality of APIs is associated with the determined context; and

in response to determining that at least one of the plurality of APIs is associated with the determined context, translating at least one word of the natural language phrase into the at least one required parameter associated with the at least one of the plurality of APIs.

11. The method of claim 10, further comprising performing a search action by calling the at least one of the plurality of APIs with the at least one required parameter.

20. The method of claim 1, further comprising:

receiving a selection of at least one of the plurality of selectable suggested actions; and

based on the selection, adjusting a predicted probability of one or more of the plurality of selectable suggested actions, wherein the predicted probability indicates a confidence the selected action fulfills the action request.

12. A computer-readable storage device which stores a set of instructions which when executed performs a method for providing an augmented conversational understanding architecture, the method executed by the set of instructions comprising:

receiving, from a user, a natural language phrase comprising an action request, wherein the natural language phrase represents a current dialogue turn of the user;

determining a context of the action request using a prior dialogue turn of the user and a data type associated with the action request;

identifying a context state associated with the natural language phrase, wherein the context state comprises at least one of a current location of the user, a previously identified user objective, and a role associated with the user;

determining one or more objectives based on the context of the action request and the context state;

providing a plurality of suggested actions based on the one or more objectives, the plurality of suggested actions being selectable and comprising a plurality of user activities based on the context, the context state, and the action request; and

performing an executable action associated with the action request.

13. The computer-readable storage device of claim 12, wherein the context state further comprises at least one of the following:

at least one previous user action request, a time, a date, a category associated with the action request from the user, a data type associated with the first action request from the user, and a data category associated with previous user action requests.

14. The computer-readable storage device of claim 12, wherein the executable action comprises at least one of the following:

a search action, a data creation action, a data modification action, and a communication action.

15. The computer-readable storage device of claim 12, wherein the at least one suggested action comprises a suggested activity derived from the context state and the natural language phrase.

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

receiving a second natural language phrase from the user;

determining whether the second natural language phrase is associated with the at least one suggested action; and

in response to determining that the second natural language phrase is associated with the at least one suggested action, performing the at least one suggested next action.

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

in response to determining that the second natural language phrase is not associated with the at least one suggested action, providing at least one second suggested action to the user.

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

updating the context state according to the second natural language phrase.

19. A system for providing a context-aware environment, the system comprising:

a memory storage; and

a processing unit coupled to the memory storage, wherein the processing unit is operative to;

receive, from a user, an natural language phrase comprising an action request, wherein the natural language phrase represents a current dialogue turn of the user;

determining a context of the action request using at least one of;

a prior dialogue turn of the user and a data type associated with the action request;

identify a context state associated with the user, wherein the context state is based at least in part on the location of the user;

identify one or more objectives according to the context of the action request and the context state, the one or more objectives comprising one or more user activities based on one or more terms in the action request;

execute the action request according to the context state;

compare the context state to a plurality of user context states each associated with a plurality of objectives to determine whether the action request is associated with accomplishing at least one of the plurality of objectives;

in response to determining that the action request is associated with accomplishing at least one of the plurality of objectives, update the context state;

determine whether the context state comprises a completed objective of the plurality of objectives; and

in response to determining that the context state does not comprise the completed objective, provide a selectable suggested action.