Augmented conversational understanding agent to identify conversation context between two humans and taking an agent action thereof

Patent metadata

Field	Value
Publication number	US-9760566-B2
Application number	US-201113076862-A
Country	US
Kind code	B2
Filing date	Mar 31, 2011
Priority date	Mar 31, 2011
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

An augmented conversational understanding agent may be provided. Upon receiving, by an agent, at least one natural language phrase from a user, a context associated with the at least one natural language phrase may be identified. The natural language phrase may be associated, for example, with a conversation between the user and a second user. An agent action associated with the identified context may be performed according to the at least one natural language phrase and a result associated with performing the action may be displayed, wherein the agent action comprises providing a list of movies, a list of night clubs, a search for restaurants, or other action suggestions.

First claim

What is claimed is:

1. A method for providing an augmented conversational understanding agent, the method comprising:
receiving, on a computing device, at least one natural language phrase from a human user, wherein the at least one natural language phrase is from a conversation between the human user and at least one second human user;
identifying, by the computing device, a context associated with the received at least one natural language phrase, the context being identified by the computing device applying an understanding model to determine whether one or more parameters are included in the received at least one natural language phrase;
performing, by the computing device, an implicitly requested agent action associated with the identified context according to the received at least one natural language phrase, wherein the agent action comprises providing a list of movies, a list of night clubs, a search for restaurants, or other action suggestions; and
displaying, by the computing device, a result associated with performing the agent action.

2. The method of claim 1 , wherein the received at least one natural language phrase is received from the human user in response to an implicit invocation.

3. The method of claim 2 , wherein the implicit invocation occurs in response to a request to begin the conversation with the at least one second human user.

4. The method of claim 3 , wherein the conversation occurs via an instant message session.

5. The method of claim 4 , wherein the conversation occurs via a telephone call.

6. The method of claim 1 , further comprising:
receiving at least one second natural language phrase;
determining whether the at least one second natural language phrase is associated with the identified context; and
when determined that the at least one second natural language phrase is associated with the identified context:
performing a second agent action associated with the identified context according to the at least one second natural language phrase, and
updating the display according to a second result associated with the second agent action.

7. The method of claim 6 , further comprising, when determined that the at least one second natural language phrase is not associated with the identified context:
identifying a second context associated with the at least one second natural language phrase;
performing a third agent action associated with the second identified context according to the at least one second natural language phrase, and
replacing the display of the result with a second result associated with the third agent action.

8. The method of claim 1 , wherein the received at least one natural language phrase is received from the human user in response to an explicit invocation.

9. The method of claim 1 , wherein identifying the context of the natural language phrase further comprises identifying at least one domain associated with at least one word of the natural language phrase.

10. A computer-readable storage device which stores a set of instructions which when executed performs a method for providing an augmented conversational understanding agent, the method executed by the set of instructions comprising:
receiving a natural language phrase from a human user, wherein the natural language phrase is from a conversation between the human user and at least one second human user;
determining whether the received natural language phrase comprises enough data to identify a context, the context being identified by applying an understanding model to determine whether one or more parameters are included in the received natural language phrase; and
when determined that the received natural language phrase comprises enough data to identify the context:
performing an implicitly requested agent action associated with the identified context according to the received natural language phrase, wherein the agent action comprises providing a list of movies, a list of night clubs, a search for restaurants, or other action suggestions, and
displaying a result associated with performing the agent action.

11. The computer-readable storage device of claim 10 , further comprising:
determining whether the result is to be shared with the at least one second human user; and
when determined that the result is to be shared with the at least one second human user, displaying the result associated with performing the agent action to the at least one second human user.

12. The computer-readable storage device of claim 11 , wherein determining whether the result is to be shared with the at least one second human user comprises determining whether the agent action comprises retrieving a personal note created by the human user.

13. The computer-readable storage device of claim 11 , wherein determining whether the result is to be shared with the at least one second human user comprises requesting authorization from the human user to share the result with the at least one second human user.

14. The computer-readable storage device of claim 11 , wherein determining whether the result is to be shared with the at least one second human user comprises determining whether a prior result associated with performing the agent action has been previously shared with the at least one second human user.

15. The computer-readable storage device of claim 11 , wherein determining whether the result is to be shared with the at least one second human user comprises determining whether the result is associated with scheduling an event.

16. The computer-readable storage device of claim 11 , wherein determining whether the result is to be shared with the at least one second human user comprises determining whether at least one second natural language phrase received from the human user refers to the result.

17. The computer-readable storage device of claim 10 , further comprising:
when determined that the received natural language phrase does not comprise enough data to identify a context, waiting to receive at least one second natural language phrase.

18. The computer-readable storage device of claim 10 , wherein the identified context comprises a merger of a first ontology associated with the human user and a second ontology associated with the at least one second human user.

19. The computer-readable storage device of claim 10 , wherein performing the action comprises retrieving data from at least one network data source.

20. 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:
invoke an agent application, wherein invoking the agent application occurs in response to a request from a first human user and wherein the request comprises at least one of the following: an explicit invocation request by the first human user and a request to begin a conversation between the first human user and at least one second human user,
receive a first natural language phrase, wherein the received first natural language phrase is from a conversation between the first human user and the at least one second human user,
determine whether the received first natural language phrase comprises enough data to identify a context, the context being identified by applying an understanding model to determine whether one or more parameters are included in the received first natural language phrase,
when determined that the received first natural language phrase does not comprise enough data to identify

Assignees

• Heck Larry Paul
• Chinthakunta Madhusudan
• Mitby David
• Stifelman Lisa
• Microsoft Technology Licensing Llc

Inventors

• Heck Larry Paul
• Chinthakunta Madhusudan
• Mitby David
• Stifelman Lisa

Classifications

• G06F40/58

  Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title

• G06F40/35 Primary

  Discourse or dialogue representation · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06N20/00

  Machine learning · CPC title

• H04M1/72519

  Electricity · mapped topic