Augmented Conversational Understanding Agent

• US 20120253788A1
• Filed: 03/31/2011
• Published: 10/04/2012
• Est. Priority Date: 03/31/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: HECK, LARRY PAUL, CHINTHAKUNTA, MADHUSUDAN, MITBY, DAVID, STIFELMAN, LISA
• Granted Patent: US 9,760,566 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04M 1/724 User interfaces specially adapted for cordless or mobile telephones

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.

Claims

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

receiving, by an agent, at least one natural language phrase from a user, wherein the at least one natural language phrase is associated with a conversation between the user and at least one second user;

identifying a context associated with the at least one natural language phrase; and

performing an agent action associated with the identified context according to the at least one natural language phrase; and

displaying a result associated with performing the agent action.

2. The method of claim 1, wherein the at least one phrase is received from the user in response to an explicit invocation of the agent.

3. The method of claim 1, wherein the at least one phrase is received from the user in response to an implicit invocation of the agent.

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

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

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

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

8. 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

in response to determining 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.

9. The method of claim 8, further comprising, in response to determining 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.

10. A computer-readable medium 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 first natural language phrase from a user, wherein the at least one natural language phrase is associated with a conversation between the user and at least one second user;

determining whether the first natural language phrase comprises enough data to identify a context; and

in response to determining that the first natural language phrase comprises enough data to identify the context;

performing an agent action associated with the identified context according to the at least one natural language phrase, and

displaying a result associated with performing the agent action.

11. The computer-readable medium of claim 10, further comprising:

in response to determining that the first natural language phrase does not comprise enough data to identify a context, waiting to receive at least one second natural language phrase.

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

13. The computer-readable medium of claim 10, further comprising:

determining whether the result is to be shared with the at least one second user; and

in response to determining that the result is to be shared with the at least one second user, displaying the result associated with performing the agent action to the at least one second user.

14. The computer-readable medium of claim 13, wherein determining whether the result is to be shared with the at least one second user comprises determining whether the agent action comprises retrieving a personal note created by the user.

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

16. The computer-readable medium of claim 13, wherein determining whether the result is to be shared with the at least one second user comprises determining whether a prior result associated with performing the agent action has been previously shared with the at least one second user.

17. The computer-readable medium of claim 13, wherein determining whether the result is to be shared with the at least one second user comprises determining whether the result is associated with scheduling an event.

18. The computer-readable medium of claim 13, wherein determining whether the result is to be shared with the at least one second user comprises determining whether at least one second natural language phrase received from the user refers to the result.

19. The computer-readable medium 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 user and wherein the request comprises at least one of the following;

an explicit invocation request by the first user and a request to begin a conversation between the first user and at least one second user,

receive a first natural language phrase,

determine whether the first natural language phrase comprises enough data to identify a context,

in response to determining that the first natural language phrase does not comprise enough data to identify a context, wait to receive at least one second natural language phrase, and

in response to determining that the first natural language phrase comprises enough data to identify a context;

perform an agent action associated with the first natural language phrase,

display a result according to the performed action,

receive at least one second natural language phrase,

determine whether the at least one second natural language phrase is associated with the identified context,

in response to determining that the at least one second natural language phrase is associated with the identified context;

update the identified context according to the at least one second natural language phrase,

perform a second agent action associated with the updated context; and

update the display according to a second result associated with the second action.