Suggesting intent frame(s) for user request(s)

• US 9,201,859 B2
• Filed: 12/15/2011
• Issued: 12/01/2015
• Est. Priority Date: 12/15/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Landry, Shane J., Sullivan, Anne K., Stifelman, Lisa J., Elman, Adam D., Heck, Larry Paul, Parthasarathy, Sarangarajan
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US13/327,305
• Publication Number:
  US 20130158980A1
• Time in Patent Office: 1,447 Days
• Field of Search: 704 7- 9, 704/257
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 13/06 Elementary speech units used in speech synthesisers; Concatenation rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Techniques are described herein that are capable of suggesting intent frame(s) for user request(s). For instance, the intent frame(s) may be suggested to elicit a request from a user. An intent frame is a natural language phrase (e.g., a sentence) that includes at least one carrier phrase and at least one slot. A slot in an intent frame is a placeholder that is identified as being replaceable by one or more words that identify an entity and/or an action to indicate an intent of the user. A carrier phrase in an intent frame includes one or more words that suggest a type of entity and/or action that is to be identified by the one or more words that may replace the corresponding slot. In accordance with these techniques, the intent frame(s) are suggested in response to determining that natural language functionality of a processing system is activated.

Claims

1. A processing system comprising:

activation logic configured to determine whether natural language functionality of the processing system is activated, the natural language functionality for enabling the processing system to interpret natural language requests;

suggestion logic, implemented using at least one processor, configured to generate one or more intent frames, each of the one or more intent frames including at least one carrier phrase and at least one slot; and

an interface configured to provide at least one of a visual representation or an audio representation of the one or more intent frames to a user to elicit a request from the user based on a determination that the natural language functionality of the processing system is activated, the at least one slot that is included in each of the one or more intent frames indicating to the user that the at least one slot is replaceable by the user with at least one phrase to indicate an intent of the user.

2. The processing system of claim 1, wherein the one or more intent frames include a first intent frame that includes one or more slots that do not include text.

3. The processing system of claim 2, wherein the one or more slots are underlined.

4. The processing system of claim 1, wherein at least one of the one or more intent frames includes one or more slots that include underlined text.

5. The processing system of claim 1, wherein the suggestion logic is configured to provide a plurality of suggested textual phrases to replace a designated slot in a specified intent frame that is included in the one or more intent frames.

6. The processing system of claim 1, further comprising:

request analysis logic configured to determine at least one of a domain or an intent of a request that is received from the user;

wherein the suggestion logic is further configured to suggest one or more second intent frames in response to the request from the user, each of the one or more second intent frames being based on the at least one of the domain or the intent, each of the one or more second intent frames including at least one respective second carrier phrase and at least one respective second slot.

7. The processing system of claim 6, wherein at least one of the one or more second intent frames is further based on at least one of a preference of the user, content that is provided to the user in response to the request, or information regarding a prior request from the user;

and

wherein the prior request precedes the request in response to which the one or more second intent frames are suggested.

8. A method comprising:

determining that natural language functionality of a processing system is activated to enable the processing system to interpret natural language requests; and

providing at least one of a visual representation or an audio representation of one or more intent frames via an interface of the processing system for a user to elicit a request from the user, using at least one processor of the processing system, in response to determining that the natural language functionality is activated, each of the one or more intent frames including at least one carrier phrase and at least one slot, the at least one slot that is included in each of the one or more intent frames indicating to the user that the at least one slot is replaceable by the user with at least one phrase to indicate an intent of the user.

9. The method of claim 8, wherein providing the at least one of the visual representation or the audio representation of the one or more intent frames comprises:

providing at least one of a visual representation or an audio representation of a first intent frame that includes one or more slots that do not include text.

10. The method of claim 9, wherein providing the at least one of the visual representation or the audio representation of the first intent frame comprises:

configuring at least one of the one or more slots to be underlined.

11. The method of claim 8, wherein providing the at least one of the visual representation or the audio representation of the one or more intent frames comprises:

suggesting a first intent frame that includes one or more slots that include underlined text.

12. The method of claim 8, wherein providing the at least one of the visual representation or the audio representation of the one or more intent frames comprises:

providing a plurality of suggested textual phrases to replace a designated slot in a first intent frame that is included in the one or more intent frames.

13. The method of claim 8, further comprising:

receiving a request from the user at the processing system;

determining at least one of a domain or an intent of the request; and

providing at least one of a visual representation or an audio representation of one or more second intent frames in response to the request from the user, each of the one or more second intent frames being based on the at least one of the domain or the intent, each of the one or more second intent frames including at least one respective second carrier phrase and at least one respective second slot.

14. The method of claim 13, wherein at least one of the one or more second intent frames is further based on at least one of a preference of the user, content that is provided to the user in response to the request, or information regarding a prior request from the user;

and

wherein the prior request precedes the request in response to which the at least one of the visual representation or the audio representation of the one or more second intent frames is provided.

15. A method comprising:

receiving a first request from a user at a processing system having natural language functionality that enables the processing system to interpret natural language requests;

determining at least one of a domain or an intent of the first request; and

providing at least one of a visual representation or an audio representation of one or more intent frames via an interface of the processing system for the user to elicit a second request from the user, using at least one processor of the processing system, in response to the first request from the user, each of the one or more intent frames being based on the at least one of the domain or the intent, each of the one or more intent frames including at least one respective carrier phrase and at least one respective slot, the at least one slot that is included in each of the one or more intent frames indicating to the user that the at least one slot is replaceable by the user with at least one phrase to indicate an intent of the user.

16. The method of claim 15, wherein at least one of the one or more intent frames is further based on information regarding one or more prior requests from the user, the one or more prior requests preceding the first request in response to which the one or more intent frames are suggested.

17. The method of claim 15, further comprising:

providing content for the user based on the first request;

wherein at least one of the one or more intent frames is further based on the content.

18. The method of claim 15, wherein at least one of the one or more intent frames is further based on at least one preference of the user.

19. The method of claim 15, further comprising:

assigning a plurality of probabilities to a plurality of respective possible intent frames, each probability indicating a likelihood that the user is to select the corresponding possible intent frame if the corresponding possible intent frame is suggested to the user; and

identifying a high-probability intent frame from the plurality of possible intent frames, the high-probability intent frame being assigned a probability that is not less than a probability that is assigned to each other possible intent frame in the plurality of possible intent frames;

wherein providing the at least one of the visual representation or the audio representation of the one or more intent frames comprises;

including at least one of a visual representation or an audio representation of the high-probability intent frame in the at least one of the visual representation or the audio representation of the one or more intent frames based on the high-probability intent frame being assigned a probability that is not less than a probability that is assigned to each other possible intent frame in the plurality of possible intent frames.

20. The method of claim 15, wherein providing the at least one of the visual representation or the audio representation of the one or more intent frames comprises:

providing at least one of a visual representation or an audio representation of a specified intent frame that includes a specified slot;

wherein the method further comprises;

determining a relevance of each of a plurality of possible textual phrases with regard to the first request from the user; and

dynamically generating a designated textual phrase from the plurality of possible textual phrases to be included in the specified slot based on the relevance of the designated textual phrase not being less than the relevance of each other possible carrier phrase in the plurality of possible carrier phrases.