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

• US 10,529,326 B2
• Filed: 01/13/2017
• Issued: 01/07/2020
• 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:
  US15/405,920
• Publication Number:
  US 20170125018A1
• Time in Patent Office: 1,089 Days
• Field of Search: 704 7- 9, 704257
• 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:

at least one element including at least one of (a) one or more processors or (b) hardware logic/electrical circuitry; and

a memory for storing instructions that when executed by the at least one element, cause the processing system to perform a method comprising;

determining whether a request for a natural language system is received;

generating one or more intent frames in response to a determination that a request for the natural language system is received, each of the one or more intent frames including at least one carrier phrase and at least one slot, and at least one slot in at least one intent frame comprises a blank slot;

determining one or more suggested textual phrases that can replace the at least one blank slot in the at least one intent frame; and

causing the one or more intent frames and the one or more suggested textual phrases to be provided to an output device for perception by a user, wherein the blank slot is identified as being replaceable and each suggested textual phrase is selectable by the user.

2. The processing system of claim 1, wherein the method further comprises prior to determining whether the request for the natural language system is received, suggesting one or more intent frames to the user to elicit a request from the user.

3. The processing system of claim 1, wherein:

the output device comprises a display and the one or more intent frames and the one or more suggested textual phrases are provided as a visual representation on the display;

or

the output device comprises a speaker and the one or more intent frames and the one or more suggested textual phrases are provided as an audio representation using the speaker.

4. The processing system of claim 1, wherein the operation of generating the one or more intent frames comprises generating at least one of the one or more intent frames based on one or more topics that are accessed by the user with respect to a software application.

5. The processing system of claim 1, wherein the operation of causing the one or more intent frames and the one or more textual phrases to be provided to the output device for perception by the user comprises causing the one or more intent frames and the one or more textual phrases to be provided to the output device based on a request not being received by the processing system since a time instance at which a natural language functionality of the processing system is activated.

6. The processing system of claim 1, wherein at least one of the one or more suggested textual phrases comprises a dynamic suggested textual phrase and the method further comprises displaying the dynamic suggested textual phrase moving with reference to a respective blank slot with which the dynamic suggested textual phrase is associated.

7. The processing system of claim 1, wherein:

the one or more suggested textual phrases comprises a plurality of suggested textual phrases;

a respective blank slot in the at least one slot comprises a designated slot; and

the method further comprises providing the plurality of suggested textual phrases to replace the designated slot in a specified intent frame that is included in the one or more intent frames, the plurality of suggested textual phrases configured to rotate about the designated slot.

8. A method, comprising:

generating one or more intent frames that each include at least one carrier phrase and a designated slot that is associated with each carrier phrase;

determining one or more user-selectable suggested textual phrases that can replace the designated slot in at least one of the one or more intent frames; and

causing a visual representation or an audio representation of each intent frame and the one or more user-selectable suggested textual phrases to be provided to an output device, wherein the designated slot is identified as being replaceable; and

in response to the visual or the audio representation, receiving a selection of a respective user-selectable suggested textual phrase for the designated slot in at least one of the one or more intent frames.

9. The method of claim 8, further comprising:

determining whether a natural language system is activated, the natural language system enabling a processing system to interpret natural language requests; and

generating the one or more intent frames in response to at least one of;

a determination that the natural language system is activated;

or

a determination that the natural language system is activated and receipt of a natural language request.

10. The method of claim 8, wherein the operation of determining the one or more user-selectable suggested textual phrases that can replace the designated slot in the at least one of the one or more intent frames comprises determining the one or more user-selectable suggested textual phrases that can replace the designated slot in the at least one of the one or more intent frames based on at least one of:

a temporal relevance comprising a passage of time associated with each textual phrase or a personal relevance comprising one or more factors associated with a user; and

the method further comprises;

determining a first user-selectable suggested textual phrase and a second user-selectable suggested textual phrase that can replace a designated slot in an intent frame;

determining a first relevance for the first user-selectable suggested textual phrase, the first relevance comprising at least one of the personal relevance associated with the user or the temporal relevance associated with the first user-selectable suggested textual phrase;

determining a second relevance for the second user-selectable suggested textual phrase, the second relevance comprising at least one of the personal relevance associated with the user or the temporal relevance associated with the second user-selectable suggested textual phrase; and

receiving a selection of either the first user-selectable suggested textual phrase based on the first relevance or the second user-selectable suggested textual phrase based on the second relevance, wherein the intent frame and the selected first or second user-selectable suggested textual phrase is to be provided to the output device.

11. The method of claim 10, wherein the personal relevance comprising one or more factors associated with the user comprises at least one of:

a geographical location of the user;

a time of day;

or

a user preference.

12. The method of claim 8, wherein each designated slot in each visual representation of a respective intent frame comprises one of:

a blank space;

or

an underlined blank space.

13. The method of claim 8, wherein the one or more user-selectable suggested textual phrases in the visual representation of the one or more intent frames is displayed proximate the designated slot associated with each user-selectable suggested textual phrase.

14. The method of claim 8, wherein the audio representation of each intent frame comprises a sequence of spoken words and each designated slot is included in a respective sequence of words and comprises an audio tone.

15. The method of claim 8, wherein the output device comprises a display that displays the visual representation of each intent frame and the one or more user-selectable suggested textual phrases.

16. The method of claim 8, wherein the output device comprises a speaker that outputs the audio representation of each intent frame and the one or more user-selectable suggested textual phrases.

17. A method, comprising:

receiving a first natural language 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 natural language request; and

causing at least one of a visual representation or an audio representation of one or more intent frames to be provided for the user to elicit a second natural language request from the user, using at least one processor of the processing system, in response to the first natural language request from the user, wherein;

each of the one or more intent frames is based on a state of an interaction with the user with the processing system and the at least one of the domain or the intent and comprises a suggested action, and

each of the one or more intent frames includes at least one respective carrier phrase and at least one respective slot that is associated with each carrier phrase.

18. The method of claim 17, further comprising prior to receiving the natural language request, receiving an operation to activate a natural language system, wherein the operation comprises one of:

a selection of an interface element;

or

a selection of a displayed element.

19. The method of claim 17, wherein:

the operation of providing at least one of the visual representation or the audio representation of one or more intent frames comprises generating at least one of the visual representation or the audio representation of a first intent frame; and

the method further comprises;

generating at least one of a visual representation or an audio representation of a second intent frame;

for each of the first intent frame and the second intent frame, determining a probability that the user will select the intent frame if the intent frame is provided to the output device; and

selecting either the first intent frame or the second intent frame based on the probability associated with first intent frame or the second intent frame, wherein the at least one of the visual representation or the audio representation of the selected first or second intent frame is to be provided to the output device.

20. The method of claim 17, wherein:

at least one slot in at least one carrier phrase comprises a blank slot; and

the method further comprises;

determining one or more user-selectable suggested textual phrases that can replace each blank slot;

receiving a selection of a respective textual phrase to replace each blank slot; and

providing at least one of a visual representation or an audio representation of the intent frame associated with each blank slot to an output device, wherein each blank slot is replaced with the selected suggested textual phrase.