BETTER RESOLUTION WHEN REFERENCING TO CONCEPTS

• US 20170186429A1
• Filed: 03/14/2017
• Published: 06/29/2017
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: GIULI, Richard D., TREADGOLD, Nicholas K.
• Granted Patent: US 10,083,690 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Systems and processes for operating a virtual assistant programmed to refer to shared domain concepts using concept nodes are provided. In an example process, user speech input is received. A textual representation of the user speech input is generated. The textual representation is parsed to determine a primary domain representing a user intent for the textual representation. A first substring from the textual representation that corresponds to a first attribute of the primary domain is identified. The identified first substring is parsed to determine a secondary domain representing a user intent for the first substring. A task flow comprising one or more tasks is performed based on the primary domain and the secondary domain.

Claims

1. A method for operating a digital assistant, the method comprising:

at an electronic device having one or more processors and memory;

receiving user speech input;

generating a textual representation of the user speech input;

parsing the textual representation to determine a primary domain representing a user intent for the textual representation;

identifying a first substring from the textual representation that corresponds to a first attribute of the primary domain;

parsing the identified first substring to determine a secondary domain representing a user intent for the first substring; and

performing a task flow comprising one or more tasks based on the primary domain and the secondary domain.

2. The method of claim 1, wherein parsing the textual representation comprises:

determining a confidence score for a plurality of interpretations of the textual representation; and

determining the primary domain representing the user intent for the textual representation based on an interpretation of the plurality of interpretations of the textual representation having the highest confidence score.

3. The method of claim 1, wherein the first attribute comprises a place, a time, an event, or a person.

4. The method of claim 1, wherein identifying the first substring from the textual representation comprises:

identifying, in the textual representation, one or more predetermined words corresponding to the first attribute; and

identifying the first substring based on the one or more predetermined words corresponding to the first attribute.

5. The method of claim 1, wherein parsing the identified first substring comprises:

determining a confidence score for a plurality of interpretations of the first substring; and

determining the secondary domain representing the user intent for the first substring based on an interpretation of the plurality of interpretations of the first substring having the highest confidence score.

6. The method of claim 5, wherein the plurality of interpretations of the first substring exclude interpretations from domains that do not include the first attribute.

7. The method of claim 1, further comprising:

identifying a second substring from the textual representation that corresponds to a second attribute of the primary domain; and

parsing the identified second substring to determine a second secondary domain representing a user intent for the second substring, wherein performing the task flow is further based on the second secondary domain.

8. The method of claim 7, wherein the second attribute comprises a place, a time, an event, or a person.

9. The method of claim 7, wherein identifying the second substring from the textual representation comprises:

identifying in the textual representation one or more predetermined words corresponding to the second attribute; and

identifying the second substring based on the one or more predetermined words corresponding to the second attribute.

10. The method of claim 7, wherein parsing the identified second substring comprises:

determining a confidence score for a plurality of interpretations of the second substring; and

determining the second secondary domain representing a user intent for the second substring based on an interpretation of the plurality of interpretations of the second substring having the highest confidence score.

11. The method of claim 10, wherein the plurality of interpretations of the second substring exclude interpretations from domains that do not output the second attribute.

12. The method of claim 1, wherein performing the task flow comprises:

identifying a primary task flow to accomplish the user intent for the textual representation;

identifying one or more constraints associated with the primary task flow;

identifying one or more queries, programs, methods, services, or APIs that satisfy the one or more constraints associated with the primary task flow; and

generating the task flow from the primary task flow and the identified one or more queries, programs, methods, services, or APIs.

13. The method of claim 12, wherein the one or more constraints comprises a type of input required by the primary task flow, and wherein the identified one or more queries, programs, methods, services, or APIs are capable of providing the type of input required by the primary task flow.

14. The method of claim 1, wherein the first attribute is represented by a first node of the primary domain, and wherein the first node of the primary domain stems from a root node of the primary domain.

15. The method of claim 14, wherein the secondary domain includes a first node representing the first attribute, and wherein the first node of the secondary domain stems from a root node of the secondary domain.

16. The method of claim 1, wherein the identified first substring is parsed to determine the secondary domain without parsing any portion of the text representation other than the identified first substring.

17. The method of claim 1, wherein the secondary domain representing the user intent for the first substring is determined based on the first attribute.

18. The method of claim 1, further comprising:

determining a value for the first attribute based on the secondary domain, wherein the task flow is performed using the determined value for the first attribute.

19. An electronic device, comprising:

one or more processors; and

memory storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for;

receiving user speech input;

generating a textual representation of the user speech input;

parsing the textual representation to determine a primary domain representing a user intent for the textual representation;

identifying a first substring from the textual representation that corresponds to a first attribute of the primary domain;

parsing the identified first substring to determine a secondary domain representing a user intent for the first substring; and

performing a task flow comprising one or more tasks based on the primary domain and the secondary domain.

20. A non-transitory computer-readable storage medium comprising computer-executable instructions for:

receiving user speech input;

generating a textual representation of the user speech input;

parsing the textual representation to determine a primary domain representing a user intent for the textual representation;

identifying a first substring from the textual representation that corresponds to a first attribute of the primary domain;

parsing the identified first substring to determine a secondary domain representing a user intent for the first substring; and

performing a task flow comprising one or more tasks based on the primary domain and the secondary domain.