Determining User Intent Based on Ontologies of Domains

• US 20130110519A1
• Filed: 12/21/2012
• Published: 05/02/2013
• Est. Priority Date: 09/08/2006
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Cheyer, Adam John, Brigham, Christopher Dean, Guzzoni, Didier Rene
• Granted Patent: US 8,942,986 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: B60K 35/00 Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 9/54 Interprogram communication
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/041 Abduction
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• 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 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 : Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 21/06 : Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence
• CPC Class Codes: H04M 1/6091 : including a wireless interface
• CPC Class Codes: H04M 1/7243 : with interactive means for internal management of messages
• CPC Class Codes: H04M 1/72448 : with means for adapting the functionality of the device according to specific conditions
• CPC Class Codes: H04M 1/72484 : wherein functions are triggered by incoming communication events

Abstract

Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A plurality of predefined domains each representing a respective area of service offered by an intelligent automated assistant are stored. A text string derived from a user request is obtained, the text string including at least one or more words derived from a speech input received from a user. From the plurality of predefined domains, a relevant domain for the user request is identified based at least on respective degrees of match between the text string derived from the user request and a respective plurality of words associated with each predefined domain. A task is executed in accordance with steps specified in a task flow associated with the relevant domain, and in accordance with one or more task parameters derived from the user request.

Claims

1. A method for operating an intelligent automated assistant, comprising:

at an electronic device comprising a processor and memory storing instructions for execution by the processor;

storing a plurality of predefined domains each representing a respective area of service offered by the intelligent automated assistant, wherein each of the predefined domains comprises a respective plurality of concepts and one or more relations relating the respective plurality of concepts, wherein each predefined domain is associated with at least one task flow specifying steps for performing a respective task in the predefined domain, and wherein each of the predefined domains is associated with a respective plurality of words relevant to the predefined domain;

obtaining a text string derived from a user request, the text string including at least one or more words derived from a speech input received from a user;

from the plurality of predefined domains, identifying a relevant domain for the user request based at least on respective degrees of match between the text string de-rived from the user request and the respective plurality of words associated with each prede-fined domain; and

executing a task in accordance with steps specified in a task flow associated with the relevant domain, and in accordance with one or more task parameters derived from the user request.

2. The method of claim 1, wherein the respective plurality of words associated with each predefined domain comprises at least two respective words that each represent a concept related to the predefined domain or an entity related to the predefined domain.

3. The method of claim 1, wherein at least one of the plurality of predefined domains is associated with a respective service model specifying an API for accessing one or more functions of an application or web-based service on behalf of the user, the application or web-based service operable to provide the one or more functions directly to the user through a user interface of the application or web-based service.

4. The method of claim 1, wherein at least one of the plurality of predefined domains is associated with a respective service model specifying an API for accessing one or more functions of an application or web-based service that provides no user interface for direct user access to the one or more functions.

5. The method of claim 1, wherein the degrees of match includes degrees of semantic match and degrees of phonetic match between the text string derived from the user request and the respective plurality of words associated with each predefined domain.

6. The method of claim 1, wherein identifying the relevant domain from the plurality of predefined domains further comprises:

generating two or more semantic parses from the text string, each semantic parse associating the text string with two or more concepts of a respective one of the plurality of predefined domains;

from among the two or more semantic parses, selecting a candidate semantic parse that associates the text string with two or more concepts of a first predefined domain, wherein the selecting is based at least on a strength of connections existing between the two or more concepts in the first predefined domain; and

identifying the relevant domain based on the candidate semantic parse.

7. The method of claim 1, wherein at least one of the plurality of predefined domains is associated with a dialog flow, the dialog flow specifying steps for the intelligent automated assistant to request information regarding one or more task parameters for a respective task associated with the at least one predefined domain.

8. The method of claim 1, wherein the user request further includes context infor-mation associated with the speech input received from the user, and one or more of the task parameters are derived based on the context information.

9. A system, comprising:

one or more processors; and

memory having instructions stored thereon, the instructions, when executed by one or more processors, cause the processors to perform operations comprising;

storing a plurality of predefined domains each representing a respective area of service offered by an intelligent automated assistant, wherein each of the predefined do-mains comprises a respective plurality of concepts and one or more relations relating the respective plurality of concepts, wherein each predefined domain is associated with at least one task flow specifying steps for performing a respective task in the predefined domain, and wherein each of the predefined domains is associated with a respective plurality of words relevant to the predefined domain;

obtaining a text string derived from a user request, the text string including at least one or more words derived from a speech input received from a user;

from the plurality of predefined domains, identifying a relevant domain for the user request based at least on respective degrees of match between the text string de-rived from the user request and the respective plurality of words associated with each prede-fined domain; and

executing a task in accordance with steps specified in a task flow associated with the relevant domain, and in accordance with one or more task parameters derived from the user request.

10. The system of claim 9, wherein the respective plurality of words associated with each predefined domain comprises at least two respective words that each represent a con-cept related to the predefined domain or an entity related to the predefined domain.

11. The system of claim 9, wherein at least one of the plurality of predefined domains is associated with a respective service model specifying an API for accessing one or more functions of an application or web-based service on behalf of the user, the application or web-based service operable to provide the one or more functions directly to the user through a user interface of the application or web-based service.

12. The system of claim 9, wherein at least one of the plurality of predefined domains is associated with a respective service model specifying an API for accessing one or more functions of an application or web-based service that provides no user interface for direct user access to the one or more functions.

13. The system of claim 9, wherein the degrees of match includes degrees of semantic match and degrees of phonetic match between the text string derived from the user request and the respective plurality of words associated with each predefined domain.

14. The system of claim 9, wherein identifying the relevant domain from the plurality of predefined domains further comprises:

generating two or more semantic parses from the text string, each semantic parse associating the text string with two or more concepts of a respective one of the plurality of predefined domains;

from among the two or more semantic parses, selecting a candidate semantic parse that associates the text string with two or more concepts of a first predefined domain, wherein the selecting is based at least on a strength of connections existing between the two or more concepts in the first predefined domain; and

identifying the relevant domain based on the candidate semantic parse.

15. The system of claim 9, wherein at least one of the plurality of predefined domains is associated with a dialog flow, the dialog flow specifying steps for the intelligent automated assistant to request information regarding one or more task parameters for a respective task associated with the at least one predefined domain.

16. The system of claim 9, wherein the user request further includes context information associated with the speech input received from the user, and one or more of the task pa-rameters are derived based on the context information.

17. A non-transitory computer readable storage medium having instructions stored thereon, the instructions, when executed by one or more processors, cause the processors to perform operations comprising:

storing a plurality of predefined domains each representing a respective area of service offered by an intelligent automated assistant, wherein each of the predefined do-mains comprises a respective plurality of concepts and one or more relations relating the respective plurality of concepts, wherein each predefined domain is associated with at least one task flow specifying steps for performing a respective task in the predefined domain, and wherein each of the predefined domains is associated with a respective plurality of words relevant to the predefined domain;

obtaining a text string derived from a user request, the text string including at least one or more words derived from a speech input received from a user;

from the plurality of predefined domains, identifying a relevant domain for the user request based at least on respective degrees of match between the text string de-rived from the user request and the respective plurality of words associated with each prede-fined domain; and

executing a task in accordance with steps specified in a task flow associated with the relevant domain, and in accordance with one or more task parameters derived from the user request.

18. The computer readable storage medium of claim 17, wherein the respective plurality of words associated with each predefined domain comprises at least two respective words that each represent a concept related to the predefined domain or an entity related to the predefined domain.

19. The computer readable storage medium of claim 17, wherein at least one of the plu-rality of predefined domains is associated with a respective service model specifying an API for accessing one or more functions of an application or web-based service on behalf of the user, the application or web-based service operable to provide the one or more functions directly to the user through a user interface of the application or web-based service.

20. The computer readable storage medium of claim 17, wherein at least one of the plu-rality of predefined domains is associated with a respective service model specifying an API for accessing one or more functions of an application or web-based service that provides no user interface for direct user access to the one or more functions.

21. The computer readable storage medium of claim 17, wherein the degrees of match includes degrees of semantic match and degrees of phonetic match between the text string derived from the user request and the respective plurality of words associated with each predefined domain.

22. The computer readable storage medium of claim 17, wherein identifying the relevant domain from the plurality of predefined domains further comprises:

generating two or more semantic parses from the text string, each semantic parse associating the text string with two or more concepts of a respective one of the plurality of predefined domains;

from among the two or more semantic parses, selecting a candidate semantic parse that associates the text string with two or more concepts of a first predefined domain, wherein the selecting is based at least on a strength of connections existing between the two or more concepts in the first predefined domain; and

identifying the relevant domain based on the candidate semantic parse.

23. The computer readable storage medium of claim 17, wherein at least one of the plu-rality of predefined domains is associated with a dialog flow, the dialog flow specifying steps for the intelligent automated assistant to request information regarding one or more task parameters for a respective task associated with the at least one predefined domain.

24. The computer readable storage medium of claim 17, wherein the user request further includes context information associated with the speech input received from the user, and one or more of the task parameters are derived based on the context information.