Maintaining context information between user interactions with a voice assistant

• US 8,731,942 B2
• Filed: 03/04/2013
• Issued: 05/20/2014
• Est. Priority Date: 01/18/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Cheyer, Adam John, Guzzoni, Didier Rene, Gruber, Thomas Robert, Brigham, Christopher Dean, Kittlaus, Dag
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US13/784,707
• Publication Number:
  US 20130185081A1
• Time in Patent Office: 442 Days
• Field of Search: 704270-275
• 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 first task is performed using a first parameter. A text string is obtained from a speech input received from a user. Based at least partially on the text string, a second task different from the first task or a second parameter different from the first parameter is identified. The first task is performed using the second parameter or the second task is performed using the first parameter.

Claims

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

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

performing a first task using a first parameter;

providing a first response to a user based on a result of performing the first task using the first parameter;

in a first operation;

obtaining a first text string from a first speech input received from the user;

determining whether the first text string includes a second task different from the first task, where the first text string does not include a recitation of the first parameter; and

in accordance with a determination that the first text string includes the second task different from the first task and does not include a recitation of the first parameter;

performing the second task using the first parameter; and

providing a second response to the user based on a result of performing the second task using the first parameter; and

in a second operation;

obtaining a second text string from a second speech input received from the user;

determining whether the second text string includes a second parameter different from the first parameter, where the second text string does not include a recitation of the first task;

in accordance with a determination that the second text string includes the second parameter different from the first parameter and does not include a recitation of the first task;

performing the first task using the second parameter; and

providing a third response to the user based on a result of performing the first task using the second parameter.

2. The method of claim 1, further comprising, prior to performing the first task using the first parameter:

obtaining an initial text string from an initial speech input from the user;

identifying, based at least in part on the initial text string, the first task and the first parameter.

3. The method of claim 2, further comprising, interpreting the initial text string to derive a first representation of user intent, wherein the identification of the first task and the first parameter is based at least in part on the first representation of user intent.

4. The method of claim 3, further comprising:

prior to obtaining the initial text string, producing an output for presentation to the user based on the performing of the first task using the first parameter.

5. The method of claim 1, wherein:

the first task is a telephone call;

the first parameter is a participant of the telephone call;

the second task is sending a text message; and

the performing the second task using the first parameter comprises sending the text message to the participant of the telephone call.

6. The method of claim 1, wherein:

the first task is a weather forecast task;

the first parameter is a first location associated with the weather forecast;

the second parameter is a second location; and

the performing the first task using the second parameter comprises presenting a second weather forecast associated with the second location to the user.

7. The method of claim 1, wherein the first parameter is a first geographic location, and wherein the second parameter is a second geographic location.

8. The method of claim 1, wherein the first parameter is a first time, and wherein the second parameter is a second time.

9. The method of claim 1, wherein the first task is a weather forecast task.

10. The method of claim 1, wherein the first task is an event planning task.

11. The method of claim 1, wherein the first task is a restaurant reservation task.

12. The method of claim 1, wherein the first task is a constrained selection task.

13. A system for operating an intelligent automated assistant, comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the processors to perform operations comprising;

performing a first task using a first parameter;

providing a first response to a user based on a result of performing the first task using the first parameter;

in a first operation;

obtaining a first text string from a first speech input received from the user;

determining whether the first text string includes a second task different from the first task, where the first text string does not include a recitation of the first parameter; and

in accordance with a determination that the first text string includes the second task different from the first task and does not include a recitation of the first parameter;

performing the second task using the first parameter; and

providing a second response to the user based on a result of performing the second task using the first parameter; and

in a second operation;

obtaining a second text string from a second speech input received from the user;

determining whether the second text string includes a second parameter different from the first parameter, where the second text string does not include a recitation of the first task;

in accordance with a determination that the second text string includes the second parameter different from the first parameter and does not include a recitation of the first task;

performing the first task using the second parameter; and

providing a third response to the user based on a result of performing the first task using the second parameter.

14. The system of claim 13, the operations further comprising, prior to performing the first task using the first parameter:

obtaining an initial text string from an initial speech input from the user;

identifying, based at least in part on the initial text string, the first task and the first parameter.

15. The system of claim 14, the operations further comprising, interpreting the initial text string to derive a first representation of user intent, wherein the identification of the first task and the first parameter is based at least in part on the first representation of user intent.

16. The system of claim 15, the operations further comprising:

prior to obtaining the initial text string, producing an output for presentation to the user based on the performing of the first task using the first parameter.

17. The system of claim 13, wherein:

the first task is a telephone call;

the first parameter is a participant of the telephone call;

the second task is sending a text message; and

the performing the second task using the first parameter comprises sending the text message to the participant of the telephone call.

18. The system of claim 13, wherein:

the first task is a weather forecast task;

the first parameter is a first location associated with the weather forecast;

the second parameter is a second location; and

the performing the first task using the second parameter comprises presenting a second weather forecast associated with the second location to the user.

19. The system of claim 13, wherein the first parameter is a first geographic location, and wherein the second parameter is a second geographic location.

20. The system of claim 13, wherein the first parameter is a first time, and wherein the second parameter is a second time.

21. The system of claim 13, wherein the first task is a weather forecast task.

22. The system of claim 13, wherein the first task is an event planning task.

23. The system of claim 13, wherein the first task is a restaurant reservation task.

24. The system of claim 13, wherein the first task is a constrained selection task.

25. A non-transitory computer readable storage medium storing instructions that, when executed by an electronic device with one or more processors, cause the processors to perform operations comprising:

performing a first task using a first parameter;

providing a first response to a user based on a result of performing the first task using the first parameter;

in a first operation;

obtaining a first text string from a first speech input received from the user;

determining whether the first text string includes a second task different from the first task, where the first text string does not include a recitation of the first parameter; and

in accordance with a determination that the first text string includes the second task different from the first task and does not include a recitation of the first parameter;

performing the second task using the first parameter; and

providing a second response to the user based on a result of performing the second task using the first parameter; and

in a second operation;

obtaining a second text string from a second speech input received from the user;

determining whether the second text string includes a second parameter different from the first parameter, where the second text string does not include a recitation of the first task;

in accordance with a determination that the second text string includes the second parameter different from the first parameter and does not include a recitation of the first task;

performing the first task using the second parameter; and

providing a third response to the user based on a result of performing the first task using the second parameter.