PROVIDING PROMPT IN AN AUTOMATED DIALOG SESSION BASED ON SELECTED CONTENT OF PRIOR AUTOMATED DIALOG SESSION

• US 20180144743A1
• Filed: 11/21/2016
• Published: 05/24/2018
• Est. Priority Date: 11/21/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Aggarwal, Vikram, Lim, Yew Jin, Goldstein, Adam
• Granted Patent: US 10,446,144 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

Methods, apparatus, and computer readable media related to soliciting feedback from a user regarding one or more content parameters of a suggestion or other content provided by the automated assistant. The user'"'"'s feedback may be used to influence future suggestions and/or other content subsequently provided, by the automated assistant in future dialog sessions, to the user and/or to other users. In some implementations, content is provided to a user by an automated assistant in a dialog session between the user and the automated assistant—and the automated assistant provides a prompt that solicits user feedback related to the provided content in a future dialog session between the user and the automated assistant. In some of those implementations, the prompt is provided following input from the user and/or output from the automated assistant, in the future dialog session, that is unrelated to the content provided in the previous dialog session.

Claims

1. A method implemented by one or more processors, comprising:

as part of a dialog session between a user and an automated assistant implemented by one or more of the processors;

receiving natural language input that is based on user interface input provided by the user via a user interface input device, and

providing, as a reply by the automated assistant to the natural language input, content that is responsive to the natural language input,

wherein the content is provided for presentation to the user via a user interface output device, and

wherein the content includes at least one content parameter selected by the automated assistant from a plurality of candidate content parameters;

as part of an additional dialog session between the user and the automated assistant that is temporally separated from the dialog session;

providing a prompt that solicits feedback on the selected content parameter,

wherein the prompt is provided for presentation to the user via the user interface output device or an additional user interface output device, and

wherein the prompt is generated to solicit feedback on the content parameter based on the content parameter being previously selected by the automated assistant and previously provided for presentation to the user as part of the dialog session, and

receiving additional input that is responsive to the prompt, the additional input being based on additional user interface input provided by the user via the user interface input device or an additional user interface input device; and

using the additional input to influence a value stored in association with the content parameter, wherein the value influences future providing of further content that includes the content parameter.

2. The method of claim 1, wherein the user initiates the additional dialog session with additional natural language input that is unrelated to the content of the previous dialog session.

3. The method of claim 2, further comprising, as part of the additional dialog session:

providing additional dialog session output that is responsive to the additional natural language input and that is also unrelated to the content of the previous dialog session;

wherein providing the prompt occurs following providing the additional dialog session output.

4. The method of claim 3, further comprising:

determining that one or more criteria are satisfied by at least one of;

the additional natural language input, and the additional dialog session output;

wherein providing the prompt is further based on determining that the criteria are satisfied.

5. The method of claim 4, wherein the criteria comprises at least one of:

the additional dialog session output being of a certain semantic type; and

an occurrence in the user prompt of at least one n-gram of a set of criteria n-grams.

6. The method of claim 1, wherein the content is a suggestion to be acted upon by the user in the future and further comprising:

determining that the user acted upon the suggestion after providing the content that includes the content parameter;

wherein providing the prompt is further based on determining that the user acted upon the suggestion.

7. The method of claim 1, wherein the user interface input device or the additional user interface input device used to generate the additional input that is responsive to the prompt includes a microphone, and further comprising:

based on providing the prompt, preemptively activating at least one component configured to process the user interface input provided via the microphone.

8. The method of claim 1, wherein the user initiates the additional dialog session and wherein providing the prompt is contingent on the user having initiated the additional dialog session.

9. The method of claim 1, further comprising, as part of the additional dialog session:

prior to providing the prompt, providing additional dialog session output;

wherein providing the prompt occurs following providing the additional dialog session output.

10. The method of claim 1, further comprising:

identifying an additional content parameter provided to the user as part of an additional prior dialog session between the user and the automated assistant; and

determining, based on one or more criteria, to provide the prompt based on the content parameter instead of an alternative prompt that is based on the additional content parameter.

11. The method of claim 10, wherein the one or more criteria comprise corresponding temporal proximities of the providing of the content parameter and of the providing of the additional content parameter.

12. The method of claim 10, wherein the one or more criteria comprise semantic types assigned to the content parameter and the additional content parameter.

13. The method of claim 1, wherein the content includes a suggestion for a particular physical location and for a particular item consumable at the particular location, and wherein the content parameter identifies the particular item.

14. The method of claim 1, wherein the content includes a suggestion for a particular physical location, and wherein the content parameter identifies a category to which the particular physical location belongs.

15. The method of claim 1, wherein the input and the additional input are both generated via the user interface input device and wherein the content and the feedback prompt are both provided for presentation via the user interface output device.

16. The method of claim 15, wherein the user interface input device includes a microphone of a single device and the user interface output device includes a speaker of the single device.

17. The method of claim 1, wherein:

the input is generated via the user interface input device of a first computing device,

the content is provided for presentation via the user interface output device of the first computing device, and

the prompt is provided for presentation via the additional user interface output device of an additional computing device.

18. A method implemented by one or more processors, comprising:

identifying, from a computer readable medium, a stored content parameter of content previously provided to a user as part of a prior dialog session between a user and an automated assistant implemented by one or more of the processors;

as part of an additional dialog session between the user and the automated assistant that is temporally separated from the dialog session;

providing a prompt that solicits feedback on the content parameter,

wherein the prompt is provided for presentation to the user via a user interface output device of a computing device of the user, and

wherein the prompt is generated to solicit feedback on the content parameter based on the content parameter being previously provided for presentation to the user as part of the prior dialog session, and

receiving additional input that is responsive to the prompt, the additional input being based on additional user interface input provided by the user via a user interface input device of the computing device; and

using the additional input to influence a value stored in association with the content parameter, wherein the value influences future providing of further content that includes the content parameter.

19. A client device, comprising:

at least one microphone;

at least one speaker;

a network interface;

one or more processors configured to;

as part of an additional dialog session between a user and an automated assistant that is temporally separated from a prior dialog session between the user and the automated assistant;

provide, via the speaker, a prompt that solicits feedback on a content parameter of content previously provided for presentation to the user as part of the prior dialog session,

wherein the prompt solicits feedback on the content parameter based on the content parameter being previously provided for presentation to the user as part of the prior dialog session; and

based on providing the prompt, preemptively activate at least one component configured to process user interface input provided via the microphone.

20. The client device of claim 19, wherein the one or more processors are further configured to:

receive, via the microphone, the user interface input that is responsive to the prompt; and

provide, over the network interface, data based on the additional input, the data provided to influence a value that is stored in association with the content parameter and that influences future providing of further content that includes the content parameter.