Proactive incorporation of unsolicited content into human-to-computer dialogs

Patent metadata

Field	Value
Publication number	US-11114100-B2
Application number	US-201916549403-A
Country	US
Kind code	B2
Filing date	Aug 23, 2019
Priority date	May 3, 2017
Publication date	Sep 7, 2021
Grant date	Sep 7, 2021

Abstract

Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

First claim

What is claimed is:

1. A method implemented by one or more processors, comprising:
identifying, based on a request input by a user as part of a dialog session involving the user and an automated assistant executed by one or more of the processors, one or more resources that satisfy multiple criteria contained in the user's request;
generating solicited natural language content, wherein the solicited natural language content conveys the one or more resources that satisfy the multiple criteria to the user;
incorporating, by the automated assistant into the dialog session involving the user and the automated assistant, the solicited natural language content;
receiving additional input from the user selecting one or more of the resources that satisfy the multiple criteria;
proactively identifying at least one additional resource that satisfies a first criterion of the multiple criteria but fails to satisfy a second criterion of the multiple criteria;
generating unsolicited natural language content, wherein the unsolicited natural language content suggests the at least one additional resource to the user as an alternative to the selected one or more resources that would require less expenditure by the user; and
causing the unsolicited natural language content to be automatically output to the user without the user specifically requesting the unsolicited natural language content, wherein the unsolicited natural language output is automatically output to the user:
after determining that the automated assistant has fulfilled any outstanding obligations of the automated assistant to the user in the same dialog session; or
in a subsequent dialog session involving the user and the automated assistant.

2. The method of claim 1 , wherein the one or more resources and the at least one additional resource comprise digital audio files.

3. The method of claim 1 , wherein the one or more resources and the at least one additional resource comprise digital video files.

4. The method of claim 1 , wherein the one or more resources and the at least one additional resource comprise passes.

5. The method of claim 1 , wherein the second criterion comprises a time, and the at least one additional resource is associated with an earlier or later time.

6. The method of claim 1 , wherein the second criterion comprises a time interval, and the at least one additional resource is associated with a different time interval that starts before, or ends after, the time interval.

7. The method of claim 1 , wherein the second criterion comprises a date, and the at least one additional resource is associated with an earlier or later date.

8. The method of claim 1 , wherein the request is directed by the user to the automated assistant.

9. The method of claim 1 , wherein the request is directed by the user to another participant of the dialog session.

10. A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to:
identify, based on a request input by a user as part of a dialog session involving the user and an automated assistant executed by one or more of the processors, one or more resources that satisfy multiple criteria contained in the user's request;
generate solicited natural language content, wherein the solicited natural language content wherein the solicited content includes one or more selectable elements corresponding to the one or more resources that satisfy the multiple criteria;
incorporate, by the automated assistant into the dialog session involving the user and the automated assistant, the solicited natural language content
proactively identify at least one additional resource that satisfies a first criterion of the multiple criteria but fails to satisfy a second criterion of the multiple criteria;
generate unsolicited natural language content, wherein the unsolicited natural language content suggests the at least one additional resource to the user as an alternative to the one or more resources that would require less expenditure by the user; and
cause the unsolicited natural language content to be automatically output to the user without the user specifically requesting the unsolicited natural language content, wherein the unsolicited natural language output is automatically output to the user:
after determining that the automated assistant has fulfilled any outstanding obligations of the automated assistant to the user; or
in a subsequent dialog session involving the user and the automated assistant.

11. The system of claim 10 , wherein the one or more resources and the at least one additional resource comprise digital audio files.

12. The system of claim 10 , wherein the one or more resources and the at least one additional resource comprise digital video files.

13. The system of claim 10 , wherein the one or more resources and the at least one additional resource comprise passes.

14. The system of claim 10 , wherein the second criterion comprises a time, and the at least one additional resource is associated with an earlier or later time.

15. The system of claim 10 , wherein the second criterion comprises a time interval, and the at least one additional resource is associated with a different time interval that starts before, or ends after, the time interval.

16. The system of claim 10 , wherein the second criterion comprises a date, and the at least one additional resource is associated with an earlier or later date.

17. The system of claim 10 , wherein the request is directed by the user to the automated assistant.

18. A method implemented by one or more processors, comprising:
identifying, based on a request input by a user as part of a dialog session involving the user and an automated assistant executed by one or more of the processors, one or more resources that satisfy multiple criteria contained in the user's request;
generating solicited content, wherein the solicited content includes one or more selectable elements corresponding to the one or more resources that satisfy the multiple criteria;
incorporating, by the automated assistant into the dialog session involving the user and the automated assistant, the solicited content;
proactively identifying at least one additional resource that satisfies a first criterion of the multiple criteria but fails to satisfy a second criterion of the multiple criteria;
generating unsolicited natural language content, wherein the unsolicited natural language content suggests the at least one additional resource to the user as an alternative to the one or more resources that would require less expenditure by the user; and
causing the unsolicited natural language content to be automatically output to the user without the user specifically requesting the unsolicited natural language content, wherein the unsolicited natural language output is automatically output to the user:
after determining that the automated assistant has fulfilled any outstanding obligations of the automated assistant to the user in the same dialog session; or
in a subsequent dialog session involving the user and the automated assistant.

19. The method of claim 18 , wherein the one or more resources and the at least one additional resource comprise passes.

20. The method of claim 18 , wherein the second criterion comprises a time, and the at least one additional resource is associated with an earner or later time.

Assignees

• Google Llc

Inventors

• Vuskovic Vladimir
• Wenger Stephan
• Ait Bahajji Zineb
• Baeuml Martin
• Dovlecel Alexandru
• Skobeltsyn Gleb

Classifications

• G06F40/56

  Natural language generation · CPC title

• G06F40/35 Primary

  Discourse or dialogue representation · CPC title

• G06F40/295 Primary

  Named entity recognition · CPC title

• G06F16/3344

  using natural language analysis · CPC title

• G06F16/3343

  using phonetics · CPC title