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

• US 10,636,418 B2
• Filed: 03/22/2017
• Issued: 04/28/2020
• Est. Priority Date: 03/22/2017
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Badr, Ibrahim, Sabur, Zaheed, Vuskovic, Vladimir, Zumbrunnen, Adrian, Mirelmann, Lucas
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US15/466,422
• Publication Number:
  US 20180277108A1
• Time in Patent Office: 1,133 Days
• CPC Class Codes: G06F 16/90335 Query processing
• 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: 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

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, in an existing human-to-computer dialog session between a user and an automated assistant, it may be determined that the automated assistant has responded to all natural language input received from the user. Based on characteristic(s) of the user, information of potential interest to the user or action(s) of potential interest to the user may be identified. Unsolicited content indicative of the information of potential interest to the user or the action(s) may be generated and incorporated by the automated assistant into the existing human-to-computer dialog session. In various implementations, the incorporating may be performed in response to the determining that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.

Claims

1. A method, comprising:

determining, by one or more processors, that in an existing human-to-computer dialog session between a user and an automated assistant occurring at a given computing device operated by the user, the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session;

determining, by one or more of the processors, that the user previously operated another computing device or the given computing device to submit a search query to a search engine, wherein the search query related to procurement of one or more items and the automated assistant lacks information about whether the one or more items were procured by the user;

searching, by one or more of the processors, one or more online sources for information responsive to the search query;

generating, by one or more of the processors, unsolicited content indicative of the information responsive to the search query; and

incorporating, by the automated assistant into the existing human-to-computer dialog session, the unsolicited content;

wherein at least the incorporating is performed in response to the determining that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.

2. The method of claim 1, wherein the unsolicited content comprises unsolicited natural language content.

3. The method of claim 1, further comprising determining, by one or more of the processors, a desirability measure that is indicative of the user'"'"'s desire to receive unsolicited content, wherein the desirability measure is determined based on one or more signals, and wherein at least the incorporating is performed in response to a determination that the desirability measure satisfies one or more thresholds.

4. The method of claim 1, wherein the unsolicited content comprises one or more user interface elements, each user interface element being selectable, by the user, to cause the automated assistant to trigger one or more actions of potential interest to the user that relate to the entity.

5. The method of claim 1, wherein the one or more items include one or more tickets.

6. A system comprising one or more processors and memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:

determining that in an existing human-to-computer dialog session between a user and an automated assistant occurring at a given computing device operated by the user, the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session;

detecting, based on a schedule of the user or one or more sensor signals generated by one or more computing devices operated by the user, that the user has arrived at a location;

generating unsolicited content comprising a user interface element that is selectable by the user to facilitate procurement of a service associated with the location; and

incorporating, by the automated assistant into the existing human-to-computer dialog session, the unsolicited content;

wherein at least the incorporating is performed in response to the determining that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.

7. The system of claim 6, wherein the unsolicited content comprises unsolicited natural language content.

8. The system of claim 6, further comprising instructions for determining a desirability measure that is indicative of the user'"'"'s desire to receive unsolicited content, wherein the desirability measure is determined based on one or more signals, and wherein at least the incorporating is performed in response to a determination that the desirability measure satisfies one or more thresholds.

9. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:

determining that in an existing human-to-computer dialog session between a user and an automated assistant occurring at a given computing device operated by the user, the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session;

determining that the user previously operated another computing device or the given computing device to submit a search query to a search engine, wherein the search query related to procurement of one or more items and the automated assistant lacks information about whether the one or more items were procured by the user;

searching one or more online sources for information responsive to the search query;

generating unsolicited content indicative of the information responsive to the search query; and

incorporating, by the automated assistant into the existing human-to-computer dialog session, the unsolicited content;

wherein at least the incorporating is performed in response to the determining that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.

10. The at least one non-transitory computer-readable medium of claim 9, wherein the unsolicited content comprises unsolicited natural language content.

11. The at least one non-transitory computer-readable medium of claim 9, further comprising instructions for determining a desirability measure that is indicative of the user'"'"'s desire to receive unsolicited content, wherein the desirability measure is determined based on one or more signals, and wherein at least the incorporating is performed in response to a determination that the desirability measure satisfies one or more thresholds.

12. The at least one non-transitory computer-readable medium of claim 9, wherein the unsolicited content comprises one or more user interface elements, each user interface element being selectable, by the user, to cause the automated assistant to trigger one or more actions of potential interest to the user that.

13. The at least one non-transitory computer-readable medium of claim 9, wherein the one or more items include one or more tickets.