Proactive incorporation of unsolicited content into human-to-computer dialogs
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.
1. A method implemented using one or more processors, comprising:
determining that in an existing human-to-computer dialog session between a user and an automated assistant, the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session;
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 indicative of a current context of the user;
identifying, based on one or more characteristics of the user, information of potential interest to the user or one or more actions of potential interest to the user;
generating unsolicited content indicative of the information of potential interest to the user or the one or more actions of potential interest; and
incorporating, into the existing human-to-computer dialog session, the unsolicited content;
wherein at least the incorporating is performed in response to a determination that the desirability measure satisfies one or more thresholds.
2. The method of claim 1 , wherein the unsolicited content comprises unsolicited natural language content.
3. The method of claim 1 , wherein the one or more signals include an indication of a state of an application executing on another computing device.
4. The method of claim 3 , wherein the indication of the state of the application includes an indication that the application is providing media playback.
5. The method of claim 1 , wherein the one or more signals include an action the user requested the automated assistant to trigger during the human-to-computer dialog session.
6. The method of claim 1 , wherein the one or more signals include mention of an emergency in the human-to-computer dialog session.
7. The method of claim 1 , wherein the one or more signals indicate the user is driving.
8. The method of claim 1 , wherein the one or more signals include an accelerometer signal.
9. The method of claim 1 , wherein the one or more signals include one or more topics detected in the human-to-computer dialog session.
10. The method of claim 9 , wherein the one or more topics include traffic or directions.
11. 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:
determine that in an existing human-to-computer dialog session between a user and an automated assistant, the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session;
determine 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 indicative of a current context of the user;
identify, based on one or more characteristics of the user, information of potential interest to the user or one or more actions of potential interest to the user;
generate unsolicited content indicative of the information of potential interest to the user or the one or more actions of potential interest; and
incorporate, into the existing human-to-computer dialog session, the unsolicited content;
wherein at least the incorporation is performed in response to a determination that the desirability measure satisfies one or more thresholds.
12. The system of claim 11 , wherein the unsolicited content comprises unsolicited natural language content.
13. The system of claim 11 , wherein the one or more signals include an indication of a state of an application executing on another computing device.
14. The system of claim 13 , wherein the indication of the state of the application includes an indication that the application is providing media playback.
15. The system of claim 11 , wherein the one or more signals include an action the user requested the automated assistant to trigger during the human-to-computer dialog session.
16. The system of claim 11 , wherein the one or more signals include mention of an emergency in the human-to-computer dialog session.
17. The system of claim 11 , wherein the one or more signals indicate the user is driving.
18. The system of claim 11 , wherein the one or more signals include an accelerometer signal.
19. The method of claim 11 , wherein the one or more signals include one or more topics detected in the human-to-computer dialog session.
20. 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, the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session;
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 indicative of a current context of the user;
identifying, based on one or more characteristics of the user, information of potential interest to the user or one or more actions of potential interest to the user;
generating unsolicited content indicative of the information of potential interest to the user or the one or more actions of potential interest; and
incorporating, into the existing human-to-computer dialog session, the unsolicited content;
wherein at least the incorporating is performed in response to a determination that the desirability measure satisfies one or more thresholds.