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 occurring at one or more computing devices 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 a current context of the user;
analyzing search queries submitted by others to identify spikes, trends, or other patterns in the search queries that are submitted by others in contexts similar to the current context of the user;
based on the spikes, trends, or other patterns, selecting one or more of the search queries submitted by others;
searching one or more online sources for information responsive to the selected one or more search queries;
generating, by one or more of the processors, unsolicited content indicative of the information responsive to the selected one or more search queries; 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 a desirability measure that is indicative of the user's desire to receive unsolicited content, wherein the desirability measure is determined based at least in part on the current context of the user, 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 current context of the user is determined based on one or more signals generated by one or more sensors integral with one or more of the computing devices.
5. The method of claim 4 , wherein the current context of the user comprises position coordinates generated by a position coordinate sensor of one or more of the computing devices operated by the user.
6. The method of claim 4 , wherein the current context of the user comprises sensor data generated by an accelerometer of one or more of the computing devices operated by the user.
7. The method of claim 1 , wherein the current context of the user comprises a location of the user.
8. The method of claim 7 , wherein the location of the user is determined based on a schedule or calendar of the user.
9. The method of claim 7 , wherein the selected one or more search queries seek information about the location of the user.
10. A system comprising one or more processors and memory storing instructions that, in response to execution 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 occurring at one or more computing devices 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;
determine a current context of the user;
analyze search queries submitted by others to identify spikes, trends, or other patterns in the search queries that are submitted by others in contexts similar to the current context of the user;
based on the spikes, trends, or other patterns, select one or more of the search queries submitted by others;
search one or more online sources for information responsive to the selected one or more search queries;
generate, by one or more of the processors, unsolicited content indicative of the information responsive to the selected one or more search queries; and
incorporate, by the automated assistant into the existing human-to-computer dialog session, the unsolicited content;
wherein at least the incorporation is performed in response to the determination that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.
11. The system of claim 10 , wherein the unsolicited content comprises unsolicited natural language content.
12. The system of claim 10 , further comprising instructions to determine a desirability measure that is indicative of the user's desire to receive unsolicited content, wherein the desirability measure is determined based at least in part on the current context of the user, and wherein at least the incorporating is performed in response to a determination that the desirability measure satisfies one or more thresholds.
13. The system of claim 10 , wherein the current context of the user is determined based on one or more signals generated by one or more sensors integral with one or more of the computing devices.
14. The system of claim 13 , wherein the current context of the user comprises position coordinates generated by a position coordinate sensor of one or more of the computing devices operated by the user.
15. The system of claim 13 , wherein the current context of the user comprises sensor data generated by an accelerometer of one or more of the computing devices operated by the user.
16. The system of claim 10 , wherein the current context of the user comprises a location of the user.
17. The system of claim 16 , wherein the location of the user is determined based on a schedule or calendar of the user.
18. The system of claim 16 , wherein the selected one or more search queries seek information about the location of the user.
19. At least one non-transitory computer-readable medium comprising instructions that, in response to execution by 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 occurring at one or more computing devices 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;
determine a current context of the user;
analyze search queries submitted by others to identify spikes, trends, or other patterns in the search queries that are submitted by others in contexts similar to the current context of the user;
based on the spikes, trends, or other patterns, select one or more of the search queries submitted by others;
search one or more online sources for information responsive to the selected one or more search queries;
generate, by one or more of the processors, unsolicited content indicative of the information responsive to the selected one or more search queries; and
incorporate, by the automated assistant into the existing human-to-computer dialog session, the unsolicited content;
wherein at least the incorporation is performed in response to the determination that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.
20. The at least one non-transitory computer-readable medium of claim 19 , wherein the unsolicited content comprises unsolicited natural language content.