Proactive provision of new content to group chat participants
Techniques are described herein for automated assistants that proactively provide content to participant(s) of multi-participant message exchange threads (e.g., group chats, audio and/or video calls in which oral messages are transcribed for analysis, etc.) based on signals such as individual participant profiles associated with participant(s). In various implementations, automated assistant(s) that may not be explicitly invoked may analyze content of a message exchange thread involving multiple human participants and/or document(s) associated with the message exchange thread. Based on the analyzing, the automated assistant(s) may identify topic(s) pertinent to the message exchange thread. Based on individual participant profiles associated with the participants, the automated assistant(s) may identify shared interest(s) of the participants. The automated assistant(s) may then select new content based both on the pertinent topic(s) and the shared interest(s) of the participants and proactively provide the new content to one or more of the participants.
1. A method that is implemented on one or more processors, the method comprising:
analyzing, by one or more automated assistants, one or both of content of a single message exchange thread involving multiple human participants and one or more documents associated with the message exchange thread, wherein the automated assistant is not explicitly invoked by any of the participants;
identifying, by one or more of the automated assistants, based on the analyzing, one or more topics pertinent to the single message exchange thread;
identifying, by one or more of the automated assistants, based on individual participant profiles associated with the participants, one or more shared interests of the participants, wherein each participant of the multiple participants is associated with an individual participant profile that includes information related to the participant;
during a first time interval immediately following initiation of the single message exchange thread:
searching, by one or more of the automated assistants, one or more data sources using one or more of the shared interests of the participants to identify first factual content, and
proactively incorporating into the message exchange thread, by one or more of the automated assistants as a participant in the message exchange thread, the first factual contend;
during a second time interval that occurs after the first time interval, when a greater number of topics pertinent to the single message exchange thread have been identified than during the first time interval:
searching, by one or more of the automated assistants, one or more of the data sources using one or more of the pertinent topics to identify a plurality of content candidates, and
selecting as second factual content, by one or more of the automated assistants based on one or more of the shared interests of the participants, one or more of the plurality of content candidates, and
proactively incorporating into the message exchange thread, by one or more of the automated assistants as a participant in the message exchange thread, the second factual content.
2. The method of claim 1 , wherein the one or more shared interests of the participants are identified based on search history associated with one or more of the individual participant profiles.
3. The method of claim 1 , wherein the one or more shared interests of the participants are identified based on location history associated with one or more of the individual participant profiles.
4. The method of claim 1 , wherein the one or more documents associated with the message exchange thread include a meeting agenda or a calendar entry.
5. The method of claim 1 , wherein selecting the second factual content is further based on prior feedback received from one or more of the participants in response to content that was proactively provided previously.
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 implement an automated assistant to:
perform speech-to-text (“STT”) processing on spoken utterances exchanged between multiple human participants during a conversation, wherein the conversation occurs proximate to a computing device on which the automated assistant is at least partially implemented;
analyze output of the STT processing, wherein the automated assistant is not explicitly invoked by any of the human participants;
identify, based on the analyzing, one or more topics pertinent to the conversation;
identify, based on individual participant profiles associated with the human participants, one or more shared interests of the human participants, wherein each participant of the multiple human participants is associated with an individual participant profile that includes information related to the human participant;
during a first time interval immediately following initiation of the conversation:
search for and retrieve first textual content that is based on one or more of the shared interests of the participants;
perform text-to-speech processing on the first textual content to generate first spoken output; and
proactively inject the first spoken output into the conversation;
during a second time interval that occurs after the first time interval, when a greater number of topics pertinent to the conversation have been identified than during the first time interval:
search for and retrieve a plurality of content candidates using one or more of the pertinent topics,
select as second textual content, based on one or more of the shared interests of the participants, one or more of the plurality of content candidates,
perform text-to-speech processing on the second textual content to generate second spoken output; and
proactively inject into the conversation, by the automated assistant as a participant in the conversation, the second spoken output.
7. The system of claim 6 , wherein the one or more shared interests of the participants are identified based on search history associated with one or more of the individual participant profiles.
8. The system of claim 6 , wherein the one or more shared interests of the participants are identified based on location history associated with one or more of the individual participant profiles.
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:
analyzing, by one or more automated assistants, one or both of content of a single message exchange thread involving multiple human participants and one or more documents associated with the message exchange thread, wherein the automated assistant is not explicitly invoked by any of the participants;
identifying, by one or more of the automated assistants, based on the analyzing, one or more topics pertinent to the single message exchange thread;
identifying, by one or more of the automated assistants, based on individual participant profiles associated with the participants, one or more shared interests of the participants, wherein each participant of the multiple participants is associated with an individual participant profile that includes information related to the participant;
during a first time interval immediately following initiation of the single message exchange thread:
searching, by one or more of the automated assistants, one or more data sources using one or more of the shared interests of the participants to identify first factual content, and
proactively incorporating into the message exchange thread, by one or more of the automated assistants as a participant in the message exchange thread, the first factual content;
during a second time interval that occurs after the first time interval, when a greater number of topics pertinent to the single message exchange thread have been identified than during the first time interval:
searching, by one or more of the automated assistants, one or more of the data sources using one or more of the pertinent topics to identify a plurality of content candidates, and
selecting as second factual content, by one or more of the automated assistants based on one or more of the shared interests of the participants, one or more of the plurality of content candidates, and
proactively incorporating into the message exchange thread, by one or more of the automated assistants as a participant in the message exchange thread, the second factual content.
10. The at least one non-transitory computer-readable medium of claim 9 , wherein the one or more shared interests of the participants are identified based on search history associated with one or more of the individual participant profiles.
11. The at least one non-transitory computer-readable medium of claim 9 , wherein the one or more shared interests of the participants are identified based on location history associated with one or more of the individual participant profiles.
12. The at least one non-transitory computer-readable medium of claim 9 , wherein the one or more documents associated with the message exchange thread include a meeting agenda or a calendar entry.
13. The at least one non-transitory computer-readable medium of claim 9 , wherein selecting the second factual content is further based on prior feedback received from one or more of the participants in response to content that was proactively provided previously.