Proactive In-Call Content Recommendations for Assistant Systems

Abstract

In one embodiment, a method includes establishing a video call between a plurality of client systems, sending, to a first client system of the plurality of client systems while maintaining the video call between the plurality of client systems, instructions for presenting a first content recommendation comprising one or more selected content items, wherein the first content recommendation comprises a prompt to share the selected content items with one or more second client systems of the plurality of client systems, receiving, from the first client system responsive to the prompt, a request to share the selected content items, and sending, to the one or more second client systems responsive to receiving the request and while maintaining the video call between the plurality of client systems, instructions for presenting the selected content items within the video call.

What is claimed is: 
     
         1 . A method comprising, by one or more computing systems:
 establishing a video call between a plurality of client systems;   sending, to a first client system of the plurality of client systems while maintaining the video call between the plurality of client systems, instructions for presenting a first content recommendation comprising one or more selected content items, wherein the first content recommendation comprises a prompt to share the selected content items with one or more second client systems of the plurality of client systems;   receiving, from the first client system responsive to the prompt, a request to share the selected content items; and   sending, to the one or more second client systems responsive to receiving the request and while maintaining the video call between the plurality of client systems, instructions for presenting the selected content items within the video call.   
     
     
         2 . The method of  claim 1 , wherein one or more of the selected content items comprise one or more content items in which one or more users of the plurality of client systems are tagged. 
     
     
         3 . The method of  claim 1 , wherein one or more of the selected content items are from a local data store of the first client system. 
     
     
         4 . The method of  claim 1 , further comprising:
 determining whether to provide content recommendations during the video call based on a current context of the video call.   
     
     
         5 . The method of  claim 4 , wherein the current context comprises a current amount of voice input in the video call. 
     
     
         6 . The method of  claim 5 , determining whether to provide content recommendations during the video call based on the current context of the video call comprises:
 determining whether the current amount voice input in the video call is less than a threshold amount of voice input, wherein:   if the current amount of voice input is less than the threshold amount of voice input, then determining to provide content recommendations; and   if the current amount of voice input is not less than the threshold amount of voice input, then determining to delay providing content recommendations until the current amount of voice input is less than the threshold amount of voice input.   
     
     
         7 . The method of  claim 1 , further comprising:
 selecting the one or more content items based on one or more events or dates associated with the content items.   
     
     
         8 . The method of  claim 1 , further comprising:
 selecting the one or more content items based on one or more topics of the video call.   
     
     
         9 . The method of  claim 1 , further comprising:
 selecting the first client system of the plurality of client systems, wherein a first user is associated with the first client system.   
     
     
         10 . The method of  claim 9 , wherein the first user is selected based on a determination that the first user is not speaking. 
     
     
         11 . The method of  claim 9 , wherein the first user is selected based on interactions by the first user with past content recommendations. 
     
     
         12 . The method of  claim 9 , wherein the first user is selected based on respective social signals associated with one or more of the selected content items. 
     
     
         13 . The method of  claim 1 , further comprising:
 selecting the one or more content items is based on respective social signals associated with the one or more content items.   
     
     
         14 . The method of  claim 1 , further comprising:
 receiving, from the first client system, a request for content recommendations, wherein the request comprises a user identifier of a first user of the first client system and a current context of the first user.   
     
     
         15 . The method of  claim 1 , wherein in response to the prompt, a first user of the first client system requests to share the one or more selected content items with all users in the call. 
     
     
         16 . The method of  claim 1 , wherein in response to the prompt, a first user of the first client system requests to share the one or more selected content items with only selected users in the call. 
     
     
         17 . The method of  claim 1 , wherein the selected content items are presented within the video call via a content sidebar. 
     
     
         18 . The method of  claim 1 , further comprising:
 selecting one or more additional content items responsive to the request to share the selected content items from the first client system; and   sending, to the first client system while maintaining the video call between the plurality of client systems, a second content recommendation comprising the one or more additional content items, wherein the second content recommendation comprises a prompt to share the one or more additional content items with the one or more second client systems of the plurality of client systems.   
     
     
         19 . A system comprising one or more processors and a memory coupled to the processors, the memory comprising instructions that, when executed by the processors, configure the processors to:
 establish a video call between a plurality of client systems;   send, to a first client system of the plurality of client systems while maintaining the video call between the plurality of client systems, instructions for presenting a first content recommendation comprising one or more selected content items, wherein the first content recommendation comprises a prompt to share the selected content items with one or more second client systems of the plurality of client systems;   receive, from the first client system responsive to the prompt, a request to share the selected content items; and   send, to the one or more second client systems responsive to receiving the request and while maintaining the video call between the plurality of client systems, instructions for presenting the selected content items within the video call.   
     
     
         20 . One or more computer-readable non-transitory storage media embodying software that is configured, when executed by a processor, to:
 establish a video call between a plurality of client systems;   send, to a first client system of the plurality of client systems while maintaining the video call between the plurality of client systems, instructions for presenting a first content recommendation comprising one or more selected content items, wherein the first content recommendation comprises a prompt to share the selected content items with one or more second client systems of the plurality of client systems;   receive, from the first client system responsive to the prompt, a request to share the selected content items; and   send, to the one or more second client systems responsive to receiving the request and while maintaining the video call between the plurality of client systems, instructions for presenting the selected content items within the video call.