Generating and providing in-meeting coaching for video calls

A system comprising:

• at least one processor;
• and
• a non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to:
• generate, from video call data extracted from past video calls associated with a user account of a content management system, a knowledge graph defining relationships between content items stored for the user account;
• detect, from video call data of an ongoing video call, a plurality of discussion topics, wherein each discussion topic comprises subject matter discussed between participants of the ongoing video call;
• select, using a topic prediction model, a discussion topic of the plurality of discussion topics according to contemporaneous video call data of the video call data;
• perform, during the ongoing video call, a continuous semantic search of the knowledge graph to identify content items corresponding to the discussion topic by:
• based on detecting the discussion topic, identifying via the continuous semantic search a first node of the knowledge graph corresponding to the discussion topic;
• and
• identifying, via the continuous semantic search, nodes of the knowledge graph that are within a threshold distance of the first node corresponding to the discussion topic;
• determine, from the continuous semantic search of the knowledge graph, a second node of the nodes that corresponds to a content item stored for the user account;
• and
• generating, for display on a client device associated with the user account during the ongoing video call, a recommendation for sharing the content item within the ongoing video call.

A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause the at least one processor to:

• generate, from video call data extracted from past video calls associated with a user account of a content management system, a knowledge graph defining relationships between content items stored for the user account;
• detect, from video call data of an ongoing video call, a plurality of discussion topics, wherein each discussion topic comprises subject matter discussed between participants of the ongoing video call;
• select, using a topic prediction model, a discussion topic of the plurality of discussion topics according to contemporaneous video call data of the video call data;
• perform, during the ongoing video call, a continuous semantic search of the knowledge graph by continually searching content items stored for the user account during the ongoing video call to identify content items corresponding to the discussion topic by:
• based on detecting the discussion topic, identifying via the continuous semantic search a first node of the knowledge graph corresponding to the discussion topic;
• and
• identifying, via the continuous semantic search, nodes of the knowledge graph that are within a threshold distance of the first node corresponding to the discussion topic;
• and
• determine, from the continuous semantic search of the knowledge graph, a second node of the nodes that corresponds to a content item stored for the user account to recommend for sharing within the ongoing video call.