Automatically Recognizing and Surfacing Important Moments in Multi-Party Conversations

A method comprising:

• receiving a transcription of a conversation, the conversation being ongoing between a plurality of participants including a given participant, the transcription received as the conversation continues;
• selecting a machine learning model for the given participant based on a profile of the given participant;
• applying, as input to the selected machine learning model, the transcription on an ongoing basis as the conversation continues;
• receiving, as output from the selected machine learning model, a portion of the transcription having relevance to the given participant;
• and
• generating for display, to the given participant, on an ongoing basis as the conversation from which the transcription was received continues, information pertaining to the portion, the information tailored to the given participant based on the portion output by the selected machine learning model.

A system comprising:

• memory with instructions encoded thereon;
• and
• one or more processors that, when executing the instructions, are caused to perform operations comprising:
• receiving a transcription of a conversation, the conversation being ongoing between a plurality of participants including a given participant, the transcription received as the conversation continues;
• selecting a machine learning model for the given participant based on a profile of the given participant;
• applying, as input to the selected machine learning model, the transcription on an ongoing basis as the conversation continues;
• receiving, as output from the selected machine learning model, a portion of the transcription having relevance to the given participant;
• and
• generating for display, to the given participant, on an ongoing basis as the conversation from which the transcription was received continues, information pertaining to the portion, the information tailored to the given participant based on the portion output by the selected machine learning model.