Intelligent agent for auto-summoning to meetings

A system comprising:

• at least one processor;
• and
• at least one memory storing computer-executable instructions that, when executed by the at least one processor, cause the at least one processor to:
• provide a digital agent, the digital agent configured to represent an invited non-participating user, access to a first communication session when the invited non-participating user is invited to the first communication session but not participating in the first communication session;
• monitor, by the digital agent, data shared between participants of the first communication session;
• identify, by the digital agent using a trained feature model, a first event during the first communication session relating to the invited non-participating user based on the monitored data, wherein the trained feature model is trained based on a profile of the invited non-participating user and recognizes a context of the first communication session according to personalized features of the invited non-participating user;
• determine, by the digital agent recognizing the context according to the personal features associated with the invited non-participating user during the first communication session, based on the recognized context of the first communication session using the trained feature model, whether to contact the invited non-participating user in real-time in response to the first event;
• and
• when it is determined to contact the invited non-participating user in real-time, communicate information about the first event to the invited non-participating user.

A computer storage medium storing computer-executable instructions that when executed cause at least one processor to perform operations, comprising:

• providing a digital agent, the digital agent configured to represent an invited non-participating user, access to a first communication session when the invited non-participating user is invited to the first communication session but not participating in the first communication session;
• monitoring, by the digital agent, data shared between participants of the first communication session;
• identifying, by the digital agent using a trained feature model, a first event during the first communication session relating to the invited non-participating user based on the monitored data, wherein the trained feature model is trained based on a profile of the invited non-participating user and recognizes a context of the first communication session according to personalized features of the invited non-participating user;
• determining, by the digital agent recognizing the context according to the personalized features associated with the invited non-participating user during the first communication session, based on the recognized context of the first communication session using the trained feature model, whether to contact the invited non-participating user in real-time in response to the first event;
• and
• in accordance with a determination to contact the invited non-participating user in real-time, communicating information about the first event to the invited non-participating user.