Intelligent matching of a user to an agent for a communication session

A computer-implemented method comprising:

• receiving, by a computing device, a request from a client device of a user to open a data communication session with an agent, the request being associated with a user account;
• identifying, by the computing device, a user intent from a message from the client device;
• determining, by the computing device, a user segment classification for the user account;
• identifying, by the computing device, an agent account of the agent to participate in the data communication session based at least in part on the agent account being associated with the user segment classification and the user intent;
• and
• establishing, by the computing device, the data communication session, via a voice or messaging application, between an agent client device for the agent and the client device based at least in part on the agent account being identified for participation in the data communication session.

A system, comprising:

• a computing device comprising a processor and a memory;
• and
• machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
• receive a communication request from a client device, the communication request being associated with a user account;
• determine that the communication request is for a first interaction with the computing device;
• establish a data communication session, via a messaging application, between an agent client device of an agent and the client device based at least in part on the determination the communication request is for the first interaction with the computing device;
• identify a message from the client device in the data communication session;
• generate a first category score of a set of user scores based at least in part on a first machine learning model and text from the message;
• generate a second category score of the set of user scores based at least in part on a second machine learning model and the text from the message;
• determine a user segment classification for the user account based at least in part on the set of user scores;
• and
• store the user segment classification in association with the user account.