International Business Machines Corporation
Layered neural networks to evaluate communication distribution

Abstract:

Techniques for communication evaluation and routing are provided. A communication for distribution to a plurality of users is received from a sending user, and the communication is parsed using one or more natural language processing (NLP) techniques to determine a context. A plurality of scores is generated for the plurality of users by processing the context using a machine learning (ML) model. It is determined, based on a first score of the plurality of scores corresponding to a first user of the plurality of users, to transmit the communication to the first user. It is further determined, based on a second score of the plurality of scores corresponding to a second user of the plurality of users, to refrain from transmitting the communication to the second user. Additionally, the system transmits the communication to the first user, and refrains from transmitting the communication to the second user.