Personalized communication text compression system

Abstract

Email clients typically store received email in a local device to allow faster retrieval of the email. There is a need to optimize the space for emails stored locally without sacrificing the ability to work in an offline mode. Emails for users are summarized and the summarized version of the email is stored on the local device without storing the original email. An electronic device receives an email that is summarized and provided to the user in a way that is easily digestible and saves storage space. A machine learning model is trained by the user to provide the user with a summarized version of the email. A baseline machine learning model is provided to a user and over time, based on user interactions that train the baseline machine learning model, a personalized machine learning model is generated to predict and provide summaries that are beneficial to the user.