The non-provisional patent, submitted in February 2020,  was issued on September 21, 2021.

 The Emakia system applies classifier models on incoming social media data, (text, image, video, and audio).  

 The classifier models from Apple Core ML 3 or Google Auto ML determine if the incoming data qualifies for harassment. 

 The classification process is similar to the ML classifiers used to filter out spam from emails.

The continuation-in-part patent, submitted in February 2021, was granted on November 09, 2021. 

 

The patent describes the Emakia system.  

 

The modifications are the bag of words and a text classifier with multiple inputs.

 ValleyML is a cross-industry community for advancing AI to empower people; as ACM, IEEE and other AI related organizations.

 

Emakia's presentation can be accessed at  https://valleyml.ai/event/keynote-talk-4-system-filters-out-harassment-from-incoming-social-media-data/