Block, Inc.

Ragavan Thurairatnam

Marc Tyndel

Rayhane Mama

Rocky Medure

Jeremy Mawson

Louay Hazami

Thomas Collier

Per Engstrom

Generation of dynamic electronic representations using modeling is described. Interaction data comprising attributes of one or more interactions between a user and the service provider or one or more third-party services integrated with the service provider is received. A model is executed to dynamically generate an electronic representation for a user profile based upon the interaction data, wherein the model is trained using attributes associated with a set of existing user profiles associated with the service provider and corresponding interaction data indicative of interaction data of the set of existing user profiles, and wherein the electronic representation is generated without input from the user. The electronic representation can be presented on an electronic device.

Modeling to generate dynamic electronic representations

Technology to encode/compress and decode/uncompress video streams is described. According to one example, a computer-implemented method includes receiving, by a server and from a first device associated with a first participant of a videoconference involving a second device associated with a second participant, a first compressed video stream and a first decoding model. The first decoding model is trained via machine learning, and the first compressed video stream is compressed using a first encoding model trained via machine learning. The first encoding and decoding models are customized to the first participant. The server is adapted to transmit to the second device, the first decoding model and the first compressed video stream.

Machine-learning based data compression for streaming media

Growing community of inventors

San Francisco, CA, United States of America

Ragavan Thurairatnam