US Patent Application 18447186. SELECTIVE TEXT PREDICTION FOR ELECTRONIC MESSAGING simplified abstract

SELECTIVE TEXT PREDICTION FOR ELECTRONIC MESSAGING

Organization Name

GOOGLE LLC

Inventor(s)

Paul Roland Lambert of Redwood City CA (US)

Timothy Youngjin Sohn of Los Altos CA (US)

Jacqueline Amy Tsay of Sunnyvale CA (US)

Gagan Bansal of Sunnyvale CA (US)

Cole Austin Bevis of Lake Forest IL (US)

Kaushik Roy of Santa Clara CA (US)

Justin Tzi-jay Lu of Mountain View CA (US)

Katherine Anna Evans of Palo Alto CA (US)

Tobias Bosch of Santa Clara CA (US)

Yinan Wang of San Jose CA (US)

Matthew Vincent Dierker of Palo Alto CA (US)

Greg Russell Bullock of Zürich (CH)

Ettore Randazzo of Zürich (CH)

Tobias Kaufmann of Zürich (CH)

Yonghui Wu of Mountain View CA (US)

Benjamin N. Lee of Mountain View CA (US)

Xu Chen of San Francisco CA (US)

Brian Strope of Palo Alto CA (US)

Yun-hsuan Sung of Mountain View CA (US)

Do Kook Choe of Sunnyvale CA (US)

Rami Eid Sammour Al-rfou' of Mountain View CA (US)

SELECTIVE TEXT PREDICTION FOR ELECTRONIC MESSAGING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18447186 titled 'SELECTIVE TEXT PREDICTION FOR ELECTRONIC MESSAGING

Simplified Explanation

- The patent application describes a computing system that includes user interface components and processors. - The user interface components receive typed user input, while the processors perform various functions. - At a first time, the system receives a first portion of text typed by a user in an electronic message being edited. - Based on this first portion of text, the system predicts a first candidate portion of text to follow it. - The predicted first candidate portion of text is then outputted for display, giving the user the option to append it to the first portion of text. - At a second time, the system determines that the electronic message is directed to a sensitive topic. - In response to this determination, the system refrains from outputting subsequent candidate portions of text for optional selection to append to the message. - The purpose of this innovation is to provide a system that can predict and suggest text to users while editing electronic messages, but with the ability to recognize and respect sensitive topics by not suggesting further text in those cases.

Original Abstract Submitted

A computing system is described that includes user interface components configured to receive typed user input; and one or more processors. The one or more processors are configured to: receive, by a computing system and at a first time, a first portion of text typed by a user in an electronic message being edited; predict, based on the first portion of text, a first candidate portion of text to follow the first portion of text; output, for display, the predicted first candidate portion of text for optional selection to append to the first portion of text; determine, at a second time that is after the first time, that the electronic message is directed to a sensitive topic; and responsive to determining that the electronic message is directed to a sensitive topic, refrain from outputting subsequent candidate portions of text for optional selection to append to text in the electronic message.