US 12,456,010 B2
Predicting text and data variables using customer-specific models
Arvind Srinivasamoorthy, Clarksburg, MD (US); Emma Jane Thomas, Reading (GB); and Maximilian Froeschl, Munich (DE)
Assigned to ORACLE INTERNATIONAL CORPORATION, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Jun. 29, 2022, as Appl. No. 17/853,684.
Prior Publication US 2024/0005095 A1, Jan. 4, 2024
Int. Cl. G06F 40/274 (2020.01); G06F 16/335 (2019.01); G06F 40/284 (2020.01); G06F 40/56 (2020.01)
CPC G06F 40/274 (2020.01) [G06F 16/335 (2019.01); G06F 40/284 (2020.01); G06F 40/56 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
for a text message being composed via an application for an intended recipient, receiving, by a text prediction system, a first portion of the text message based upon a current cursor position in the text message;
identifying, by the text prediction system, a customer associated with the intended recipient;
identifying, by the text prediction system, a customer-specific model for the customer;
predicting, by the text prediction system, text to be suggested for insertion at the current cursor position using the customer-specific model and based upon the first portion of the text message, the suggested text including a first data variable, wherein the first data variable is replaceable with a first value determined from data stored for the customer;
causing, by the text prediction system, the suggested text including the first data variable to be output via the application, wherein the first data variable is represented by a data variable name in the suggested text;
for the text message being composed via the application for the intended recipient, receiving, by the text prediction system, a second portion of the text message based upon a new current cursor position in the text message;
predicting, by the text prediction system, text to be suggested for insertion at the new current cursor position using the customer-specific model and based upon the second portion of the text message, the suggested text including a second data variable, wherein the second data variable is replaceable with a second value determined from data stored for the customer;
causing, by the text prediction system, the suggested text including the second data variable to be output via the application;
receiving, by the application, a signal to replace the first data variable in the suggested text with the first value and the second data variable in the suggested text with a second value; and
causing, by the application, the suggested text including the first value associated with the first variable and the second value associated with the second variable to be output via the application.