US 12,106,199 B2
Real-time predictions based on machine learning models
Rakesh Ganapathi Karanth, San Mateo, CA (US); Arun Kumar Jagota, Sunnyvale, CA (US); Kaushal Bansal, Pleasanton, CA (US); and Amrita Dasgupta, San Francisco, CA (US)
Assigned to Salesforce, Inc., San Francisco, CA (US)
Filed by Salesforce, Inc., San Francisco, CA (US)
Filed on Apr. 20, 2023, as Appl. No. 18/304,284.
Application 18/304,284 is a continuation of application No. 16/777,686, filed on Jan. 30, 2020, granted, now 11,651,291.
Prior Publication US 2023/0259831 A1, Aug. 17, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/20 (2019.01); G06N 7/01 (2023.01)
CPC G06N 20/20 (2019.01) [G06N 7/01 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for performing predictions, the method comprising:
receiving, by a client device from an online system, a regression based machine learning model;
receiving a request for a task;
extracting features of the task;
determining an available network bandwidth for the client device;
responsive to determining that the available network bandwidth for the client device is below a threshold:
executing the regression based machine learning model with the extracted features of the task as input to generate a first output;
responsive to determining that the available network bandwidth for the client device is above the threshold:
serializing the extracted features of the task;
transmitting, from the client device to the online system, the serialized features, causing the online system to execute a second machine learning based model with the features of the task as input to generate a second output; and
receiving, from the online system, the second output of the second machine learning based model; and
performing the task using the received first output or second output.