US 11,755,949 B2
Multi-platform machine learning systems
Patrick O'Reilly, Belfast (GB); Nilesh Malpekar, Lincolnshire, IL (US); Robert Andrew Nendorf, Chicago, IL (US); Bich-Thuy Le, Mount Prospect, IL (US); and Younuskhan Mohamed Iynoolkhan, Rolling Meadows, IL (US)
Assigned to Allstate Insurance Company, Northbrook, IL (US)
Filed by Allstate Insurance Company, Northbrook, IL (US)
Filed on May 19, 2020, as Appl. No. 16/878,120.
Application 16/878,120 is a continuation in part of application No. 15/673,872, filed on Aug. 10, 2017, granted, now 10,878,144.
Prior Publication US 2020/0279181 A1, Sep. 3, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) 17 Claims
OG exemplary drawing
 
7. A method comprising:
receiving, by a computing device, a raw dataset formatted using a first data format;
generating, by the computing device, a first input dataset by processing the raw dataset, wherein the first input dataset is formatted using a common data format, wherein the processing the raw dataset comprises determining a structure of the first input dataset indicating one or more features within the raw data, and wherein the processing comprises audio sampling to identify particular waveforms within audio data;
determining, by the computing device, a first machine learning classifier based on the first input dataset;
triggering, by the computing device, execution of the first machine learning classifier to process the first input dataset and determining labels and/or confidence metrics for the features;
obtaining, by the computing device, a historical statistical distribution generated based on the first input dataset;
calculating, by the computing device, a statistical distribution based on the first output dataset; and
determining, by the computing device, a change in the distribution of values between the historical statistical distribution and the statistical distribution;
transmitting, by the computing device, a notification indicating the change in distribution of values based on the change exceeding a threshold value, wherein the change in distribution of values is between the historical statistical distribution based on the first input dataset and the statistical distribution based on the first output dataset;
receiving, by the computing device, a first output dataset generated based on execution of the first machine learning classifier;
generating, by the computing device, a second input dataset based on the first output dataset, wherein the second input dataset is formatted using the common data format;
automatically determining, by the computing device and based on the second input dataset, a second machine learning classifier;
triggering, by the computing device, execution of the second machine learning classifier, wherein the execution of the second machine learning classifier is based on the second input dataset;
obtaining, by the computing device, a second output dataset generated based on the execution of the second machine learning classifier; and
storing, by the computing device, the second output dataset.