US 11,783,223 B2
Techniques for machine language model creation
Michael R. Siracusa, Mountain View, CA (US); Alexander B. Brown, Mountain View, CA (US); Dheeraj Goswami, Cupertino, CA (US); Nathan C. Wertman, Grand Junction, CO (US); Jacob T. Sawyer, Sunnyvale, CA (US); and Donald M. Firlik, Cupertino, CA (US)
Assigned to APPLE INC., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Oct. 31, 2019, as Appl. No. 16/670,914.
Claims priority of provisional application 62/855,958, filed on Jun. 1, 2019.
Prior Publication US 2020/0380301 A1, Dec. 3, 2020
Int. Cl. G06F 3/048 (2013.01); G06N 20/00 (2019.01); G06F 3/0486 (2013.01); G06F 8/34 (2018.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01); G06F 18/2431 (2023.01); G06V 10/776 (2022.01)
CPC G06N 20/00 (2019.01) [G06F 3/048 (2013.01); G06F 3/0486 (2013.01); G06F 8/34 (2013.01); G06F 18/2148 (2023.01); G06F 18/2193 (2023.01); G06F 18/2431 (2023.01); G06V 10/776 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for using graphical user interface to generate a machine learning model, the method, performed by an electronic device, comprising:
receiving, via a user interface, a selection of a template of a plurality of templates defining a machine learning model, each template corresponding to a category of a type of data, wherein the category of the type of data comprises one of images, text, sound, or tabular data;
identifying a location of a plurality of training data comprising a first plurality of structured data records and first associated metadata records, each metadata record of the first associated metadata records identifying at least a classification label of the first plurality of structured data records;
training the machine learning model by analyzing each of the first plurality of structured data records and the first associated metadata records to generate a trained model;
identifying a location of a plurality of validation data comprising a second plurality of structured data records and second associated metadata records, each metadata record of the second associated metadata records identifying at least the classification label of the second plurality of structured data records;
validating the trained model by analyzing each of the second plurality of structured data records to generate an identification for each of the second plurality of structured data records;
displaying an accuracy score of the identification provided by the machine learning model that is generated by comparing the identification for each of the second plurality of structured data records against the second associated metadata records; and
generating executable code for the trained model, the executable code including the trained model and executable on a mobile device to classify data obtained from a sensor of the mobile device, wherein the sensor corresponds to the type of data of the selected template.