US 12,192,865 B2
Method for mobile device-based cooperative data capture
Jonathan Matus, San Francisco, CA (US); Pankaj Risbood, San Francisco, CA (US); Aditya Karnik, San Francisco, CA (US); and Manish Sachdev, San Francisco, CA (US)
Assigned to Credit Karma, LLC, Oakland, CA (US)
Filed by Credit Karma, LLC, Oakland, CA (US)
Filed on Apr. 17, 2023, as Appl. No. 18/135,597.
Application 18/135,597 is a continuation of application No. 16/814,444, filed on Mar. 10, 2020, granted, now 11,659,368.
Application 16/814,444 is a continuation of application No. 15/921,152, filed on Mar. 14, 2018, granted, now 10,631,147, issued on Apr. 21, 2020.
Application 15/921,152 is a continuation of application No. 15/702,601, filed on Sep. 12, 2017, granted, now 9,955,319, issued on Apr. 24, 2018.
Claims priority of provisional application 62/393,308, filed on Sep. 12, 2016.
Prior Publication US 2023/0254673 A1, Aug. 10, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04W 4/40 (2018.01); G08B 21/04 (2006.01); G08B 25/01 (2006.01); G08G 1/00 (2006.01); H04W 4/02 (2018.01); G08G 1/16 (2006.01)
CPC H04W 4/40 (2018.02) [G08B 21/04 (2013.01); G08B 25/016 (2013.01); G08G 1/205 (2013.01); H04W 4/023 (2013.01); H04W 4/027 (2013.01); G08G 1/162 (2013.01); H04W 4/026 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for a plurality of mobile devices in a vehicle, the method comprising:
with a first computer onboard a first mobile device, receiving at least a portion of a first movement dataset corresponding to a first sensor of the first mobile device of the plurality of mobile devices, wherein the first movement dataset comprises at least one of: position, velocity, and acceleration data;
with a second computer onboard a second mobile device, receiving at least a portion of a second movement dataset corresponding to a second sensor of the second mobile device of the plurality of mobile devices, wherein the second movement dataset comprises at least one of: position, velocity, and acceleration data;
based on an at least partial overlap between the first and the second movement datasets, determining, with a remote computer in communication with the first and second computers, satisfaction of a device association condition indicative of the first and the second mobile devices residing in the vehicle; and
based on determining the satisfaction of the device association condition and with the remote computer:
with a trained machine learning multi-device-based vehicle movement model and the first and second movement datasets, determining a vehicle movement characteristic comprising a driver classification associated with a user of the first mobile device; and
initiating an action based on the driver classification, wherein the action comprises: collecting additional data of the first movement dataset; and ceasing collection of additional data of the second movement dataset.