US 12,394,527 B2
Systems and methods for detecting eating patterns of a pet
Aletha Carson, Gaston, OR (US); David Allen, Charleston, SC (US); and Laura Prescott, Makawao, HI (US)
Assigned to Mars, Incorporated, McLean, VA (US)
Filed by Mars, Incorporated, McLean, VA (US)
Filed on Dec. 6, 2022, as Appl. No. 18/062,238.
Claims priority of provisional application 63/286,721, filed on Dec. 7, 2021.
Prior Publication US 2023/0178246 A1, Jun. 8, 2023
Int. Cl. G16H 50/30 (2018.01); A61B 5/00 (2006.01); G16H 50/70 (2018.01)
CPC G16H 50/30 (2018.01) [A61B 5/6802 (2013.01); G16H 50/70 (2018.01); A61B 2503/40 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for using historical pet eating data to determine changes in pet eating behavior, the method comprising:
receiving, by one or more processors, pet sensor data captured in real-time by one or more pet sensors worn by a pet, wherein the pet sensor data includes pet eating data corresponding to one or more pet eating events, wherein the pet sensor data includes one or more sensor identifiers corresponding to the one or more pet sensors and one or more time durations that the pet wore the one or more pet sensors;
analyzing, by the one or more processors, the one or more pet sensors and the one or more time durations to determine a historical sensor wearing ratio;
updating, by the one or more processors, a plurality of historical pet eating data records in a database to include the pet eating data, wherein each record of the plurality of historical pet eating data records includes a historical meal event value, a corresponding historical meal event date, and the historical sensor wearing ratio;
determining, by the one or more processors, a subset of the plurality of historical pet eating data records that each include a historical sensor wearing ratio that meets or exceeds a sensor wearing threshold, wherein the determining includes removing at least one of the plurality of historical pet eating data records from the database;
determining, by the one or more processors, an expected distribution based on the subset of the plurality of historical pet eating data records, the expected distribution including a baseline, an upper threshold, and a lower threshold, wherein the upper threshold and the lower threshold correspond to the baseline;
receiving, by the one or more processors, current pet data from the one or more pet sensors worn by the pet, the current pet data including a total meal event value;
analyzing, by the one or more processors, whether the total meal event value exceeds the upper threshold or the lower threshold to determine a result;
receiving, by the one or more processors, additional pet behavior data for the pet, wherein the additional pet behavior data includes one or more of: scratching data of the pet, licking data of the pet, sleeping data of the pet, and drinking data of the pet;
calculating, by the one or more processors, a wellness score based on analyzing the additional pet behavior data and the pet sensor data;
generating, by the one or more processors, a user-interactive graphical display of the wellness score, the result, the current pet data, the expected distribution, the upper threshold, and the lower threshold;
outputting, by the one or more processors, the user-interactive graphical display on a user interface of a mobile device, wherein the user-interactive graphical display includes an electronic communication option;
receiving, by the one or more processors, a user selection corresponding to the electronic communication option to send a real-time communication to an external server system; and
in response to the user selection, transmitting, by the one or more processors, an electronic communication that includes the user-interactive graphical display from the mobile device via a network to the external server system.