US 11,755,686 B2
System for classifying the usage of a handheld consumer device
Faiz Feisal Sherman, Mason, OH (US); and Xiaole Mao, Mason, OH (US)
Assigned to Braun GmbH, Kronberg (DE)
Filed by Braun GmbH, Kronberg (DE)
Filed on Feb. 15, 2019, as Appl. No. 16/276,947.
Claims priority of application No. 18157358 (EP), filed on Feb. 19, 2018; and application No. 18157362 (EP), filed on Feb. 19, 2018.
Prior Publication US 2019/0278786 A1, Sep. 12, 2019
Int. Cl. G06F 18/213 (2023.01); A46B 15/00 (2006.01); A61C 17/22 (2006.01); A61C 17/26 (2006.01); G06F 16/28 (2019.01); G06N 3/08 (2023.01); G08B 21/18 (2006.01); G06V 40/20 (2022.01); G06N 3/02 (2006.01); G06N 3/04 (2023.01); G06F 18/00 (2023.01); A61C 17/34 (2006.01); G06N 3/044 (2023.01); B26B 21/40 (2006.01); A61C 17/16 (2006.01)
CPC G06F 18/213 (2023.01) [A46B 15/0073 (2013.01); A61C 17/22 (2013.01); A61C 17/221 (2013.01); A61C 17/26 (2013.01); G06F 16/285 (2019.01); G06F 18/00 (2023.01); G06N 3/044 (2023.01); G06N 3/08 (2013.01); G06V 40/20 (2022.01); G08B 21/18 (2013.01); A46B 15/0002 (2013.01); A46B 15/004 (2013.01); A46B 15/0036 (2013.01); A46B 15/0038 (2013.01); A46B 15/0071 (2013.01); A46B 2200/1066 (2013.01); A61B 2562/0219 (2013.01); A61B 2562/0247 (2013.01); A61B 2562/0252 (2013.01); A61C 17/16 (2013.01); A61C 17/3409 (2013.01); B26B 21/4056 (2013.01); B26B 21/4081 (2013.01); G06F 2218/16 (2023.01)] 23 Claims
OG exemplary drawing
 
1. A system for classifying the usage of a toothbrush with respect to a target surface, the system comprising:
the toothbrush comprising a sensor unit including at least one of an inertial sensor, a gyroscope, a magnetometer, and a force sensor, the sensor unit being structured to determine at least one usage data at successive time instants and to provide a temporally successive sequence of usage data relating to a motion of the toothbrush or a force acting thereon during a usage session; and
an analyzing device comprising a processor and structured to classify the usage of the toothbrush with respect to at least one set of at least two usage classes relating to different usage properties, wherein the analyzing device assembles a temporally successive sequence of input tuples of usage data relating to a predetermined time period of the usage session, each of the input tuples comprising at least one element representing the usage data at the respective time instant and for inputting the sequence of input tuples into at least one artificial neural network that is arranged to output at least one output tuple that comprises a number of elements in accordance with the number of usage classes, each element of the output tuple representing a prediction value that the usage of the consumer device at the given time instant relates to a respective usage class, and wherein the analyzing device determines a single usage class answer for the time period based on the sequence of output tuples.