US 12,440,193 B2
System, method and apparatus for forming machine learning sessions
Vikram Kashyap, San Francisco, CA (US); Dan Cheung, San Francisco, CA (US); Ting-Hsuan Lin, San Francisco, CA (US); Gabrielle Kim, San Francisco, CA (US); and Parmoon Sarmadi, San Francisco, CA (US)
Assigned to Toi Labs, Inc., San Francisco, CA (US)
Filed by Toi Labs, Inc., San Francisco, CA (US)
Filed on May 8, 2023, as Appl. No. 18/144,815.
Application 18/144,815 is a continuation in part of application No. 17/701,799, filed on Mar. 23, 2022, granted, now 12,089,822.
Application 17/701,799 is a continuation of application No. 16/446,111, filed on Jun. 19, 2019, granted, now 11,298,112, issued on Apr. 12, 2022.
Application 16/446,111 is a continuation of application No. 16/016,559, filed on Jun. 23, 2018, granted, now 10,376,246, issued on Aug. 13, 2019.
Application 16/016,559 is a continuation of application No. PCT/US2018/026618, filed on Apr. 6, 2018.
Application 18/144,815 is a continuation in part of application No. 17/432,955, filed on Aug. 23, 2021.
Claims priority of provisional application 63/339,407, filed on May 6, 2022.
Claims priority of provisional application 62/482,912, filed on Apr. 7, 2017.
Prior Publication US 2023/0277162 A1, Sep. 7, 2023
Int. Cl. E03D 11/13 (2006.01); A61B 10/00 (2006.01); G01N 21/31 (2006.01); G01N 33/483 (2006.01); G01N 33/49 (2006.01); G01N 33/493 (2006.01); H04N 23/11 (2023.01); H04N 25/76 (2023.01); G01G 19/50 (2006.01); G01G 21/28 (2006.01)
CPC A61B 10/0038 (2013.01) [A61B 10/007 (2013.01); E03D 11/13 (2013.01); G01N 21/31 (2013.01); G01N 33/4833 (2013.01); G01N 33/49 (2013.01); G01N 33/493 (2013.01); H04N 23/11 (2023.01); H04N 25/76 (2023.01); A61B 2010/0083 (2013.01); G01G 19/50 (2013.01); G01G 21/28 (2013.01)] 41 Claims
OG exemplary drawing
 
1. A method to automatically label toileting acts of a user, the method comprising:
activating a sensor to record the toileting acts in a plurality of frames, each frame capturing one or more activities during a discrete time interval and each frame separated from a subsequent frame by a time interval;
forming one or more sequences by grouping the frames separated from each other by a substantially constant time interval; and
forming one or more sessions by grouping the sequences as a function of a differential interval;
labeling each frame by identifying one or more conditions present in the frame;
labeling each sequence by identifying one or more conditions present in the plurality of frames in the respective sequence; and
labeling each session by identifying one or more conditions present in the plurality of sequences in the respective session.