US 12,190,051 B2
Facilitating customization and proliferation of state models
Tianyi Xia, San Francisco, CA (US); Leonid Boris Pekelis, San Francisco, CA (US); and David Makanalani Lundgren, San Francisco, CA (US)
Assigned to Opendoor Labs Inc., San Francisco, CA (US)
Filed by Opendoor Labs Inc., San Francisco, CA (US)
Filed on Dec. 1, 2023, as Appl. No. 18/526,333.
Application 18/526,333 is a continuation of application No. 17/994,839, filed on Nov. 28, 2022, granted, now 11,928,424.
Application 17/994,839 is a continuation of application No. 16/668,747, filed on Oct. 30, 2019, granted, now 11,556,701.
Claims priority of provisional application 62/870,611, filed on Jul. 3, 2019.
Prior Publication US 2024/0095444 A1, Mar. 21, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/00 (2020.01); G06F 30/20 (2020.01); G06F 40/177 (2020.01); G06Q 30/0201 (2023.01); G06Q 50/16 (2012.01)
CPC G06F 40/177 (2020.01) [G06F 30/20 (2020.01); G06Q 30/0206 (2013.01); G06Q 50/16 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
at least one processor and memory having instructions that, when executed, cause the at least one processor to perform operations comprising:
selecting a first machine learning model from a plurality of machine learning models, the first machine learning model including logic for processing table information to generate predicted values, the table information including rows describing homes and columns describing attributes of the homes;
receiving the predicted values from the first machine learning model;
appending the predicted values to the table information to generate appended table information; and
iterating the receiving and the appending operations, the iterating the operations including processing the table information through a sequence of states, each iteration includes processing the table information to transition the rows describing the homes from a first state to a next state by appending additional predicted values to the appended table information to generate additional appended table information, the receiving operation being performed by at least one machine interface and not being performed via any user interface by a user, the iterating the operations to facilitate a customization and a proliferation of the first machine learning model.