US 12,307,536 B2
Systems and methods for automated staging and capture of real estate negotiations
Christianne C. Chen, San Francisco, CA (US); Christina Jackson, San Francisco, CA (US); Tim Brandt, Denver, CO (US); Syed Ibrahim, Denver, CO (US); Kendra Cislo, Denver, CO (US); and Erik Stock, Denver, CO (US)
Assigned to PROLOGIS, L.P., San Francisco, CA (US)
Filed by PROLOGIS, L.P., San Francisco, CA (US)
Filed on Jun. 16, 2020, as Appl. No. 16/903,288.
Prior Publication US 2021/0390647 A1, Dec. 16, 2021
Int. Cl. G06Q 50/18 (2012.01); G06F 16/25 (2019.01); G06Q 10/107 (2023.01); G06Q 10/1093 (2023.01); G06Q 30/0204 (2023.01); G06Q 50/16 (2024.01)
CPC G06Q 50/188 (2013.01) [G06F 16/258 (2019.01); G06Q 10/107 (2013.01); G06Q 10/1095 (2013.01); G06Q 30/0205 (2013.01); G06Q 50/16 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A client device for intelligently staging negotiations, comprising:
a memory configured to store non-transitory computer readable instructions; and
a processor communicatively coupled to the memory, wherein the processor, when executing the non-transitory computer readable instructions, is configured to:
receive, from a server, a copy of a machine-learning model trained on a dataset of preferences from a first party and a second party,
wherein the machine-learning model is deployed on the server for use by the client device when the client device is connected to the server, and
wherein the dataset of preferences comprises a transaction history related to the first party and a transaction history related to the second party;
configure the copy of the machine-learning model for use by the client device when the client device lacks a connection to the server;
cache the copy of the machine-learning model locally on the client device;
receive a first proposal from the first party;
lock the first proposal;
generate a clone of the first proposal, wherein the clone of the first proposal is editable by the second party;
receive at least one edit to the clone of the first proposal from the second party;
receive current market data related to the first proposal;
input the at least one edit and the current market data related to the first proposal to the copy of the machine-learning model cached on the client device when the client device lacks the connection to the server;
compare the at least one edit and the current market data to the dataset of preferences from the first party and the second party;
based on comparing the at least one edit and the current market data to the dataset, update the machine-learning model deployed on the server when the client device is connected to the server;
based on the update of the machine-learning model on the server, generate at least one counter-proposal suggestion;
receive an approval indication of the at least one counter-proposal suggestion, wherein the approval indication transforms the at least one counter-proposal suggestion into the counter-proposal; and
transmit the counter-proposal to the first party.