IP Library › Granted Patent US 12,530,731
Granted Patent B2
US 12,530,731 · App. 16/370,182 · Granted Jan 20, 2026

Cloud-based artificial intelligence routing for emergency evacuation systems using Wi-Fi access points over data communication systems

Inventors: Seyed Dawood Sajjadi Torshizi (Burnaby, CA); Yanjie Gu (Surrey, CA)
Assignee: Fortinet, Inc.
G06Q90/205G06N5/04H04L67/10H04W4/023H04W4/024H04W4/33H04W4/90G06N20/00H04W84/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,530,731
App. No.
16/370,182
Granted
Jan 20, 2026
Kind
B2
Abstract

A cloud-based intelligence to emergency evacuation systems using Wi-Fi access points over data communication systems. A layout of emergency exits for a building being monitored and AP locations within the building layout is configured. A density map is generated from a number of stations within radio range of each AP including stations that are connected and stations that are not connected. An emergency that requires evacuation of people from the building from an emergency system associated with the building is detected. In response, an optimal evacuation route from each AP based on the density map and the building layout is generated. Evacuation instructions for each AP can be displayed on the stations within range of each AP.

Claims (25)

1 . A computer-implemented method in a Wi-Fi controller device, implemented at least partially in hardware and communicatively coupled to a plurality of access points on a data communication network which are in turn coupled to a plurality of wireless stations on a Wi-Fi portion of the data communication network, the method for emergency evacuation routing through access points on a data communication network, the method comprising the steps of:

configuring a layout of emergency exits for a building being monitored and access point locations within the building layout;

tracking wireless stations that are active and connected to access point locations and tracking wireless stations that are active and are not connected to access point locations, wherein the connected wireless stations are part of the enterprise network and wherein the non-connected wireless stations are not part of the enterprise system but are heard within RF range;

training artificial intelligence to estimate a number of people near each access point based on a number of connected wireless stations and a number of non-connected wireless stations, associated with each access point;

detecting an emergency that requires evacuation of people from the building from an emergency system associated with the building;

estimating a current density using artificial intelligence;

generating an optimal evacuation route from each access point based on the current density and the building layout; and

displaying the optimal evacuation route for each access point on the connected wireless stations within range of each access point.

2 . The method of claim 1 , wherein the step of training artificial intelligence to estimate a number of people near each access point based on a number of wireless connected stations and a number of non-connected wireless stations, associated with each access point, comprises estimating a number people near each access point based on data throughput.

3 . A non-transitory computer-readable medium to, when executed by a processor, perform a computer-implemented method in a central locationing server implemented at least partially in hardware and communicatively coupled to a plurality of access points on a data communication network which are in turn coupled to a plurality of wireless stations on a Wi-Fi portion of the data communication network for emergency evacuating routing through access points on a data communication network, the method comprising the steps of:

configuring a layout of emergency exits for a building being monitored and access point locations within the building layout;

tracking wireless stations that are active and connected to access point locations and tracking wireless stations that are active and are not connected to access point locations, wherein the connected wireless stations are part of the enterprise network and wherein the non-connected wireless stations are not part of the enterprise system but are heard within RF range;

training artificial intelligence to estimate a number of people near each access point based on a number of connected wireless stations and a number of non-connected wireless stations, associated with each access point;

detecting an emergency that requires evacuation of people from the building from an emergency system associated with the building;

estimating a current density using artificial intelligence;

generating an optimal evacuation route from each access point based on the current density and the building layout; and

displaying the optimal evacuation route for each access point on the connected wireless stations within range of each access point.

4 . A Wi-Fi controller device implemented at least partially in hardware and communicatively coupled to a plurality of access points on a data communication network which are in turn coupled to a plurality of wireless stations on a Wi-Fi portion of the data communication network, for emergency evacuation routing through access points on a data communication network, the Wi-Fi controller comprising:

a processor;

a network interface, communicatively coupled to the processor; and

a memory, communicatively coupled to the processor and storing:

a layout module to configure a layout of emergency exits for a building being monitored and access point locations within the building layout using a building configuration database;

a tracking module to track wireless stations that are active and connected to access point locations and tracking wireless stations that are active and are not connected to access point locations, wherein the connected wireless stations are part of the enterprise network and wherein the non- connected wireless stations are not part of the enterprise system but are heard within RF range;

a density map module to train artificial intelligence to estimate a number of people near each access point based on a number of connected wireless stations and a number of non-connected wireless stations, associated with each access point;

an AI routing module to detect an emergency that requires evacuation of people from the building from an emergency system associated with the building, estimate a current density using artificial intelligence, generate an optimal evacuation route from each access point based on the current density and the building layout, display the optimal evacuation route for each access point on the connected wireless stations within range of each access point.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 2, 2019
From: TORSHIZI, SEYED DAWOOD SAJJADI; GU, YANJIE
To: FORTINET, INC
Reel/Frame 048760/0496 →
Continuity (1)
Related Publication 20200311852A1 · Oct 1, 2020
References Cited (24)
US 7349768B2 · Bruce · 2008 [cited by examiner]
US 8818713B2 · Kumar · 2014 [cited by examiner]
US 8972357B2 · Shim · 2015 [cited by examiner]
US 9467662B2 · Childers · 2016 [cited by examiner]
US 20110105084A1 · Chandrasekaran · 2011 [cited by examiner]
US 20130024106A1 · Kumar · 2013 [cited by examiner]
US 20180242169A1 · Kowal · 2018 [cited by examiner]
US 20210035203A1 · Daigle · 2021 [cited by examiner]
KR 20120027969A · 2010 [cited by examiner]
KR 20150073574A · 2015 [cited by examiner]
KR 20170106665A · 2016 [cited by examiner]
KR 20180005840A · 2018 [cited by examiner]
WO WO2016194129A1 · 2016 [cited by examiner]
WO WO2019159106A1 · 2019 [cited by examiner]
F. M. Naini, O. Dousse, P. Thiran and M. Vetterli, “Opportunistic Sampling for Joint Population Size and Density Estimation,” in IEEE Transactions on Mobile Computing, vol. 14, No. 12, pp. 2530-2543, Dec. 1, 2015, doi: … [cited by examiner]
A. Filippoupolitis, G. Gorbil and E. Gelenbe, “Spatial Computers for Emergency Management,” 2011 Fifth IEEE Conference on Self-Adaptive and Self-Organizing Systems Workshops, 2011, pp. 61-66, doi: 10.1109/SASOW.2011.13.… [cited by examiner]
KR-20120027969-A Translation (Year: 2010). [cited by examiner]
Translation KR 20170106665 A (Year: 2018). [cited by examiner]
Translation of WO-2016194129-A1 (Year: 2016). [cited by examiner]
H. Bi, “Emergency navigation systems and algorithms in confined spaces,” 2016 3rd International Conference on Information and Communication Technologies for Disaster Management (ICT-DM), 2016, pp. 1-8, doi: 10.1109/ICT-… [cited by examiner]
M. B. Yassein, S. Aljawarneh and S. Alodibat, “A mathematical model of integrated cloud computing and WSNs for emergency systems,” 2017 International Conference on Engineering & MIS (ICEMIS), 2017, pp. 1-12, doi: 10.110… [cited by examiner]
O. J. Akinwande and H. Bi, “Routing diverse crowds in emergency with dynamic grouping,” 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), 2015, pp. 487-492, doi: 1… [cited by examiner]
J. Radianti, O.-C. Granmo, N. Bouhmala, P. Sarshar, A. Yazidi and J. Gonzalez, “Crowd Models for Emergency Evacuation: A Review Targeting Human-Centered Sensing,” 2013 46th Hawaii International Conference on System Scie… [cited by examiner]
S. S. Kulkarni and S. D. Agashe, “Study of Intelligent Evacuation Systems of High-Rise Buildings in India—a review,” 2016 International Conference on Computing, Analytics and Security Trends (CAST), 2016, pp. 190-194, d… [cited by examiner]