IP Library › Granted Patent US 12,568,170
Granted Patent B2
US 12,568,170 · App. 19/220,169 · Granted Mar 3, 2026

Prioritizing emergency calls based on caller response to automated query

Inventors: Alexander Dizengof (New York, NY); Roman Malih (New York, NY); Alex Gruber (New York, NY)
Assignee: Carbyne Ltd.
H04M3/5116H04M3/42357
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 12,568,170
App. No.
19/220,169
Granted
Mar 3, 2026
Kind
B2
Abstract

Incoming emergency calls prioritization, comprising receiving one or more emergency calls originating from one or more client devices used to report one or more emergency events, computing an event zone for each emergency event based on one or more event attributes of the emergency event retrieved according to data extracted from the emergency call, receiving one or more subsequent emergency calls originating from one or more another client devices, computing spatiotemporal metrics including a location of each another client device with respect to the event zone of one or more of the emergency events and/or a timing of each subsequent emergency call with respect to the one or more emergency calls, responding to the subsequent emergency calls with one or more queries generated automatically according to the spatiotemporal metrics, and prioritizing the subsequent emergency calls according to a response to the to the query(s) via the another client devices.

Claims (44)

1 . A computer implemented method of prioritizing incoming emergency calls, comprising:

receiving at least one emergency call originating from at least one client device used to report at least one emergency event;

computing at least one event zone for the at least one emergency event based on at least one event attribute of the at least one emergency event retrieved according to data extracted from the at least one emergency call;

receiving at least one subsequent emergency call originating from at least one another client device;

computing at least one spatiotemporal metric for the at least one subsequent emergency call selected from the group consisting of:

a location of the at least one another client device with respect to the at least one event zone of the at least one emergency event; and

a timing of the at least one subsequent emergency call with respect to the at least one emergency call;

responding to the at least one subsequent emergency call with at least one query generated automatically according to the at least one spatiotemporal metric; and

prioritizing the at least one subsequent emergency call in a call queue according to a response received via the at least one another client device to the at least one query;

wherein when said at least one emergency call is automatically initiated by at least one automated device automatically placing an emergency call upon automatic detection of a triggering event, directing said automatically initiated at least one emergency call to at least one dedicated route, upon reception of said automatically initiated at least one emergency call.

2 . The computer implemented method of claim 1 , further comprising:

determining a location of the at least one client device;

determining a timing of the at least one emergency call;

determining a perimeter of the location of one or more of the at least one client device for which the timing of one or more of the at least one emergency call that originated therefrom meets a threshold condition; and

computing the at least one event zone according to the perimeter.

3 . The computer implemented method of claim 2 , further comprising responding to the at least one emergency call with at least one another query generated automatically according to the perimeter, and retrieving the at least one event attribute and/or adjusting the perimeter according to a response received via the at least one client device to the at least one another query.

4 . The computer implemented method of claim 1 , further comprising responding to the at least one subsequent emergency call in the call queue by at least one virtual agent.

5 . The computer implemented method of claim 1 , further comprising automatically transcribing the at least one emergency call and/or at least one subsequent emergency call in real time and applying on the transcription of the at least one emergency call and/or the at least one subsequent emergency call at least one machine learning model to retrieve and cast emergency event information and/or caller identification into a structured format.

6 . The computer implemented method of claim 1 , further comprising applying at least one audio augmentation technique to the at least one emergency call and/or the at least one subsequent emergency call.

7 . The computer implemented method of claim 1 , further comprising analyzing an interaction flow of the at least one subsequent emergency call comprising the at least one query and the response received thereto via the at least one another client device for extracting at least one another event attribute of the at least one emergency event, and responsive to a call taker answering the at least one subsequent emergency call providing the call taker with the at least one another event attribute.

8 . The computer implemented method of claim 1 , further comprising dynamically adjusting the at least one event zone according to at least one event attribute retrieved according to data extracted from the at least one subsequent emergency call.

9 . The computer implemented method of claim 1 , further comprising adjusting the at least one event zone according to a member selected from the group consisting of: at least one physical feature identified at and/or in proximity to the at least one event zone; at least one environmental condition; at least one timing parameter; at least one unrelated event and/or activity identified in proximity to a location of the at least one event zone.

10 . The computer implemented method of claim 1 , further comprising adjusting the at least one query based on the at least one event attribute of the at least one emergency event.

11 . The computer implemented method of claim 1 , further comprising using at least one generative machine learning model for generating the at least one query.

12 . The computer implemented method of claim 1 , further comprising prioritizing the at least one subsequent emergency call according to at least one call attribute responsive to failure to receive a verbal response during a predefined time period.

13 . The computer implemented method of claim 1 , wherein the prioritization of the subsequent emergency calls is conducted using at least one trained machine learning model.

14 . The computer implemented method of claim 13 , wherein the at least one trained machine learning model is further trained to filter out false positive emergency calls irrelevant to the at least one emergency event.

15 . The computer implemented method of claim 13 , further comprising using a plurality of machine learning models each trained for prioritizing emergency calls relating to a respective one of a plurality of emergency events.

16 . The computer implemented method of claim 1 , further comprising adjusting a graphical user interface (GUI) presented on a display of at least one call center terminal according to the prioritization.

17 . The computer implemented method of claim 1 , wherein each of the at least one emergency call and/or the at least one subsequent emergency call is initiated by a user or an automated device.

18 . The computer implemented method of claim 16 , wherein emergency calls from automated devices are automatically handled by at least one virtual agent.

19 . The computer implemented method of claim 1 , wherein the at least one event attribute is stored in an event log created for the at least one emergency event based on the at least one emergency call.

20 . The computer implemented method of claim 19 , further comprising updating the event log based on the at least one subsequent emergency call.

21 . A system for prioritizing incoming emergency calls, comprising:

at least one processor configured to execute a code, the code comprising:

code instructions to receive at least one emergency call originating from at least one client device used to report at least one emergency event;

code instructions to compute at least one event zone for the at least one emergency event based on at least one event attribute of the at least one emergency event retrieved according to data extracted from the at least one emergency call;

code instructions to receive at least one subsequent emergency call originating from at least one another client device;

code instructions to compute at least one spatiotemporal metric for the at least one subsequent emergency call selected from the group consisting of:

a location of the at least one another client device with respect to the at least one event zone of the at least one emergency event; and

a timing of the at least one subsequent emergency call with respect to the at least one emergency call;

code instructions to respond to the at least one subsequent emergency call with at least one query generated automatically according to the at least one spatiotemporal metric; and

code instructions to prioritize the at least one subsequent emergency call in a call queue according to a response received via the at least one another client device to the at least one query;

wherein when said at least one emergency call is automatically initiated by at least one automated device automatically placing an emergency call upon automatic detection of a triggering event, directing said automatically initiated at least one emergency call to at least one dedicated route, upon reception of said automatically initiated at least one emergency call.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 8, 2025
From: DIZENGOF, ALEXANDER; MALIH, ROMAN
To: CARBYNE LTD.
Reel/Frame 071623/0773 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 8, 2025
From: GRUBER, ALEX
To: CARBYNE LTD.
Reel/Frame 071623/0797 →
Continuity (3)
Continuation In Part PCTIL2024050729 · Jul 24, 2024
Continuation 18237416 · Aug 24, 2023
Related Publication 20250286953A1 · Sep 11, 2025
References Cited (29)
US 6754335B1 · Shaffer et al. · 2004 [cited by applicant]
US 8976939B1 · Hamilton et al. · 2015 [cited by applicant]
US 9420116B1 · Hamilton et al. · 2016 [cited by applicant]
US 10212281B2 · Czachor, Jr. et al. · 2019 [cited by applicant]
US 10362168B1 · Pitta Eswara Chandra et al. · 2019 [cited by applicant]
US 10743168B1 · Erenel · 2020 [cited by examiner]
US 11375063B1 · Frenkel · 2022 [cited by examiner]
US 20090284348A1 · Pfeffer · 2009 [cited by examiner]
US 20150111526A1 · Fletcher · 2015 [cited by examiner]
US 20170061761A1 · Kolla · 2017 [cited by examiner]
US 20180189913A1 · Knopp · 2018 [cited by examiner]
US 20180288224A1 · Dizengof et al. · 2018 [cited by applicant]
US 20190149661A1 · Klaban · 2019 [cited by applicant]
US 20190385711A1 · Shriberg · 2019 [cited by examiner]
US 20200068025A1 · Duran · 2020 [cited by examiner]
US 20200118431A1 · Amacker · 2020 [cited by examiner]
US 20210200424A1 · Therrien · 2021 [cited by examiner]
US 20220007165A1 · Ekl · 2022 [cited by applicant]
US 20220337702A1 · Smetek · 2022 [cited by examiner]
US 20220377522A1 · Martin · 2022 [cited by examiner]
US 20230395204A1 · Mitjans · 2023 [cited by examiner]
US 20240412856A1 · Mensch et al. · 2024 [cited by applicant]
US 20250071205A1 · Dizengof · 2025 [cited by examiner]
JP 7292824 · 2023 [cited by applicant]
WO WO0182580 · 2001 [cited by applicant]
International Search Report and the Written Opinion Dated Sep. 30, 2024 From the International Searching Authority Re. Application No. PCT/IL2024/050729. (14 Pages). [cited by applicant]
Official Action Dated May 23, 2025 from the US Patent and Trademark Office Re. U.S. Appl. No. 18/237,416. (16 pages). [cited by applicant]
Alfalqi et al. “An Emergency Event Detection Ensemble Model Based on Big Data”, Big Data and Cognitive Computing, 6(2): 42-1-42-18, Apr. 16, 2022. [cited by applicant]
Official Action Dated Oct. 8, 2025 from the US Patent and Trademark Office Re. U.S. Appl. No. 18/237,416. (18 pages). [cited by applicant]