IP Library Granted Patent US 12,424,032
Granted Patent B2
US 12,424,032 · App. 16/667,210 · Granted Sep 23, 2025

Processing system for dynamic collision verification and sensor selection

Inventor: Emad S. Isaac (Downers Grove, IL)
Assignee: Allstate Insurance Co.
G07C5/008G06N20/00G07C5/0841H04W4/029
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 12,424,032
App. No.
16/667,210
Granted
Sep 23, 2025
Kind
B2
Abstract

Aspects of the disclosure relate to computing platforms that utilize improved techniques for dynamic event verification and sensor selection. A computing platform may determine accuracy for each of a plurality of sensor devices for each of a plurality of data types. For each of the data types, the computing platform may rank the plurality of sensor devices based on their corresponding accuracy. The computing platform may direct a first sensor device and a second sensor device to provide first and second source data respectively. These sensor devices may be the most accurate sources of data types corresponding to the first and second source data respectively. The computing platform may receive the first source data and the second source data. Based on the first source data and the second source data, the computing platform may generate an event output indicating whether a vehicle experienced an event.

Claims (80)

1. A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

access a sensor capability database to determine an accuracy output associated with each of a plurality of sensor devices for each of a plurality of data types;

rank, for each of the plurality of data types and based on accuracy outputs associated with the plurality of data types, the plurality of sensor devices under one or more specific conditions, resulting in one or more ranked lists of the plurality of sensor devices, the one or more ranked lists comprising a first ranking of one or more of the plurality of sensor devices based on accuracy outputs associated with acceleration data, the one or more ranked lists further comprising a second ranking of one or more of the plurality of sensor devices based on accuracy outputs associated with braking data;

send one or more commands directing a first sensor device to provide first source data;

receive, from the first sensor device, the first source data in response to the one or more commands;

generate, based on the first source data, an event output indicating whether a vehicle associated with the first source data experienced an event under a specific condition;

following the generation of the event output indicating an event has occurred, establish a connection to a second sensor device that has already collected at least a portion of a second source data, the second sensor device being selected based on a corresponding accuracy output for the specific condition;

send one or more commands directing the second sensor device to provide the second source data, wherein the first sensor device is ranked highest on one of either the first ranking that is based on accuracy outputs associated with acceleration data or the second ranking that is based on accuracy outputs associated with braking data, and wherein the second sensor device is ranked highest on the other of the first ranking that is based on accuracy outputs associated with acceleration data or the second ranking that is based on accuracy outputs associated with braking data;

receive, from the second sensor device, the second source data in response to the one or more commands directing the second sensor device to provide the second source data; and

confirm, based on the second source data, the event output by comparing the first source data and the second source data.

2. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

establish a wireless connection with a geographic policy database;

send, while the wireless connection is established and after ranking the plurality of sensor devices, one or more commands directing the geographic policy database to provide an indication of whether use of the first sensor device complies with geographic policies; and

receive, while the wireless connection is established, the indication of whether use of the first sensor device complies with geographic policies.

3. The computing platform of claim 2 , wherein sending the one or more commands directing the first sensor device to provide first source data is in response to determining, based on the indication of whether the use of the first sensor device complies with geographic policies, that the first sensor device complies with geographic policies.

4. The computing platform of claim 2 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

send, while the wireless connection is established and after ranking the plurality of sensor devices, one or more commands directing the geographic policy database to provide an indication of whether use of a third sensor device complies with geographic policies, wherein the third sensor device is ranked highest on a third ranking of the one or more ranked lists, the third ranking being based on accuracy outputs associated with a data type corresponding to third source data;

receive, while the wireless connection is established, the indication of whether use of the third sensor device complies with geographic policies;

determine, based on the indication of whether use of the third sensor device complies with geographic policies, that the third sensor device is non-compliant with the geographic policies;

send, after determining that the third sensor device is non-compliant with the geographic policies, one or more commands directing the geographic policy database to provide an indication of whether use of a fourth sensor device complies with geographic policies, wherein the fourth sensor device is ranked second highest on the third ranking of the one or more ranked lists; and

send, in response to determining, based on the indication of whether the use of the fourth sensor device complies with geographic policies, that the fourth sensor device complies with geographic policies, one or more commands directing the fourth sensor device to provide the third source data.

5. The computing platform of claim 2 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

determine that event analysis should occur locally at one of the plurality of sensor devices;

rank the plurality of sensor devices based on available processing power at each of the plurality of sensor devices, resulting in a ranked list of sensor devices by processing power; and

send one or more commands to the first sensor device directing the first sensor device to determine the event output, wherein the first sensor device is a highest ranked device on the ranked list of sensor devices by processing power.

6. The computing platform of claim 2 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to determine that event analysis should occur at the computing platform.

7. The computing platform of claim 6 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to determine the event output in response to determining that the event analysis should occur at the computing platform.

8. The computing platform of claim 7 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to determine, using one or more machine learning algorithms and one or more machine learning datasets, an indication of whether the vehicle experienced the event.

9. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, further cause the computing platform to:

establish a wireless connection with an event assistance platform; and

send, while the wireless connection is established and to the event assistance platform, the event output and one or more commands directing the event assistance platform to cause display of the event output.

10. A method comprising:

at a computing platform comprising at least one processor, a communication interface, and memory:

accessing a sensor capability database to determine an accuracy output associated with each of a plurality of sensor devices for each of a plurality of data types;

ranking, for each of the plurality of data types and based on accuracy outputs associated with the plurality of data types, the plurality of sensor devices under one or more specific conditions, resulting in one or more ranked lists of the plurality of sensor devices, the one or more ranked lists comprising a first ranking of one or more of the plurality of sensor devices based on accuracy outputs associated with acceleration data, the one or more ranked lists further comprising a second ranking of one or more of the plurality of sensor devices based on accuracy outputs associated with braking data;

sending one or more commands directing a first sensor device to provide first source data;

receiving, from the first sensor device, the first source data in response to the one or more commands;

generating, based on the first source data, an event output indicating whether a vehicle associated with the first source data experienced an event under a specific condition;

following the generation of the event output indicating an event has occurred, establishing a connection to a second sensor device that has already collected at least a portion of a second source data, the second sensor device being selected based on a corresponding accuracy output for the specific condition;

sending one or more commands directing the second sensor device to provide the second source data, wherein the first sensor device is ranked highest on one of either the first ranking that is based on accuracy outputs associated with acceleration data or the second ranking that is based on accuracy outputs associated with braking data, and wherein the second sensor device is ranked highest on the other of the first ranking that is based on accuracy outputs associated with acceleration data or the second ranking that is based on accuracy outputs associated with braking data;

receiving, from the second sensor device, the second source data in response to the one or more commands directing the second sensor device to provide the second source data; and

confirming, based on the first source data and the second source data, the first source data based on comparison of the first source data and the second source data.

11. The method of claim 10 , further comprising:

establishing a wireless connection with a geographic policy database;

sending, while the wireless connection is established and after ranking the plurality of sensor devices, one or more commands directing the geographic policy database to provide an indication of whether use of the first sensor device complies with geographic policies; and

receiving, while the wireless connection is established, the indication of whether use of the first sensor device complies with geographic policies.

12. The method of claim 11 , wherein sending the one or more commands directing the first sensor device to provide first source data is in response to determining, based on the indication of whether the use of the first sensor device complies with geographic policies, that the first sensor device complies with geographic policies.

13. The method of claim 11 , further comprising:

sending, while the wireless connection is established and after ranking the plurality of sensor devices, one or more commands directing the geographic policy database to provide an indication of whether use of a third sensor device complies with geographic policies, wherein the third sensor device is ranked highest on a third ranking of the one or more ranked lists, the third ranking being based on accuracy outputs associated with a data type corresponding to third source data;

receiving, while the wireless connection is established, the indication of whether use of the third sensor device complies with geographic policies;

determining, based on the indication of whether use of the third sensor device complies with geographic policies, that the third sensor device is non-compliant with the geographic policies;

sending, after determining that the third sensor device is non-compliant with the geographic policies, one or more commands directing the geographic policy database to provide an indication of whether use of a fourth sensor device complies with geographic policies, wherein the fourth sensor device is ranked second highest on the third ranking of the one or more ranked lists; and

sending, in response to determining, based on the indication of whether the use of the fourth sensor device complies with geographic policies, that the fourth sensor device complies with geographic policies, one or more commands directing the fourth sensor device to provide the third source data.

14. The method of claim 11 , further comprising:

determining that event analysis should occur locally at one of the plurality of sensor devices;

ranking the plurality of sensor devices based on available processing power at each of the plurality of sensor devices, resulting in a ranked list of sensor devices by processing power; and

sending one or more commands to the first sensor device directing the first sensor device to determine the event output, wherein the first sensor device is a highest ranked device on the ranked list of sensor devices by processing power.

15. The method of claim 11 , further comprising determining that event analysis should occur at the computing platform.

16. The method of claim 15 , wherein the determining the event output is in response to determining that the event analysis should occur at the computing platform.

17. The method of claim 16 , wherein determining the event output comprises determining, using one or more machine learning algorithms and one or more machine learning datasets, an indication of whether the vehicle experienced an event.

18. The method of claim 10 , further comprising:

establishing a wireless connection with an event assistance platform; and

sending, while the wireless connection is established and to the event assistance platform, the event output and one or more commands directing the event assistance platform to cause display of the event output.

19. One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:

access a sensor capability database to determine an accuracy output associated with each of a plurality of sensor devices for each of a plurality of data types;

rank, for each of the plurality of data types and based on accuracy outputs associated with the plurality of data types, the plurality of sensor devices under one or more specific conditions, resulting in one or more ranked lists of the plurality of sensor devices, the one or more ranked lists comprising a first ranking of one or more of the plurality of sensor devices based on accuracy outputs associated with acceleration data, the one or more ranked lists further comprising a second ranking of one or more of the plurality of sensor devices based on accuracy outputs associated with braking data;

send one or more commands directing a first sensor device to provide first source data;

receive, from the first sensor device, the first source data in response to the one or more commands;

generate, based on the first source data, an event output indicating whether a vehicle associated with the first source data experienced an event under a specific condition;

following the generation of the event output indicating an event has occurred, establish a connection to a second sensor device that has already collected at least a portion of a second source data, the second sensor device being selected based on a corresponding accuracy output for the specific condition;

sending one or more commands directing the second sensor device to provide the second source data, wherein the first sensor device is ranked highest on one of either the first ranking that is based on accuracy outputs associated with acceleration data or the second ranking that is based on accuracy outputs associated with braking data, and wherein the second sensor device is ranked highest on the other of the first ranking that is based on accuracy outputs associated with acceleration data or the second ranking that is based on accuracy outputs associated with braking data;

receive, from the second sensor device, the first source data and the second source data; and

confirm, based on the second source data, the event output by comparing the first source data and the second source data.

20. The one or more non-transitory computer-readable media of claim 19 , wherein the non-transitory computer-readable media stores additional instructions that, when executed by the computing platform, cause the computing platform to:

establish a wireless connection with a geographic policy database;

send, while the wireless connection is established and after ranking the plurality of sensor devices, one or more commands directing the geographic policy database to provide an indication of whether use of the first sensor device complies with geographic policies; and

receive, while the wireless connection is established, the indication of whether use of the first sensor device complies with geographic policies.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 30, 2019
From: ISAAC, EMAD S.
To: ALLSTATE INSURANCE COMPANY
Reel/Frame 050858/0983 →
Continuity (1)
Related Publication 20210125423A1 · Apr 29, 2021
References Cited (34)
US 7102496B1 · Ernst, Jr. et al. · 2006 [cited by applicant]
US 7283904B2 · Benjamin et al. · 2007 [cited by applicant]
US 7284769B2 · Breed · 2007 [cited by applicant]
US 7532196B2 · Hinckley · 2009 [cited by applicant]
US 8010256B2 · Oowada · 2011 [cited by applicant]
US 8781669B1 · Teller et al. · 2014 [cited by applicant]
US 9043130B2 · Ricci · 2015 [cited by applicant]
US 9165469B2 · Bowers et al. · 2015 [cited by applicant]
US 9275093B2 · Pandey et al. · 2016 [cited by applicant]
US 9412273B2 · Ricci · 2016 [cited by applicant]
US 9701307B1 · Newman et al. · 2017 [cited by applicant]
US 9720418B2 · Stenneth · 2017 [cited by applicant]
US 10127810B2 · Durie, Jr. et al. · 2018 [cited by applicant]
US 10163350B1 · Fields et al. · 2018 [cited by applicant]
US 10360742B1 · Bellas · 2019 [cited by examiner]
US 20020105423A1 · Rast · 2002 [cited by applicant]
US 20040036261A1 · Breed · 2004 [cited by examiner]
US 20100250021A1 · Cook · 2010 [cited by examiner]
US 20120197852A1 · Dutta et al. · 2012 [cited by applicant]
US 20140163768A1 · Purdy et al. · 2014 [cited by applicant]
US 20170131716A1 · Brekke · 2017 [cited by examiner]
US 20170164158A1 · Watkins et al. · 2017 [cited by applicant]
US 20180033220A1 · Pal · 2018 [cited by examiner]
US 20190054858A1 · Pedersen · 2019 [cited by applicant]
CN 102303605A · 2012 [cited by applicant]
CN 102673561B · 2015 [cited by applicant]
CN 107609522A · 2018 [cited by applicant]
KR 101912453B1 · 2018 [cited by applicant]
WO 2018225067A1 · 2018 [cited by applicant]
Gunjan S. Sant “Study of Sensors for Automobile Safety with Automated Road Transport: a Review” International Conference on Ideas, Impact and Innovation in Mechanical Engineering (ICIIIME 2017) vol. 5 Issue 6 https://jr… [cited by applicant]
Nikos Floudas “Track Based Multi Sensor Data Fusion for Collison Mitigation” Fusion http://fusion.isif.org/proceedings/fusion08CD/papers/1569105871.pdf? website visited Oct. 29, 2019, pp. 1-8. [cited by applicant]
Raja Sekhar Rao Dheekonda et al. “Object Detection from a Vehicle using Deep Learning Network and Future Integration with Multi-Sensor Fusion Algorithm” SAE International 2017, https://scholarworks.iupui.edu/bitstream/h… [cited by applicant]
Varuna De Silva “Fusion of LiDAR and Camera Sensor Data for Environment Sensing in Driverless Vehicles” IEEE Sensors Journal https://www.semanticscholar.org/paper/Fusion-of-LiDAR-and-Camera-Sensor-Data-for-Sensing-Silva… [cited by applicant]
Jan. 22, 2021—(WO) International Search Report & Written Opinion—PCT/US20/57349. [cited by applicant]