Method and system for vehicular collision reconstruction

Patent metadata

Field	Value
Publication number	US-11928739-B2
Application number	US-202117222406-A
Country	US
Kind code	B2
Filing date	Apr 5, 2021
Priority date	Jan 22, 2020
Publication date	Mar 12, 2024
Grant date	Mar 12, 2024

Abstract

A system for accident reconstruction can include and/or be configured to interface with any or all of: a set of models, a set of modules, a processing system, client application, a user device (equivalently referred to herein as a mobile device), a set of sensors, a vehicle, and/or any other suitable components. A method for accident reconstruction includes collecting a set of inputs; detecting a collision and/or one or more features of the collision; reconstructing the collision; and producing an output based on the reconstruction. Additionally or alternatively, the method can include training a set of models and/or modules, and/or any other suitable processes.

First claim

We claim:

1. A method for the detection and reconstruction of a collision, the method comprising:
at a computing system in communication with a mobile device associated with a driver, receiving a location dataset, a motion dataset, and a pressure dataset from the mobile device;
processing the location dataset, the motion dataset, and the pressure dataset with a set of modules to determine a set of outputs, the set of outputs comprising a confidence associated with the detection of the collision;
determining a score associated with a road segment arranged proximal to a location of the collision based on the set of outputs;
assigning the score to the road segment; and
providing a route recommendation based on the score assigned to the road segment, wherein the route comprises the road segment;
further comprising implementing an emergency response based on the set of outputs.

2. The method of claim 1 , wherein the set of modules comprises a machine learning model.

3. The method of claim 2 , further comprising updating the machine learning model based on the set of outputs.

4. The method of claim 1 , wherein the set of outputs further comprises:
a severity associated with the collision; and
a direction of impact of a vehicle, wherein the driver is arranged in the vehicle.

5. The method of claim 4 , further comprising transmitting the set of outputs to an insurance entity.

6. The method of claim 5 , further comprising transmitting a set of auxiliary outputs to the insurance entity.

7. The method of claim 6 , wherein the set of auxiliary outputs comprises at least one of: a set of gravitational force equivalent values and a speed of the vehicle prior to the collision.

8. The method of claim 1 , wherein the computing system is a remote computing system.

9. A method for the detection and reconstruction of a collision, the method comprising:
at a computing system in communication with a mobile device associated with a driver, receiving a dataset from the mobile device, the dataset comprising a location dataset, a motion dataset, and a pressure dataset;
processing the set of inputs with a set of modules to determine a set of outputs, the set of outputs comprising:
a confidence associated with the detection of the collision;
a severity associated with the collision;
a direction of impact of a vehicle, wherein the driver is arranged in the vehicle; and
a fraud metric associated with the collision, wherein determining the fraud metric comprises analyzing a subset of data from the dataset, wherein the subset of data is associated with a set of time points prior to a time of the impact;
transmitting the set of outputs to an insurance entity;
further comprising implementing an emergency response based on the set of outputs.

10. The method of claim 9 , further comprising receiving a second set of inputs after the collision.

11. The method of claim 10 , further comprising updating the set of modules based on the set of outputs and the second set of inputs.

12. The method of claim 9 , wherein the emergency response is determined at least in part based on the severity.

13. The method of claim 12 , wherein the emergency response is further determined based on the confidence.

14. The method of claim 13 , wherein implementing the emergency response comprises transmitting a notification to the driver at the mobile device, wherein an emergency action is triggered based on at least one of: a response from the driver at the mobile device and a lack of a response from the driver at the mobile device.

15. The method of claim 9 , wherein the set of modules comprises a machine learning model.

16. The method of claim 15 , wherein the set of modules further comprises a rule-based model.

17. The method of claim 9 , further comprising updating a score associated with a location proximal to the collision based on the set of outputs.

18. A method for the detection and reconstruction of a collision, the method comprising:
at a computing system in communication with a mobile device associated with a driver, receiving a set of inputs from the mobile device, the set of inputs comprising at least one of:
a location dataset;
A motion dataset; and
A pressure dataset;
processing the set of inputs with a set of modules to determine a set of outputs, wherein the set of outputs comprises at least one of:
a confidence associated with the detection of the collision;
a severity associated with the collision; and
a direction of impact of a vehicle, wherein the driver is arranged in the vehicle;
transmitting, to an insurance entity, the set of outputs and a set of auxiliary outputs comprising at least one of: a set of gravitational force equivalent values and a speed of the vehicle prior to the collision;
determining a score associated with a road segment arranged proximal to a location of the collision based on the set of outputs;
assigning the score to the road segment; and
providing a route recommendation based on the score assigned to the road segment, wherein the route comprises the road segment;
further comprising implementing an emergency response based on the set of outputs.

Assignees

• Zendrive Inc

Inventors

• Salodkar Nitin Dileep
• Mudaliar Nikhil
• Pal Jayanta Kumar
• Risbood Pankaj
• Matus Jonathan

Classifications

• B60R21/013

  including means for detecting collisions, impending collisions or roll-over · CPC title

• B60R21/0132

  responsive to vehicle motion parameters {, e.g. to vehicle longitudinal or transversal deceleration or speed value} · CPC title

• B60R16/0232

  for measuring vehicle parameters and indicating critical, abnormal or dangerous conditions · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title