Patent Issued for Machine learning based accident assessment (USPTO 11720971): Allstate Insurance Company

2023 AUG 30 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Kelsh, John P. (Antioch, IL, US), Marlow, Clint J. (Barrington Hills, IL, US), filed on February 3, 2021, was published online on August 8, 2023.

The assignee for this patent, patent number 11720971, is Allstate Insurance Company (Northbrook, Illinois, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “In some instances, an incident and/or accident may cause damage to a vehicle. The timely determination of the extent of the damages to the vehicle (e.g., whether the accident resulted in a total loss of the vehicle) may be paramount in ensuring the safety of those affected by the incident and/or accident, as well the integrity of the property or vehicle involved. In conventional accident assessment systems, however, an inspection is required to determine the extent of damages to a vehicle after an accident, which is dependent on the availability of the inspector, and can result in owners driving vehicles unfit for operation.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “Aspects of the disclosure address these and/or other technological shortcomings by using machine learning algorithms to assess vehicle operational data associated with a vehicle accident. In particular, one or more aspects of the disclosure provide effective, efficient, scalable, and convenient technical solutions that address and overcome the technical problems associated with accident assessment systems. For example, one or more aspects of the disclosure provide techniques for using machine learning algorithms to identify whether an accident resulted in a total loss.

“In accordance with one or more embodiments, an accident assessment server having at least one processor, communication interface and memory, may receive, via the communication interface, from a telematics device associated with a vehicle, data indicating that the vehicle was involved in an accident. The accident assessment server may compare, via machine learning algorithms, the received data with other known data to identify whether the accident resulted in a total loss. Responsive to determining that the accident resulted in the total loss, the accident assessment server may request, by the communication interface, further information regarding the vehicle from the telematics device. The accident assessment server may identify, based on the received data and further data, a baseline value range for the vehicle. The accident assessment server may request, by the communication interface, from a mobile device associated with an owner of the vehicle, updated information regarding the vehicle. The accident assessment server may receive, by the communication interface, updated information from the mobile device of the owner of the vehicle. The accident assessment server may identify, based on the updated information, a final value of the vehicle.

“In some embodiments, responsive to determining that the final value of the vehicle is within the baseline value range of the vehicle, the accident assessment server may provide payment to the owner corresponding to the final value of the vehicle.

“In some embodiments, the updated information includes one or more of exact mileage, presence of aftermarket parts (e.g., parts or materials purchased and/or installed on a vehicle after manufacture of the vehicle and purchase by a user), and vehicle specification information associated with the vehicle and the received data indicating that the vehicle was involved in the accident includes one or more of an indication of airbag deployment, an indication of vehicle impact, a deceleration value above a first predetermined threshold, and a braking force value above a second predetermined threshold.

“In some embodiments, to compare the received data with the other known data to identify whether the accident resulted in the total loss, the accident assessment server may identify, based on the received data, a make, model, and year associated with the vehicle involved in the accident. The accident assessment server may sort one or more databases based on the make model and year associated with the vehicle and compare, via the machine learning algorithms, other known data associated with one or more vehicles of the make, model, and year corresponding to the vehicle.”

The claims supplied by the inventors are:

“1. An accident assessment server, 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 accident assessment server to: receive vehicle operational data from a telematics device associated with a vehicle; determine, from the operational data, if the vehicle was involved in an accident; determine, by machine learning algorithms, based on comparing historical accident data with data received from the telematics device associated with the vehicle, that the accident resulted in a total loss; and responsive to determining that the accident resulted in the total loss: request further information associated with a baseline monetary value range for the vehicle; determine, based on receiving the further information from the telematics device, the baseline monetary value range for the vehicle; request updated information associated with the vehicle; determine, by a loss determination model, based on receiving the updated information regarding the vehicle from a device associated with an owner of the vehicle, a final monetary value of the vehicle; and determine, based on whether the final monetary value of the vehicle is within in the baseline monetary value range for the vehicle, whether to provide payment to the owner of the vehicle.

“2. The accident assessment server of claim 1, wherein the instructions, when executed by the at least one processor, further cause the accident assessment server to: responsive to determining that the final monetary value of the vehicle is within the baseline monetary value range of the vehicle, provide the payment to the owner, wherein the payment corresponds to the final monetary value of the vehicle.

“3. The accident assessment server of claim 1, wherein the data received from the telematics device comprises one or more of: an indication of airbag deployment, an indication of vehicle impact, a deceleration value above a first predetermined threshold, and a braking force value above a second predetermined threshold, and wherein the updated information comprises one or more of: mileage, presence of aftermarket parts, and vehicle specification information associated with the vehicle.

“4. The accident assessment server of claim 1, wherein the data received from the telematics device comprise a make, model, and year of the vehicle, and wherein the instructions, when executed by the at least one processor, further cause the accident assessment server to compare the historical accident data with the data received from the telematics device by: querying a database for historical accidents associated with one or more vehicles of the make, model, and year of the vehicle; and comparing the data received from the telematics device with the historical accidents associated with the one or more vehicles of the make, model, and year of the vehicle.

“5. The accident assessment server of claim 1, wherein the instructions, when executed by the at least one processor, further cause the accident assessment server to: receive, from one or more databases storing information associated with the vehicle, the further information, wherein the one or more databases comprise at least one of: a vehicle identification number (VIN) database, a used car listing database, a vehicle history database, a vehicle maintenance history database, a state department of motor vehicle database, and an insurance claims database.

“6. The accident assessment server of claim 1, wherein the instructions, when executed by the at least one processor, further cause the accident assessment server to: schedule, responsive to determining that the final monetary value of the vehicle is outside of the baseline monetary value range of the vehicle, a vehicle inspection appointment with the owner of the vehicle.

“7. The accident assessment server of claim 6, wherein the instructions, when executed by the at least one processor, further cause the accident assessment server to: transmit, to the device of the owner of the vehicle, a scheduling request for the vehicle inspection appointment.

“8. A method, comprising: receiving vehicle operational data from a telematics device associated with a vehicle; determining, from the operational data, if the vehicle was involved in an accident; determining, by machine learning algorithms and by a computing device, and based on comparing historical accident data with the operational data received from the telematics device associated with the vehicle, that the accident resulted in a total loss; and responsive to determining that the accident resulted in a total loss: requesting further information associated with a baseline monetary value range for the vehicle; determining, based on receiving the further information from the telematics device, the baseline monetary value range for the vehicle; requesting updated information associated with the vehicle; determining, by a loss determination model, based on receiving the updated information regarding the vehicle from a device associated with an owner of the vehicle, a final monetary value of the vehicle; and determining, based on whether the final monetary value of the vehicle is within the baseline monetary value range for the vehicle, whether to provide payment to the owner of the vehicle.

“9. The method of claim 8, further comprising: providing, by the computing device and responsive to determining that the final monetary value of the vehicle is within the baseline monetary value range of the vehicle, the payment to the owner, wherein the payment corresponds to the final monetary value of the vehicle.

“10. The method of claim 8, wherein the updated information comprises one or more of: mileage, presence of aftermarket parts, and vehicle specification information associated with the vehicle.

“11. The method of claim 8, wherein the data received from the telematics device comprises one or more of: an indication of airbag deployment, an indication of vehicle impact, a deceleration value above a first predetermined threshold, and a braking force value above a second predetermined threshold.

“12. The method of claim 8, wherein the data received from the telematics device comprise a make, model, and year of the vehicle, and wherein comparing the historical accident data with the data received from the telematics device comprises: querying a database for historical accidents associated with one or more vehicles of the make, model, and year of the vehicle; and comparing the data received from the telematics device with the historical accidents associated with the one or more vehicles of the make, model, and year of the vehicle.

“13. The method of claim 8, the method further comprising: receiving, from one or more databases storing information associated with the vehicle, the further information, wherein the one or more databases comprise at least one of: a vehicle identification number (VIN) database, a used car listing database, a vehicle history database, a vehicle maintenance history database, a state department of motor vehicle database, and an insurance claims database.

“14. The method of claim 8, further comprising: scheduling, by the computing device and responsive to determining that the final monetary value of the vehicle is outside of the baseline monetary value range of the vehicle, a vehicle inspection appointment with the owner of the vehicle.

“15. The method of claim 14, further comprising: transmitting, to the device of the owner of the vehicle, a scheduling request for the vehicle inspection appointment.

“16. One or more non-transitory, computer-readable media storing instructions that, when executed by at least one processor, cause a computing device to: receive vehicle operational data from a telematics device associated with a vehicle; determine, from the operational data, if the vehicle was involved in an accident; determine, by machine learning algorithms, based on comparing historical accident data with data received from the telematics device associated with the vehicle, that the vehicle was involved in an accident resulted in a total loss; and responsive to determining that the accident resulted in the total loss: request further information associated with a baseline monetary value range for the vehicle; determine, based on receiving the further information from the telematics device, the baseline monetary value range for the vehicle; request updated information associated with the vehicle; determine, by a loss determination model, based on receiving the updated information regarding the vehicle from a device associated with an owner of the vehicle, a final monetary value of the vehicle; and determine, based on whether the final monetary value of the vehicle is within in the baseline monetary value range for the vehicle, whether to provide payment to the owner of the vehicle.

“17. The one or more non-transitory, computer-readable media of claim 16, wherein the instructions, when executed at least one processor, cause the computing device to: responsive to determining that the final monetary value of the vehicle is within the baseline monetary value range of the vehicle, provide the payment to the owner of the vehicle, wherein the payment corresponds to the final monetary value of the vehicle.”

There are additional claims. Please visit full patent to read further.

For more information, see this patent: Kelsh, John P. Machine learning based accident assessment. U.S. Patent Number 11720971, filed February 3, 2021, and published online on August 8, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11720971)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)