Patent Issued for Using contextual information for vehicle trip loss risk assessment scoring (USPTO 11856061): State Farm Mutual Automobile Insurance Company

2024 JAN 11 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States) has been issued patent number 11856061, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Black, Zebediah Robert (Wylie, TX, US), Casmedes, Corey (Plano, TX, US), Dang, Hoang (Garland, TX, US), Gao, Yuncheng (Garland, TX, US), Hargreaves, Tyler (Flower Mound, TX, US), Kirtzic, John Steven (Plano, TX, US), Li, Zongzhe (Richardson, TX, US), Longva, Einar (Manhattan, NY, US), Mao, Victor (Export, PA, US), Nemmani, Krishna (McKinney, TX, US), Nguyen, Trac (Norcross, GA, US), Panguluri, Sivarama Kirshna (McKinney, TX, US), Sherer, Dalton (Richardson, TX, US), Yang, Edward (Frisco, TX, US).

This patent was filed on October 31, 2022 and was published online on December 26, 2023.

From the background information supplied by the inventors, news correspondents obtained the following quote: “Organizations such as insurance companies have an interest in obtaining information from which they can determine insurance premiums that reward good driving habits. For example, for an automobile insurance company, demographic information of a driver (such as residence location, age, years of driving experience and moving violation history) has been used as input to loss risk assessment models. More individualized information about the driver and how she drives can help to reward good driving habits. For a driver whose activity indicates that she drives in a manner that is less likely to result in loss for the automobile insurance company, this may result in a lower automobile insurance premium for the driver than for other drivers with similar demographic attributes.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “Driver activity information alone, even when combined with demographic information, may not be sufficient for loss risk assessment and may not properly reward good driving behavior. That is, without considering the context of the environment in which the driver activity information was generated, the driver activity information may be an inaccurate indicator of loss risk. In some cases, the actual loss risk corresponding to particular driver activity may be lower and, in other cases, the actual loss risk corresponding to a particular driver activity may be higher when considering the context of the environment in which the driver activity information was generated.

“This disclosure describes, in part, techniques to develop an indication of loss risk assessment for a driving trip of a vehicle. The techniques may include, during the vehicle driving trip, observing driver activity. Identifying driver activity may include collecting data from sensors that are attached to the vehicle or are otherwise moving with the vehicle during the driving trip. The techniques may also include, during the trip, obtaining information indicative of a context of the identified driver activity, at the time and location of the identified driver activity. Such context may include, for example, environmental conditions at the time and location of the identified driver activity.

“Obtaining information indictive of environmental conditions may include, for example, obtaining information indicative of weather, traffic, and/or road work occurring at the time and location of the identified driver activity. As another example, such environmental conditions may include laws and/or regulations in place governing driving at the time and location of the observed driver activity, which may include, for example, information about a speed limit at the time and location of the observed driver activity.

“Obtaining information indicative of a context of the identified driver activity may include observing conditions at the vehicle and/or may include interrogating one or more collections of data (e.g., datastores) indicative of conditions for multiple locations throughout a geographic territory. The collections of data may be provided, for example, by one or more services that collect and provides contextual information for locations throughout a territory. Interrogating a collection of data may include, for example, accessing the information (e.g., information indicative of the context of the identified driver activity) using one or more application programming interfaces (APIs).

“The techniques may further include, during the driving trip, generating, using a computing device, event records that include an indication of identified driver activity correlated with an indication of obtained contextual information for the identified driver activity. Generating event records during a driving trip may include, for example, receiving, with a computing device, information indicative of driver activity at times/locations during the vehicle trip, and obtaining, with the computing device, information indicative of a context of the identified driver activity, at the times/locations of the observed driver activity. The computing device may collect the event records into a data set.”

The claims supplied by the inventors are:

“1. A method, comprising: receiving, at a vehicle and by a computing device comprising one or more processors, driver activity information indicative of an operation of the vehicle by a driver; receiving, by the computing device, context information indicative of an environment at a particular time and a particular location, the context information including at least one of weather conditions, traffic conditions, or construction activity at the particular location and at the particular time; determining, by the computing device and based at least in part on the particular time and the particular location, that the driver activity information is correlated with the context information; generating, by the computing device and based at least in part on determining that the driver activity information is correlated with the context information, a data set having a type of event field associated with the driver activity information, wherein the type of event field includes a first index and a second index, the first index indicating a type of driver activity and the second index indicating a subtype of the driver activity; and sending, to one or more servers, the data set, wherein the one or more servers are configured to generate a score based at least in part on the data set.

“2. The method of claim 1, wherein: the driver activity information includes speed of the vehicle at the particular location and at the particular time.

“3. The method of claim 1, further comprising: generating, by a computing device, the score, wherein generating the score includes: adjusting a speed limit threshold for the particular location based at least upon the context information, wherein the context information is indicative of the environment at the particular location; comparing the speed of the vehicle as indicated by the driver activity information to the adjusted speed limit threshold at the particular location; and generating the score at least in part based on a result of the comparing.

“4. The method of claim 1, wherein the driver activity information is received from at least one of: a sensor or a second computing device associated with the vehicle.

“5. The method of claim 1, wherein the data set comprises a plurality of data fields, individual ones of the data fields corresponding to the driver activity information, the context information, and the particular time.

“6. The method of claim 1, further comprising: requesting the context information using an application programming interface of a service provider system, wherein the context information is received from a service provider system in response to requesting the context information.

“7. The method of claim 6, wherein the service provider system is an online weather service.

“8. The method of claim 1, further comprising: generating the context information at the vehicle, based at least on a signal from a sensor used by the vehicle in operating the vehicle.

“9. The method of claim 1, further comprising: determining, by the computing device, that a particular trip has ended, wherein sending the data set is based at least in part on the determining that the particular trip has ended.

“10. The method of claim 1, wherein the first index indicates one of: (i) an acceleration/deceleration event; (ii) a speeding event; or (iii) a distracted driving event.

“11. A device, comprising: one or more processors; and memory coupled to the one or more processors, the memory storing instructions executable by the one or more processors to perform operations including: receiving driver activity information indicative of operation of a vehicle by a driver; receiving context information indicative of an environment at a particular time and a particular location, the context information including at least one of weather conditions, traffic conditions, or construction activity at the particular location and at the particular time; determining that the driver activity information is associated with the context information; generating, based at least in part on determining that the driver activity information is correlated with the context information, a data set having a type of event field associated with the driver activity information, wherein the type of event field includes a first index and a second index, the first index indicating a type of driver activity and the second index indicating a subtype of the driver activity; and sending, to one or more servers, the data set.

“12. The device of claim 11, wherein: the driver activity information includes speed of the vehicle at the particular location and at the particular time.

“13. The device of claim 11, wherein the operations further include: generating a score based at least in part on the data set; and sending the score to the one or more servers.

“14. The device of claim 11, the operations further comprising: transmitting a request for the context information from the vehicle via a network.

“15. The device of claim 11, the operations further comprising: requesting the context information using an application programming interface of a service, wherein the context information is received from a service, in response to requesting the context information.

“16. The device of claim 11, wherein the data set comprises a plurality of data fields, individual ones of the data fields corresponding to the driver activity information, the context information, and the particular time.

“17. The device of claim 11, the operations further comprising: generating the context information at the vehicle, based at least on a signal from a sensor used by the vehicle in operating the vehicle.

“18. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors of a device at a vehicle, configure the device to perform operations including: receiving driver activity information indicative of operation of the vehicle; receiving context information indicative of an environment at a particular time and a particular location, the context information including at least one of weather conditions, traffic conditions, or construction activity at the particular location and at the particular time; generating, based at least in part on determining that the driver activity information is correlated with the context information, a data set having a type of event field associated with the driver activity information, wherein the type of event field includes a first index and a second index, the first index indicating a type of driver activity and the second index indicating a subtype of the driver activity; and sending the data set to one or more servers configured to generate a score based at least in part on the data set.

“19. The one or more computer-readable media of claim 18, wherein the operations include: generating the score based at least in part on the data set; and sending the score to the one or more servers.

“20. The one or more computer-readable media of claim 18, the operations further comprising: transmitting a request for the context information from the vehicle via a network.”

For the URL and additional information on this patent, see: Black, Zebediah Robert. Using contextual information for vehicle trip loss risk assessment scoring. U.S. Patent Number 11856061, filed October 31, 2022, and published online on December 26, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11856061)&db=USPAT&type=ids

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