Patent Issued for Vehicle commute location patterns based on user location data (USPTO 11770682): Allstate Insurance Company

2023 OCT 12 (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 Alwar, Narayanan (Bloomingdale, IL, US), Chintakindi, Sunil (Naperville, IL, US), Gibson, Timothy W. (Barrington, IL, US), Stroila, Matei (Chicago, IL, US), filed on August 17, 2021, was published online on September 26, 2023.

The assignee for this patent, patent number 11770682, is Allstate Insurance Company (Northbrook, Illinois, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Location data collected using a telematics solution consists in a series of Global Positioning System (GPS) locations that describe the mobility of the user. These points can be classified as commute location data into Origin, Waypoints, and Destination. As the name implies, Origin and Destination refer to the start and end points of a trip, while the series of waypoints are the interim destinations along the route. There may be a need for identifying significant locations in mobility data, understanding the mobility behavior, and thus understanding and estimating risk in combination with a risk map.

“Aspects described herein may address these and other problems, and generally classifying destination locations and/or commute locations and inferences that can be derived from the classification to enhance risk modeling and price estimation for the insurance industry. Aspects described herein may be utilized for the insurance industry to understand a customer’s mobility risks, but may be also extendable for several other industries and applications.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “In light of the foregoing background, the following presents a simplified summary of the present disclosure in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. It is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. The following summary merely presents some concepts of the invention in a simplified form as a prelude to the more detailed description provided below.

“In some aspects, the system may comprise: a processor; a display with a user interface; and a memory unit storing computer-executable instructions. The computer-executable instruction, which when executed by the processor, may cause the system to: receive and determine commute location data that includes a plurality of trips by a user between a plurality of origins, a plurality of destinations, and a plurality of waypoints in between each of the corresponding origins and destinations; aggregate the commute location data; cluster the aggregated commute location data using one or more hierarchical cluster levels; form, by a machine learning algorithm operating on the processor, one or more location clusters into a plurality of commute locations from the aggregated commute location data and based on the one or more hierarchical cluster levels; filter, using a temporal filter, the plurality of commute locations, into one or more temporal classifications; generate a commute location map that includes a plurality of location icons; determine a risk index for the user based on the commute location map and a risk map, wherein the risk index is used for insurance pricing for the user; and display, via the user interface, the commute location map and the risk index for the user. Each of the plurality of location icons may represent each of the temporal filtered plurality of commute locations. The plurality of commute locations may be defined from the one or more location clusters.

“According to some embodiments, the commute location data may be received from one or more sensors from a mobile device for the user. The computer-executable instruction, which when executed by the processor, may also cause the system to detect and filter out noise location data from the commute location data. The noise location data may be defined as inaccuracies from the one or more sensors and the commute location data. The one or more temporal classifications may include filtering the plurality of commute locations based on a time of day window for each of the plurality of commute locations. The time of day window may include morning, day, evening, and night. The one or more temporal classifications may include filtering the plurality of commute locations based on a minimum number of visits per time period to each of the plurality of commute locations. The one or more temporal classifications may include filtering the plurality of commute locations based on a maximum time of stay at each of the plurality of commute locations. The one or more hierarchical cluster levels may include one or more of the following: a destination-based cluster level, a spatial aggregation layer cluster level, a temporal cluster level, a point of interest based cluster level, or a regional cluster level. Each of the location icons for the plurality of commute locations may include a size that is proportional to a location frequency that the user visits a specific location associated with each of the plurality of commute locations. The size may be larger when the location frequency is more frequent and the size may be smaller when the location frequency is less frequent. Each of the location icons for the plurality of commute locations may include a color that represents a distance the users are commuting to these commute locations. The color may include a first color and a second color different from the first color, with the first color defining a shorter distance to the commute location and the second color defining a longer distance to the commute location.

“Additionally, a variety of aspects described herein provide a computer-implemented method and/or one or more non-transitory computer-readable media storing instructions that, when executed by a computing device, cause the computing device to: receive and determine, by a processor operating on the computing device, commute location data; aggregate, by the processor, the commute location data; cluster, by the processor, the aggregated commute location data using one or more hierarchical cluster levels; form, by a machine learning algorithm operating on the processor, one or more location clusters into a plurality of commute locations from the aggregated commute location data and based on the one or more hierarchical cluster levels; filter, using a temporal filter, the plurality of commute locations, into one or more temporal classifications; generate, by the processor, a commute location map that includes a plurality of location icons; determine a risk index for the user based on the commute location map and a risk map; and display, by the processor via a user interface connected to the processor, the commute location map and the risk index for the user. The commute location data may be received from one or more sensors from a mobile device for the user. The commute location data may include a plurality of trips by a user between a plurality of origins, a plurality of destinations, and a plurality of waypoints in between each of the corresponding origins and destinations. The one or more temporal classifications may include one or more of: filtering the plurality of commute locations based on a time of day window for each of the plurality of commute locations, filtering the plurality of commute locations based on a minimum number of visits per time period to each of the plurality of commute locations, or filtering the plurality of commute locations based on a maximum time of stay at each of the plurality of commute locations. The one or more hierarchical cluster levels may include one or more of the following: a destination-based cluster level, a spatial aggregation layer cluster level, a temporal cluster level, a point of interest based cluster level, or a regional cluster level. Each of the plurality of location icons may represent each of the temporal filtered plurality of commute locations. The plurality of commute locations may be defined from the one or more location clusters. Each of the location icons for the plurality of commute locations may include a size that is proportional to a location frequency that the user visits a specific location associated with each of the plurality of commute locations. The size may be larger when the location frequency is more frequent and the size may be smaller when the location frequency is less frequent. The risk index may be used for insurance pricing for the user.

“The methods and systems of the above-referenced embodiments may also include other additional elements, steps, computer-executable instructions, or computer-readable data structures. In this regard, other embodiments are disclosed and claimed herein as well. The details of these and other embodiments of the present invention are set forth in the accompanying drawings and the description below. Other features and advantages of the invention will be apparent from the description, drawings, and claims. These features, along with many others, are discussed in greater detail below.”

The claims supplied by the inventors are:

“1. A system comprising: a processor; a display with a user interface; and a memory unit storing computer-executable instructions, which when executed by the processor, cause the system to: receive and determine commute location data that includes a plurality of trips by a user between a plurality of origins, a plurality of destinations, and a plurality of waypoints in between each of the plurality of origins and the plurality of destinations; aggregate the commute location data; cluster the aggregated commute location data using one or more cluster levels; form, by a machine learning algorithm operating on the processor, one or more location clusters into a plurality of commute locations from the aggregated commute location data and based on the one or more cluster levels; filter, using a temporal filter, the plurality of commute locations, into one or more temporal classifications; generate a commute location map that includes a plurality of location icons, wherein each of the plurality of location icons represents each of the temporal filtered plurality of commute locations, wherein the plurality of commute locations is defined from the one or more location clusters; determine a risk index for the user based on the commute location map and a risk map, wherein the risk index is used for insurance pricing for the user; and display, via the user interface, the commute location map and the risk index for the user.

“2. The system of claim 1, wherein the commute location data is received from one or more sensors from a mobile device for the user.

“3. The system of claim 2, wherein the memory unit storing computer-executable instructions, which when executed by the processor, further cause the system to: detect and filter out noise location data from the commute location data, wherein the noise location data is defined as inaccuracies from the one or more sensors and the commute location data.

“4. The system of claim 1, wherein the one or more temporal classifications includes filtering the plurality of commute locations based on a time of day window for each of the plurality of commute locations.

“5. The system of claim 4, wherein the time of day window includes morning, day, evening, and night.

“6. The system of claim 1, wherein the one or more temporal classifications include filtering the plurality of commute locations based on a minimum number of visits per time period to each of the plurality of commute locations.

“7. The system of claim 1, wherein the one or more temporal classifications include filtering the plurality of commute locations based on a maximum time of stay at each of the plurality of commute locations.

“8. The system of claim 1, wherein the one or more cluster levels includes hierarchical clusters levels of one or more of the following: a destination-based cluster level, a spatial aggregation layer cluster level, a temporal cluster level, a point of interest based cluster level, or a regional cluster level.

“9. The system of claim 1, wherein each of the location icons for the plurality of commute locations includes a size that is proportional to a location frequency that the user visits a specific location associated with each of the plurality of commute locations, wherein the size is larger when the location frequency is more frequent and the size is smaller when the location frequency is less frequent.

“10. The system of claim 1, wherein each of the location icons for the plurality of commute locations includes a color that represents a distance the user is commuting to these commute locations, wherein the color includes a first color and a second color different from the first color, the first color defining a shorter distance to the commute location and the second color defining a longer distance to the commute location.

“11. A computer-implemented method comprising: at a mobility pattern system: receive and determine, by a processor and a memory unit storing computer-executable instructions operating on the mobility pattern system, commute location data that includes a plurality of trips by a user between a plurality of origins, a plurality of destinations, and a plurality of waypoints in between each of the plurality of origins and the plurality of destinations, wherein the commute location data is received from one or more sensors from a mobile device for the user; aggregate, by the processor, the commute location data; detect and filter out, by the processor, noise location data from the commute location data, wherein the noise location data is defined as inaccuracies from the one or more sensors and the commute location data; cluster, by the processor, the aggregated commute location data using one or more cluster levels; form, by a machine learning algorithm operating on the processor, one or more location clusters into a plurality of commute locations from the aggregated commute location data and based on the one or more cluster levels; filter, using a temporal filter, the plurality of commute locations, into one or more temporal classifications; generate, by the processor, a commute location map that includes a plurality of location icons, wherein each of the plurality of location icons represents each of the temporal filtered plurality of commute locations, wherein the plurality of commute locations is defined from the one or more location clusters; and display, by the processor via a user interface connected to the processor, the commute location map for the user.

“12. The method of claim 11, wherein the one or more temporal classifications includes filtering the plurality of commute locations based on a time of day window for each of the plurality of commute locations, and wherein the time of day window includes morning, day, evening, and night.

“13. The method of claim 11, wherein the one or more temporal classifications include filtering the plurality of commute locations based on a minimum number of visits per month to each of the plurality of commute locations.

“14. The method of claim 11, wherein the one or more temporal classifications include filtering the plurality of commute locations based on a maximum time of stay at each of the plurality of commute locations.

“15. The method of claim 11, wherein the one or more cluster levels includes hierarchical clusters levels of one or more of the following: a destination-based cluster level, a spatial aggregation layer cluster level, a temporal cluster level, a point of interest based cluster level, or a regional cluster level.

“16. The method of claim 11, further including the step of: determine, by the processor, a risk index for the user based on the commute location map and a risk map, wherein the risk index is used for insurance pricing for the user.

“17. The method of claim 11, wherein each of the location icons for the plurality of commute locations includes one of a size or a color that represents a distance the user is commuting to these commute locations and wherein each of the location icons for the plurality of commute locations includes the other of the size or the color that is proportional to a location frequency that the user visits a specific location associated with each of the plurality of commute locations.

“18. One or more non-transitory computer-readable media storing instructions that, when executed by a computing device, cause the computing device to: receive and determine, by a processor operating on the computing device, commute location data that includes a plurality of trips by a user between a plurality of origins, a plurality of destinations, and a plurality of waypoints in between each of the plurality of origins and the plurality of destinations, wherein the commute location data is received from one or more sensors from a mobile device for the user; aggregate, by the processor, the commute location data; cluster, by the processor, the aggregated commute location data using one or more cluster levels; form, by a machine learning algorithm operating on the processor, one or more location clusters into a plurality of commute locations from the aggregated commute location data and based on the one or more cluster levels; filter, using a temporal filter, the plurality of commute locations, into one or more temporal classifications, wherein the one or more temporal classifications include one or more of: filtering the plurality of commute locations based on a time of day window for each of the plurality of commute locations, filtering the plurality of commute locations based on a minimum number of visits per month to each of the plurality of commute locations, or filtering the plurality of commute locations based on a maximum time of stay at each of the plurality of commute locations; generate, by the processor, a commute location map that includes a plurality of location icons, wherein each of the plurality of location icons represents each of the temporal filtered plurality of commute locations, wherein the plurality of commute locations is defined from the one or more location clusters; and display, by the processor via a user interface connected to the processor, the commute location map for the user.

“19. The one or more non-transitory computer-readable media storing instructions of claim 18, wherein each of the location icons for the plurality of commute locations includes one of a color or a size that represents a distance the user is commuting to these commute locations and wherein each of the location icons for the plurality of commute locations includes the other of the color or the size that is proportional to a location frequency that the user visits a specific location associated with each of the plurality of commute locations.”

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

For more information, see this patent: Alwar, Narayanan. Vehicle commute location patterns based on user location data. U.S. Patent Number 11770682, filed August 17, 2021, and published online on September 26, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11770682)&db=USPAT&type=ids

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