Patent Issued for Vehicle mobility patterns based on user location data (USPTO 11800323): Allstate Insurance Company
2023 NOV 15 (NewsRx) -- By a
Patent number 11800323 is assigned to
The following quote was obtained by the news editors from the background information supplied by the inventors: “In today’s connected world, location data is instrumental to offering a variety of services to consumers. The location data from consumers is used in a wide variety of ways to offer services that are relevant to that industry. Some of the services include real time location-based services, navigation services, safety alerts and location-based advertising.
“Aspects described herein may address these and other problems, and generally building and quantifying mobility patterns based on user location data, specifically defining a mobility region of a user or collection of users derived from the origins and destinations of their travel over a period. Aspects described herein may be utilized for the insurance industry to understand customer’s mobility region and the associated risks, but may be also extendable for several other industries and applications.”
In addition to the background information obtained for this patent, NewsRx journalists 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 include a system comprising: 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 location data that includes a plurality of trips by a user between a plurality of origins and a plurality of destinations; aggregate the location data; cluster the aggregated 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 nodes from the aggregated location data and based on the one or more hierarchical cluster levels; generate a region of mobility based on the mobility graph; and display, via the user interface, the region of mobility for the user. The mobility graph may include the plurality of nodes and a plurality of edges. The plurality of nodes may be defined from the one or more location clusters. The plurality of edges may be defined by each of the plurality of trips between one of the plurality of origins and one of the plurality of destinations. The region of mobility may be a homogeneous spatial region based on a specific location included with the plurality of nodes and the plurality of edges that meet a location criteria.
“According to some embodiments, the 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 cause the system to: detect and filter one or more noise location data from the aggregated location data based on environmental noise and inaccuracies from the location data. 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 nodes may include a node size that defines a location frequency that the user visits a specific location associated with each of the plurality of nodes. The node size may be larger when the location frequency is more frequent and the node size may be smaller when the location frequency is less frequent. The plurality of edges may include an edge weight based on a trip frequency. The edge weight may be larger when the trip frequency is more frequent and the edge weight may be smaller when the trip frequency is less frequent. The location criteria may include one or more of: a frequency of visit, a time of visit, a length of stay at each specific location, or a type of location visited. The region of mobility may be a home mobility region defined as the region of mobility around a home location of the user. The region of mobility may be a work mobility region defined as the region of mobility around a work location of the user. The region of mobility may be a point of interest mobility region defined as the region of mobility around a specific point of interest for the user. The computer-executable instruction, which when executed by the processor, may cause the system to: determine a risk index for the user based on the region of mobility of the user, wherein the risk index is used for insurance pricing for the user.
“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, location data that includes a plurality of trips by a user between a plurality of origins and a plurality of destinations; aggregate, by the processor, the location data; detect and filter, by the processor, noise location data from the aggregated location data, wherein the noise location data comprises environmental noise data and inaccuracies from the location data; cluster, by the processor, the aggregated 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 nodes from the aggregated location data and based on the one or more hierarchical cluster levels; generate, by the processor, a mobility graph; generate, by the processor, a region of mobility based on the mobility graph; determine, by the processor, a risk index for the user based on the region of mobility of the user; and display, by the processor via a user interface connected to the processor, the region of mobility and the risk index for the user. The location data may be received from one or more sensors from a mobile device for the user. 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. The mobility graph may include the plurality of nodes and a plurality of edges. The plurality of nodes may be defined from the one or more location clusters. The plurality of edges may be defined by each of the plurality of trips between one of the plurality of origins and one of the plurality of destinations. Each of the plurality of nodes may include a node weight that defines a location frequency that the user visits a specific location associated with each of the plurality of nodes. The node weight may be larger when the location frequency is more frequent and the node weight may be smaller when the location frequency is less frequent. Each of the plurality of edges may include an edge weight based on a trip frequency. The edge weight may be larger when the trip frequency is more frequent and the edge weight may be smaller when the trip frequency is less frequent. The region of mobility may be defined as a convex hull of the plurality of nodes with the node weight above a node threshold and the plurality of edges with the edge weight above an edge threshold. 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 location data that includes a plurality of trips by a user between a plurality of origins and a plurality of destinations; aggregate the location data; cluster the aggregated 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 nodes from the aggregated location data and based on the one or more cluster levels; generate a mobility graph that includes the plurality of nodes and a plurality of edges, wherein the plurality of nodes is defined from the one or more location clusters, and the plurality of edges is defined by each of the plurality of trips between one of the plurality of origins and one of the plurality of destinations; generate a region of mobility based on the mobility graph, wherein the region of mobility is a spatial region based on a specific location included with the plurality of nodes and the plurality of edges that meet a location criteria; and display, via the user interface, the plurality of nodes and the plurality of edges, the plurality of nodes having displayed sizes corresponding to location frequencies for the plurality of nodes, and the plurality of edges having displayed edge weights corresponding to trip frequencies between nodes defining the plurality of edges.
“2. The system of claim 1, wherein the location data is received from one or more sensors from a mobile device for the user.
“3. The system of claim 1, wherein the memory unit storing computer-executable instructions, which when executed by the processor, further cause the system to: detect and filter one or more noise location data from the aggregated location data based on environmental noise and inaccuracies from the location data.
“4. The system of claim 1, wherein the one or more cluster levels includes at least one of: 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.
“5. The system of claim 1, wherein each of the plurality of nodes includes a node size that defines a location frequency that the user visits each specific location, wherein the node size is larger when the location frequency is more frequent and the node size is smaller when the location frequency is less frequent.
“6. The system of claim 1, wherein the plurality of edges includes an edge weight based on a trip frequency, wherein the edge weight is larger when the trip frequency is more frequent and the edge weight is smaller when the trip frequency is less frequent.
“7. The system of claim 1, wherein the location criteria includes one or more of: a frequency of visit, a time of visit, a length of stay at each specific location, or a type of location visited.
“8. The system of claim 1, wherein the region of mobility is a home mobility region defined as the region of mobility around a home location of the user.
“9. The system of claim 1, wherein the region of mobility is a work mobility region defined as the region of mobility around a work location of the user.
“10. The system of claim 1, wherein the region of mobility is a point of interest mobility region defined as the region of mobility around a specific point of interest for the user.
“11. The system of claim 1, wherein the memory unit storing computer-executable instructions, which when executed by the processor, further cause the system to: determine a risk index for the user based on the region of mobility of the user, wherein the risk index is used for insurance pricing for the user.
“12. A computer-implemented method comprising: at a mobility region system: receive, by a processor and a memory unit storing computer-executable instructions operating on the mobility region system, location data that includes a plurality of trips by a user between a plurality of origins and a plurality of destinations; aggregate, by the processor, the location data; detect and filter, by the processor, noise location data from the aggregated location data, wherein the noise location data comprises environmental noise data and inaccuracies from the location data; cluster, by the processor, the aggregated 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 nodes from the aggregated location data and based on the one or more cluster levels; generate, by the processor, a mobility graph that includes the plurality of nodes and a plurality of edges, wherein the plurality of nodes is defined from the one or more location clusters, and the plurality of edges is defined by each of the plurality of trips between one of the plurality of origins and one of the plurality of destinations; generate, by the processor, a region of mobility based on the mobility graph, wherein the region of mobility is a spatial region based on a specific location included with the plurality of nodes and the plurality of edges that meet a location criteria; and display, by the processor via a user interface connected to the processor, the plurality of nodes and the plurality of edges, the plurality of nodes having displayed sizes corresponding to location frequencies for the plurality of nodes.
“13. The method of claim 12, wherein the location data is received from one or more sensors from a mobile device for the user.
“14. The method of claim 12, wherein each of the plurality of nodes includes a node size that defines a location frequency that the user visits each specific location, wherein the node size is larger when the location frequency is more frequent and the node size is smaller when the location frequency is less frequent, and further wherein each of the plurality of edges includes an edge weight based on a trip frequency, wherein the edge weight is larger when the trip frequency is more frequent and the edge weight is smaller when the trip frequency is less frequent.
“15. The method of claim 12, wherein the location criteria comprises one or more of: a frequency of visit, a time of visit, a length of stay at each specific location, or a type of location visited.
“16. The method of claim 12, wherein the region of mobility includes at least one of: a home mobility region defined as the region of mobility around a home location of the user; a work mobility region defined as the region of mobility around a work location of the user; or a point of interest mobility region defined as the region of mobility around a specific point of interest for the user.
“17. The method of claim 12, further including the step of: determine, by the processor, a risk index for the user based on the region of mobility of the user.
“18. One or more non-transitory computer-readable media storing instructions that, when executed by a computing device, cause the computing device to: receive, by a processor operating on the computing device, location data that includes a plurality of trips by a user between a plurality of origins and a plurality of destinations; aggregate, by the processor, the location data; detect and filter, by the processor, noise location data from the aggregated location data, wherein the noise location data comprises environmental noise data and inaccuracies from the location data; cluster, by the processor, the aggregated 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 nodes from the aggregated location data and based on the one or more cluster levels; generate, by the processor, a mobility graph that includes the plurality of nodes and a plurality of edges, wherein the plurality of nodes is defined from the one or more location clusters, and the plurality of edges is defined by each of the plurality of trips between one of the plurality of origins and one of the plurality of destinations; generate, by the processor, a region of mobility based on the mobility graph; and display, by the processor via a user interface connected to the processor, the plurality of nodes and the plurality of edges, the plurality of edges having presented edge weights corresponding to trip frequencies between nodes defining the plurality of edges.
“19. The one or more non-transitory computer-readable media storing instructions of claim 18, wherein the region of mobility is one of: a home mobility region defined as the region of mobility around a home location of the user; a work mobility region defined as the region of mobility around a work location of the user; or a point of interest mobility region defined as the region of mobility around a specific point of interest for the user.
“20. The one or more non-transitory computer-readable media storing instructions of claim 18, wherein the region of mobility is based on location criteria that includes one or more of: a frequency of visit, a time of visit, a length of stay at a specific location, or a type of location visited.”
URL and more information on this patent, see: Alwar, Narayanan. Vehicle mobility patterns based on user location data.
(Our reports deliver fact-based news of research and discoveries from around the world.)
Study Results from University of Southern California (USC) Update Understanding of Otolaryngology (Association of Ethnicity and Time To Surgery Among Patients With Chronic Rhinosinusitis): Health and Medicine – Otolaryngology
“Self-Quoting System For Life Contingent And Guaranteed Future Payments” in Patent Application Approval Process (USPTO 20230342856): Patent Application
Advisor News
- Wealth management: why some insurance companies are opting out of a lucrative opportunity
- Middle-income households exceeding retirement savings expectations
- How SECURE impacts inherited IRA beneficiaries
- 62% of workers face serious financial anxieties
- Nearly half of retirees lack a structured decumulation strategy
More Advisor NewsAnnuity News
Health/Employee Benefits News
- Harbin Medical University Reports Findings in Hip Fracture (Conjoint effect of post-discharge physical exercise and co-managed care on health outcomes of older patients with hip fracture in China: A post-hoc factorial analysis): Hip Fracture
- Elizabeth Warren on UnitedHealthcare CEO assassination: ‘People can only be pushed so far’
- Millions will see rise in health insurance premiums if federal subsidies expire
- Festive event educates residents on health plans and privacy protections
- Are partnerships the answer to the long-term care crisis?
More Health/Employee Benefits NewsLife Insurance News