Patent Issued for Determining policy characteristics based on route similarity (USPTO 11330018): United Services Automobile Association
2022 MAY 26 (NewsRx) -- By a
The assignee for this patent, patent number 11330018, is
Reporters obtained the following quote from the background information supplied by the inventors: “Insurance companies gather information regarding insured parties and use such data to determine pricing for insurance policies. For example, an auto insurance company may use data regarding driver’s location, age, vehicle, driving history, or other information to determine a premium or a deductible of an auto insurance policy for the driver. Traditionally, data regarding a policy holder or a vehicle may be self-reported by policy holder, or may be reported by third parties such as repair shops, government agencies, or other drivers. Because such data may be infrequently or inconsistently reported, the data may become out-of-date over time. Accordingly, an insurance company may have difficulty developing and maintaining an accurate, current evaluation of the risk associated with insuring an individual.”
In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “Implementations of the present disclosure are generally directed to adjusting characteristic(s) of a policy based on analysis of dynamic data collected during trip(s) taken by a vehicle and/or static data associated with the trip(s). More particularly, implementations of the present disclosure are directed to determining similarity metric(s) indicating the similarity between routes taken in a vehicle, and adjusting policy characteristic(s) based on the similarity metric(s). Implementations are also directed to determining recommended route(s) based on the similarity metric(s) indicating similarity between previous trip(s) and future, or current, trip(s).
“In general, innovative aspects of the subject matter described in this specification can be embodied in methods that includes actions of: based on data collected by one or more sensors during trips by one or more vehicles, determining changes in movement of the one or more vehicles during the trips; determining a similarity metric for at least one pair of the trips that includes a first trip and a second trip, the similarity metric based at least partly on a similarity between the changes in movement during the first trip and the changes in movement during the second trip; based at least partly on the similarity metric, determining at least one characteristic of at least one policy associated with one of the one or more vehicles; and providing the at least one characteristic of the at least one policy for presentation in a user interface on a computing device.
“Implementations can include one or more of the following features: accessing risk data describing a risk of the first trip; determining a risk of the second trip based on: the risk of the first trip; and the similarity metric for the first trip and the second trip; and based at least partly on the similarity metric for the first trip and the second trip, determining the at least one characteristic of the at least one policy associated with the second trip based at least partly on the risk of the second trip; the risk data describes a history of incidents that occurred on a route corresponding to the first trip; accessing static data describing one or more of a road characteristic, a terrain characteristic, or a neighborhood characteristic of a route corresponding to the second trip; and the risk of the second trip is further based on the static data; the first trip and the second trip have different starting locations; the first trip and the second trip have different ending locations; or the first trip and the second trip have different starting locations and different ending locations; the data indicates one or more of: changes in speed of the vehicle; or changes in orientation of the vehicle; the one or more sensors include one or more of: a sensor incorporated into the vehicle; a sensor incorporated into at least one other vehicle; a sensor included in a mobile computing device of a driver of the vehicle; a sensor included in a mobile computing device of a driver of the at least one other vehicle; or an external sensor in proximity to the vehicle during at least one of the plurality of times; the at least one characteristic of the policy includes one or more of: a coverage type; a coverage amount; a deductible amount; a premium amount; or a price; the at least one policy includes one or more of: a vehicle insurance policy for a vehicle on the second trip; a life insurance policy for a driver of the vehicle; or a health insurance policy for the driver of the vehicle; the data further indicates one or more dynamic conditions present during the first trip and the second trip; the one or more dynamic conditions include one or more of: a time of day; a day of the week or month; a weather condition; a road condition; a number other vehicles; a traffic condition (e.g., an accident or absence thereof, congestion or absence thereof) independent of or dependent on a number of other vehicles in the vicinity; and/or a presence of a repair crew; and the similarity metric is further based on a similarity between the one or more dynamic conditions present during the first trip and the second trip.
“Other implementations of any of the above aspects include corresponding systems, apparatus, and computer programs that are configured to perform the actions of the methods, encoded on computer storage devices.
“Implementations of the present disclosure provide one or more of the following technical advantages and/or improvements compared to traditional systems. Dynamic sensor data describing the movement, location, condition, or other operational characteristics of a vehicle may be received and analyzed (e.g., in real time) to determine a complexity of a trip or a similarity between the trip and other trips. One or both of the complexity or similarity may be employed to (e.g., dynamically) set insurance premiums or other policy characteristics for a driver, and (e.g., dynamically) recommend routes that minimize accident risk for the driver. By employing dynamic sensor data to generate outputs such as route recommendations and/or policy characteristic determinations, implementations provide route recommendations and/or policy characteristic determinations that are more accurate and/or more up-to-date compared to traditional systems that may employ static and/or out-of-date information. Accordingly, traditional systems may need to recalculate their outputs frequently if they are to remain current and accurate, thus consuming more processing power, storage space, network capacity, active memory, and/or other computing resources compared systems according to the implementations described herein.”
The claims supplied by the inventors are:
“1. A computer-implemented method performed by at least one processor, the method comprising: obtaining driving preferences associated with a driver, wherein the driving preferences are inferences from a machine learning model analysis of the driver’s past trips; receiving data collected by a plurality of sensors during one or more trips by a vehicle along a route, the data indicating changes in movement of the vehicle during the one or more trips along the route and the plurality of sensors comprising: at least one sensor incorporated into the vehicle; and at least one external sensor in proximity to the vehicle at one or more times during the one or more trips; determining a first sequence of movements by the vehicle during the one or more trips based on changes in orientation, speed, and acceleration of the vehicle during the one or more trips; receiving data indicating a proposed trip to be taken by the vehicle, wherein the proposed trip has a starting location or an ending location that is different from a respective starting location or ending location of the route; identifying at least a first candidate route for the proposed trip and a second candidate route for the proposed trip; determining a first similarity metric between the first candidate route and the one or more trips, the first similarity metric indicating a similarity in a sequence of expected vehicle movements along the first candidate route with the first sequence of movements during the one or more trips; determining a second similarity metric between the second candidate route and the one or more trips, the second similarity metric indicating a similarity in a sequence of expected vehicle movements along the second candidate route with the first sequence of movements during the one or more trips, wherein the first candidate route and the second candidate route incorporate the driving preferences; selecting, based on the first similarity metric and the second similarity metric, the first route as a recommended route for the proposed trip; and providing the recommended route for presentation in a navigation interface of a computing device.
“2. The method of claim 1, wherein selecting the first candidate route as the recommended route for the proposed trip comprises determining that the first similarity metric is greater than the second similarity metric.
“3. The method of claim 1, wherein both the starting location and ending location of the proposed trip are different from the respective starting location and ending location of the route.
“4. The method of claim 1, wherein the proposed trip is for a driver that is different than one or more other drivers of the one or more trips.
“5. The method of claim 1, wherein the proposed trip is for a vehicle that is different than the one or more vehicles of the one or more trips.
“6. The method of claim 1 further comprising receiving user input indicating preferences for the proposed trip, and wherein the first candidate route and the second candidate route incorporate the preferences.
“7. The method of claim 6, wherein the preferences include one or more of a driver-indicated waypoint for the proposed trip or a request to avoid a location.
“8. The method of claim 1 further comprising obtaining route data indicating one or more of road conditions along the first candidate route and the second candidate route, traffic conditions along the first candidate route and the second candidate route, and weather conditions along the first candidate route and the second candidate route, and wherein the recommended route is selected based on the first similarity metric, the second similarity metric, and the route data.
“9. A system comprising: at least one processor; and a memory communicatively coupled to the at least one processor, the memory storing instructions which, when executed, cause the at least one processor to perform operations comprising: obtaining driving preferences associated with a driver, wherein the driving preferences are inferences from a machine learning model analysis of the driver’s past trips; receiving data collected by a plurality of sensors during one or more trips by a vehicle along a route, the data indicating changes in movement of the vehicle during the one or more trips along the route and the plurality of sensors comprising: at least one sensor incorporated into the vehicle; and at least one external sensor in proximity to the vehicle at one or more times during the one or more trips; determining a first sequence of movements by the vehicle during the one or more trips based on changes in orientation, speed, and acceleration of the vehicle during the one or more trips; receiving data indicating a proposed trip to be taken by the vehicle, wherein the proposed trip has a starting location or an ending location that is different from a respective starting location or ending location of the route; identifying at least a first candidate route for the proposed trip and a second candidate route for the proposed trip; determining a first similarity metric between the first candidate route and the one or more trips, the first similarity metric indicating a similarity in a sequence of expected vehicle movements along the first candidate route with the first sequence of movements during the one or more trips; determining a second similarity metric between the second candidate route and the one or more trips, the second similarity metric indicating a similarity in a sequence of expected vehicle movements along the second candidate route with the first sequence of movements during the one or more trips, wherein the first candidate route and the second candidate route incorporate the driving preferences; selecting, based on the first similarity metric and the second similarity metric, the first route as a recommended route for the proposed trip; and providing the recommended route for presentation in a navigation interface of a computing device.
“10. The system of claim 9, wherein selecting the first candidate route as the recommended route for the proposed trip comprises determining that the first similarity metric is greater than the second similarity metric.
“11. The system of claim 9 further comprising receiving user input indicating preferences for the proposed trip, and wherein the first candidate route and the second candidate route incorporate the preferences.
“12. The system of claim 11, wherein the preferences include one or more of a driver-indicated waypoint for the proposed trip or a request to avoid a location.
“13. The system of claim 9 further comprising obtaining route data indicating one or more of road conditions along the first candidate route and the second candidate route, traffic conditions along the first candidate route and the second candidate route, and weather conditions along the first candidate route and the second candidate route, and wherein the recommended route is selected based on the first similarity metric, the second similarity metric, and the route data.
“14. One or more non-transitory computer-readable storage media storing instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising: obtaining driving preferences associated with a driver, wherein the driving preferences are inferences from a machine learning model analysis of the driver’s past trips; receiving data collected by a plurality of sensors during one or more trips by a vehicle along a route, the data indicating changes in movement of the vehicle during the one or more trips along the route and the plurality of sensors comprising: at least one sensor incorporated into the vehicle; and at least one external sensor in proximity to the vehicle at one or more times during the one or more trips; determining a first sequence of movements by the vehicle during the one or more trips based on changes in orientation, speed, and acceleration of the vehicle during the one or more trips; receiving data indicating a proposed trip to be taken by the vehicle, wherein the proposed trip has a starting location or an ending location that is different from a respective starting location or ending location of the route; identifying at least a first candidate route for the proposed trip and a second candidate route for the proposed trip; determining a first similarity metric between the first candidate route and the one or more trips, the first similarity metric indicating a similarity in a sequence of expected vehicle movements along the first candidate route with the first sequence of movements during the one or more trips; determining a second similarity metric between the second candidate route and the one or more trips, the second similarity metric indicating a similarity in a sequence of expected vehicle movements along the second candidate route with the first sequence of movements during the one or more trips, wherein the first candidate route and the second candidate route incorporate the driving preferences; selecting, based on the first similarity metric and the second similarity metric, the first route as a recommended route for the proposed trip; and providing the recommended route for presentation in a navigation interface of a computing device.
“15. The media of claim 14, wherein selecting the first candidate route as the recommended route for the proposed trip comprises determining that the first similarity metric is greater than the second similarity metric.
“16. The media of claim 14 further comprising receiving user input indicating preferences for the proposed trip, wherein the preferences include one or more of a driver-indicated waypoint for the proposed trip or a request to avoid a location, and wherein the first candidate route and the second candidate route incorporate the preferences.”
There are additional claims. Please visit full patent to read further.
For more information, see this patent:
(Our reports deliver fact-based news of research and discoveries from around the world.)
Florida lawmakers leave lots of unfinished business on property insurance reforms [Orlando Sentinel]
Studies from Deakin University in the Area of Civil Engineering Reported (An Analysis of Quality Liability Insurance for Prefabricated Components Using Evolutionary Game Theory): Engineering – Civil Engineering
Advisor News
- Year-end planning errors retirees should avoid
- Social cultivation: How to talk with wealthy prospects
- How important is a written financial plan?
- Coalition wants to advise people impacted by policy changes in new administration
- Diagnosing miscommunication in retirement planning
More Advisor NewsAnnuity News
Health/Employee Benefits News
- Data on Managed Care Reported by Researchers at Duke University Hospital (Assessment of Embedded Versus Remote Pharmacist Versus Remote Student Pharmacist Outreach On Statin Prescribing): Managed Care
- What your generation needs to know
- Studies in the Area of Human Papillomavirus Vaccines Reported from University of Connecticut (Accountable Care Organizations and Hpv Vaccine Uptake: a Multilevel Analysis): Immunization and Public Health – Human Papillomavirus Vaccines
- New attempt made to drop circumcision from Medicaid coverage in NH
- National Health Insurance Service Ilsan Hospital Reports Findings in Pneumothorax (Impact of Deep Learning-Based Computer-Aided Detection and Electronic Notification System for Pneumothorax on Time to Treatment: Clinical Implementation): Respiratory Tract Diseases and Conditions – Pneumothorax
More Health/Employee Benefits NewsLife Insurance News