State Farm Mutual Automobile Insurance Company

Other

Sunish Shreenarayan Menon

Scott T Christensen

Jeffrey Wilson Stoiber

David James Dosher

Phillip Sangpil Moon

Jeffrey Kinsey

Michael Shawn Jacob

Rajiv C Shah

Erin Ann Olander

Jeffrey David Hevrin

Lucas Allen

Sripriya Sundararaman

James Dykeman

Susan M Dunham

Ellakate LeFebre

Weixin Wu

Jeremy Shawn Fogg

Bernardo Bracero

Stan E Gozur

EllaKate LeFebre

Provided herein is a damage prevention and mitigation (DPM) computing device including at least one processor in communication with a memory device. The at least one processor may be configured to identify a plurality of property parameters associated with a property wherein the property parameters are associated with one of a structure and design of the property; receive, via one or more telematics sensors, property telematics data; determine one or more damage factors associated with the property, wherein each damage factor includes an aspect of the property that increases a likelihood of the property incurring some damage; and generate a damage profile for the property based upon the determined damage factors, wherein the damage profile includes at least (a) one or more recommendations to address the damage factors and mitigate the likelihood that the property will incur damage, and (b) an insurance coverage amount for the property.

Systems and methods for property damage prevention and mitigation

Provided herein is a modeling computing device including a processor in communication with a memory device. The processor is configured to: (i) retrieve, from the at least one memory device, historical data associated with a plurality of users, wherein the historical data includes historical liability amount data and historical user data, and wherein the historical user data includes at least one of historical personal information, historical vehicle telematics data, and historical environmental data, (ii) generate a model that relates the historical liability amount data and the historical user data, (iii) store the model in the at least one memory device, (iv) collect current user data associated with a candidate user, wherein the current user data includes current personal information, current vehicle telematics data, and current environmental data, and (v) analyze the collected current user data using the generated model.

Systems and methods for modeling telematics, positioning, and environmental data

A computer implemented method for determining a primary movement window from a vehicle trip is presented. A client computing device may be placed in a vehicle, be free to move with respect to movement of the vehicle, and include an accelerometer. A computer network may receive a plurality of telematics data originating from the client computing device. One or more processors may select one or more data points from the telematics data, and determine that a total spectral power of the selected data points meets a threshold value. The one or more processors may identify a primary movement window including the selected data points if the total spectral power of the selected data points does not meet the threshold value.

System and method for identifying primary and secondary movement using spectral domain analysis

A computer implemented method for determining a primary movement window from a vehicle trip is presented. A client computing device may be placed in a vehicle, be free to move with respect to movement of the vehicle, and include an accelerometer. A computer network may receive a plurality of telematics data originating from the client computing device. One or more processors may summarize the plurality of telematics data at a specified sample rate, convert the plurality of telematics data from a time domain to a spectral domain, select one or more data points from the converted telematics data, and determine that a total spectral power of the selected data points meets a threshold value. The one or more processors may identify a first primary movement window including the selected data points if the total spectral power of the selected data points does not meet the threshold value.

A computer-implemented method for generating an automated response to a catastrophic event, that includes (1) analyzing a sample set of data generated in association with a catastrophic event to determine a threshold pattern; (2) receiving, with customer permission or affirmative consent, home sensor data from a smart home controller via wireless communication or data transmission, the home sensor data including data regarding at least one of (i) structural status; (ii) wind speed; (iii) availability of electricity; (iv) presence of water; (v) temperature; (vi) pressure; and/or (vii) presence of pollutants in the air and/or water; (3) determining, based upon or from computer analysis of the home sensor data, whether the home sensor data indicates a match to the threshold pattern; and (4) automatically generating a response if the home sensor data indicates a match to the threshold pattern. As a result, catastrophic events and responses thereto may be improved through usage of a remote network of home sensors.

Sensor data to identify catastrophe areas

A computer-implemented method for identifying a property usage type based upon sensor data includes, with customer permission or affirmative consent, receiving data generated by various sensors; generating a report that includes a listing of events recorded by each sensor; analyzing data from the report to determine a property usage type score; receiving data regarding types and levels of insurance coverage associated with the property usage type score; receiving data derived from a homeowner's insurance policy; comparing the types and levels of insurance coverage associated with the property usage type score with the types and levels of insurance coverage from the homeowner's current insurance policy; and transmitting a message to the homeowner to update their insurance policy if there are differences between (i) the insurance coverage that the homeowner has, and (ii) the insurance coverage the homeowner should have based upon the property usage type score.

Identifying property usage type based upon smart sensor data

A computer implemented method for determining one or more idling time windows from a vehicle trip is presented. A data server may receive, via a computer network, a plurality of telematics data originating from a client computing device and identify primary movement data from the plurality of telematics data. The data server may also measure a total variance from the plurality of telematics data at one or more time stamps and determine an average total variance for an entire trip from the plurality of telematics data. The data server may further normalize total variance at the one or more time stamps using the generated average and determine one or more idling time windows from the normalized total variance.

System and method for identifying idling times of a vehicle using accelerometer data

A system estimates the speed of a moving vehicle and hence the driving behavior of an individual driving the vehicle using accelerometer data. To do so, the system analyzes received accelerometer data to find idling points when the vehicle is not moving during a driving session. Based on the idling points, the system may divide the driving session into two or more segments. The system may then determine the speed of the vehicle at one or more boundary points of each segment. For each segment, the system may analyze the accelerometer data to determine the acceleration of the vehicle for points when the vehicle is moving. Subsequently, the system may calculate the speed of the vehicle for the points when the vehicle is moving based on the acceleration of the vehicle at the points when the vehicle is moving and the speed of the vehicle at the boundary points.

Systems and methods for estimating vehicle speed and hence driving behavior using accelerometer data during periods of intermittent GPS

A method and system may identify vehicle collisions in real-time or at least near real-time based on statistical data collected from previous vehicle collisions. The statistical data may be used to train a machine learning model for identifying whether a portable computing device is in a vehicle collision based on sensor data from the portable computing device. The machine learning model may be trained based on a first subset of sensor data collected from vehicle trips involved in vehicle collisions and a second subset of sensor data collected from vehicle trips not involved in vehicle collisions. When a current set of sensor data is obtained from a portable computing device in a vehicle, the current set of sensor data is compared to the machine learning model to determine whether the portable computing device is in a vehicle involved in a vehicle collision.

Growing community of inventors

Normal, IL, United States of America

Sunish Shreenarayan Menon