Allstate Insurance Company

Arity International Limited

Other

Caret Holdings, Inc.

Kyle Patrick Schmitt

Pratheek M Harish

Venu Madhav Tammali

Benjamin Robertson Yeomans

Alexander Herrmann

Dana Ferguson

Dipti Karmarkar

Larry Layne

Jared S Snyder

David E Lambert

Jeremy Ber

Clayton Jeschke

Jeremy Deram

Melanie Hanna

Samantha Mait

Connor Walsh

Andrew L Carbery

Eric Campbell

Olivia Mahler-Haug

David Evan Shields

Ross Reichardt

Ronald Lettofsky

Christopher Mark Leight

Joseph Allan Plattenburg

Bennett Hansen

Rachael Rubin

Christopher Ciesielski

David Grady

Pratheek Mylanahalli Harish

Venu Tammali

Systems and methods are disclosed for determining whether or not a crash involving a vehicle has occurred. A computing device may receive acceleration measurement(s) measured by one or more accelerometers during a time window. The computing device may determine, for one or more acceleration measurements, a corresponding acceleration magnitude. Based on the corresponding acceleration magnitude(s), the computing device may identify, from the acceleration measurement(s), an acceleration measurement and/or may determine whether the acceleration magnitude exceeds a threshold acceleration magnitude. The computing device may corroborate whether a vehicle associated with the mobile computing device was involved in a crash. Data associated with the acceleration magnitude and/or an event, such as a crash event, may be transmitted to a server.

Automatic crash detection

Systems and methods in accordance with embodiments of the invention can obtain and use a variety of telematics and other data to predict potential claim or accident outcomes arising from a variety of incidents, such as automobile accidents. The claim or accident outcomes, such as parts of the vehicle damaged, accident category, expected liabilities, and many others, can be predicted based on the telematics and other data, such as accelerometer data, heading data, location/GPS, barometer, gyroscope, magnetometer data, and the like. The machine learning classifiers that can be generated are trained on historical data, consisting of claims, telematics, and/or other relevant data. In a variety of embodiments, the telematics data can be captured using a telematics device installed in the vehicle and/or via a mobile device associated with the vehicle.

Applying machine learning to telematics data to predict accident outcomes

Methods, computer-readable media, software, and apparatuses may determine, based upon edge-computing operations, that a vehicular trip has been initiated and cause one or more sensors to collect vehicle data. One or more trip segments for at least a portion of the vehicular trip may be determined. In some aspects, for each trip segment, a first plurality of time features and a second plurality of frequency features may be determined, and may be concatenated with a third plurality of GPS features to form a feature vector. An accuracy measure may be determined based on the feature vector, and a mode for the vehicle may be predicted.

Vehicle mode determination based on edge-computing

Systems and methods in accordance with embodiments of the invention can proactively determine if a vehicle has stopped during a trip and calculate a likelihood that the vehicle is in need of roadside assistance. Information can be collected from a variety of devices, such as mobile phones, including the vehicle's location, the type of road, passing vehicles, and/or ambient noise. The likelihood of needing roadside assistance can be determined based on a configurable probability that the vehicle is experiencing a roadside event. The arrangements described herein provide for receiving and processing data in real-time to efficiently and accurately detect stopped vehicles, determine whether the vehicle is stopped for an urgent or non-urgent situation reason, and provide assistance accordingly.

Roadside assistance detection

Raw sensor data from a device of a user is collected. Trips from the sensor data are identified as raw trip data. Metadata for the trips is identified, linked to the trips, and maintained separately from the trip data. The trips are staged, and the corresponding trip data normalized when obtained from a storage or memory location. Normalized trip data is piped or made accessible to feature enhancing applications (apps), each app associating one or more features and events with a given trip. The features and events are maintained for the trips in event and feature level of detail tables. The tables are processed by consuming apps for purposes of updating user-level attributes associated with the user. In an embodiment, custom apps process the raw trip data to add additional features and events, which are directly integrated and updated in the tables for access by the consuming apps.

Data features integration pipeline

Systems and methods are disclosed for receiving and transmitting accelerometer data and/or usage data, and analyzing the data to detect movement or usage of the device within a vehicle. A device, such as a mobile device, may detect a device movement event or a device usage event associated with the device. Based on the detection of the device movement event or the device usage event, a time associated with the event may be stored. The device may determine whether another event associated with the device occurs within a threshold amount of time from the time associated with the event. Based on a determination of whether the other event occurs within the threshold amount of time, the device may determine an event session associated with the device. The event session may comprise an instantaneous event or a continuous event. Data indicative of the event session may be transmitted to a server.

Detecting device movement and/or device usage within a vehicle

Aspects of the disclosure relate to computing platforms that utilize machine learning to reduce false positive/negative collision output generation. A computing platform may apply machine learning algorithms on received data to generate a collision output. In response to generating the collision output indicating a collision, the computing platform may identify a data collection location. If the data collection location is within a predetermined radius of a false positive collection location, the computing platform may modify the collision output to indicate a non-collision. If the data collection location is not within the predetermined radius, the computing platform may compute a score using telematics data and compare the score to a predetermined threshold. If the score does not exceed the predetermined threshold, the computing platform may modify the collision output to indicate a non-collision. If the score exceeds the predetermined threshold, the computing platform may affirm the collision output indicating a collision.

Collision analysis platform using machine learning to reduce generation of false collision outputs

Aspects of the disclosure relate to processing remotely captured sensor data. A computing platform having at least one processor, a communication interface, and memory may receive, via the communication interface, from a user computing device, sensor data captured by the user computing device using one or more sensors built into the user computing device. Subsequently, the computing platform may analyze the sensor data received from the user computing device by executing one or more data processing modules. Then, the computing platform may generate trip record data based on analyzing the sensor data received from the user computing device and may store the trip record data in a trip record database. In addition, the computing platform may generate user record data based on analyzing the sensor data received from the user computing device and may store the user record data in a user record database.

Distributed data processing systems for processing remotely captured sensor data

Systems, methods, computer-readable media, and apparatuses for providing hazard detection and broadcast functions are provided. In some examples, sensor data may be captured by a mobile device, vehicle, or the like. The data may be used to detect a hazard, identify a type of hazard, and the like. One or more users or groups of users for notification of the hazard may be identified and one or more notifications may be transmitted to users within the group.

Multi-computer system for dynamically detecting and identifying hazards

Distributed data processing systems for processing remotely captured sensor  data

Growing community of inventors

Chicago, IL, United States of America

Kyle Patrick Schmitt