Distributed data processing systems for processing remotely captured sensor data

Patent metadata

Field	Value
Publication number	US-11067408-B2
Application number	US-201816028676-A
Country	US
Kind code	B2
Filing date	Jul 6, 2018
Priority date	Jul 14, 2017
Publication date	Jul 20, 2021
Grant date	Jul 20, 2021

Abstract

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.

First claim

What is claimed is:

1. A computing platform, comprising:
at least one processor;
a communication interface; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive, via the communication interface, from a first user computing device, first sensor data captured by the first user computing device using one or more sensors built into the first user computing device, wherein the first sensor data is captured by the first user computing device during a first trip in a vehicle;
analyze the first sensor data received from the first user computing device to determine a point in time at which a user of the first user computing device exited the vehicle;
based on determining the point in time at which the user of the first user computing device exited the vehicle, generate exit-point-detection data relating the point in time at which the user of the first user computing device exited the vehicle to the first sensor data received from the first user computing device;
store, in at least one database maintained by the computing platform and accessible to one or more data analysis modules associated with the computing platform, the exit-point-detection data relating the point in time at which the user of the first user computing device exited the vehicle to the first sensor data received from the first user computing device;
analyze the first sensor data received from the first user computing device to identify an end location of the first trip in the vehicle;
based on analyzing the first sensor data received from the first user computing device to identify the end location of the first trip in the vehicle, update a user-specific listing of trip-end locations;
after updating the user-specific listing of trip-end locations, receive, via the communication interface, from the first user computing device, second sensor data captured by the first user computing device using the one or more sensors built into the first user computing device, wherein the second sensor data is captured by the first user computing device during a second trip in a vehicle;
determine a distance between the end location of the first trip and a start location of the second trip;
based on the distance between the end location of the first trip and the start location of the second trip, generate driver-detection data indicative of whether the user of the first user computing device is a driver during the second trip or a passenger during the second trip; and
store, in the at least one database maintained by the computing platform and accessible to the one or more data analysis modules associated with the computing platform, the driver-detection data indicative of whether the user of the first user computing device is a driver during the second trip or a passenger during the second trip,
wherein generating the driver-detection data indicative of whether the user of the first user computing device is a driver during the second trip or a passenger during the second trip comprises:
generating data indicating that the user of the first user computing device is a driver during the second trip when the distance between the end location of the first trip and the start location of the second trip does not exceed a user-specific distance threshold; and
generating data indicating that the user of the first user computing device is a passenger during the second trip when the distance between the end location of the first trip and the start location of the second trip exceeds the user-specific distance threshold, and

wherein the user-specific distance threshold is learned by the computing platform based on information indicating end points of multiple previous trips taken by the user of the first user computing device and information indicating how closely to each end point of each previous trip of the multiple previous trips a subsequent car trip started.

2. The computing platform of claim 1 , wherein receiving the first sensor data captured by the first user computing device using the one or more sensors built into the first user computing device comprises receiving data captured by one or more of an accelerometer, a gyroscope, a magnetometer, a barometer, a gravitometer, a proximity sensor, an ambient light sensor, an ambient temperature sensor, an orientation sensor, a pedometer, an altimeter, a satellite positioning sensor, or an activity recognition sensor built into the first user computing device.

3. The computing platform of claim 1 , wherein analyzing the first sensor data received from the first user computing device to determine the point in time at which the user of the first user computing device exited the vehicle comprises using a sliding window approach to determine the point in time at which the user of the first user computing device exited the vehicle.

4. The computing platform of claim 3 , wherein using the sliding window approach to determine the point in time at which the user of the first user computing device exited the vehicle comprises:
creating a plurality of partially overlapping window frames based on the first sensor data received from the first user computing device;
calculating one or more statistical features, peak-based features, or spectral features of each window frame of the plurality of partially overlapping window frames;
correlating peak-based features identified in the plurality of partially overlapping window frames with peak profiles associated with known car-exit events; and
based on correlating the peak-based features with the peak profiles associated with the known car-exit events, identifying an onset of walking noise in the first sensor data received from the first user computing device to determine an exit point.

5. The computing platform of claim 1 , wherein analyzing the first sensor data received from the first user computing device to determine the point in time at which the user of the first user computing device exited the vehicle comprises identifying a time window in which the user of the first user computing device exited the vehicle.

6. The computing platform of claim 1 , wherein analyzing the first sensor data received from the first user computing device to determine the point in time at which the user of the first user computing device exited the vehicle comprises assigning probability values to a plurality of time windows associated with possible times at which the user of the first user computing device exited the vehicle.

7. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
based on analyzing the first sensor data received from the first user computing device to determine the point in time at which the user of the first user computing device exited the vehicle, generate a notification indicating the point in time at which the user of the first user computing device exited the vehicle; and
send, via the communication interface, to the first user computing device, the notification indicating the point in time at which the user of the first user computing device exited the vehicle, wherein sending the notification indicating the point in time at which the user of the first user computing device exited the vehicle to the first user computing device causes the first user computing device to prompt the first user associated with the first user computing device to confirm the point in time at which the user of the first user computing device exited the vehicle.

8. The computing platform of claim 1 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, caus

Assignees

• Allstate Insurance Co

Inventors

• Harish Pratheek M
• Yeomans Benjamin Robertson
• Herrmann Alexander
• Schmitt Kyle Patrick
• Karmarkar Dipti

Classifications

• H04L67/52

  specially adapted for the location of the user terminal · CPC title

• H04W4/40

  for vehicles, e.g. vehicle-to-pedestrians [V2P] · CPC title

• G01C21/3476

  using point of interest [POI] information, e.g. a route passing visible POIs · CPC title

• G06Q40/08

  Insurance · CPC title

• G06F16/22

  Indexing; Data structures therefor; Storage structures · CPC title