公开(公告)号：US20240157934A1

公开(公告)日：2024-05-16

申请号：US18499707

申请日：2023-11-01

Applicant: Geotab Inc.

Inventor： Xin Zhang ,  Gregory Gordon Douglas Hines ,  Jiawei Yu ,  Willem Petersen ,  Tuhin Tiwari ,  Meenakshi Sundaram Murugesan ,  Javed Siddique ,  Jason Jiajie Yan ,  Narasimha Rao Durgam ,  Li Zhang

IPC: B60W30/095 ,  G07C5/00

CPC classification number: B60W30/0953 ,  G07C5/008

Abstract: Systems and methods for generating vehicle safety scores and vehicle collision probabilities are provided. The methods involve operating at least one processor to: retrieve vehicle data originating from a telematics device installed in a vehicle, the vehicle data including a plurality of safety exception events performed by the vehicle; determine a plurality of exception rates based on the vehicle data, each exception rate representing a normalized rate of occurrence of one of the exception event types; determine plurality of collision sub-probabilities using a plurality of collision probability models and the plurality of exception rates, each collision probability model associated with one of the exception event types and operable to predict one of the collision sub-probabilities based on one of the exception rates of the associated exception event type; and determine a collision probability for the vehicle based on the plurality of collision sub-probabilities.

公开(公告)号：US20230143809A1

公开(公告)日：2023-05-11

申请号：US17714570

申请日：2022-04-06

Applicant: Geotab Inc.

Inventor： William John Ballantyne ,  Javed Siddique

IPC: G06K9/62 ,  G05B13/02

CPC classification number: G06K9/6256 ,  G05B13/0265

Abstract: Systems and methods by a telematics server are provided. The method includes receiving, over a network, training data including model input data and a known output label corresponding to the model input data from a first device, training a centralized machine-learning model using the training data, determining, by the centralized machine-learning model, an output label prediction certainty based on the model input data, determining an increase in the output label prediction certainty over a prior predicted output label certainty of the centralized machine-learning model, and sending, over the network, a machine-learning model update to a second device in response to determining that the increase in the output label prediction certainty is greater than an output label prediction increase threshold.

公开(公告)号：US11530961B2

公开(公告)日：2022-12-20

申请号：US16878849

申请日：2020-05-20

Applicant: GEOTAB INC.

Inventor： Javed Siddique ,  Robert Bradley ,  Xiaochen Zhang

IPC: G01M17/007 ,  G07C5/08 ,  G06N20/00 ,  G01S19/42 ,  G08G1/00 ,  H04W4/029 ,  G06K9/62 ,  G07C5/00 ,  G07C5/02

Abstract: System for automatically classifying vehicle vocation and benchmarking vehicle performance relative to other vehicles having the same vocation classification, independent of vehicle fleet groupings, industry vehicle application groupings and vehicle type groupings, is disclosed. The system includes a vehicle vocation classifier in communication with a data management system to store historical vehicle data including recurring vehicle usage data, and assign one or more predicted vocations for each vehicle based on the recurring vehicle usage data using a machine learning technique. The system also includes a benchmarking management system for grouping the historical vehicle data for vehicles of same determined predicted vocation, determining therefrom benchmarking vehicles having better performance characteristics than other vehicles of the same determined predicted vocation, and benchmarking performance of the other predicted vocation vehicles relative to the benchmarking vehicles.

公开(公告)号：US10928277B1

公开(公告)日：2021-02-23

申请号：US16894673

申请日：2020-06-05

Applicant: Geotab Inc.

Inventor： Javed Siddique ,  Robert Bradley ,  Xiaochen Zhang

IPC: G06F11/30 ,  G01M17/007 ,  G06N20/00 ,  G07C5/08

Abstract: Automatic classifying vehicles by vocation and benchmarking vehicle performance relative to other vehicles of the same vocation are disclosed. Vehicles having a same vocation relative to each other and independent of vehicle fleet, industry vehicle application and vehicle type are benchmarked. Historical vehicle data that includes recurring vehicle usage data is stored. Using a learned trained classifier for each vehicle of the plurality of vehicles, a predicted vocation based on vehicle usage data may be obtained. A grouping based on the predicted vocations and the historical vehicle data is made. A determination from the benchmarked vehicles having better performance characteristics than other vehicles of the same predicted vocations is made. Performance of the other vehicles relative to benchmarking vehicles is made.