	US 11,995,616 B2
	Asset health management for vehicles
Hitesh Hinduja, Thane (IN); Gaurav Agarwal, Bangalore (IN); Krishna Koushik Vsr, Bangalore (IN); Smruti Chourasia, Jabalpur (IN); Shreya Kekkar, Pune (IN); Hrishikesh Bharadwaj Chakrapani, Bangalore (IN); and Punit Mahipal, Bangalore (KR)
Assigned to ANI TECHNOLOGIES PRIVATE LIMITED, Bengaluru (IN)
Filed by ANI TECHNOLOGIES PRIVATE LIMITED, Bengaluru (IN)
Filed on Dec. 31, 2020, as Appl. No. 17/139,953.
Claims priority of application No. 202041044112 (IN), filed on Oct. 9, 2020.
Prior Publication US 2022/0114559 A1, Apr. 14, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/20 (2023.01)

CPC G06Q 10/20 (2013.01)

12 Claims

1. A method for asset health management, the method comprising:

retrieving, by a server, from a database associated with a transportation service provider corresponding to a set of vehicles, a first maintenance data, a first booking data, a first vehicle data, a first operational data, and a labelled dataset for the set of vehicles over a first time-interval, wherein the set of vehicles are communicatively coupled to a communication network, wherein the labelled dataset includes at least an actual health index observed over the first time-interval for each vehicle of the set of vehicles;

determining, by the server, a first plurality of features and a corresponding first plurality of feature values based on the first maintenance data, the first booking data, the first vehicle data, and the first operational data, wherein the first plurality of features comprises of at least one of a vehicle make, a vehicle model, a region of operation of a vehicle, an age of a vehicle, an active age of a vehicle, a dormant age of a vehicle, a repair downtime of a vehicle, an active duration of a vehicle, and a dormant duration of a vehicle, and wherein the first plurality of feature values include at least a first set of cost per unit distance values forecasted over a future time-interval occurring after the first time-interval for one or more components of each vehicle of the set of vehicles, and wherein determining the first set of cost per unit distance values comprises:

receiving, by the server, a third maintenance data, a third vehicle data, a third booking data, and time-series data for the set of vehicles, wherein the third maintenance data, the third vehicle data, and the third booking data are associated with a second time-interval, wherein the second time-interval is prior to the first time-interval, and wherein the time-series data includes at least a second set of cost per unit distance values observed during the second time-interval for the one or more components of each vehicle of the set of vehicles;

determining, by the server, a second plurality of features and a corresponding second plurality of feature values based on the third maintenance data, the third vehicle data, and the third booking data;

training, by the server, a second prediction model based on the second plurality of features, the second plurality of feature values, and the time-series data;

correlating, by the server, the second plurality of features and the second plurality of feature value to the actual cost per unit distance values included in the time-series data of the one or more components of each vehicle of the set of vehicles during the second time-interval;

based on the correlation, forecasting, by the server, over the future time-interval, the first set of cost per unit distance values based on the trained second prediction model, the first maintenance data, the first booking data, and the first vehicle data;

inputting, by the server, the first set of cost per unit distance values into a first prediction model:

training, by the server, a first prediction model based on the first plurality of features, the first plurality of feature values, the first set of cost per unit distance values, and the labelled dataset; and

generating, by the server, the health index of the target vehicle based on the trained first prediction model and a first dataset associated with the target vehicle.