Updating asset ownership systems and methods

Patent metadata

Field	Value
Publication number	US-11574283-B2
Application number	US-202017123013-A
Country	US
Kind code	B2
Filing date	Dec 15, 2020
Priority date	Dec 15, 2020
Publication date	Feb 7, 2023
Grant date	Feb 7, 2023

Abstract

The present disclosure is directed to systems and methods for updating asset ownership for telematics-enabled machinery. In some embodiments, the updating asset ownership system comprises asset entities that transmit telemetry data. A communication interface of the updating asset ownership system can receive the telemetry data. An asset ownership data store of the updating asset ownership system can be configured to store asset owner data that identify designated owners associated with the asset entities. An asset ownership comparator of the updating asset ownership system can process the received telemetry data. Based on the processing, the asset ownership comparator can update designated owners of asset entities stored in the asset ownership data store.

First claim

What is claimed is:

1. A system for automatically updating asset ownership for telematics-enabled work machinery, the system comprising:
a plurality of work machine asset entities comprising the telematics-enabled work machinery, wherein each work machine asset entity transmits a plurality of telemetry data records;
a communication interface that receives one or more of the plurality of telemetry data records from at least one of the plurality of work machine asset entities;
an asset ownership data store configured to store one or more asset owner data records associated with the at least one of the plurality of work machine asset entities, wherein the asset owner data record identifies as a designated owner at least a first owner entity that is associated with the at least one of the plurality of work machine asset entities; and
an asset ownership comparator having circuitry that:
identifies, using a plurality of different trained machine learning likelihood models, a first plurality of likely owner entities associated with the at least one of the plurality of work machine asset entities;
receives inconsistent ownership feedback data in terms of ownership of one or more of the at least one of the plurality of work machine asset entities;
retrains the plurality of different trained machine learning likelihood models based on the received inconsistent ownership feedback data;
determines, using the plurality of different retrained machine learning likelihood models, a second plurality of likely owner entities associated with one or more work machine asset entities;
based on the determination, automatically identifies, using an aggregator of the asset ownership comparator that receives outputs of the plurality of different retrained machine learning likelihood models having processed the inconsistent ownership feedback data, from among the second plurality of likely owner entities, a most likely owner of the at least one of the plurality of work machine asset entities, the most likely owner being different from the first owner;
replaces in the asset ownership data store the first owner as the designated owner with the most likely owner as the designated owner; and
outputs for display on a display device, an indication that the most likely owner is the designated owner of the at least one of the plurality of work machine asset entities.

2. The system of claim 1 , wherein the plurality of telemetry data records comprises one or more of: location information, sensory data, asset condition, performance data, oil levels, battery levels, temperature, time of use, proximity data, service meter units, vehicle data, engine data, operation warning errors, normative behavior, or fault codes.

3. The system of claim 1 , wherein the asset owner data records of the asset ownership data store are updated at a predefined periodicity.

4. The system of claim 1 , wherein the plurality of different trained machine learning likelihood models comprise at least one of: asset lifecycle model, party fleet model, party purchase model, ownership geographies model, ownership path model, or asset usage model.

5. A computer-implemented method for automatically updating asset ownership comprising:
receiving, using circuitry, one or more of a plurality of telemetry data records from at least one of a plurality of work machine asset entities;
storing, using the circuitry, one or more asset owner data records associated with the at least one of the plurality of work machine asset entities, wherein the asset owner data record identifies as a designated owner at least a first owner entity that is associated with the at least one of the plurality of work machine asset entities;
processing, using the circuitry and a plurality of different trained machine learning likelihood models, one or more of the received telemetry data records;
based on the processing, identifying, using the circuitry and the plurality of different trained machine learning likelihood models, a first plurality of likely owner entities associated with the at least one of the plurality of work machine asset entities;
responsive to queries about ownership to the first plurality of likely owner entities, electronically receiving, using the circuitry, ownership feedback data from at least one of the first plurality of likely owner entities, the electronically received ownership feedback data being inconsistent in terms of ownership of one or more of the at least one of the plurality of work machine asset entities;
retraining, using the circuitry, the plurality of different trained machine learning likelihood models based on the received ownership feedback data;
determining, using the circuitry and the plurality of different retrained machine learning likelihood models, a second plurality of likely owner entities associated with one or more work machine asset entities associated with the inconsistent ownership feedback data;
based on said determining, automatically identifying, using an aggregator receiving outputs of the plurality of different retrained machine learning likelihood models having processed the inconsistent ownership feedback data, from among the second plurality of likely owner entities, a most likely owner of the at least one of the plurality of work machine asset entities, the most likely owner being different from the first owner;
automatically electronically assigning the most likely owner as the designated owner of the at least one of the plurality of work machine asset entities;
electronically replacing in computer-readable memory the first owner as the designated owner with the most likely owner as the designated owner; and
electronically outputting for display on a display device, an indication that the most likely owner is the designated owner of the at least one of the plurality of work machine asset entities.

6. The method of claim 5 , further comprising storing a plurality of asset information data records, wherein the plurality of asset information data records comprises one or more of: asset model/type information, asset age, dealership history and information, sales history and information, auction history and information, usage information, contact information, rent history and information, lease history and information, buyer history and information, customer information, service history and information, manually entered ownership information, asset inspection information, inventory information, miscellaneous information, work order history, fleet information, or invoices for work done.

7. The method of claim 5 , wherein the plurality of work machine asset entities comprises one or more of: machines, vehicles, equipment, or devices.

8. The method of claim 5 , wherein the method further comprises:
identifying a set of nearby asset entities in proximity to the at least one of the plurality of work machine asset entities using the circuitry and GPS data from GPS sensors of each of the nearby asset entities;
determining, using the circuitry, a plurality of likely owner entities that each own at least one of the set of nearby asset entities;
wherein said determining the plurality of likely owner entities that each own at least one of the set of nearby asset entities includes:
generating one or more features from one or more of the telemetry data records, wherein the one or more features comprise the set of nearby asset entities;
inputting the generated one or more features to the plurality of different trained machine learning likelihood models; and
using the plurality of different trained machine learning likelihood models, calculating a plurality of ownership likelihood values associated with a plurality of likely owner entities that each own at least one of the set of nearby asset

Assignees

• Caterpillar Inc

Inventors

• Tennent Toby
• Philips Eric J
• Hootman Brandon
• Belkin Anatoly
• Radakovic Daniela

Classifications

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• G06Q10/087 Primary

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• H04W4/38

  for collecting sensor information · CPC title

• G06F16/9038

  Presentation of query results · CPC title