Predictive modelling

Patent metadata

Field	Value
Publication number	US-12461520-B2
Application number	US-202318244527-A
Country	US
Kind code	B2
Filing date	Sep 11, 2023
Priority date	Dec 19, 2016
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

Systems, methods, and non-transitory computer-readable media can be configured to perform receiving a notification of a maintenance event associated with a resource. The method includes retrieving historic maintenance data in relation to the resource with which the fault is associated, the maintenance information originating from a time period preceding the time of the maintenance event. The method includes identifying at least a portion of the retrieved historic maintenance data as being indicative of the maintenance event. The method also includes causing the portion of the retrieved historic maintenance data identified as being indicative of the maintenance event to be stored as a precursor signal of the maintenance event. The method also includes causing future maintenance data received from a plurality of resources related to the resource with which the maintenance event is associated to be monitored to predict a future occurrence of the maintenance event in the plurality of resources.

First claim

The invention claimed is:

1 . A computer-implemented method of predicting maintenance events with respect to resources, the method being performed by one or more processors or special-purpose computing hardware, the method comprising:
determining, based on an ontology, first data associated with a first maintenance event of a first resource; retrieving from the first data, first historic maintenance data in relation to the first resource, the first historic maintenance data originating from a time period preceding a first time of the first maintenance event; identifying a first subset of the retrieved first historic maintenance data as being indicative of the first maintenance event; storing the first subset as one or more precursor signals of a type of the first maintenance event; generating or obtaining a modified ontology, wherein the modified ontology comprises a new or modified parser definition compared to an original parser definition corresponding to the first data, wherein the original parser definition associates a first format to a first object type or a first property type and the new or modified parser definition associates a second format to a second object type or a second property type; determining, based on the modified ontology or the ontology, second data associated with a second maintenance event of the first resource or a second resource; retrieving second historic maintenance data in relation to the first resource or the second resource, the second historic maintenance data originating from a time period preceding a second time of the second maintenance event; identifying a second subset of the retrieved second historic maintenance data as being indicative of the second maintenance event; updating the one or more precursor signals based on the second subset; monitoring subsequent maintenance data from the first resource, the second resource, or a third resource to predict, based on the update of the one or more precursor signals, a subsequent occurrence of the maintenance event in the first resource, the second resource, or a third resource; and displaying on a display screen a menu listing one or more resources including the first resource; and additionally being configured to display on the display screen a resource summary reachable directly from the menu, wherein the resource summary displays limited resource data within one or more screen sections, the one or more screen sections being configured to, upon an input, launch a more detailed view of the limited resource data, wherein the resource summary is displayed while the one or more screen sections are in an unlaunched state.

2 . The computer-implemented method of claim 1 , wherein the first historic maintenance data or the second historic maintenance data comprises sensor data.

3 . The computer-implemented method of claim 1 wherein the original parser definition specifies that any input data having the first format is validated as the first property type and any input data lacking the first format is invalidated as the first property type.

4 . The computer-implemented method of claim 3 , further comprising:
selectively incorporating any input data that is validated as the first property type into a data storage.

5 . The computer-implemented method of claim 1 , wherein the predicting of the subsequent occurrence is based on a machine learning model.

6 . The computer-implemented method of claim 5 , wherein the machine learning model comprises a decision tree, a Bayesian network, or an artificial neural network.

7 . A system for predicting maintenance events, the system comprising one or more processors or special-purpose computing hardware configured to perform:
determining, based on an ontology, first data associated with a first maintenance event of a first resource; retrieving from the first data, first historic maintenance data in relation to the first resource, the first historic maintenance data originating from a time period preceding a first time of the first maintenance event; identifying a first subset of the retrieved first historic maintenance data as being indicative of the first maintenance event; storing the first subset as one or more precursor signals of a type of the first maintenance event; generating or obtaining a modified ontology, wherein the modified ontology comprises a new or modified parser definition compared to an original parser definition corresponding to the first data, wherein the original parser definition associates a first format to a first object type or a first property type and the new or modified parser definition associates a second format to a second object type or a second property type; determining, based on the modified ontology or the ontology, second data associated with a second maintenance event of the first resource or a second resource; retrieving second historic maintenance data in relation to the first resource or the second resource, the second historic maintenance data originating from a time period preceding a second time of the second maintenance event; identifying a second subset of the retrieved second historic maintenance data as being indicative of the second maintenance event; updating the one or more precursor signals based on the second subset; monitoring subsequent maintenance data from the first resource, the second resource, or a third resource to predict, based on the update of the one or more precursor signals, a subsequent occurrence of the maintenance event in the first resource, the second resource, or a third resource; and displaying on a display screen a menu listing one or more resources including the first resource; and additionally being configured to display on the display screen a resource summary reachable directly from the menu, wherein the resource summary displays limited resource data within one or more screen sections, the one or more screen sections being configured to, upon an input, launch a more detailed view of the limited resource data, wherein the resource summary is displayed while the one or more screen sections are in an unlaunched state.

8 . The system of claim 7 , wherein the first historic maintenance data or the second historic maintenance data comprises sensor data.

9 . The system of claim 7 , wherein the original parser definition specifies that any input data having the first format is validated as the first property type and any input data lacking the first format is invalidated as the first property type.

10 . The system of claim 9 , wherein the one or more processors or special-purpose computing hardware are further configured to perform:
selectively incorporating any input data that is validated as the first property type into a data storage.

11 . The system of claim 7 , wherein the predicting of the subsequent occurrence is based on a machine learning model.

12 . The system of claim 11 , wherein the machine learning model comprises a decision tree, a Bayesian network, or an artificial neural network.

13 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
determining, based on an ontology, first data associated with a first maintenance event of a first resource; retrieving from the first data, first historic maintenance data in relation to the first resource, the first historic maintenance data originating from a time period preceding a first time of the first maintenance event; identifying a first subset of the retrieved first historic maintenance data as being indicative of t

Assignees

• Palantir Technologies Inc

Inventors

• Spiro Ezra
• Menck Andre Frederico Cavalheiro
• Maag Peter
• Powell Thomas

Classifications

• G06Q10/20

  Administration of product repair or maintenance · CPC title

• G06Q10/06

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06F11/3476

  Data logging (G06F11/14, G06F11/2205 take precedence) · CPC title

• G06F11/3089

  Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents (software debugging using additional hardware using a specific debug interface G06F11/3656; performance evaluation by tracing or monitoring G06F11/3466) · CPC title

• G06F11/3003

  Monitoring arrangements specially adapted to the computing system or computing system component being monitored · CPC title