Task allocation

Patent metadata

Field	Value
Publication number	US-10430741-B2
Application number	US-201715839745-A
Country	US
Kind code	B2
Filing date	Dec 12, 2017
Priority date	Dec 19, 2016
Publication date	Oct 1, 2019
Grant date	Oct 1, 2019

Abstract

A method of assigning a task to a resource in a multiple resource environment is performed by one or more processors or special-purpose computing hardware. The method includes receiving task information relating to at least one task to be performed by a resource in the multiple resource environment. The method also includes determining a cost value for each task, the cost value indicating a cost incurred if a maintenance event occurs during performance of the respective task. The method also includes receiving predictive maintenance information in relation to each of the multiple resources in the multiple resource environment, the predictive maintenance information indicating a likelihood of a maintenance event with respect to each of the multiple resources in the multiple resource environment. The method also includes allocating the at least one task to one of the resources in the multiple resource environment dependent on the predictive maintenance information of the multiple resources and the calculated cost score.

First claim

The invention claimed is:

1. A computer-implemented method of assigning a task to a resource in a multiple resource environment, the method being performed by one or more processors or special-purpose computing hardware, the method comprising:
receiving task information relating to at least one task to be performed by a resource in the multiple resource environment;
determining a cost score for each task of the at least one task, the cost score indicating a cost incurred if a maintenance event occurs during performance of the respective task during a specified interval;
generating a machine learning model based on data associated with the multiple resources in the multiple resource environment, the data comprising any of sensor data, maintenance logs, or fault logs;
receiving predictive maintenance information output from the machine learning model in relation to each of the multiple resources in the multiple resource environment, the predictive maintenance information indicating a likelihood of a maintenance event within the specified interval with respect to each of the multiple resources in the multiple resource environment; and
allocating, for at least a portion of the specified interval, the at least one task to one of the resources in the multiple resource environment dependent on the predictive maintenance information of the multiple resources and the determined cost score, wherein if the at least one task has a high determined cost score relative to a first threshold, the at least one task is allocated to a particular resource of the multiple resource environment indicating a low likelihood of a maintenance event relative to a second threshold, and wherein if the at least one task has a low determined cost score relative to the first threshold, the at least one task is allocated to a different resource of the multiple resource environment indicating a high likelihood of a maintenance event relative to the second threshold.

2. The method of claim 1 , further comprising ranking the multiple resources in accordance with the likelihood of a maintenance event with respect to each of the respective resources.

3. The method of claim 1 , wherein allocating the at least one task to one of the resources comprises allocating the task to the resource having the lowest likelihood of a maintenance event.

4. The method of claim 1 , wherein the task information relates to a plurality of tasks, the method further comprising ranking the plurality of tasks in accordance with the cost score of each of the respective tasks.

5. The method of claim 4 , further comprising selecting the task having the highest cost score and allocating the selected task to an available resource having the lowest likelihood of a maintenance event.

6. The method of claim 1 , wherein a subset of the multiple resources are identified as available resources based on one or more criteria related to the or each task.

7. The method of claim 1 , wherein the cost incurred comprises one or more of a time cost, a financial cost, a personnel cost, a component cost, a machinery cost, and a distance cost.

8. The method of claim 1 , wherein receiving predictive maintenance information comprises receiving maintenance information output from a machine learning model in relation to each of the resources.

9. The method of claim 8 , wherein the maintenance information from a machine learning model comprises information derived from at least one of: sensor log data, fault log data, maintenance log data.

10. The method of claim 1 , wherein the predictive maintenance information for each resource comprises an aggregated risk value based on risk values derived from one or more sub-systems of the resource.

11. 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:
receiving task information relating to at least one task to be performed by a resource in the multiple resource environment;
determining a cost score for each task of the at least one task, the cost score indicating a cost incurred if a maintenance event occurs during performance of the respective task during a specified interval;
generating a machine learning model based on data associated with the multiple resources in the multiple resource environment, the data comprising any of sensor data, maintenance logs, or fault logs;
receiving predictive maintenance information output from the machine learning model in relation to each of the multiple resources in the multiple resource environment, the predictive maintenance information indicating a likelihood of a maintenance event within the specified interval with respect to each of the multiple resources in the multiple resource environment; and
allocating, for at least a portion of the specified interval, the at least one task to one of the resources in the multiple resource environment dependent on the predictive maintenance information of the multiple resources and the determined cost score, wherein if the at least one task has a high determined cost score relative to a first threshold, the at least one task is allocated to a particular resource of the multiple resource environment indicating a low likelihood of a maintenance event relative to a second threshold, and wherein if the at least one task has a low determined cost score relative to the first threshold, the at least one task is allocated to a different resource of the multiple resource environment indicating a high likelihood of a maintenance event relative to the second threshold.

12. A system for assigning a task to a resource in a multiple resource environment, the system comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the system to:
receive task information relating to at least one task to be performed by a resource in the multiple resource environment;
determine a cost score for each task of the at least one task, the cost score indicating a cost incurred if a maintenance event occurs during performance of the respective task during a specified interval;
generate a machine learning model based on data associated with the multiple resources in the multiple resource environment, the data comprising any of sensor data, maintenance logs, or fault logs;
receive predictive maintenance information output from the machine learning model in relation to each of the multiple resources in the multiple resource environment, the predictive maintenance information indicating a likelihood of a maintenance event within the specified interval with respect to each of the multiple resources in the multiple resource environment; and
allocate, for at least a portion of the specified interval, the at least one task to one of the resources in the multiple resource environment dependent on the predictive maintenance information of the multiple resources and the determined cost score, wherein if the at least one task has a high determined cost score relative to a first threshold, the at least one task is allocated to a particular resource of the multiple resource environment indicating a low likelihood of a maintenance event relative to a second threshold, and wherein if the at least one task has a low determined cost score relative to the first threshold, the at least one task is allocated to a different resource of the multiple resource environment indicating a high likelihood of a maintenance event relative to the second threshold.

13. The system according to claim 12 , wherein the instructions further cause the system to rank the multiple

Assignees

• Palantir Technologies Inc

Inventors

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

Classifications

• G06Q10/0631

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title

• G06F11/3476

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

• G06Q10/0635

  Risk analysis of enterprise or organisation activities · CPC title

• G06Q10/1097

  using calendar-based scheduling for task assignment · CPC title

• G06Q10/04

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title