Generating labor requirements

• US 9,824,318 B1
• Filed: 09/25/2013
• Issued: 11/21/2017
• Est. Priority Date: 09/25/2013
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Lusthaus, Michael, Usmani, Kashif, Derevyanchenko, Borys, Lord, Julien Samuel
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US14/036,785
• Time in Patent Office: 1,518 Days
• CPC Class Codes: G06Q 10/06312 Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function

Abstract

Disclosed are various implementations for a labor recommendation application. Historical worker assignments and work buffer states for materials processing facilities are selected. Lost labor times are determined as a function of the historical worker assignments and buffer states. A statistical analysis is performed on the lost labor times, the historical worker assignments, or the work buffer states. A labor recommendation for a materials processing facility to minimize estimated lost labor time.

Claims

1. A non-transitory computer-readable medium embodying a program executable in at least one computing device, wherein, when executed, the program causes the at least one computing device to at least:

query, over a network, a plurality of worker client devices for a plurality of past worker assignments and a plurality of work buffer states, individual ones of the worker client devices being associated with one of a plurality of processing stages in one of a plurality of materials processing facilities, individual ones of the worker client devices receiving an input from a worker indicative of an initial time of the worker beginning work at one of the processing stages and the input being used to determine a timestamp of a check-in of the worker, each work buffer state representing an amount of work awaiting processing at one of the plurality of processing stages at a particular time period;

receive from the individual ones of the worker client devices the past worker assignments and the work buffer states, the past worker assignments and the work buffer states being retrieved from a memory of the worker client devices;

select a subset of the plurality of past worker assignments for a predefined work period associated with the processing stages of the materials processing facilities;

determine a lost labor time as a function of a change in the amount of work awaiting processing at the one of the plurality of processing stages between a first one of the plurality of work buffer states associated with a first time period and a second one of the plurality of work buffer states associated with a second time period;

generate a labor recommendation for the one of the plurality of processing stages of at least one of the materials processing facilities as a function of a statistical correlation between the subset of the past worker assignments and the lost labor time, the labor recommendation being associated with the predefined work period and including a recommended number of workers that is different from a current number of workers assigned to the one of the plurality of processing stages of the at least one of the materials processing facilities;

encode the labor recommendation for display on a manager client device;

wherein the labor recommendation reduces a predicted amount of lost labor time associated with the at least one of the materials processing facilities; and

wherein the subset of the past worker assignments, the work buffer states, or the lost labor time are weighted as a function of at least one previous occurrence of the predefined work period.

2. The non-transitory computer-readable medium of claim 1, wherein the predefined work period comprises a seasonal work period or an establishment period of the at least one of the materials processing facilities.

3. The non-transitory computer-readable medium of claim 1, wherein the subset of the past worker assignments, the work buffer states, or the lost labor time are weighted as a function of a degree of similarity between the at least one of the materials processing facilities and a respective one of the materials processing facilities, and the degree of similarity is determined based at least in part on a determination of a plurality of facility attributes corresponding between the at least one of the materials processing facilities and the respective one of the materials processing facilities.

4. The non-transitory computer-readable medium of claim 1, wherein the plurality of workers comprises a plurality of automated robotic devices.

5. A system, comprising:

at least one computing device; and

a labor recommendation application executed in the at least one computing device, wherein, when executed, the labor recommendation application causes the at least one computing device to at least;

query, over a network, a worker client device for historical worker assignment data and a plurality of work buffer states, the worker client device being associated with one of a plurality of processing stages in at least one materials processing facility, each work buffer state representing an amount of work awaiting processing at the one of the plurality of processing stages at a particular time period;

receive from the worker client device the historical worker assignment data and the work buffer states, the historical worker assignment data and the work buffer states being retrieved from a memory of the worker client device;

select a subset of the historical worker assignment data associated with a work period of the at least one materials processing facility;

generate a lost labor time data as a function of a change in the amount of work awaiting processing at the one of the plurality of processing stages between a first one of the plurality of work buffer states associated with a first time period and a second one of the plurality of work buffer states associated with a second time period;

generate a labor recommendation for the one of the plurality of processing stages as a function of the historical worker assignment data and the lost labor time data, wherein generating the labor recommendation comprises performing a statistical correlation between the lost labor time data and the historical worker assignment data, the labor recommendation being associated with the work period and including a recommended number of workers that is different from a current number of workers assigned to the one of the plurality of processing stages; and

wherein the labor recommendation reduces a predicted amount of lost labor time associated with the at least one materials processing facility.

6. The system of claim 5, wherein the at least one materials processing facility is a first at least one materials processing facility, the historical worker assignment data is further associated with a second at least one materials processing facility, and wherein generating the labor recommendation further causes the at least one computing device to weigh the historical worker assignment data or the lost labor time data as a function of a degree of similarity between the first at least one materials processing facility and the second at least one materials processing facility.

7. The system of claim 5, wherein the labor recommendation is associated with a seasonal work period, and wherein generating the labor recommendation further causes the at least one computing device to weigh the historical worker assignment data or the lost labor time data as a function of at least one previous occurrence of the seasonal work period.

8. The system of claim 5, wherein the labor recommendation is generated in accordance with an anticipated change in throughput of the at least one materials processing facility.

9. The system of claim 5, wherein the lost labor time data is generated as a function of at least one worker transition between a first processing stage of the at least one materials processing facility and a second processing stage of the at least one materials processing facility.

10. The system of claim 5, wherein the lost labor time data is generated as a function of an idle period for at least one worker of the at least one materials processing facility.

11. The system of claim 5, wherein the historical worker assignment data comprises a plurality of work buffer sizes of the processing stages.

12. The system of claim 5, wherein the labor recommendation comprises at least one recommended worker.

13. The system of claim 5, wherein the labor recommendation application further causes the at least one computing device to at least:

encode the labor recommendation in a file that comprises at least one of a document or a spreadsheet; and

transmit, over the network, the file to a manager client device for display.

14. A method, comprising:

querying, by a computing device over a network, a worker client device for a plurality of past worker assignments and a plurality of work buffer states, the worker client device being associated with one of a plurality of processing stages in one of a plurality of materials processing facilities, each work buffer state representing an amount of work awaiting processing at the one of the plurality of processing stages at a particular time period;

receiving, by the computing device, from the worker client device the plurality of past worker assignments and the work buffer states, the plurality of past worker assignments and the work buffer states being retrieved from a memory of the worker client device;

selecting, by the computing device, a subset of the plurality of past worker assignments associated with a work period of the one of the plurality of processing stages of at least one materials processing facility;

generating, by the computing device, lost labor time data based at least in part on a change in the amount of work awaiting processing at the one of the plurality of processing stages between a first one of the plurality of work buffer states associated with a first time period and a second one of the plurality of work buffer states associated with a second time period;

generating, by the computing device, a labor recommendation for the one of the plurality of processing stages of the at least one materials processing facility as a function of performing a statistical correlation between the lost labor time data and the past worker assignments, the labor recommendation being associated with the work period and including a recommended number of workers that is different from a current number of workers assigned to the one of the plurality of processing stages; and

wherein the labor recommendation minimizes a predicted amount of lost labor time associated with the at least one materials processing facility.

15. The method of claim 14, further comprising:

calculating, by the computing device, based at least in part on the past worker assignments, a lost labor time as a function of at least one worker transition between a first one of the processing stages and a second one of the processing stages of the at least one materials processing facility; and

wherein the labor recommendation is based at least in part on the lost labor time.

16. The method of claim 14, further comprising:

calculating, by the computing device, based at least in part on the work buffer states, a lost labor time as a function of a period of worker idleness indicated by an empty work buffer; and

wherein the labor recommendation is based at least in part on the lost labor time.

17. The method of claim 14, wherein the labor recommendation is generated as a function of an establishment period of the at least one materials processing facility.

18. The method of claim 14, wherein the labor recommendation is associated with a seasonal work period, and generating the labor recommendation further comprises weighing, by the computing device, the past worker assignments or the work buffer states as a function of at least one previous occurrence of the seasonal work period.

19. The method of claim 14, further comprising:

adding, by the computing device, timestamp data to a plurality of aggregated worker check-ins; and

wherein the past worker assignments comprise the aggregated worker check-ins.