Granted Patent B2

US 12,373,734 · App. 17/960,943 · Granted Jul 29, 2025

Inventors: Bradford Everman (Haddonfield, NJ); Brian Bradke (Brookfield, VT)

G06N20/00G06N3/0442G06N3/08G06N5/022

Abstract

Claims (46)

1. An apparatus for machine operator feedback correlation, comprising:

at least a processor; and

a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to:

receive, through a sensing device, performance data of at least a machine operator;

classify the performance data to a performance category using a performance classifier;

compare the performance data to a performance parameter comprising a metric related to a task;

calculate a performance determination comprising a scoring of completion of the task as a function of the comparison;

generate, as a function of the performance determination, a feedback correlation using a machine operator feedback machine learning model comprising a supervised machine learning process, wherein generating the feedback correlation further comprises:

receive machine operator feedback training data and wherein the machine operator feedback training data is a data set that correlates performance parameters and performance determination to machine operator feedback parameters;

train, iteratively, the machine operator feedback machine learning model using the machine operator training data and utilizing a scoring function representing an expected loss of an algorithm relating inputs to outputs wherein the expected loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to an input-output pair provided in the machine operator training data;

generate, as a function of the trained machine operator feedback machine learning model, a feedback correlation; and

generate at least one confidence level for the feedback correlation;

generate an automation determination as a function of the performance determination and an automation threshold, wherein the automation determination comprises a level of control of a machine of the at least a machine operator, wherein generating the automation determination further comprises:

training an automation machine learning model using training data correlating performance determinations and automation thresholds to automation determinations; and

generating the automation determination as a function of the performance determination and the automation threshold using the trained automation machine learning model; and

provide the feedback correlation and the at least one confidence level for the feedback correlation to the at least a machine operator through a display device.

2. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to predict, as a function of the machine operator feedback machine learning model, the performance determination of the at least a machine operator.

3. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to generate, as a function of the feedback correlation, a machine operator optimization plan.

4. The apparatus of claim 3 , wherein the memory contains instructions further configuring the at least a processor to display, through the display device, the machine operator optimization plan to the at least a machine operator.

5. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to classify the performance data to an environmental parameter.

6. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to classify the performance data to a physiological parameter.

7. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to generate a machine operator feedback timeline as a function of the machine operator feedback machine learning model.

8. The apparatus of claim 1 , wherein the sensing device comprises an eye movement sensor.

9. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to determine a temporal element of the performance determination.

10. A method of machine operator feedback correlation using a computing device, comprising:

receiving, at a computing device and using a sensing device, performance data of at least a machine operator;

classifying, at the computing device, the performance data to a performance category using a performance classifier;

comparing, at the computing device, the performance data to a performance parameter comprising a metric related to a task;

calculating, at the computing device, a performance determination comprising a scoring of completion of the task as a function of the comparison;

generating, at the computing device, as a function of the performance determination, a feedback correlation using a machine operator feedback machine learning model, comprising a supervised machine learning process, wherein generating the feedback correlation further comprises:

receiving machine operator feedback training data and wherein the machine operator feedback training data is a data set that correlates performance parameters and performance determination to machine operator feedback parameters;

training, iteratively, the machine operator feedback machine learning model using the machine operator training data and utilizing a scoring function representing an expected loss of an algorithm relating inputs to outputs wherein the expected loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to an input-output pair provided in the machine operator training data;

generating, as a function of the trained machine operator feedback machine learning model, a feedback correlation; and

generating at least one confidence level for the feedback correlation;

generating, an automation determination as a function of the performance determination and an automation threshold, wherein the automation determination comprises a level of control of a machine of the at least a machine operator, wherein generating the automation determination further comprises:

training an automation machine learning model using training data correlating performance determinations and automation thresholds to automation determinations; and

generating the automation determination as a function of the performance determination and the automation threshold using the trained automation machine learning model; and

providing the feedback correlation and the at least one confidence level for the feedback correlation to the at least a machine operator through a display device.

11. The method of claim 10 , further comprising predicting, as a function of the machine operator feedback machine learning model, the performance determination of the at least a machine operator.

12. The method of claim 10 , wherein generating further comprises generating, as a function of the feedback correlation, a machine operator optimization plan.

13. The method of claim 12 , further comprising displaying, through the display device, the machine operator optimization plan to the at least a machine operator.

14. The method of claim 10 , wherein classifying further comprises classifying the performance data to an environmental parameter.

15. The method of claim 10 , wherein classifying further comprises classifying the performance data to a world event parameter.

16. The method of claim 10 , wherein generating comprises generating a performance timeline as a function of the machine operator feedback machine learning model.

17. The method of claim 10 , wherein the sensing device comprises an eye movement sensor.

18. The method of claim 10 , further comprising determining, at the computing device, a temporal element of the performance determination.

Continuity (1)

References Cited (13)

Cited By (1)

US 12,647,722