METHOD FOR ESTIMATING STRESS FROM TEMPORAL WORK PATTERNS

• US 20110125547A1
• Filed: 11/20/2009
• Published: 05/26/2011
• Est. Priority Date: 11/20/2009
• Status: Active Grant

• Current Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Su, Norman Makato, Brdiczka, Oliver
• Granted Patent: US 8,117,054 B2
• Time in Patent Office: Days
• US Class Current: 705/7.26
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 10/06316 Sequencing of tasks or work
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function

Abstract

One embodiment of the present invention provides a system for estimating a number of stress factors related to a worker. During operation, the system records a sequence of work steps of the worker for a predetermined period of time, and extracts a number of temporal patterns (T-patterns) from the sequence of work steps. Based on the extracted T-patterns, the system calculates T-pattern statistics, and applies a classification method on the calculated T-pattern statistics to produce a classification result. The system then estimates one or more of the stress factors based on the classification result.

Claims

1. A computer-executable method for estimating a number of stress factors related to a worker, the method comprising:

recording a sequence of work steps of the worker for a predetermined period of time;

extracting a number of temporal patterns (T-patterns) from the sequence of work steps;

calculating T-pattern statistics based on the extracted T-patterns;

applying a classification method on the calculated T-pattern statistics to produce a classification result; and

estimating one or more of the stress factors based on the classification result.

2. The method of claim 1, wherein the T-pattern statistics comprise:

a minimum temporal length of the T-patterns; and

a variance of the minimum temporal length.

3. The method of claim 1, wherein recording the work steps comprises:

recording the beginning and ending times of the work steps; and

recording an artifact and/or communicative channel used by the worker to accomplish the work steps.

4. The method of claim 1, wherein the work steps comprise logging events on a computing device.

5. The method of claim 4, wherein the logging events comprise one or more of:

opening and/or closing an application;

opening and/or closing a document; and

accessing an email account.

6. The method of claim 1, wherein the classification method comprises at least one of:

using a supporting-vector-machine (SVM) method; and

applying a Bayesian classifier.

7. The method of claim 1, wherein the work steps of the worker are recorded using one or more of the following methods:

running logging software installed on a computing device of the worker;

monitoring the worker using a camera; and

allowing a human observer to shadow the worker.

8. The method of claim 1, wherein the stress factors of the worker comprise at least one of:

a work-load factory;

an autonomy factor; and

a productivity factor.

9. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for estimating a number of stress factors related to a worker, the method comprising:

recording a sequence of work steps of the worker for a predetermined period of time;

extracting a number of temporal patterns (T-patterns) from the sequence of work steps;

calculating T-pattern statistics based on the extracted T-patterns;

applying a classification method on the calculated T-pattern statistics to produce a classification result; and

estimating one or more of the stress factors based on the classification result.

10. The computer-readable storage medium of claim 9, wherein the T-pattern statistics comprise:

a minimum temporal length of one or more of the T-patterns; and

a variance of the minimum temporal length.

11. The computer-readable storage medium of claim 9, wherein recording the work steps comprises:

recording the beginning and ending times of the work steps; and

recording an artifact and/or communicative channel used to accomplish the work steps.

12. The computer-readable storage medium of claim 9, wherein the work steps comprise logging events on a computing device.

13. The computer-readable storage medium of claim 12, wherein the logging events comprise one or more of:

opening and/or closing an application;

opening and/or closing a document; and

accessing an email account.

14. The computer-readable storage medium of claim 9, wherein the classification method comprises at least one of:

using a supporting-vector-machine (SVM) method; and

applying a Bayesian classifier.

15. The computer-readable storage medium of claim 9, wherein the work steps of the worker are recorded using one or more of the following methods:

running logging software installed on a computing device of the worker;

monitoring the worker using a camera; and

allowing a human observer to shadow the worker.

16. The computer-readable storage medium of claim 9, wherein the stress factors of the worker comprise at least one of:

a work-load factor;

an autonomy factor; and

a productivity factor.

17. A system for estimating a number of stress factors related to a worker, the system comprising:

a recording mechanism configured to record a sequence of work steps of the worker for a predetermined period of time;

an extraction mechanism configured to extract a number of temporal patterns (T-patterns) from the sequence of work steps;

a calculation mechanism configured to the calculate T-pattern statistics based on the extracted T-patterns;

a classification mechanism configured to apply a classification method on calculated T-pattern statistics to produce a classification result; and

an estimation mechanism configured to estimate one or more of the stress factors based on the classification result.

18. The system of claim 17, wherein the T-pattern statistics comprise:

a minimum temporal length of one or more of the T-patterns; and

a variance of the minimum temporal length.

19. The system of claim 17, wherein the recording mechanism is configured to:

record the beginning and ending times of the work steps; and

record an artifact and/or communicative channel used to accomplish the work steps.

20. The system of claim 17, wherein the work steps comprise logging events on a computing device.

21. The system of claim 20, wherein the logging events comprise one or more of:

opening and/or closing an application;

opening and/or closing a document; and

accessing an email account

22. The system of claim 17, wherein the classification method comprises at least one of:

using a supporting-vector-machine (SVM) method; and

applying a Bayesian classifier.

23. The system of claim 17, wherein the work steps of the worker are recorded using one or more of the following methods:

running software installed on a computing device of the worker;

monitoring the worker using a camera; and

allowing a human observer to shadow the worker.

24. The system of claim 17, wherein the stress factors of the worker comprise at least one of:

a work load factor;

an autonomy factor; and

a productivity factor.