METHOD AND SYSTEM FOR EEG-BASED TASK MANAGEMENT

• US 20140242559A1
• Filed: 02/28/2013
• Published: 08/28/2014
• Est. Priority Date: 02/28/2013
• Status: Active Grant

• Current Assignee: Konica Minolta Laboratory U.S.A., Inc. (Konica Minolta Inc.)
• Original Assignee: Konica Minolta Laboratory U.S.A., Inc. (Konica Minolta Inc.)
• Inventors: Gu, Haisong, Patel, Ami
• Granted Patent: US 9,583,013 B2
• Time in Patent Office: Days
• US Class Current: 434/236
• CPC Class Codes: G09B 5/00 Electrically-operated educational appliances working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F

Abstract

A method and system are disclosed for determining a task for a subject, which includes sensing electrical activity along a scalp of a subject; characterizing a mental state of the subject based on the electrical activity of the subject; comparing the mental state of the subject with a pre-defined task list to select a task for the subject based on the mental state of the subject; and assigning the task to the subject based on the comparison of the mental state of the subject and the pre-defined task list.

Claims

1. A method for determining a task for a subject, comprising:

sensing electrical activity along a scalp of a subject;

characterizing a mental state of the subject based on the electrical activity of the subject;

comparing the mental state of the subject with a pre-defined task list to select a task for the subject based on the mental state of the subject; and

assigning the task to the subject based on the comparison of the mental state of the subject and the pre-defined task list.

2. The method of claim 1, comprising:

sensing the electrical activity of the subject using an electroencephalograph (EEG) device.

3. The method of claim 2, comprising:

recording the electrical activity over one or more frequency bands, wherein the one or more frequency bands include electrical signals between approximately 0.1 Hz and 100 Hz; and

determining the mental state of the subject based on a plurality of pre-defined frequencies within the one or more frequency bands, wherein each of the plurality of pre-defined frequencies correlates to at least one mental state of the subject.

4. The method of claim 1, wherein the step of characterizing the mental state of the subject is based on a learning based method, the learning based method comprising:

establishing one or more predefined mental state labels based on at least one behavioral study;

requesting the one or more subjects to provide a mental state based on personal judgment and/or productivity before, during and/or after performing a diagnostic test during the at least one behavioral study; and

employing a learning algorithm to the at least one behavioral study to generate one or more feature vectors correlating to the mental state of the one or more subjects during the at least one behavioral study

5. The method of claim 1, comprising:

converting the electrical activity of the subject into a vector of mental state dimensions, the mental state dimensions including one or more the following dimensions;

creativity level, focus level, and/or relaxation level; and

assigning the task based on comparing the vector of mental state dimensions to one or more tasks in the pre-defined task list, wherein step of assigning the task is chosen based on a minimum Euclidean distance between the vector of mental state dimensions and a vector of ideal mental state for the task assigned to the subject.

6. A method for determining a task for a subject, comprising:

sensing biological activity of a subject;

characterizing a mental state of the subject based on the biological activity of the subject;

comparing the mental state of the subject with a pre-defined task list to select a task for the subject based on the mental state of the subject; and

assigning the task to the subject based on the comparison of the mental state of the subject and the task allocation database.

7. The method of claim 6, wherein the biological signals are brainwave signals, and the biological activity is electrical activity, which is obtained using an electroencephalograph (EEG) device.

8. The method of claim 7, comprising:

recording the electrical activity over one or more frequency bands, wherein the one or more frequency bands include electrical signals between approximately 0.1 Hz and 100 Hz, and wherein the plurality of signals are in pre-defined frequency bands as follows;

(1) 0.1 to 3 Hz;

(2) 4 Hz to 7 Hz;

(3) 8 Hz to 12 Hz;

(4) 12 Hz to 30 Hz; and

(5) 30 Hz to 100 Hz.

9. The method of claim 8, comprising:

determining the mental state of the subject based on a plurality of pre-defined frequencies within the one or more frequency bands, wherein each of the plurality of pre-defined frequencies correlates to at least one mental state of the subject.

10. The method of claim 6, wherein the step of characterizing the mental state of the subject is based on a learning based method, the learning based method comprising:

establishing one or more predefined mental state labels based on at least one behavioral study;

requesting the one or more subjects to provide a mental state based on personal judgment and/or productivity before, during and/or after performing a diagnostic test during the at least one behavioral study; and

employing a learning algorithm to the at least one behavioral study to generate one or more feature vectors correlating to the mental state of the one or more subjects during the at least one behavioral study

11. The method of claim 6, comprising:

converting the biological activity of the subject into a vector of mental state dimensions, the mental state dimensions including one or more the following dimensions;

creativity level, focus level, and/or relaxation level; and

assigning the task based on comparing the vector of mental state dimensions to one or more tasks in the pre-defined task list, wherein step of assigning the task is chosen based on a minimum Euclidean distance between the vector of mental state dimensions and a vector of ideal mental state for the task assigned to the subject.

12. A system for determining a task for a subject, comprising:

a sensing device for sensing electrical activity over one or more frequency bands along a scalp of a subject; and

a computer device having executable instructions for;

characterizing a mental state of the subject based on the electrical activity of the subject;

comparing the mental state of the subject with a pre-defined task list to select a task for the subject based on the mental state of the subject; and

assigning the task to the subject based on the comparison of the mental state of the subject and the pre-defined task list.

13. The system of claim 12, wherein the sensing device is an electroencephalograph (EEG) device;

and

wherein the electrical activity is recorded over one or more frequency bands, wherein the one or more frequency bands include electrical signals between approximately 0.1 Hz and 100 Hz, and wherein the plurality of signals are in pre-defined frequency bands.

14. The system of claim 13, comprising:

recording the electrical activity over one or more frequency bands, wherein the one or more frequency bands include electrical signals between approximately 0.1 Hz and 100 Hz; and

determining the mental state of the subject based on a plurality of pre-defined frequencies within the one or more frequency bands, wherein each of the plurality of pre-defined frequencies correlates to at least one mental state of the subject.

15. The system of claim 12, wherein the step of characterizing the mental state of the subject is based on a learning based method, the learning based method comprising:

establishing one or more predefined mental state labels based on at least one behavioral study;

requesting the one or more subjects to provide a mental state based on personal judgment and/or productivity before, during and/or after performing a diagnostic test during the at least one behavioral study; and

employing a learning algorithm to the at least one behavioral study to generate one or more feature vectors correlating to the mental state of the one or more subjects during the at least one behavioral study

16. The system of claim 12, comprising:

converting the electrical activity of the subject into a vector of mental state dimensions, the mental state dimensions including one or more the following dimensions;

creativity level, focus level, and/or relaxation level; and

assigning the task based on comparing the vector of mental state dimensions to one or more tasks in the pre-defined task list, wherein step of assigning the task is chosen based on a minimum Euclidean distance between the vector of mental state dimensions and a vector of ideal mental state for the task assigned to the subject.

17. A non-transitory computer readable medium containing a computer program having computer readable code embodied for determining a task for a subject, comprising:

sensing electrical activity along a scalp of a subject;

characterizing a mental state of the subject based on the electrical activity of the subject;

comparing the mental state of the subject with a pre-defined task list to select a task for the subject based on the mental state of the subject; and

assigning the task to the subject based on the comparison of the mental state of the subject and the pre-defined task list.

18. The computer readable medium of claim 17, comprising:

sensing the electrical activity of the subject using an electroencephalograph (EEG) device.

19. The computer readable medium of claim 18, comprising:

recording the electrical activity over one or more frequency bands, wherein the one or more frequency bands include electrical signals between approximately 0.1 Hz and 100 Hz; and

determining the mental state of the subject based on a plurality of pre-defined frequencies within the one or more frequency bands, wherein each of the plurality of pre-defined frequencies correlates to at least one mental state of the subject.

20. The computer readable medium of claim 17, wherein the step of characterizing the mental state of the subject is based on a learning based method, the learning based method comprising:

establishing one or more predefined mental state labels based on at least one behavioral study;

requesting the one or more subjects to provide a mental state based on personal judgment and/or productivity before, during and/or after performing a diagnostic test during the at least one behavioral study; and

employing a learning algorithm to the at least one behavioral study to generate one or more feature vectors correlating to the mental state of the one or more subjects during the at least one behavioral study

21. The computer readable medium of claim 17, comprising:

converting the electrical activity of the subject into a vector of mental state dimensions, the mental state dimensions including one or more the following dimensions;

creativity level, focus level, and/or relaxation level; and

assigning the task based on comparing the vector of mental state dimensions to one or more tasks in the pre-defined task list, wherein step of assigning the task is chosen based on a minimum Euclidean distance between the vector of mental state dimensions and a vector of ideal mental state for the task assigned to the subject.